Authors: Kimji N. Pellano, Inga Str\"umke, Daniel Groos, Lars Adde, Espen Alexander F. Ihlen
Abstract: Early detection of Cerebral Palsy (CP) is crucial for effective intervention and monitoring. This paper tests the reliability and applicability of Explainable AI (XAI) methods using a deep learning method that predicts CP by analyzing skeletal data extracted from video recordings of infant movements. Specifically, we use XAI evaluation metrics -- namely faithfulness and stability -- to quantitatively assess the reliability of Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) in this specific medical application. We utilize a unique dataset of infant movements and apply skeleton data perturbations without distorting the original dynamics of the infant movements. Our CP prediction model utilizes an ensemble approach, so we evaluate the XAI metrics performances for both the overall ensemble and the individual models. Our findings indicate that both XAI methods effectively identify key body points influencing CP predictions and that the explanations are robust against minor data perturbations. Grad-CAM significantly outperforms CAM in the RISv metric, which measures stability in terms of velocity. In contrast, CAM performs better in the RISb metric, which relates to bone stability, and the RRS metric, which assesses internal representation robustness. Individual models within the ensemble show varied results, and neither CAM nor Grad-CAM consistently outperform the other, with the ensemble approach providing a representation of outcomes from its constituent models.
Authors: John Oyekan, Liam Quantrill, Christopher Turner, Ashutosh Tiwari
Abstract: In this work, we explore a deep learning based automated visual inspection and verification algorithm, based on the Siamese Neural Network architecture. Consideration is also given to how the input pairs of images can affect the performance of the Siamese Neural Network. The Siamese Neural Network was explored alongside Convolutional Neural Networks. In addition to investigating these model architectures, additional methods are explored including transfer learning and ensemble methods, with the aim of improving model performance. We develop a novel voting scheme specific to the Siamese Neural Network which sees a single model vote on multiple reference images. This differs from the typical ensemble approach of multiple models voting on the same data sample. The results obtained show great potential for the use of the Siamese Neural Network for automated visual inspection and verification tasks when there is a scarcity of training data available. The additional methods applied, including the novel similarity voting, are also seen to significantly improve the performance of the model. We apply the publicly available omniglot dataset to validate our approach. According to our knowledge, this is the first time a detailed study of this sort has been carried out in the automatic verification of installed brackets in the aerospace sector via Deep Neural Networks.
Authors: Hua Yu, Yaqing Hou, Wenbin Pei, Qiang Zhang
Abstract: Diverse human motion prediction (HMP) aims to predict multiple plausible future motions given an observed human motion sequence. It is a challenging task due to the diversity of potential human motions while ensuring an accurate description of future human motions. Current solutions are either low-diversity or limited in expressiveness. Recent denoising diffusion models (DDPM) hold potential generative capabilities in generative tasks. However, introducing DDPM directly into diverse HMP incurs some issues. Although DDPM can increase the diversity of the potential patterns of human motions, the predicted human motions become implausible over time because of the significant noise disturbances in the forward process of DDPM. This phenomenon leads to the predicted human motions being hard to control, seriously impacting the quality of predicted motions and restricting their practical applicability in real-world scenarios. To alleviate this, we propose a novel conditional diffusion-based generative model, called DivDiff, to predict more diverse and realistic human motions. Specifically, the DivDiff employs DDPM as our backbone and incorporates Discrete Cosine Transform (DCT) and transformer mechanisms to encode the observed human motion sequence as a condition to instruct the reverse process of DDPM. More importantly, we design a diversified reinforcement sampling function (DRSF) to enforce human skeletal constraints on the predicted human motions. DRSF utilizes the acquired information from human skeletal as prior knowledge, thereby reducing significant disturbances introduced during the forward process. Extensive results received in the experiments on two widely-used datasets (Human3.6M and HumanEva-I) demonstrate that our model obtains competitive performance on both diversity and accuracy.
Authors: Shahab Aldin Shojaeezadeh, Abdelrazek Elnashar, Tobias Karl David Weber
Abstract: Crop phenology determines crop growth stages and is valuable information for decision makers to plant and adapt agricultural management strategies to enhance food security. In the era of big Earth observation data ubiquity, attempts have been made to accurately predict crop phenology based on Remote Sensing (RS) data. However, most studies either focused on large scale interpretations of phenology or developed methods which are not adequate to help crop modeler communities on leveraging the value of RS data evaluated using more accurate and confident methods. Here, we estimate phenological developments for eight major crops and 13 phenological stages across Germany at 30m scale using a novel framework which fuses Landsat and Sentinel 2 (Harmonized Landsat and Sentinel data base; HLS) and radar of Sentinel 1 with a Machine Learning (ML) model. We proposed a thorough feature fusion analysis to find the best combinations of RS data on detecting phenological developments based on the national phenology network of Germany (German Meteorological Service; DWD) between 2017 and 2021. The nation-wide predicted crop phenology at 30 m resolution showed a very high precision of R2 > 0.9 and a very low Mean Absolute Error (MAE) < 2 (days). These results indicate that our fusing strategy of optical and radar datasets is highly performant with an accuracy highly relevant for practical applications, too. The subsequent uncertainty analysis indicated that fusing optical and radar data increases the reliability of the RS predicted crop growth stages. These improvements are expected to be useful for crop model calibrations and evaluations, facilitate informed agricultural decisions, and contribute to sustainable food production to address the increasing global food demand.
Authors: Yujie Wang, Baoquan Chen, Praneeth Chakravarthula
Abstract: Recent holographic display approaches propelled by deep learning have shown remarkable success in enabling high-fidelity holographic projections. However, these displays have still not been able to demonstrate realistic focus cues, and a major gap still remains between the defocus effects possible with a coherent light-based holographic display and those exhibited by incoherent light in the real world. Moreover, existing methods have not considered the effects of the observer's eye pupil size variations on the perceived quality of 3D projections, especially on the defocus blur due to varying depth-of-field of the eye. In this work, we propose a framework that bridges the gap between the coherent depth-of-field of holographic displays and what is seen in the real world due to incoherent light. To this end, we investigate the effect of varying shape and motion of the eye pupil on the quality of holographic projections, and devise a method that changes the depth-of-the-field of holographic projections dynamically in a pupil-adaptive manner. Specifically, we introduce a learning framework that adjusts the receptive fields on-the-go based on the current state of the observer's eye pupil to produce image effects that otherwise are not possible in current computer-generated holography approaches. We validate the proposed method both in simulations and on an experimental prototype holographic display, and demonstrate significant improvements in the depiction of depth-of-field effects, outperforming existing approaches both qualitatively and quantitatively by at least 5 dB in peak signal-to-noise ratio.
Authors: Jiawei Lian, Shaohui Mei, Xiaofei Wang, Yi Wang, Lefan Wang, Yingjie Lu, Mingyang Ma, Lap-Pui Chau
Abstract: It has been widely substantiated that deep neural networks (DNNs) are susceptible and vulnerable to adversarial perturbations. Existing studies mainly focus on performing attacks by corrupting targeted objects (physical attack) or images (digital attack), which is intuitively acceptable and understandable in terms of the attack's effectiveness. In contrast, our focus lies in conducting background adversarial attacks in both digital and physical domains, without causing any disruptions to the targeted objects themselves. Specifically, an effective background adversarial attack framework is proposed to attack anything, by which the attack efficacy generalizes well between diverse objects, models, and tasks. Technically, we approach the background adversarial attack as an iterative optimization problem, analogous to the process of DNN learning. Besides, we offer a theoretical demonstration of its convergence under a set of mild but sufficient conditions. To strengthen the attack efficacy and transferability, we propose a new ensemble strategy tailored for adversarial perturbations and introduce an improved smooth constraint for the seamless connection of integrated perturbations. We conduct comprehensive and rigorous experiments in both digital and physical domains across various objects, models, and tasks, demonstrating the effectiveness of attacking anything of the proposed method. The findings of this research substantiate the significant discrepancy between human and machine vision on the value of background variations, which play a far more critical role than previously recognized, necessitating a reevaluation of the robustness and reliability of DNNs. The code will be publicly available at https://github.com/JiaweiLian/Attack_Anything
Authors: Daniel E. Hurtado, Axel Osses, Rodrigo Quezada
Abstract: Deformable image registration is a standard engineering problem used to determine the distortion experienced by a body by comparing two images of it in different states. This study introduces two new DIR methods designed to capture non-affine deformations using Radon transform-based similarity measures and a classical regularizer based on linear elastic deformation energy. It establishes conditions for the existence and uniqueness of solutions for both methods and presents synthetic experimental results comparing them with a standard method based on the sum of squared differences similarity measure. These methods have been tested to capture various non-affine deformations in images, both with and without noise, and their convergence rates have been analyzed. Furthermore, the effectiveness of these methods was also evaluated in a lung image registration scenario.
Authors: Debesh Jha, Nikhil Kumar Tomar, Vanshali Sharma, Quoc-Huy Trinh, Koushik Biswas, Hongyi Pan, Ritika K. Jha, Gorkem Durak, Alexander Hann, Jonas Varkey, Hang Viet Dao, Long Van Dao, Binh Phuc Nguyen, Khanh Cong Pham, Quang Trung Tran, Nikolaos Papachrysos, Brandon Rieders, Peter Thelin Schmidt, Enrik Geissler, Tyler Berzin, P{\aa}l Halvorsen, Michael A. Riegler, Thomas de Lange, Ulas Bagci
Abstract: Colonoscopy is the primary method for examination, detection, and removal of polyps. Regular screening helps detect and prevent colorectal cancer at an early curable stage. However, challenges such as variation among the endoscopists' skills, bowel quality preparation, and complex nature of the large intestine which cause large number of polyp miss-rate. These missed polyps can develop into cancer later on, which underscores the importance of improving the detection methods. A computer-aided diagnosis system can support physicians by assisting in detecting overlooked polyps. However, one of the important challenges for developing novel deep learning models for automatic polyp detection and segmentation is the lack of publicly available, multi-center large and diverse datasets. To address this gap, we introduce PolypDB, a large scale publicly available dataset that contains 3934 still polyp images and their corresponding ground truth from real colonoscopy videos to design efficient polyp detection and segmentation architectures. The dataset has been developed and verified by a team of 10 gastroenterologists. PolypDB comprises of images from five modalities: Blue Light Imaging (BLI), Flexible Imaging Color Enhancement (FICE), Linked Color Imaging (LCI), Narrow Band Imaging (NBI), and White Light Imaging (WLI) and three medical centers from Norway, Sweden and Vietnam. Thus, we split the dataset based on modality and medical center for modality-wise and center-wise analysis. We provide a benchmark on each modality using eight popular segmentation methods and six standard benchmark polyp detection methods. Furthermore, we also provide benchmark on center-wise under federated learning settings. Our dataset is public and can be downloaded at \url{https://osf.io/pr7ms/}.
URLs: https://osf.io/pr7ms/
Authors: Thakshila Thilakanayake, Oscar De Silva, Thumeera R. Wanasinghe, George K. Mann, Awantha Jayasiri
Abstract: This paper presents a generative adversarial network (GAN) based approach for radar image enhancement. Although radar sensors remain robust for operations under adverse weather conditions, their application in autonomous vehicles (AVs) is commonly limited by the low-resolution data they produce. The primary goal of this study is to enhance the radar images to better depict the details and features of the environment, thereby facilitating more accurate object identification in AVs. The proposed method utilizes high-resolution, two-dimensional (2D) projected light detection and ranging (LiDAR) point clouds as ground truth images and low-resolution radar images as inputs to train the GAN. The ground truth images were obtained through two main steps. First, a LiDAR point cloud map was generated by accumulating raw LiDAR scans. Then, a customized LiDAR point cloud cropping and projection method was employed to obtain 2D projected LiDAR point clouds. The inference process of the proposed method relies solely on radar images to generate an enhanced version of them. The effectiveness of the proposed method is demonstrated through both qualitative and quantitative results. These results show that the proposed method can generate enhanced images with clearer object representation compared to the input radar images, even under adverse weather conditions.
Authors: Sha Lu, Xuecheng Xu, Yuxuan Wu, Haojian Lu, Xieyuanli Chen, Rong Xiong, Yue Wang
Abstract: Global localization using onboard perception sensors, such as cameras and LiDARs, is crucial in autonomous driving and robotics applications when GPS signals are unreliable. Most approaches achieve global localization by sequential place recognition and pose estimation. Some of them train separate models for each task, while others employ a single model with dual heads, trained jointly with separate task-specific losses. However, the accuracy of localization heavily depends on the success of place recognition, which often fails in scenarios with significant changes in viewpoint or environmental appearance. Consequently, this renders the final pose estimation of localization ineffective. To address this, we propose a novel paradigm, PR-by-PE localization, which improves global localization accuracy by deriving place recognition directly from pose estimation. Our framework, RING#, is an end-to-end PR-by-PE localization network operating in the bird's-eye view (BEV) space, designed to support both vision and LiDAR sensors. It introduces a theoretical foundation for learning two equivariant representations from BEV features, which enables globally convergent and computationally efficient pose estimation. Comprehensive experiments on the NCLT and Oxford datasets across both vision and LiDAR modalities demonstrate that our method outperforms state-of-the-art approaches. Furthermore, we provide extensive analyses to confirm the effectiveness of our method. The code will be publicly released.
Authors: Christian Arnold, Andreas K\"upfer
Abstract: When photographers and other editors of image material produce an image, they make a statement about what matters by situating some objects in the foreground and others in the background. While this prominence of objects is a key analytical category to qualitative scholars, recent quantitative approaches to automated image analysis have not yet made this important distinction but treat all areas of an image similarly. We suggest carefully considering objects' prominence as an essential step in analyzing images as data. Its modeling requires defining an object and operationalizing and measuring how much attention a human eye would pay. Our approach combines qualitative analyses with the scalability of quantitative approaches. Exemplifying object prominence with different implementations -- object size and centeredness, the pixels' image depth, and salient image regions -- we showcase the usefulness of our approach with two applications. First, we scale the ideology of eight US newspapers based on images. Second, we analyze the prominence of women in the campaign videos of the U.S. presidential races in 2016 and 2020. We hope that our article helps all keen to study image data in a conceptually meaningful way at scale.
Authors: Sheng Cheng, Zbigniew A. Starosolski, Devika Subramanian
Abstract: Recent advancements in deep learning for Medical Artificial Intelligence have demonstrated that models can match the diagnostic performance of clinical experts in adult chest X-ray (CXR) interpretation. However, their application in the pediatric context remains limited due to the scarcity of large annotated pediatric image datasets. Additionally, significant challenges arise from the substantial variability in pediatric CXR images across different hospitals and the diverse age range of patients from 0 to 18 years. To address these challenges, we propose SCC, a novel approach that combines transfer learning with self-supervised contrastive learning, augmented by an unsupervised contrast enhancement technique. Transfer learning from a well-trained adult CXR model mitigates issues related to the scarcity of pediatric training data. Contrastive learning with contrast enhancement focuses on the lungs, reducing the impact of image variations and producing high-quality embeddings across diverse pediatric CXR images. We train SCC on one pediatric CXR dataset and evaluate its performance on two other pediatric datasets from different sources. Our results show that SCC's out-of-distribution (zero-shot) performance exceeds regular transfer learning in terms of AUC by 13.6% and 34.6% on the two test datasets. Moreover, with few-shot learning using 10 times fewer labeled images, SCC matches the performance of regular transfer learning trained on the entire labeled dataset. To test the generality of the framework, we verify its performance on three benchmark breast cancer datasets. Starting from a model trained on natural images and fine-tuned on one breast dataset, SCC outperforms the fully supervised learning baseline on the other two datasets in terms of AUC by 3.6% and 5.5% in zero-shot learning.
Authors: Shuangquan Feng, Virginia R. de Sa
Abstract: Automatic facial action unit (AU) recognition is used widely in facial expression analysis. Most existing AU recognition systems aim for cross-participant non-calibrated generalization (NCG) to unseen faces without further calibration. However, due to the diversity of facial attributes across different identities, accurately inferring AU activation from single images of an unseen face is sometimes infeasible, even for human experts -- it is crucial to first understand how the face appears in its neutral expression, or significant bias may be incurred. Therefore, we propose to perform one-frame calibration (OFC) in AU recognition: for each face, a single image of its neutral expression is used as the reference image for calibration. With this strategy, we develop a Calibrating Siamese Network (CSN) for AU recognition and demonstrate its remarkable effectiveness with a simple iResNet-50 (IR50) backbone. On the DISFA, DISFA+, and UNBC-McMaster datasets, we show that our OFC CSN-IR50 model (a) substantially improves the performance of IR50 by mitigating facial attribute biases (including biases due to wrinkles, eyebrow positions, facial hair, etc.), (b) substantially outperforms the naive OFC method of baseline subtraction as well as (c) a fine-tuned version of this naive OFC method, and (d) also outperforms state-of-the-art NCG models for both AU intensity estimation and AU detection.
Authors: Yijian Fan, Zhenbang Yang, Rui Liu, Mingjie Li, Xiaojun Chang
Abstract: Medical report generation is a critical task in healthcare that involves the automatic creation of detailed and accurate descriptions from medical images. Traditionally, this task has been approached as a sequence generation problem, relying on vision-and-language techniques to generate coherent and contextually relevant reports. However, in this paper, we propose a novel perspective: rethinking medical report generation as a multi-label classification problem. By framing the task this way, we leverage the radiology nodes from the commonly used knowledge graph, which can be better captured through classification techniques. To verify our argument, we introduce a novel report generation framework based on BLIP integrated with classified key nodes, which allows for effective report generation with accurate classification of multiple key aspects within the medical images. This approach not only simplifies the report generation process but also significantly enhances performance metrics. Our extensive experiments demonstrate that leveraging key nodes can achieve state-of-the-art (SOTA) performance, surpassing existing approaches across two benchmark datasets. The results underscore the potential of re-envisioning traditional tasks with innovative methodologies, paving the way for more efficient and accurate medical report generation.
Authors: Srija Mukhopadhyay, Abhishek Rajgaria, Prerana Khatiwada, Vivek Gupta, Dan Roth
Abstract: Vision-language models (VLMs) excel at tasks requiring joint understanding of visual and linguistic information. A particularly promising yet under-explored application for these models lies in answering questions based on various kinds of maps. This study investigates the efficacy of VLMs in answering questions based on choropleth maps, which are widely used for data analysis and representation. To facilitate and encourage research in this area, we introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China), each containing 1000 questions. Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning. It also includes maps with discrete and continuous values, encompassing variations in color-mapping, category ordering, and stylistic patterns, enabling comprehensive analysis. We evaluate the performance of multiple VLMs on this benchmark, highlighting gaps in their abilities and providing insights for improving such models.
Authors: Sudarshan Rajagopalan, Vishal M. Patel
Abstract: All-Weather Image Restoration (AWIR) under adverse weather conditions is a challenging task due to the presence of different types of degradations. Prior research in this domain relies on extensive training data but lacks the utilization of additional contextual information for restoration guidance. Consequently, the performance of existing methods is limited by the degradation cues that are learnt from individual training samples. Recent advancements in visual in-context learning have introduced generalist models that are capable of addressing multiple computer vision tasks simultaneously by using the information present in the provided context as a prior. In this paper, we propose All-Weather Image Restoration using Visual In-Context Learning (AWRaCLe), a novel approach for AWIR that innovatively utilizes degradation-specific visual context information to steer the image restoration process. To achieve this, AWRaCLe incorporates Degradation Context Extraction (DCE) and Context Fusion (CF) to seamlessly integrate degradation-specific features from the context into an image restoration network. The proposed DCE and CF blocks leverage CLIP features and incorporate attention mechanisms to adeptly learn and fuse contextual information. These blocks are specifically designed for visual in-context learning under all-weather conditions and are crucial for effective context utilization. Through extensive experiments, we demonstrate the effectiveness of AWRaCLe for all-weather restoration and show that our method advances the state-of-the-art in AWIR.
Authors: Leonardo Ramos Thomas
Abstract: The Real Face Dataset is a pedestrian face detection benchmark dataset in the wild, comprising over 11,000 images and over 55,000 detected faces in various ambient conditions. The dataset aims to provide a comprehensive and diverse collection of real-world face images for the evaluation and development of face detection and recognition algorithms. The Real Face Dataset is a valuable resource for researchers and developers working on face detection and recognition algorithms. With over 11,000 images and 55,000 detected faces, the dataset offers a comprehensive and diverse collection of real-world face images. This diversity is crucial for evaluating the performance of algorithms under various ambient conditions, such as lighting, scale, pose, and occlusion. The dataset's focus on real-world scenarios makes it particularly relevant for practical applications, where faces may be captured in challenging environments. In addition to its size, the dataset's inclusion of images with a high degree of variability in scale, pose, and occlusion, as well as its focus on practical application scenarios, sets it apart as a valuable resource for benchmarking and testing face detection and recognition methods. The challenges presented by the dataset align with the difficulties faced in real-world surveillance applications, where the ability to detect faces and extract discriminative features is paramount. The Real Face Dataset provides an opportunity to assess the performance of face detection and recognition methods on a large scale. Its relevance to real-world scenarios makes it an important resource for researchers and developers aiming to create robust and effective algorithms for practical applications.
Authors: Jiatong Li, Kalliopi Basioti, Vladimir Pavlovic
Abstract: A large amount of procedural videos on the web show how to complete various tasks. These tasks can often be accomplished in different ways and step orderings, with some steps able to be performed simultaneously, while others are constrained to be completed in a specific order. Flow graphs can be used to illustrate the step relationships of a task. Current task-based methods try to learn a single flow graph for all available videos of a specific task. The extracted flow graphs tend to be too abstract, failing to capture detailed step descriptions. In this work, our aim is to learn accurate and rich flow graphs by extracting them from a single video. We propose Box2Flow, an instance-based method to predict a step flow graph from a given procedural video. In detail, we extract bounding boxes from videos, predict pairwise edge probabilities between step pairs, and build the flow graph with a spanning tree algorithm. Experiments on MM-ReS and YouCookII show our method can extract flow graphs effectively.
Authors: Shounak Sural, Naren, Ragunathan Rajkumar
Abstract: In recent years, there has been a notable increase in the development of autonomous vehicle (AV) technologies aimed at improving safety in transportation systems. While AVs have been deployed in the real-world to some extent, a full-scale deployment requires AVs to robustly navigate through challenges like heavy rain, snow, low lighting, construction zones and GPS signal loss in tunnels. To be able to handle these specific challenges, an AV must reliably recognize the physical attributes of the environment in which it operates. In this paper, we define context recognition as the task of accurately identifying environmental attributes for an AV to appropriately deal with them. Specifically, we define 24 environmental contexts capturing a variety of weather, lighting, traffic and road conditions that an AV must be aware of. Motivated by the need to recognize environmental contexts, we create a context recognition dataset called DrivingContexts with more than 1.6 million context-query pairs relevant for an AV. Since traditional supervised computer vision approaches do not scale well to a variety of contexts, we propose a framework called ContextVLM that uses vision-language models to detect contexts using zero- and few-shot approaches. ContextVLM is capable of reliably detecting relevant driving contexts with an accuracy of more than 95% on our dataset, while running in real-time on a 4GB Nvidia GeForce GTX 1050 Ti GPU on an AV with a latency of 10.5 ms per query.
Authors: Yuxiang Guo, Faizan Siddiqui, Yang Zhao, Rama Chellappa, Shao-Yuan Lo
Abstract: Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to focus more on the semantic content of videos, often overlooking emotional stimuli. Hence, most existing MLLMs fall short in estimating viewers' emotional reactions and providing plausible explanations. To address this issue, we propose StimuVAR, a spatiotemporal Stimuli-aware framework for Video Affective Reasoning (VAR) with MLLMs. StimuVAR incorporates a two-level stimuli-aware mechanism: frame-level awareness and token-level awareness. Frame-level awareness involves sampling video frames with events that are most likely to evoke viewers' emotions. Token-level awareness performs tube selection in the token space to make the MLLM concentrate on emotion-triggered spatiotemporal regions. Furthermore, we create VAR instruction data to perform affective training, steering MLLMs' reasoning strengths towards emotional focus and thereby enhancing their affective reasoning ability. To thoroughly assess the effectiveness of VAR, we provide a comprehensive evaluation protocol with extensive metrics. StimuVAR is the first MLLM-based method for viewer-centered VAR. Experiments demonstrate its superiority in understanding viewers' emotional responses to videos and providing coherent and insightful explanations.
Authors: Sandra Zhang Ding, Jiafeng Mao, Kiyoharu Aizawa
Abstract: Based on recent advanced diffusion models, Text-to-image (T2I) generation models have demonstrated their capabilities in generating diverse and high-quality images. However, leveraging their potential for real-world content creation, particularly in providing users with precise control over the image generation result, poses a significant challenge. In this paper, we propose an innovative training-free pipeline that extends existing text-to-image generation models to incorporate a sketch as an additional condition. To generate new images with a layout and structure closely resembling the input sketch, we find that these core features of a sketch can be tracked with the cross-attention maps of diffusion models. We introduce latent optimization, a method that refines the noisy latent at each intermediate step of the generation process using cross-attention maps to ensure that the generated images closely adhere to the desired structure outlined in the reference sketch. Through latent optimization, our method enhances the fidelity and accuracy of image generation, offering users greater control and customization options in content creation.
Authors: Gursimran Singh, Tianxi Hu, Mohammad Akbari, Qiang Tang, Yong Zhang
Abstract: 3D models, particularly AI-generated ones, have witnessed a recent surge across various industries such as entertainment. Hence, there is an alarming need to protect the intellectual property and avoid the misuse of these valuable assets. As a viable solution to address these concerns, we rigorously define the novel task of automated 3D visible watermarking in terms of two competing aspects: watermark quality and asset utility. Moreover, we propose a method of embedding visible watermarks that automatically determines the right location, orientation, and number of watermarks to be placed on arbitrary 3D assets for high watermark quality and asset utility. Our method is based on a novel rigid-body optimization that uses back-propagation to automatically learn transforms for ideal watermark placement. In addition, we propose a novel curvature-matching method for fusing the watermark into the 3D model that further improves readability and security. Finally, we provide a detailed experimental analysis on two benchmark 3D datasets validating the superior performance of our approach in comparison to baselines. Code and demo are available.
Authors: Guang Yang (Paul G. Allen School of Computer Science & Engineering, University of Washington, United States), Muru Zhang (Paul G. Allen School of Computer Science & Engineering, University of Washington, United States), Lin Qiu (Paul G. Allen School of Computer Science & Engineering, University of Washington, United States), Yanming Wan (Paul G. Allen School of Computer Science & Engineering, University of Washington, United States), Noah A. Smith (Paul G. Allen School of Computer Science & Engineering, University of Washington, United States, Allen Institute for Artificial Intelligence, United States)
Abstract: Optical music recognition (OMR) aims to convert music notation into digital formats. One approach to tackle OMR is through a multi-stage pipeline, where the system first detects visual music notation elements in the image (object detection) and then assembles them into a music notation (notation assembly). Most previous work on notation assembly unrealistically assumes perfect object detection. In this study, we focus on the MUSCIMA++ v2.0 dataset, which represents musical notation as a graph with pairwise relationships among detected music objects, and we consider both stages together. First, we introduce a music object detector based on YOLOv8, which improves detection performance. Second, we introduce a supervised training pipeline that completes the notation assembly stage based on detection output. We find that this model is able to outperform existing models trained on perfect detection output, showing the benefit of considering the detection and assembly stages in a more holistic way. These findings, together with our novel evaluation metric, are important steps toward a more complete OMR solution.
Authors: Zi-Wei Sun, Ze-Xi Hua, Heng-Chao Li, Zhi-Peng Qi, Xiang Li, Yan Li, Jin-Chi Zhang
Abstract: A Flying Bird Dataset for Surveillance Videos (FBD-SV-2024) is introduced and tailored for the development and performance evaluation of flying bird detection algorithms in surveillance videos. This dataset comprises 483 video clips, amounting to 28,694 frames in total. Among them, 23,833 frames contain 28,366 instances of flying birds. The proposed dataset of flying birds in surveillance videos is collected from realistic surveillance scenarios, where the birds exhibit characteristics such as inconspicuous features in single frames (in some instances), generally small sizes, and shape variability during flight. These attributes pose challenges that need to be addressed when developing flying bird detection methods for surveillance videos. Finally, advanced (video) object detection algorithms were selected for experimentation on the proposed dataset, and the results demonstrated that this dataset remains challenging for the algorithms above. The FBD-SV-2024 is now publicly available: Please visit https://github.com/Ziwei89/FBD-SV-2024_github for the dataset download link and related processing scripts.
Authors: Jun Li, Jinying Wu, Qiming Li, Feifei Guo
Abstract: With the continuous development of deep learning, the field of repetitive action counting is gradually gaining notice from many researchers. Extraction of pose keypoints using human pose estimation networks is proven to be an effective pose-level method. However, existing pose-level methods suffer from the shortcomings that the single coordinate is not stable enough to handle action distortions due to changes in camera viewpoints, thus failing to accurately identify salient poses, and is vulnerable to misdetection during the transition from the exception to the actual action. To overcome these problems, we propose a simple but efficient Global Multi-geometric Feature Learning Network (GMFL-Net). Specifically, we design a MIA-Module that aims to improve information representation by fusing multi-geometric features, and learning the semantic similarity among the input multi-geometric features. Then, to improve the feature representation from a global perspective, we also design a GBFL-Module that enhances the inter-dependencies between point-wise and channel-wise elements and combines them with the rich local information generated by the MIA-Module to synthesise a comprehensive and most representative global feature representation. In addition, considering the insufficient existing dataset, we collect a new dataset called Countix-Fitness-pose (https://github.com/Wantong66/Countix-Fitness) which contains different cycle lengths and exceptions, a test set with longer duration, and annotate it with fine-grained annotations at the pose-level. We also add two new action classes, namely lunge and rope push-down. Finally, extensive experiments on the challenging RepCount-pose, UCFRep-pose, and Countix-Fitness-pose benchmarks show that our proposed GMFL-Net achieves state-of-the-art performance.
Authors: Makoto M. Itoh, Qingrui Hu, Takayuki Niizato, Hiroaki Kawashima, Keisuke Fujii
Abstract: The study of collective animal behavior, especially in aquatic environments, presents unique challenges and opportunities for understanding movement and interaction patterns in the field of ethology, ecology, and bio-navigation. The Fish Tracking Challenge 2024 (https://ftc-2024.github.io/) introduces a multi-object tracking competition focused on the intricate behaviors of schooling sweetfish. Using the SweetFish dataset, participants are tasked with developing advanced tracking models to accurately monitor the locations of 10 sweetfishes simultaneously. This paper introduces the competition's background, objectives, the SweetFish dataset, and the appraoches of the 1st to 3rd winners and our baseline. By leveraging video data and bounding box annotations, the competition aims to foster innovation in automatic detection and tracking algorithms, addressing the complexities of aquatic animal movements. The challenge provides the importance of multi-object tracking for discovering the dynamics of collective animal behavior, with the potential to significantly advance scientific understanding in the above fields.
Authors: Xiao Fang, Yi Lin, Dong Zhang, Kwang-Ting Cheng, Hao Chen
Abstract: Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability. In this work, we propose ViP, a novel visual symptom-guided prompt learning framework for medical image analysis, which facilitates general knowledge transfer from CLIP. ViP consists of two key components: a visual symptom generator (VSG) and a dual-prompt network. Specifically, VSG aims to extract explicable visual symptoms from pre-trained large language models, while the dual-prompt network utilizes these visual symptoms to guide the training on two learnable prompt modules, i.e., context prompt and merge prompt, which effectively adapts our framework to medical image analysis via large VLMs. Extensive experimental results demonstrate that ViP can outperform state-of-the-art methods on two challenging datasets.
Authors: Zanlin Ni, Yulin Wang, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang
Abstract: Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of steps. However, NATs usually necessitate configuring a complicated generation policy comprising multiple manually-designed scheduling rules. These heuristic-driven rules are prone to sub-optimality and come with the requirements of expert knowledge and labor-intensive efforts. Moreover, their one-size-fits-all nature cannot flexibly adapt to the diverse characteristics of each individual sample. To address these issues, we propose AdaNAT, a learnable approach that automatically configures a suitable policy tailored for every sample to be generated. In specific, we formulate the determination of generation policies as a Markov decision process. Under this framework, a lightweight policy network for generation can be learned via reinforcement learning. Importantly, we demonstrate that simple reward designs such as FID or pre-trained reward models, may not reliably guarantee the desired quality or diversity of generated samples. Therefore, we propose an adversarial reward design to guide the training of policy networks effectively. Comprehensive experiments on four benchmark datasets, i.e., ImageNet-256 & 512, MS-COCO, and CC3M, validate the effectiveness of AdaNAT. Code and pre-trained models will be released at https://github.com/LeapLabTHU/AdaNAT.
Authors: Bonan Liu, Handi Yin, Manuel Kaufmann, Jinhao He, Sammy Christen, Jie Song, Pan Hui
Abstract: We present EgoHDM, an online egocentric-inertial human motion capture (mocap), localization, and dense mapping system. Our system uses 6 inertial measurement units (IMUs) and a commodity head-mounted RGB camera. EgoHDM is the first human mocap system that offers dense scene mapping in near real-time. Further, it is fast and robust to initialize and fully closes the loop between physically plausible map-aware global human motion estimation and mocap-aware 3D scene reconstruction. Our key idea is integrating camera localization and mapping information with inertial human motion capture bidirectionally in our system. To achieve this, we design a tightly coupled mocap-aware dense bundle adjustment and physics-based body pose correction module leveraging a local body-centric elevation map. The latter introduces a novel terrain-aware contact PD controller, which enables characters to physically contact the given local elevation map thereby reducing human floating or penetration. We demonstrate the performance of our system on established synthetic and real-world benchmarks. The results show that our method reduces human localization, camera pose, and mapping accuracy error by 41%, 71%, 46%, respectively, compared to the state of the art. Our qualitative evaluations on newly captured data further demonstrate that EgoHDM can cover challenging scenarios in non-flat terrain including stepping over stairs and outdoor scenes in the wild.
Authors: Kushal Kumar Jain, Ankith Varun J, Anoop Namboodiri
Abstract: Portrait sketching involves capturing identity specific attributes of a real face with abstract lines and shades. Unlike photo-realistic images, a good portrait sketch generation method needs selective attention to detail, making the problem challenging. This paper introduces \textbf{Portrait Sketching StyleGAN (PS-StyleGAN)}, a style transfer approach tailored for portrait sketch synthesis. We leverage the semantic $W+$ latent space of StyleGAN to generate portrait sketches, allowing us to make meaningful edits, like pose and expression alterations, without compromising identity. To achieve this, we propose the use of Attentive Affine transform blocks in our architecture, and a training strategy that allows us to change StyleGAN's output without finetuning it. These blocks learn to modify style latent code by paying attention to both content and style latent features, allowing us to adapt the outputs of StyleGAN in an inversion-consistent manner. Our approach uses only a few paired examples ($\sim 100$) to model a style and has a short training time. We demonstrate PS-StyleGAN's superiority over the current state-of-the-art methods on various datasets, qualitatively and quantitatively.
Authors: Fuchen Zheng, Xuhang Chen, Weihuang Liu, Haolun Li, Yingtie Lei, Jiahui He, Chi-Man Pun, Shounjun Zhou
Abstract: In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless, previous models often falter when segmenting small, irregularly shaped tumors. To this end, we introduce SMAFormer, an efficient, Transformer-based architecture that fuses multiple attention mechanisms for enhanced segmentation of small tumors and organs. SMAFormer can capture both local and global features for medical image segmentation. The architecture comprises two pivotal components. First, a Synergistic Multi-Attention (SMA) Transformer block is proposed, which has the benefits of Pixel Attention, Channel Attention, and Spatial Attention for feature enrichment. Second, addressing the challenge of information loss incurred during attention mechanism transitions and feature fusion, we design a Feature Fusion Modulator. This module bolsters the integration between the channel and spatial attention by mitigating reshaping-induced information attrition. To evaluate our method, we conduct extensive experiments on various medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, achieving state-of-the-art results. Code and models are available at: \url{https://github.com/CXH-Research/SMAFormer}.
Authors: Hsiang-Wei Huang, Jiacheng Sun, Cheng-Yen Yang, Zhongyu Jiang, Li-Yu Huang, Jenq-Neng Hwang, Yu-Ching Yeh
Abstract: Assessing gross motor development in toddlers is crucial for understanding their physical development and identifying potential developmental delays or disorders. However, existing datasets for action recognition primarily focus on adults, lacking the diversity and specificity required for accurate assessment in toddlers. In this paper, we present ToddlerAct, a toddler gross motor action recognition dataset, aiming to facilitate research in early childhood development. The dataset consists of video recordings capturing a variety of gross motor activities commonly observed in toddlers aged under three years old. We describe the data collection process, annotation methodology, and dataset characteristics. Furthermore, we benchmarked multiple state-of-the-art methods including image-based and skeleton-based action recognition methods on our datasets. Our findings highlight the importance of domain-specific datasets for accurate assessment of gross motor development in toddlers and lay the foundation for future research in this critical area. Our dataset will be available at https://github.com/ipl-uw/ToddlerAct.
Authors: Kunming Su, Qiuxia Wu, Panpan Cai, Xiaogang Zhu, Xuequan Lu, Zhiyong Wang, Kun Hu
Abstract: Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational variations. In this paper, we propose a novel Rotation-Invariant Masked AutoEncoders (RI-MAE) to address two major challenges: 1) achieving rotation-invariant latent representations, and 2) facilitating self-supervised reconstruction in a rotation-invariant manner. For the first challenge, we introduce RI-Transformer, which features disentangled geometry content, rotation-invariant relative orientation and position embedding mechanisms for constructing rotation-invariant point cloud latent space. For the second challenge, a novel dual-branch student-teacher architecture is devised. It enables the self-supervised learning via the reconstruction of masked patches within the learned rotation-invariant latent space. Each branch is based on an RI-Transformer, and they are connected with an additional RI-Transformer predictor. The teacher encodes all point patches, while the student solely encodes unmasked ones. Finally, the predictor predicts the latent features of the masked patches using the output latent embeddings from the student, supervised by the outputs from the teacher. Extensive experiments demonstrate that our method is robust to rotations, achieving the state-of-the-art performance on various downstream tasks.
Authors: Mostafa Mansour, Ahmed Abdelsalam, Ari Happonen, Jari Porras, Esa Rahtu
Abstract: Recent advancements in monocular neural depth estimation, particularly those achieved by the UniDepth network, have prompted the investigation of integrating UniDepth within a Gaussian splatting framework for monocular SLAM.This study presents UDGS-SLAM, a novel approach that eliminates the necessity of RGB-D sensors for depth estimation within Gaussian splatting framework. UDGS-SLAM employs statistical filtering to ensure local consistency of the estimated depth and jointly optimizes camera trajectory and Gaussian scene representation parameters. The proposed method achieves high-fidelity rendered images and low ATERMSE of the camera trajectory. The performance of UDGS-SLAM is rigorously evaluated using the TUM RGB-D dataset and benchmarked against several baseline methods, demonstrating superior performance across various scenarios. Additionally, an ablation study is conducted to validate design choices and investigate the impact of different network backbone encoders on system performance.
Authors: Juan E. Tapia, Naser Damer, Christoph Busch, Juan M. Espin, Javier Barrachina, Alvaro S. Rocamora, Kristof Ocvirk, Leon Alessio, Borut Batagelj, Sushrut Patwardhan, Raghavendra Ramachandra, Raghavendra Mudgalgundurao, Kiran Raja, Daniel Schulz, Carlos Aravena
Abstract: This paper summarises the Competition on Presentation Attack Detection on ID Cards (PAD-IDCard) held at the 2024 International Joint Conference on Biometrics (IJCB2024). The competition attracted a total of ten registered teams, both from academia and industry. In the end, the participating teams submitted five valid submissions, with eight models to be evaluated by the organisers. The competition presented an independent assessment of current state-of-the-art algorithms. Today, no independent evaluation on cross-dataset is available; therefore, this work determined the state-of-the-art on ID cards. To reach this goal, a sequestered test set and baseline algorithms were used to evaluate and compare all the proposals. The sequestered test dataset contains ID cards from four different countries. In summary, a team that chose to be "Anonymous" reached the best average ranking results of 74.80%, followed very closely by the "IDVC" team with 77.65%.
Authors: YuanZheng Wu, Jin Liu, Shunping Ji
Abstract: Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention. However, the unstructured nature of 3DGS poses challenges for large-scale surface reconstruction from aerial images. To address this gap, we propose the first large-scale surface reconstruction method for multi-view stereo (MVS) aerial images based on 3DGS, named Aerial Gaussian Splatting (AGS). Initially, we introduce a data chunking method tailored for large-scale aerial imagery, making the modern 3DGS technology feasible for surface reconstruction over extensive scenes. Additionally, we integrate the Ray-Gaussian Intersection method to obtain normal and depth information, facilitating geometric constraints. Finally, we introduce a multi-view geometric consistency constraint to enhance global geometric consistency and improve reconstruction accuracy. Our experiments on multiple datasets demonstrate for the first time that the GS-based technique can match traditional aerial MVS methods on geometric accuracy, and beat state-of-the-art GS-based methods on geometry and rendering quality.
Authors: Qingbin Tian, Yukang Huo, Mingyuan Yao, Haihua Wang
Abstract: Dead fish frequently appear on the water surface due to various factors. If not promptly detected and removed, these dead fish can cause significant issues such as water quality deterioration, ecosystem damage, and disease transmission. Consequently, it is imperative to develop rapid and effective detection methods to mitigate these challenges. Conventional methods for detecting dead fish are often constrained by manpower and time limitations, struggling to effectively manage the intricacies of aquatic environments. This paper proposes an end-to-end detection model built upon an enhanced YOLOv10 framework, designed specifically to swiftly and precisely detect deceased fish across extensive water surfaces.Key enhancements include: (1) Replacing YOLOv10's backbone network with FasterNet to reduce model complexity while maintaining high detection accuracy; (2) Improving feature fusion in the Neck section through enhanced connectivity methods and replacing the original C2f module with CSPStage modules; (3) Adding a compact target detection head to enhance the detection performance of smaller objects. Experimental results demonstrate significant improvements in P(precision), R(recall), and AP(average precision) compared to the baseline model YOLOv10n. Furthermore, our model outperforms other models in the YOLO series by significantly reducing model size and parameter count, while sustaining high inference speed and achieving optimal AP performance. The model facilitates rapid and accurate detection of dead fish in large-scale aquaculture systems. Finally, through ablation experiments, we systematically analyze and assess the contribution of each model component to the overall system performance.
Authors: Yu-Fan Lin, Ching-Heng Cheng, Bo-Cheng Qiu, Cheng-Jun Kang, Chia-Ming Lee, Chih-Chung Hsu
Abstract: Fusarium Head Blight (FHB) is a serious fungal disease affecting wheat (including durum), barley, oats, other small cereal grains, and corn. Effective monitoring and accurate detection of FHB are crucial to ensuring stable and reliable food security. Traditionally, trained agronomists and surveyors perform manual identification, a method that is labor-intensive, impractical, and challenging to scale. With the advancement of deep learning and Hyper-spectral Imaging (HSI) and Remote Sensing (RS) technologies, employing deep learning, particularly Convolutional Neural Networks (CNNs), has emerged as a promising solution. Notably, wheat infected with serious FHB may exhibit significant differences on the spectral compared to mild FHB one, which is particularly advantageous for hyperspectral image-based methods. In this study, we propose a self-unsupervised classification method based on HSI endmember extraction strategy and top-K bands selection, designed to analyze material signatures in HSIs to derive discriminative feature representations. This approach does not require expensive device or complicate algorithm design, making it more suitable for practical uses. Our method has been effectively validated in the Beyond Visible Spectrum: AI for Agriculture Challenge 2024. The source code is easy to reproduce and available at {https://github.com/VanLinLin/Automated-Crop-Disease-Diagnosis-from-Hyperspectral-Imagery-3rd}.
URLs: https://github.com/VanLinLin/Automated-Crop-Disease-Diagnosis-from-Hyperspectral-Imagery-3rd
Authors: Munish Monga, Sachin Kumar Giroh, Ankit Jha, Mainak Singha, Biplab Banerjee, Jocelyn Chanussot
Abstract: Multi-Target Domain Adaptation (MTDA) entails learning domain-invariant information from a single source domain and applying it to multiple unlabeled target domains. Yet, existing MTDA methods predominantly focus on addressing domain shifts within visual features, often overlooking semantic features and struggling to handle unknown classes, resulting in what is known as Open-Set (OS) MTDA. While large-scale vision-language foundation models like CLIP show promise, their potential for MTDA remains largely unexplored. This paper introduces COSMo, a novel method that learns domain-agnostic prompts through source domain-guided prompt learning to tackle the MTDA problem in the prompt space. By leveraging a domain-specific bias network and separate prompts for known and unknown classes, COSMo effectively adapts across domain and class shifts. To the best of our knowledge, COSMo is the first method to address Open-Set Multi-Target DA (OSMTDA), offering a more realistic representation of real-world scenarios and addressing the challenges of both open-set and multi-target DA. COSMo demonstrates an average improvement of $5.1\%$ across three challenging datasets: Mini-DomainNet, Office-31, and Office-Home, compared to other related DA methods adapted to operate within the OSMTDA setting. Code is available at: https://github.com/munish30monga/COSMo
Authors: Shangquan Sun, Wenqi Ren, Juxiang Zhou, Jianhou Gan, Rui Wang, Xiaochun Cao
Abstract: Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch hybrid Transformer-Mamba network, denoted as TransMamba, aimed at effectively capturing long-range rain-related dependencies. Based on the prior of distinct spectral-domain features of rain degradation and background, we design a spectral-banded Transformer blocks on the first branch. Self-attention is executed within the combination of the spectral-domain channel dimension to improve the ability of modeling long-range dependencies. To enhance frequency-specific information, we present a spectral enhanced feed-forward module that aggregates features in the spectral domain. In the second branch, Mamba layers are equipped with cascaded bidirectional state space model modules to additionally capture the modeling of both local and global information. At each stage of both the encoder and decoder, we perform channel-wise concatenation of dual-branch features and achieve feature fusion through channel reduction, enabling more effective integration of the multi-scale information from the Transformer and Mamba branches. To better reconstruct innate signal-level relations within clean images, we also develop a spectral coherence loss. Extensive experiments on diverse datasets and real-world images demonstrate the superiority of our method compared against the state-of-the-art approaches.
Authors: Longyun Liao, Rong Zheng
Abstract: 2D-to-3D human pose lifting is an ill-posed problem due to depth ambiguity and occlusion. Existing methods relying on spatial and temporal consistency alone are insufficient to resolve these problems because they lack semantic information of the motions. To overcome this, we propose ActionPose, a framework that leverages action knowledge by aligning motion embeddings with text embeddings of fine-grained action labels. ActionPose operates in two stages: pretraining and fine-tuning. In the pretraining stage, the model learns to recognize actions and reconstruct 3D poses from masked and noisy 2D poses. During the fine-tuning stage, the model is further refined using real-world 3D human pose estimation datasets without action labels. Additionally, our framework incorporates masked body parts and masked time windows in motion modeling to mitigate the effects of ambiguous boundaries between actions in both temporal and spatial domains. Experiments demonstrate the effectiveness of ActionPose, achieving state-of-the-art performance in 3D pose estimation on public datasets, including Human3.6M and MPI-INF-3DHP. Specifically, ActionPose achieves an MPJPE of 36.7mm on Human3.6M with detected 2D poses as input and 15.5mm on MPI-INF-3DHP with ground-truth 2D poses as input.
Authors: Jacob Fein-Ashley, Rajgopal Kannan, Viktor Prasanna
Abstract: Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often struggle with the noisy nature of the SAR data, frequently learning from background noise rather than the most relevant image features. Attention mechanisms address this limitation by focusing on crucial image components, such as the shadows and small parts of a vehicle, which are crucial for accurate target classification. By dynamically prioritizing these significant features, attention-based models can efficiently characterize the entire image with a few pixels, thus enhancing recognition performance. This capability allows for the discrimination of targets from background clutter, leading to more practical and robust SAR ATR models. We show that attention modules increase top-1 accuracy, improve input robustness, and are qualitatively more explainable on the MSTAR dataset.
Authors: Shentong Mo, Haofan Wang
Abstract: Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale visual features to localize sounding objects in each image. Despite their promising performance, they omitted multi-scale visual features of the corresponding image, and they cannot learn discriminative regions compared to ground truths. To address this issue, we propose a novel multi-scale multi-instance visual sound localization framework, namely M2VSL, that can directly learn multi-scale semantic features associated with sound sources from the input image to localize sounding objects. Specifically, our M2VSL leverages learnable multi-scale visual features to align audio-visual representations at multi-level locations of the corresponding image. We also introduce a novel multi-scale multi-instance transformer to dynamically aggregate multi-scale cross-modal representations for visual sound localization. We conduct extensive experiments on VGGSound-Instruments, VGG-Sound Sources, and AVSBench benchmarks. The results demonstrate that the proposed M2VSL can achieve state-of-the-art performance on sounding object localization and segmentation.
Authors: Bin Hu, Run Luo, Zelin Liu, Cheng Wang, Wenyu Liu
Abstract: Temporal motion modeling has always been a key component in multiple object tracking (MOT) which can ensure smooth trajectory movement and provide accurate positional information to enhance association precision. However, current motion models struggle to be both efficient and effective across different application scenarios. To this end, we propose TrackSSM inspired by the recently popular state space models (SSM), a unified encoder-decoder motion framework that uses data-dependent state space model to perform temporal motion of trajectories. Specifically, we propose Flow-SSM, a module that utilizes the position and motion information from historical trajectories to guide the temporal state transition of object bounding boxes. Based on Flow-SSM, we design a flow decoder. It is composed of a cascaded motion decoding module employing Flow-SSM, which can use the encoded flow information to complete the temporal position prediction of trajectories. Additionally, we propose a Step-by-Step Linear (S$^2$L) training strategy. By performing linear interpolation between the positions of the object in the previous frame and the current frame, we construct the pseudo labels of step-by-step linear training, ensuring that the trajectory flow information can better guide the object bounding box in completing temporal transitions. TrackSSM utilizes a simple Mamba-Block to build a motion encoder for historical trajectories, forming a temporal motion model with an encoder-decoder structure in conjunction with the flow decoder. TrackSSM is applicable to various tracking scenarios and achieves excellent tracking performance across multiple benchmarks, further extending the potential of SSM-like temporal motion models in multi-object tracking tasks.
Authors: Chia-Yu Hsu, Wenwen Li, Sizhe Wang
Abstract: Research on geospatial foundation models (GFMs) has become a trending topic in geospatial artificial intelligence (AI) research due to their potential for achieving high generalizability and domain adaptability, reducing model training costs for individual researchers. Unlike large language models, such as ChatGPT, constructing visual foundation models for image analysis, particularly in remote sensing, encountered significant challenges such as formulating diverse vision tasks into a general problem framework. This paper evaluates the recently released NASA-IBM GFM Prithvi for its predictive performance on high-level image analysis tasks across multiple benchmark datasets. Prithvi was selected because it is one of the first open-source GFMs trained on time-series of high-resolution remote sensing imagery. A series of experiments were designed to assess Prithvi's performance as compared to other pre-trained task-specific AI models in geospatial image analysis. New strategies, including band adaptation, multi-scale feature generation, and fine-tuning techniques, are introduced and integrated into an image analysis pipeline to enhance Prithvi's domain adaptation capability and improve model performance. In-depth analyses reveal Prithvi's strengths and weaknesses, offering insights for both improving Prithvi and developing future visual foundation models for geospatial tasks.
Authors: Vage Egiazarian, Denis Kuznedelev, Anton Voronov, Ruslan Svirschevski, Michael Goin, Daniil Pavlov, Dan Alistarh, Dmitry Baranchuk
Abstract: Text-to-image diffusion models have emerged as a powerful framework for high-quality image generation given textual prompts. Their success has driven the rapid development of production-grade diffusion models that consistently increase in size and already contain billions of parameters. As a result, state-of-the-art text-to-image models are becoming less accessible in practice, especially in resource-limited environments. Post-training quantization (PTQ) tackles this issue by compressing the pretrained model weights into lower-bit representations. Recent diffusion quantization techniques primarily rely on uniform scalar quantization, providing decent performance for the models compressed to 4 bits. This work demonstrates that more versatile vector quantization (VQ) may achieve higher compression rates for large-scale text-to-image diffusion models. Specifically, we tailor vector-based PTQ methods to recent billion-scale text-to-image models (SDXL and SDXL-Turbo), and show that the diffusion models of 2B+ parameters compressed to around 3 bits using VQ exhibit the similar image quality and textual alignment as previous 4-bit compression techniques.
Authors: Lemeng Zhao, Junjie Hu, Jianchao Bi, Yanbing Bai, Erick Mas, Shunichi Koshimura
Abstract: In recent years, unmanned aerial vehicles (UAVs) have played an increasingly crucial role in supporting disaster emergency response efforts by analyzing aerial images. While current deep-learning models focus on improving accuracy, they often overlook the limited computing resources of UAVs. This study recognizes the imperative for real-time data processing in disaster response scenarios and introduces a lightweight and efficient approach for aerial video understanding. Our methodology identifies redundant portions within the video through policy networks and eliminates this excess information using frame compression techniques. Additionally, we introduced the concept of a `station point,' which leverages future information in the sequential policy network, thereby enhancing accuracy. To validate our method, we employed the wildfire FLAME dataset. Compared to the baseline, our approach reduces computation costs by more than 13 times while boosting accuracy by 3$\%$. Moreover, our method can intelligently select salient frames from the video, refining the dataset. This feature enables sophisticated models to be effectively trained on a smaller dataset, significantly reducing the time spent during the training process.
Authors: William Heyden, Habib Ullah, M. Salman Siddiqui, Fadi Al Machot
Abstract: In Generalized Zero-Shot Learning (GZSL), we aim to recognize both seen and unseen categories using a model trained only on seen categories. In computer vision, this translates into a classification problem, where knowledge from seen categories is transferred to unseen categories by exploiting the relationships between visual features and available semantic information, such as text corpora or manual annotations. However, learning this joint distribution is costly and requires one-to-one training with corresponding semantic information. We present a reversed conditional Diffusion-based model (RevCD) that mitigates this issue by generating semantic features synthesized from visual inputs by leveraging Diffusion models' conditional mechanisms. Our RevCD model consists of a cross Hadamard-Addition embedding of a sinusoidal time schedule and a multi-headed visual transformer for attention-guided embeddings. The proposed approach introduces three key innovations. First, we reverse the process of generating semantic space based on visual data, introducing a novel loss function that facilitates more efficient knowledge transfer. Second, we apply Diffusion models to zero-shot learning - a novel approach that exploits their strengths in capturing data complexity. Third, we demonstrate our model's performance through a comprehensive cross-dataset evaluation. The complete code will be available on GitHub.
Authors: Shivam Pande, Baki Uzun, Florent Guiotte, Thomas Corpetti, Florian Delerue, S\'ebastien Lef\`evre
Abstract: In this study, we tackle the challenge of identifying plant species from ultra high resolution (UHR) remote sensing images. Our approach involves introducing an RGB remote sensing dataset, characterized by millimeter-level spatial resolution, meticulously curated through several field expeditions across a mountainous region in France covering various landscapes. The task of plant species identification is framed as a semantic segmentation problem for its practical and efficient implementation across vast geographical areas. However, when dealing with segmentation masks, we confront instances where distinguishing boundaries between plant species and their background is challenging. We tackle this issue by introducing a fuzzy loss within the segmentation model. Instead of utilizing one-hot encoded ground truth (GT), our model incorporates Gaussian filter refined GT, introducing stochasticity during training. First experimental results obtained on both our UHR dataset and a public dataset are presented, showing the relevance of the proposed methodology, as well as the need for future improvement.
Authors: Baki Uzun, Shivam Pande, Gwendal Cachin-Bernard, Minh-Tan Pham, S\'ebastien Lef\`evre, Rumais Blatrix, Doyle McKey
Abstract: Regular patterns of vegetation are considered widespread landscapes, although their global extent has never been estimated. Among them, spotted landscapes are of particular interest in the context of climate change. Indeed, regularly spaced vegetation spots in semi-arid shrublands result from extreme resource depletion and prefigure catastrophic shift of the ecosystem to a homogeneous desert, while termite mounds also producing spotted landscapes were shown to increase robustness to climate change. Yet, their identification at large scale calls for automatic methods, for instance using the popular deep learning framework, able to cope with a vast amount of remote sensing data, e.g., optical satellite imagery. In this paper, we tackle this problem and benchmark some state-of-the-art deep networks on several landscapes and geographical areas. Despite the promising results we obtained, we found that more research is needed to be able to map automatically these earth mounds from space.
Authors: Alper Canberk, Maksym Bondarenko, Ege Ozguroglu, Ruoshi Liu, Carl Vondrick
Abstract: Creative processes such as painting often involve creating different components of an image one by one. Can we build a computational model to perform this task? Prior works often fail by making global changes to the image, inserting objects in unrealistic spatial locations, and generating inaccurate lighting details. We observe that while state-of-the-art models perform poorly on object insertion, they can remove objects and erase the background in natural images very well. Inverting the direction of object removal, we obtain high-quality data for learning to insert objects that are spatially, physically, and optically consistent with the surroundings. With this scalable automatic data generation pipeline, we can create a dataset for learning object insertion, which is used to train our proposed text conditioned diffusion model. Qualitative and quantitative experiments have shown that our model achieves state-of-the-art results in object insertion, particularly for in-the-wild images. We show compelling results on diverse insertion prompts and images across various domains.In addition, we automate iterative insertion by combining our insertion model with beam search guided by CLIP.
Authors: Sayan Rakshit, Hmrishav Bandyopadhyay, Nibaran Das, Biplab Banerjee
Abstract: Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new domains. We illuminate this current neural network model weakness and develop a forgetting-resistant incremental learning strategy. Here, we propose a new unsupervised incremental open-set domain adaptation (IOSDA) issue for image classification. Open-set domain adaptation adds complexity to the incremental domain adaptation issue since each target domain has more classes than the Source domain. In IOSDA, the model learns training with domain streams phase by phase in incremented time. Inference uses test data from all target domains without revealing their identities. We proposed IOSDA-Net, a two-stage learning pipeline, to solve the problem. The first module replicates prior domains from random noise using a generative framework and creates a pseudo source domain. In the second step, this pseudo source is adapted to the present target domain. We test our model on Office-Home, DomainNet, and UPRN-RSDA, a newly curated optical remote sensing dataset.
Authors: Sicheng Wang, Che Liu, Rossella Arcucci
Abstract: Recent advancements in medical vision-language pre-training (MedVLP) have significantly enhanced zero-shot medical vision tasks such as image classification by leveraging large-scale medical image-text pair pre-training. However, the performance of these tasks can be heavily influenced by the variability in textual prompts describing the categories, necessitating robustness in MedVLP models to diverse prompt styles. Yet, this sensitivity remains underexplored. In this work, we are the first to systematically assess the sensitivity of three widely-used MedVLP methods to a variety of prompts across 15 different diseases. To achieve this, we designed six unique prompt styles to mirror real clinical scenarios, which were subsequently ranked by interpretability. Our findings indicate that all MedVLP models evaluated show unstable performance across different prompt styles, suggesting a lack of robustness. Additionally, the models' performance varied with increasing prompt interpretability, revealing difficulties in comprehending complex medical concepts. This study underscores the need for further development in MedVLP methodologies to enhance their robustness to diverse zero-shot prompts.
Authors: Fazle Rahat, M Shifat Hossain, Md Rubel Ahmed, Sumit Kumar Jha, Rickard Ewetz
Abstract: Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation, translation, and resizing. Recent approaches use generative AI models to improve dataset diversity. However, the generative methods struggle with issues such as subject corruption and the introduction of irrelevant artifacts. In this paper, we propose the Automated Generative Data Augmentation (AGA). The framework combines the utility of large language models (LLMs), diffusion models, and segmentation models to augment data. AGA preserves foreground authenticity while ensuring background diversity. Specific contributions include: i) segment and superclass based object extraction, ii) prompt diversity with combinatorial complexity using prompt decomposition, and iii) affine subject manipulation. We evaluate AGA against state-of-the-art (SOTA) techniques on three representative datasets, ImageNet, CUB, and iWildCam. The experimental evaluation demonstrates an accuracy improvement of 15.6% and 23.5% for in and out-of-distribution data compared to baseline models, respectively. There is also a 64.3% improvement in SIC score compared to the baselines.
Authors: Yuanwei Li, Elizaveta Ivanova, Martins Bruveris
Abstract: Automatic image anomaly detection is important for quality inspection in the manufacturing industry. The usual unsupervised anomaly detection approach is to train a model for each object class using a dataset of normal samples. However, a more realistic problem is zero-/few-shot anomaly detection where zero or only a few normal samples are available. This makes the training of object-specific models challenging. Recently, large foundation vision-language models have shown strong zero-shot performance in various downstream tasks. While these models have learned complex relationships between vision and language, they are not specifically designed for the tasks of anomaly detection. In this paper, we propose the Few-shot/zero-shot Anomaly Detection Engine (FADE) which leverages the vision-language CLIP model and adjusts it for the purpose of industrial anomaly detection. Specifically, we improve language-guided anomaly segmentation 1) by adapting CLIP to extract multi-scale image patch embeddings that are better aligned with language and 2) by automatically generating an ensemble of text prompts related to industrial anomaly detection. 3) We use additional vision-based guidance from the query and reference images to further improve both zero-shot and few-shot anomaly detection. On the MVTec-AD (and VisA) dataset, FADE outperforms other state-of-the-art methods in anomaly segmentation with pixel-AUROC of 89.6% (91.5%) in zero-shot and 95.4% (97.5%) in 1-normal-shot. Code is available at https://github.com/BMVC-FADE/BMVC-FADE.
Authors: Hanxin Zhu, Tianyu He, Anni Tang, Junliang Guo, Zhibo Chen, Jiang Bian
Abstract: Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual concepts within the generated video, such as the motion and appearance of specific characters and the movement of viewpoints. In this work, we propose a novel paradigm that generates each concept in 3D representation separately and then composes them with priors from Large Language Models (LLM) and 2D diffusion models. Specifically, given an input textual prompt, our scheme consists of three stages: 1) We leverage LLM as the director to first decompose the complex query into several sub-prompts that indicate individual concepts within the video~(\textit{e.g.}, scene, objects, motions), then we let LLM to invoke pre-trained expert models to obtain corresponding 3D representations of concepts. 2) To compose these representations, we prompt multi-modal LLM to produce coarse guidance on the scales and coordinates of trajectories for the objects. 3) To make the generated frames adhere to natural image distribution, we further leverage 2D diffusion priors and use Score Distillation Sampling to refine the composition. Extensive experiments demonstrate that our method can generate high-fidelity videos from text with diverse motion and flexible control over each concept. Project page: \url{https://aka.ms/c3v}.
URLs: https://aka.ms/c3v
Authors: Sanuwani Dayarathna, Kh Tohidul Islam, Bohan Zhuang, Guang Yang, Jianfei Cai, Meng Law, Zhaolin Chen
Abstract: Magnetic Resonance Imaging (MRI) is instrumental in clinical diagnosis, offering diverse contrasts that provide comprehensive diagnostic information. However, acquiring multiple MRI contrasts is often constrained by high costs, long scanning durations, and patient discomfort. Current synthesis methods, typically focused on single-image contrasts, fall short in capturing the collective nuances across various contrasts. Moreover, existing methods for multi-contrast MRI synthesis often fail to accurately map feature-level information across multiple imaging contrasts. We introduce McCaD (Multi-Contrast MRI Conditioned Adaptive Adversarial Diffusion), a novel framework leveraging an adversarial diffusion model conditioned on multiple contrasts for high-fidelity MRI synthesis. McCaD significantly enhances synthesis accuracy by employing a multi-scale, feature-guided mechanism, incorporating denoising and semantic encoders. An adaptive feature maximization strategy and a spatial feature-attentive loss have been introduced to capture more intrinsic features across multiple contrasts. This facilitates a precise and comprehensive feature-guided denoising process. Extensive experiments on tumor and healthy multi-contrast MRI datasets demonstrated that the McCaD outperforms state-of-the-art baselines quantitively and qualitatively. The code is provided with supplementary materials.
Authors: Biyuan Liu, Huaixin Chen, Huiyao Zhan, Sijie Luo, Zhou Huang
Abstract: Despite the eye-catching breakthroughs achieved by deep visual networks in detecting region-level surface defects, the challenge of high-quality pixel-wise defect detection remains due to diverse defect appearances and data scarcity. To avoid over-reliance on defect appearance and achieve accurate defect segmentation, we proposed a change-aware Siamese network that solves the defect segmentation in a change detection framework. A novel multi-class balanced contrastive loss is introduced to guide the Transformer-based encoder, which enables encoding diverse categories of defects as the unified class-agnostic difference between defect and defect-free images. The difference presented by a distance map is then skip-connected to the change-aware decoder to assist in the location of both inter-class and out-of-class pixel-wise defects. In addition, we proposed a synthetic dataset with multi-class liquid crystal display (LCD) defects under a complex and disjointed background context, to demonstrate the advantages of change-based modeling over appearance-based modeling for defect segmentation. In our proposed dataset and two public datasets, our model achieves superior performances than the leading semantic segmentation methods, while maintaining a relatively small model size. Moreover, our model achieves a new state-of-the-art performance compared to the semi-supervised approaches in various supervision settings.
Authors: Shaorong Sun, Shuchao Pang, Yazhou Yao, Xiaoshui Huang
Abstract: The controllability of 3D object generation methods is achieved through input text. Existing text-to-3D object generation methods primarily focus on generating a single object based on a single object description. However, these methods often face challenges in producing results that accurately correspond to our desired positions when the input text involves multiple objects. To address the issue of controllability in generating multiple objects, this paper introduces COMOGen, a COntrollable text-to-3D Multi-Object Generation framework. COMOGen enables the simultaneous generation of multiple 3D objects by the distillation of layout and multi-view prior knowledge. The framework consists of three modules: the layout control module, the multi-view consistency control module, and the 3D content enhancement module. Moreover, to integrate these three modules as an integral framework, we propose Layout Multi-view Score Distillation, which unifies two prior knowledge and further enhances the diversity and quality of generated 3D content. Comprehensive experiments demonstrate the effectiveness of our approach compared to the state-of-the-art methods, which represents a significant step forward in enabling more controlled and versatile text-based 3D content generation.
Authors: Xujie Wan, Wenjie Li, Guangwei Gao, Huimin Lu, Jian Yang, Chia-Wen Lin
Abstract: Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multi-scale features and promote their complementarity is crucial for enhancing FSR. However, existing hybrid network-based FSR methods ignore this, only simply combining the Transformer and CNN. To address this issue, we propose an attention-guided Multi-scale interaction network (AMINet), which contains local and global feature interactions as well as encoder-decoder phases feature interactions. Specifically, we propose a Local and Global Feature Interaction Module (LGFI) to promote fusions of global features and different receptive fields' local features extracted by our Residual Depth Feature Extraction Module (RDFE). Additionally, we propose a Selective Kernel Attention Fusion Module (SKAF) to adaptively select fusions of different features within LGFI and encoder-decoder phases. Our above design allows the free flow of multi-scale features from within modules and between encoder and decoder, which can promote the complementarity of different scale features to enhance FSR. Comprehensive experiments confirm that our method consistently performs well with less computational consumption and faster inference.
Authors: Xuefeng Liang, Zhenyou Liu, Jian Lin, Xiaohui Yang, Takatsune Kumada
Abstract: Previous Facial Beauty Prediction (FBP) methods generally model FB feature of an image as a point on the latent space, and learn a mapping from the point to a precise score. Although existing regression methods perform well on a single dataset, they are inclined to be sensitive to test data and have weak generalization ability. We think they underestimate two inconsistencies existing in the FBP problem: 1. inconsistency of FB standards among multiple datasets, and 2. inconsistency of human cognition on FB of an image. To address these issues, we propose a new Uncertainty-oriented Order Learning (UOL), where the order learning addresses the inconsistency of FB standards by learning the FB order relations among face images rather than a mapping, and the uncertainty modeling represents the inconsistency in human cognition. The key contribution of UOL is a designed distribution comparison module, which enables conventional order learning to learn the order of uncertain data. Extensive experiments on five datasets show that UOL outperforms the state-of-the-art methods on both accuracy and generalization ability.
Authors: Xinhe Xu, Zhuoer Wang, Yihan Zhang, Yizhou Liu, Zhaoyue Wang, Zhihao Xu, Muhan Zhao
Abstract: This article compares two style transfer methods in image processing: the traditional method, which synthesizes new images by stitching together small patches from existing images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background. The traditional method excels in creating artistic abstractions but can struggle with seamlessness, whereas the machine learning method preserves the integrity of foreground elements while enhancing the background, offering improved aesthetic quality and computational efficiency. Our study indicates that machine learning-based methods are more suited for real-world applications where detail preservation in foreground elements is essential.
Authors: Lipeng Gu, Mingqiang Wei, Xuefeng Yan, Dingkun Zhu, Wei Zhao, Haoran Xie, Yong-Jin Liu
Abstract: Multi-modal 3D multi-object tracking (MOT) typically necessitates extensive computational costs of deep neural networks (DNNs) to extract multi-modal representations. In this paper, we propose an intriguing question: May we learn from multiple modalities only during training to avoid multi-modal input in the inference phase? To answer it, we propose \textbf{YOLOO}, a novel multi-modal 3D MOT paradigm: You Only Learn from Others Once. YOLOO empowers the point cloud encoder to learn a unified tri-modal representation (UTR) from point clouds and other modalities, such as images and textual cues, all at once. Leveraging this UTR, YOLOO achieves efficient tracking solely using the point cloud encoder without compromising its performance, fundamentally obviating the need for computationally intensive DNNs. Specifically, YOLOO includes two core components: a unified tri-modal encoder (UTEnc) and a flexible geometric constraint (F-GC) module. UTEnc integrates a point cloud encoder with image and text encoders adapted from pre-trained CLIP. It seamlessly fuses point cloud information with rich visual-textual knowledge from CLIP into the point cloud encoder, yielding highly discriminative UTRs that facilitate the association between trajectories and detections. Additionally, F-GC filters out mismatched associations with similar representations but significant positional discrepancies. It further enhances the robustness of UTRs without requiring any scene-specific tuning, addressing a key limitation of customized geometric constraints (e.g., 3D IoU). Lastly, high-quality 3D trajectories are generated by a traditional data association component. By integrating these advancements into a multi-modal 3D MOT scheme, our YOLOO achieves substantial gains in both robustness and efficiency.
Authors: Xiaoyu Zhang, Guangwei Liu, Zihao Liu, Ningyi Xu, Yunhui Liu, Ji Zhao
Abstract: In autonomous driving, there is growing interest in end-to-end online vectorized map perception in bird's-eye-view (BEV) space, with an expectation that it could replace traditional high-cost offline high-definition (HD) maps. However, the accuracy and robustness of these methods can be easily compromised in challenging conditions, such as occlusion or adverse weather, when relying only on onboard sensors. In this paper, we propose HRMapNet, leveraging a low-cost Historical Rasterized Map to enhance online vectorized map perception. The historical rasterized map can be easily constructed from past predicted vectorized results and provides valuable complementary information. To fully exploit a historical map, we propose two novel modules to enhance BEV features and map element queries. For BEV features, we employ a feature aggregation module to encode features from both onboard images and the historical map. For map element queries, we design a query initialization module to endow queries with priors from the historical map. The two modules contribute to leveraging map information in online perception. Our HRMapNet can be integrated with most online vectorized map perception methods. We integrate it in two state-of-the-art methods, significantly improving their performance on both the nuScenes and Argoverse 2 datasets. The source code is released at https://github.com/HXMap/HRMapNet.
Authors: Manthan Chelenahalli Satish, Duo Lu, Bharatesh Chakravarthi, Mohammad Farhadi, Yezhou Yang
Abstract: Traffic roundabouts, as complex and critical road scenarios, pose significant safety challenges for autonomous vehicles. In particular, the encounter of a vehicle with a dilemma zone (DZ) at a roundabout intersection is a pivotal concern. This paper presents an automated system that leverages trajectory forecasting to predict DZ events, specifically at traffic roundabouts. Our system aims to enhance safety standards in both autonomous and manual transportation. The core of our approach is a modular, graph-structured recurrent model that forecasts the trajectories of diverse agents, taking into account agent dynamics and integrating heterogeneous data, such as semantic maps. This model, based on graph neural networks, aids in predicting DZ events and enhances traffic management decision-making. We evaluated our system using a real-world dataset of traffic roundabout intersections. Our experimental results demonstrate that our dilemma forecasting system achieves a high precision with a low false positive rate of 0.1. This research represents an advancement in roundabout DZ data mining and forecasting, contributing to the assurance of intersection safety in the era of autonomous vehicles.
Authors: Dingyuan Zhang, Dingkang Liang, Zichang Tan, Xiaoqing Ye, Cheng Zhang, Jingdong Wang, Xiang Bai
Abstract: Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. Although many sparse query-based methods have already attempted to improve the efficiency of 3D detectors, they neglect to consider the backbone, especially when using Vision Transformers (ViT) for better performance. To tackle this problem, we explore the efficient ViT backbones for multi-view 3D detection via token compression and propose a simple yet effective method called TokenCompression3D (ToC3D). By leveraging history object queries as foreground priors of high quality, modeling 3D motion information in them, and interacting them with image tokens through the attention mechanism, ToC3D can effectively determine the magnitude of information densities of image tokens and segment the salient foreground tokens. With the introduced dynamic router design, ToC3D can weigh more computing resources to important foreground tokens while compressing the information loss, leading to a more efficient ViT-based multi-view 3D detector. Extensive results on the large-scale nuScenes dataset show that our method can nearly maintain the performance of recent SOTA with up to 30% inference speedup, and the improvements are consistent after scaling up the ViT and input resolution. The code will be made at https://github.com/DYZhang09/ToC3D.
Authors: Gangwei Xu, Xianqi Wang, Zhaoxing Zhang, Junda Cheng, Chunyuan Liao, Xin Yang
Abstract: Stereo matching is a core component in many computer vision and robotics systems. Despite significant advances over the last decade, handling matching ambiguities in ill-posed regions and large disparities remains an open challenge. In this paper, we propose a new deep network architecture, called IGEV++, for stereo matching. The proposed IGEV++ builds Multi-range Geometry Encoding Volumes (MGEV) that encode coarse-grained geometry information for ill-posed regions and large disparities and fine-grained geometry information for details and small disparities. To construct MGEV, we introduce an adaptive patch matching module that efficiently and effectively computes matching costs for large disparity ranges and/or ill-posed regions. We further propose a selective geometry feature fusion module to adaptively fuse multi-range and multi-granularity geometry features in MGEV. We then index the fused geometry features and input them to ConvGRUs to iteratively update the disparity map. MGEV allows to efficiently handle large disparities and ill-posed regions, such as occlusions and textureless regions, and enjoys rapid convergence during iterations. Our IGEV++ achieves the best performance on the Scene Flow test set across all disparity ranges, up to 768px. Our IGEV++ also achieves state-of-the-art accuracy on the Middlebury, ETH3D, KITTI 2012, and 2015 benchmarks. Specifically, IGEV++ achieves a 3.23% 2-pixel outlier rate (Bad 2.0) on the large disparity benchmark, Middlebury, representing error reductions of 31.9% and 54.8% compared to RAFT-Stereo and GMStereo, respectively. We also present a real-time version of IGEV++ that achieves the best performance among all published real-time methods on the KITTI benchmarks. The code is publicly available at https://github.com/gangweiX/IGEV-plusplus
Authors: Tanisha Singh, Shreshtha Jha, Nidhi Bhatt, Palak Handa, Nidhi Goel, Sreedevi Indu
Abstract: The escalating global mortality and morbidity rates associated with gastrointestinal (GI) bleeding, compounded by the complexities and limitations of traditional endoscopic methods, underscore the urgent need for a critical review of current methodologies used for addressing this condition. With an estimated 300,000 annual deaths worldwide, the demand for innovative diagnostic and therapeutic strategies is paramount. The introduction of Video Capsule Endoscopy (VCE) has marked a significant advancement, offering a comprehensive, non-invasive visualization of the digestive tract that is pivotal for detecting bleeding sources unattainable by traditional methods. Despite its benefits, the efficacy of VCE is hindered by diagnostic challenges, including time-consuming analysis and susceptibility to human error. This backdrop sets the stage for exploring Machine Learning (ML) applications in automating GI bleeding detection within capsule endoscopy, aiming to enhance diagnostic accuracy, reduce manual labor, and improve patient outcomes. Through an exhaustive analysis of 113 papers published between 2008 and 2023, this review assesses the current state of ML methodologies in bleeding detection, highlighting their effectiveness, challenges, and prospective directions. It contributes an in-depth examination of AI techniques in VCE frame analysis, offering insights into open-source datasets, mathematical performance metrics, and technique categorization. The paper sets a foundation for future research to overcome existing challenges, advancing gastrointestinal diagnostics through interdisciplinary collaboration and innovation in ML applications.
Authors: Or Greenberg, Eran Kishon, Dani Lischinski
Abstract: We introduce Seed-to-Seed Translation (StS), a novel approach for Image-to-Image Translation using diffusion models (DMs), aimed at translations that require close adherence to the structure of the source image. In contrast to existing methods that modify images during the diffusion sampling process, we leverage the semantic information encoded within the space of inverted seeds of a pretrained DM, dubbed as the seed-space. We demonstrate that inverted seeds can be used for discriminative tasks, and can also be manipulated to achieve desired transformations in an unpaired image-to-image translation setting. Our method involves training an sts-GAN, an unpaired translation model between source and target seeds, based on CycleGAN. The final translated images are obtained by initiating the DM's sampling process from the translated seeds. A ControlNet is used to ensure the structural preservation of the input image. We demonstrate the effectiveness of our approach for the task of translating automotive scenes, showcasing superior performance compared to existing GAN-based and diffusion-based methods, as well as for several other unpaired image translation tasks. Our approach offers a fresh perspective on leveraging the semantic information encoded within the seed-space of pretrained DMs for effective image editing and manipulation.
Authors: Zhuofeng Wu, Doehyung Lee, Zihua Liu, Kazunori Yoshizaki, Yusuke Monno, Masatoshi Okutomi
Abstract: A quad-pixel (QP) sensor is increasingly integrated into commercial mobile cameras. The QP sensor has a unit of 2$\times$2 four photodiodes under a single microlens, generating multi-directional phase shifting when out-focus blurs occur. Similar to a dual-pixel (DP) sensor, the phase shifting can be regarded as stereo disparity and utilized for depth estimation. Based on this, we propose a QP disparity estimation network (QPDNet), which exploits abundant QP information by fusing vertical and horizontal stereo-matching correlations for effective disparity estimation. We also present a synthetic pipeline to generate a training dataset from an existing RGB-Depth dataset. Experimental results demonstrate that our QPDNet outperforms state-of-the-art stereo and DP methods. Our code and synthetic dataset are available at https://github.com/Zhuofeng-Wu/QPDNet.
Authors: Xiaoxiang Sun, Geoffrey Fox
Abstract: 3D object detection is critical for autonomous driving, leveraging deep learning techniques to interpret LiDAR data. The PointPillars architecture is a prominent model in this field, distinguished by its efficient use of LiDAR data. This study provides an analysis of enhancing the performance of PointPillars model under various dropout rates to address overfitting and improve model generalization. Dropout, a regularization technique, involves randomly omitting neurons during training, compelling the network to learn robust and diverse features. We systematically compare the effects of different enhancement techniques on the model's regression performance during training and its accuracy, measured by Average Precision (AP) and Average Orientation Similarity (AOS). Our findings offer insights into the optimal enhancements, contributing to improved 3D object detection in autonomous driving applications.
Authors: Ashish Tiwari, Satoshi Ikehata, Shanmuganathan Raman
Abstract: Photometric stereo typically demands intricate data acquisition setups involving multiple light sources to recover surface normals accurately. In this paper, we propose MERLiN, an attention-based hourglass network that integrates single image-based inverse rendering and relighting within a single unified framework. We evaluate the performance of photometric stereo methods using these relit images and demonstrate how they can circumvent the underlying challenge of complex data acquisition. Our physically-based model is trained on a large synthetic dataset containing complex shapes with spatially varying BRDF and is designed to handle indirect illumination effects to improve material reconstruction and relighting. Through extensive qualitative and quantitative evaluation, we demonstrate that the proposed framework generalizes well to real-world images, achieving high-quality shape, material estimation, and relighting. We assess these synthetically relit images over photometric stereo benchmark methods for their physical correctness and resulting normal estimation accuracy, paving the way towards single-shot photometric stereo through physically-based relighting. This work allows us to address the single image-based inverse rendering problem holistically, applying well to both synthetic and real data and taking a step towards mitigating the challenge of data acquisition in photometric stereo.
Authors: Xin Su, Zhuoran Zheng
Abstract: Privacy protection has always been an ongoing topic, especially for AI. Currently, a low-cost scheme called Machine Unlearning forgets the private data remembered in the model. Specifically, given a private dataset and a trained neural network, we need to use e.g. pruning, fine-tuning, and gradient ascent to remove the influence of the private dataset on the neural network. Inspired by this, we try to use this concept to bridge the gap between the fields of image restoration and security, creating a new research idea. We propose the scene for the All-In-One model (a neural network that restores a wide range of degraded information), where a given dataset such as haze, or rain, is private and needs to be eliminated from the influence of it on the trained model. Notably, we find great challenges in this task to remove the influence of sensitive data while ensuring that the overall model performance remains robust, which is akin to directing a symphony orchestra without specific instruments while keeping the playing soothing. Here we explore a simple but effective approach: Instance-wise Unlearning through the use of adversarial examples and gradient ascent techniques. Our approach is a low-cost solution compared to the strategy of retraining the model from scratch, where the gradient ascent trick forgets the specified data and the performance of the adversarial sample maintenance model is robust. Through extensive experimentation on two popular unified image restoration models, we show that our approach effectively preserves knowledge of remaining data while unlearning a given degradation type.
Authors: Weiping Xiao, Yiqiang Wu, Chang Liu, Yu Qin, Xiaomao Li, Liming Xin
Abstract: Inadequate bounding box modeling in regression tasks constrains the performance of one-stage 3D object detection. Our study reveals that the primary reason lies in two aspects: (1) The limited center-offset prediction seriously impairs the bounding box localization since many highest response positions significantly deviate from object centers. (2) The low-quality sample ignored in regression tasks significantly impacts the bounding box prediction since it produces unreliable quality (IoU) rectification. To tackle these problems, we propose Decoupled and Interactive Regression Modeling (DIRM) for one-stage detection. Specifically, Decoupled Attribute Regression (DAR) is implemented to facilitate long regression range modeling for the center attribute through an adaptive multi-sample assignment strategy that deeply decouples bounding box attributes. On the other hand, to enhance the reliability of IoU predictions for low-quality results, Interactive Quality Prediction (IQP) integrates the classification task, proficient in modeling negative samples, with quality prediction for joint optimization. Extensive experiments on Waymo and ONCE datasets demonstrate that DIRM significantly improves the performance of several state-of-the-art methods with minimal additional inference latency. Notably, DIRM achieves state-of-the-art detection performance on both the Waymo and ONCE datasets.
Authors: Qiu Guan, Mengjie Pan, Feng Chen, Zhiqiang Yang, Zhongwen Yu, Qianwei Zhou, Haigen Hu
Abstract: Effective lesion detection in medical image is not only rely on the features of lesion region,but also deeply relative to the surrounding information.However,most current methods have not fully utilize it.What is more,multi-scale feature fusion mechanism of most traditional detectors are unable to transmit detail information without loss,which makes it hard to detect small and boundary ambiguous lesion in early stage disease.To address the above issues,we propose a novel intra- and across-layer feature interaction FCOS model (IAFI-FCOS) with a multi-scale feature fusion mechanism ICAF-FPN,which is a network structure with intra-layer context augmentation (ICA) block and across-layer feature weighting (AFW) block.Therefore,the traditional FCOS detector is optimized by enriching the feature representation from two perspectives.Specifically,the ICA block utilizes dilated attention to augment the context information in order to capture long-range dependencies between the lesion region and the surrounding.The AFW block utilizes dual-axis attention mechanism and weighting operation to obtain the efficient across-layer interaction features,enhancing the representation of detailed features.Our approach has been extensively experimented on both the private pancreatic lesion dataset and the public DeepLesion dataset,our model achieves SOTA results on the pancreatic lesion dataset.
Authors: Xiuqi Zheng, Yuhang Zhang, Haoran Zhang, Hongrui Liang, Xueqi Bao, Zhuqing Jiang, Qicheng Lao
Abstract: Adapting large pre-trained foundation models, e.g., SAM, for medical image segmentation remains a significant challenge. A crucial step involves the formulation of a series of specialized prompts that incorporate specific clinical instructions. Past works have been heavily reliant on a singular type of prompt for each instance, necessitating manual input of an ideally correct prompt, which is less efficient. To tackle this issue, we propose to utilize prompts of different granularity, which are sourced from original images to provide a broader scope of clinical insights. However, combining prompts of varying types can pose a challenge due to potential conflicts. In response, we have designed a coarse-to-fine mechanism, referred to as curriculum prompting, that progressively integrates prompts of different types. Through extensive experiments on three public medical datasets across various modalities, we demonstrate the effectiveness of our proposed approach, which not only automates the prompt generation process but also yields superior performance compared to other SAM-based medical image segmentation methods. Code is available at: https://github.com/AnnaZzz-zxq/Curriculum-Prompting.
Authors: Karim El Khoury, Maxime Zanella, Beno\^it G\'erin, Tiffanie Godelaine, Beno\^it Macq, Sa\"id Mahmoudi, Christophe De Vleeschouwer, Ismail Ben Ayed
Abstract: Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining. However, their conventional usage in zero-shot scene classification methods still involves dividing large images into patches and making independent predictions, i.e., inductive inference, thereby limiting their effectiveness by ignoring valuable contextual information. Our approach tackles this issue by utilizing initial predictions based on text prompting and patch affinity relationships from the image encoder to enhance zero-shot capabilities through transductive inference, all without the need for supervision and at a minor computational cost. Experiments on 10 remote sensing datasets with state-of-the-art Vision-Language Models demonstrate significant accuracy improvements over inductive zero-shot classification. Our source code is publicly available on Github: https://github.com/elkhouryk/RS-TransCLIP
Authors: Aditya Chandrasekar, Goirik Chakrabarty, Jai Bardhan, Ramya Hebbalaguppe, Prathosh AP
Abstract: We introduce $\texttt{ReMOVE}$, a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measures such as LPIPS and CLIPScore, $\texttt{ReMOVE}$ addresses the challenge of evaluating inpainting without a reference image, common in practical scenarios. It effectively distinguishes between object removal and replacement. This is a key issue in diffusion models due to stochastic nature of image generation. Traditional metrics fail to align with the intuitive definition of inpainting, which aims for (1) seamless object removal within masked regions (2) while preserving the background continuity. $\texttt{ReMOVE}$ not only correlates with state-of-the-art metrics and aligns with human perception but also captures the nuanced aspects of the inpainting process, providing a finer-grained evaluation of the generated outputs.
Authors: Zhaojie Fang, Xiao Yu, Guanyu Zhou, Ke Zhuang, Yifei Chen, Ruiquan Ge, Changmiao Wang, Gangyong Jia, Qing Wu, Juan Ye, Maimaiti Nuliqiman, Peifang Xu, Ahmed Elazab
Abstract: Ultra-Wide-Field Fluorescein Angiography (UWF-FA) enables precise identification of ocular diseases using sodium fluorescein, which can be potentially harmful. Existing research has developed methods to generate UWF-FA from Ultra-Wide-Field Scanning Laser Ophthalmoscopy (UWF-SLO) to reduce the adverse reactions associated with injections. However, these methods have been less effective in producing high-quality late-phase UWF-FA, particularly in lesion areas and fine details. Two primary challenges hinder the generation of high-quality late-phase UWF-FA: the scarcity of paired UWF-SLO and early/late-phase UWF-FA datasets, and the need for realistic generation at lesion sites and potential blood leakage regions. This study introduces an improved latent diffusion model framework to generate high-quality late-phase UWF-FA from limited paired UWF images. To address the challenges as mentioned earlier, our approach employs a module utilizing Cross-temporal Regional Difference Loss, which encourages the model to focus on the differences between early and late phases. Additionally, we introduce a low-frequency enhanced noise strategy in the diffusion forward process to improve the realism of medical images. To further enhance the mapping capability of the variational autoencoder module, especially with limited datasets, we implement a Gated Convolutional Encoder to extract additional information from conditional images. Our Latent Diffusion Model for Ultra-Wide-Field Late-Phase Fluorescein Angiography (LPUWF-LDM) effectively reconstructs fine details in late-phase UWF-FA and achieves state-of-the-art results compared to other existing methods when working with limited datasets. Our source code is available at: https://github.com/Tinysqua/****.
Authors: Shahriar Jahan, Roknuzzaman, Md Robiul Islam
Abstract: Upsurging abnormal activities in crowded locations such as airports, train stations, bus stops, shopping malls, etc., urges the necessity for an intelligent surveillance system. An intelligent surveillance system can differentiate between normal and suspicious activities from real-time video analysis that will enable to take appropriate measures regarding the level of an anomaly instantaneously and efficiently. Video-based human activity recognition has intrigued many researchers with its pressing issues and a variety of applications ranging from simple hand gesture recognition to crucial behavior recognition in a surveillance system. This paper provides a critical survey of video-based Human Activity Recognition (HAR) techniques beginning with an examination of basic approaches for detecting and recognizing suspicious behavior followed by a critical analysis of machine learning and deep learning techniques such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Hidden Markov Model (HMM), K-means Clustering etc. A detailed investigation and comparison are done on these learning techniques on the basis of feature extraction techniques, parameter initialization, and optimization algorithms, accuracy, etc. The purpose of this review is to prioritize positive schemes and to assist researchers with emerging advancements in this field's future endeavors. This paper also pragmatically discusses existing challenges in the field of HAR and examines the prospects in the field.
Authors: Ziqiang Dang, Tianxing Fan, Boming Zhao, Xujie Shen, Lei Wang, Guofeng Zhang, Zhaopeng Cui
Abstract: Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to AR/VR. In this paper, we present MoManifold, a novel human motion prior, which models plausible human motion in continuous high-dimensional motion space. Different from existing mathematical or VAE-based methods, our representation is designed based on the neural distance field, which makes human dynamics explicitly quantified to a score and thus can measure human motion plausibility. Specifically, we propose novel decoupled joint acceleration manifolds to model human dynamics from existing limited motion data. Moreover, we introduce a novel optimization method using the manifold distance as guidance, which facilitates a variety of motion-related tasks. Extensive experiments demonstrate that MoManifold outperforms existing SOTAs as a prior in several downstream tasks such as denoising real-world human mocap data, recovering human motion from partial 3D observations, mitigating jitters for SMPL-based pose estimators, and refining the results of motion in-betweening.
Authors: Andrea Maracani, Lorenzo Rosasco, Lorenzo Natale
Abstract: Deep Neural Networks have significantly impacted many computer vision tasks. However, their effectiveness diminishes when test data distribution (target domain) deviates from the one of training data (source domain). In situations where target labels are unavailable and the access to the labeled source domain is restricted due to data privacy or memory constraints, Source-Free Unsupervised Domain Adaptation (SF-UDA) has emerged as a valuable tool. Recognizing the key role of SF-UDA under these constraints, we introduce a novel approach marked by two key contributions: Few Trusted Samples Pseudo-labeling (FTSP) and Temperature Scaled Adaptive Loss (TSAL). FTSP employs a limited subset of trusted samples from the target data to construct a classifier to infer pseudo-labels for the entire domain, showing simplicity and improved accuracy. Simultaneously, TSAL, designed with a unique dual temperature scheduling, adeptly balance diversity, discriminability, and the incorporation of pseudo-labels in the unsupervised adaptation objective. Our methodology, that we name Trust And Balance (TAB) adaptation, is rigorously evaluated on standard datasets like Office31 and Office-Home, and on less common benchmarks such as ImageCLEF-DA and Adaptiope, employing both ResNet50 and ViT-Large architectures. Our results compare favorably with, and in most cases surpass, contemporary state-of-the-art techniques, underscoring the effectiveness of our methodology in the SF-UDA landscape.
Authors: Huixin Zhang, Guangming Wang, Xinrui Wu, Chenfeng Xu, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang
Abstract: This paper introduces a 3D point cloud sequence learning model based on inconsistent spatio-temporal propagation for LiDAR odometry, termed DSLO. It consists of a pyramid structure with a spatial information reuse strategy, a sequential pose initialization module, a gated hierarchical pose refinement module, and a temporal feature propagation module. First, spatial features are encoded using a point feature pyramid, with features reused in successive pose estimations to reduce computational overhead. Second, a sequential pose initialization method is introduced, leveraging the high-frequency sampling characteristic of LiDAR to initialize the LiDAR pose. Then, a gated hierarchical pose refinement mechanism refines poses from coarse to fine by selectively retaining or discarding motion information from different layers based on gate estimations. Finally, temporal feature propagation is proposed to incorporate the historical motion information from point cloud sequences, and address the spatial inconsistency issue when transmitting motion information embedded in point clouds between frames. Experimental results on the KITTI odometry dataset and Argoverse dataset demonstrate that DSLO outperforms state-of-the-art methods, achieving at least a 15.67\% improvement on RTE and a 12.64\% improvement on RRE, while also achieving a 34.69\% reduction in runtime compared to baseline methods. Our implementation will be available at https://github.com/IRMVLab/DSLO.
Authors: Wei Sun, Weixia Zhang, Yuqin Cao, Linhan Cao, Jun Jia, Zijian Chen, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai
Abstract: UHD images, typically with resolutions equal to or higher than 4K, pose a significant challenge for efficient image quality assessment (IQA) algorithms, as adopting full-resolution images as inputs leads to overwhelming computational complexity and commonly used pre-processing methods like resizing or cropping may cause substantial loss of detail. To address this problem, we design a multi-branch deep neural network (DNN) to assess the quality of UHD images from three perspectives: global aesthetic characteristics, local technical distortions, and salient content perception. Specifically, aesthetic features are extracted from low-resolution images downsampled from the UHD ones, which lose high-frequency texture information but still preserve the global aesthetics characteristics. Technical distortions are measured using a fragment image composed of mini-patches cropped from UHD images based on the grid mini-patch sampling strategy. The salient content of UHD images is detected and cropped to extract quality-aware features from the salient regions. We adopt the Swin Transformer Tiny as the backbone networks to extract features from these three perspectives. The extracted features are concatenated and regressed into quality scores by a two-layer multi-layer perceptron (MLP) network. We employ the mean square error (MSE) loss to optimize prediction accuracy and the fidelity loss to optimize prediction monotonicity. Experimental results show that the proposed model achieves the best performance on the UHD-IQA dataset while maintaining the lowest computational complexity, demonstrating its effectiveness and efficiency. Moreover, the proposed model won first prize in ECCV AIM 2024 UHD-IQA Challenge. The code is available at https://github.com/sunwei925/UIQA.
Authors: Tim Raven, Arthur Matei, Gernot A. Fink
Abstract: While methods based on Vision Transformers (ViT) have achieved state-of-the-art performance in many domains, they have not yet been applied successfully in the domain of writer retrieval. The field is dominated by methods using handcrafted features or features extracted from Convolutional Neural Networks. In this work, we bridge this gap and present a novel method that extracts features from a ViT and aggregates them using VLAD encoding. The model is trained in a self-supervised fashion without any need for labels. We show that extracting local foreground features is superior to using the ViT's class token in the context of writer retrieval. We evaluate our method on two historical document collections. We set a new state-at-of-art performance on the Historical-WI dataset (83.1\% mAP), and the HisIR19 dataset (95.0\% mAP). Additionally, we demonstrate that our ViT feature extractor can be directly applied to modern datasets such as the CVL database (98.6\% mAP) without any fine-tuning.
Authors: Haojian Huang, Chuanyu Qin, Zhe Liu, Kaijing Ma, Jin Chen, Han Fang, Chao Ban, Hao Sun, Zhongjiang He
Abstract: Multi-view classification (MVC) faces inherent challenges due to domain gaps and inconsistencies across different views, often resulting in uncertainties during the fusion process. While Evidential Deep Learning (EDL) has been effective in addressing view uncertainty, existing methods predominantly rely on the Dempster-Shafer combination rule, which is sensitive to conflicting evidence and often neglects the critical role of neighborhood structures within multi-view data. To address these limitations, we propose a Trusted Unified Feature-NEighborhood Dynamics (TUNED) model for robust MVC. This method effectively integrates local and global feature-neighborhood (F-N) structures for robust decision-making. Specifically, we begin by extracting local F-N structures within each view. To further mitigate potential uncertainties and conflicts in multi-view fusion, we employ a selective Markov random field that adaptively manages cross-view neighborhood dependencies. Additionally, we employ a shared parameterized evidence extractor that learns global consensus conditioned on local F-N structures, thereby enhancing the global integration of multi-view features. Experiments on benchmark datasets show that our method improves accuracy and robustness over existing approaches, particularly in scenarios with high uncertainty and conflicting views. The code will be made available at https://github.com/JethroJames/TUNED.
Authors: Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki
Abstract: In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we investigate and rethink the training data from the perspectives of diversity and quality, {thereby addressing the question of ``How important is SR training for SR models?''}. To this end, we propose an automated image evaluation pipeline. With this, we stratify existing high-resolution image datasets and larger-scale image datasets such as ImageNet and PASS to compare their performances. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance. We hope that the proposed simple-yet-effective dataset curation pipeline will inform the construction of SR datasets in the future and yield overall better models.
Authors: Luigi Capogrosso, Andrea Toaiari, Andrea Avogaro, Uzair Khan, Aditya Jivoji, Franco Fummi, Marco Cristani
Abstract: Patterns of human motion in outdoor and indoor environments are substantially different due to the scope of the environment and the typical intentions of people therein. While outdoor trajectory forecasting has received significant attention, indoor forecasting is still an underexplored research area. This paper proposes SITUATE, a novel approach to cope with indoor human trajectory prediction by leveraging equivariant and invariant geometric features and a self-supervised vision representation. The geometric learning modules model the intrinsic symmetries and human movements inherent in indoor spaces. This concept becomes particularly important because self-loops at various scales and rapid direction changes often characterize indoor trajectories. On the other hand, the vision representation module is used to acquire spatial-semantic information about the environment to predict users' future locations more accurately. We evaluate our method through comprehensive experiments on the two most famous indoor trajectory forecasting datasets, i.e., TH\"OR and Supermarket, obtaining state-of-the-art performance. Furthermore, we also achieve competitive results in outdoor scenarios, showing that indoor-oriented forecasting models generalize better than outdoor-oriented ones. The source code is available at https://github.com/intelligolabs/SITUATE.
Authors: Zhihao Huang, Santiago Lopez-Tapia, Aggelos K. Katsaggelos
Abstract: Video deblurring is a challenging task that aims to recover sharp sequences from blur and noisy observations. The image-formation model plays a crucial role in traditional model-based methods, constraining the possible solutions. However, this is only the case for some deep learning-based methods. Despite deep-learning models achieving better results, traditional model-based methods remain widely popular due to their flexibility. An increasing number of scholars combine the two to achieve better deblurring performance. This paper proposes introducing knowledge of the image-formation model into a deep learning network by using the pseudo-inverse of the blur. We use a deep network to fit the blurring and estimate pseudo-inverse. Then, we use this estimation, combined with a variational deep-learning network, to deblur the video sequence. Notably, our experimental results demonstrate that such modifications can significantly improve the performance of deep learning models for video deblurring. Furthermore, our experiments on different datasets achieved notable performance improvements, proving that our proposed method can generalize to different scenarios and cameras.
Authors: Ravi Prakash, Sinnu Susan Thomas
Abstract: This paper introduces a novel fingerprint classification technique based on a multi-layered fuzzy logic classifier. We target the cause of missed detection by identifying the fingerprints at an early stage among dry, standard, and wet. Scanned images are classified based on clarity correlated with the proposed feature points. We also propose a novel adaptive algorithm based on eigenvector space for generating new samples to overcome the multiclass imbalance. Proposed methods improve the performance of ensemble learners. It was also found that the new approach performs better than the neural-network based classification methods. Early-stage improvements give a suitable dataset for fingerprint detection models. Leveraging the novel classifier, the best set of `standard' labelled fingerprints is used to generate a unique hybrid fingerprint orientation map (HFOM). We introduce a novel min-rotate max-flow optimization method inspired by the min-cut max-flow algorithm. The unique properties of HFOM generation introduce a new use case for biometric data protection by using HFOM as a virtual proxy of fingerprints.
Authors: Martin Mayr, Marcel Dreier, Florian Kordon, Mathias Seuret, Jochen Z\"ollner, Fei Wu, Andreas Maier, Vincent Christlein
Abstract: The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. Our approach sets a new benchmark in our comprehensive evaluation. It outperforms all existing imitation methods at both line and paragraph levels, considering combined style and content preservation.
Authors: Haoyu Lan, Bino A. Varghese, Nasim Sheikh-Bahaei, Farshid Sepehrband, Arthur W Toga, Jeiran Choupan
Abstract: Multi-center neuroimaging studies face technical variability due to batch differences across sites, which potentially hinders data aggregation and impacts study reliability.Recent efforts in neuroimaging harmonization have aimed to minimize these technical gaps and reduce technical variability across batches. While Generative Adversarial Networks (GAN) has been a prominent method for addressing image harmonization tasks, GAN-harmonized images suffer from artifacts or anatomical distortions. Given the advancements of denoising diffusion probabilistic model which produces high-fidelity images, we have assessed the efficacy of the diffusion model for neuroimaging harmonization. we have demonstrated the diffusion model's superior capability in harmonizing images from multiple domains, while GAN-based methods are limited to harmonizing images between two domains per model. Our experiments highlight that the learned domain invariant anatomical condition reinforces the model to accurately preserve the anatomical details while differentiating batch differences at each diffusion step. Our proposed method has been tested on two public neuroimaging dataset ADNI1 and ABIDE II, yielding harmonization results with consistent anatomy preservation and superior FID score compared to the GAN-based methods. We have conducted multiple analysis including extensive quantitative and qualitative evaluations against the baseline models, ablation study showcasing the benefits of the learned conditions, and improvements in the consistency of perivascular spaces (PVS) segmentation through harmonization.
Authors: Eden Ship, Eitan Spivak, Shubham Agarwal, Raz Birman, Ofer Hadar
Abstract: Accurate classification of weather conditions in images is essential for enhancing the performance of object detection and classification models under varying weather conditions. This paper presents a comprehensive study on classifying weather conditions in images into four categories: rainy, low light, haze, and clear. The motivation for this work stems from the need to improve the reliability and efficiency of automated systems, such as autonomous vehicles and surveillance, which must operate under diverse weather conditions. Misclassification of weather conditions can lead to significant performance degradation in these systems, making robust weather classification crucial. Utilizing the Support Vector Machine (SVM) algorithm, our approach leverages a robust set of features, including brightness, saturation, noise level, blur metric, edge strength, motion blur, Local Binary Patterns (LBP) mean and variance for radii 1, 2, and 3, edges mean and variance, and color histogram mean and variance for blue, green, and red channels. Our SVM-based method achieved a notable accuracy of 92.8%, surpassing typical benchmarks in the literature, which range from 80% to 90% for classical machine learning methods. While deep learning methods can achieve up to 94% accuracy, our approach offers a competitive advantage in terms of computational efficiency and real-time classification capabilities. Detailed analysis of each feature's contribution highlights the effectiveness of texture, color, and edge-related features in capturing the unique characteristics of different weather conditions. This research advances the state-of-the-art in weather image classification and provides insights into the critical features necessary for accurate weather condition differentiation, underscoring the potential of SVMs in practical applications where accuracy is paramount.
Authors: Aradhya N. Mathur, Apoorv Khattar, Ojaswa Sharma
Abstract: In this work, we present a novel approach for reconstructing shape point clouds using planar sparse cross-sections with the help of generative modeling. We present unique challenges pertaining to the representation and reconstruction in this problem setting. Most methods in the classical literature lack the ability to generalize based on object class and employ complex mathematical machinery to reconstruct reliable surfaces. We present a simple learnable approach to generate a large number of points from a small number of input cross-sections over a large dataset. We use a compact parametric polyline representation using adaptive splitting to represent the cross-sections and perform learning using a Graph Neural Network to reconstruct the underlying shape in an adaptive manner reducing the dependence on the number of cross-sections provided.
Authors: Haobo Yang, Shiyan Zhang, Zhuoyi Yang, Xinyu Zhang, Li Wang, Yifan Tang, Jilong Guo, Jun Li
Abstract: With the increasing complexity of the traffic environment, the significance of safety perception in intelligent driving is intensifying. Traditional methods in the field of intelligent driving perception rely on deep learning, which suffers from limited interpretability, often described as a "black box." This paper introduces a novel type of loss function, termed "Entropy Loss," along with an innovative training strategy. Entropy Loss is formulated based on the functionality of feature compression networks within the perception model. Drawing inspiration from communication systems, the information transmission process in a feature compression network is expected to demonstrate steady changes in information volume and a continuous decrease in information entropy. By modeling network layer outputs as continuous random variables, we construct a probabilistic model that quantifies changes in information volume. Entropy Loss is then derived based on these expectations, guiding the update of network parameters to enhance network interpretability. Our experiments indicate that the Entropy Loss training strategy accelerates the training process. Utilizing the same 60 training epochs, the accuracy of 3D object detection models using Entropy Loss on the KITTI test set improved by up to 4.47\% compared to models without Entropy Loss, underscoring the method's efficacy. The implementation code is available at \url{https://github.com/yhbcode000/Eloss-Interpretability}.
Authors: Anas Mahmoud, Ali Harakeh, Steven Waslander
Abstract: Pre-trained on extensive and diverse multi-modal datasets, 2D foundation models excel at addressing 2D tasks with little or no downstream supervision, owing to their robust representations. The emergence of 2D-to-3D distillation frameworks has extended these capabilities to 3D models. However, distilling 3D representations for autonomous driving datasets presents challenges like self-similarity, class imbalance, and point cloud sparsity, hindering the effectiveness of contrastive distillation, especially in zero-shot learning contexts. Whereas other methodologies, such as similarity-based distillation, enhance zero-shot performance, they tend to yield less discriminative representations, diminishing few-shot performance. We investigate the gap in structure between the 2D and the 3D representations that result from state-of-the-art distillation frameworks and reveal a significant mismatch between the two. Additionally, we demonstrate that the observed structural gap is negatively correlated with the efficacy of the distilled representations on zero-shot and few-shot 3D semantic segmentation. To bridge this gap, we propose a relational distillation framework enforcing intra-modal and cross-modal constraints, resulting in distilled 3D representations that closely capture the structure of the 2D representation. This alignment significantly enhances 3D representation performance over those learned through contrastive distillation in zero-shot segmentation tasks. Furthermore, our relational loss consistently improves the quality of 3D representations in both in-distribution and out-of-distribution few-shot segmentation tasks, outperforming approaches that rely on the similarity loss.
Authors: Nazmul Karim, Abdullah Al Arafat, Adnan Siraj Rakin, Zhishan Guo, Nazanin Rahnavard
Abstract: Studies on backdoor attacks in recent years suggest that an adversary can compromise the integrity of a deep neural network (DNN) by manipulating a small set of training samples. Our analysis shows that such manipulation can make the backdoor model converge to a bad local minima, i.e., sharper minima as compared to a benign model. Intuitively, the backdoor can be purified by re-optimizing the model to smoother minima. However, a na\"ive adoption of any optimization targeting smoother minima can lead to sub-optimal purification techniques hampering the clean test accuracy. Hence, to effectively obtain such re-optimization, inspired by our novel perspective establishing the connection between backdoor removal and loss smoothness, we propose Fisher Information guided Purification (FIP), a novel backdoor purification framework. Proposed FIP consists of a couple of novel regularizers that aid the model in suppressing the backdoor effects and retaining the acquired knowledge of clean data distribution throughout the backdoor removal procedure through exploiting the knowledge of Fisher Information Matrix (FIM). In addition, we introduce an efficient variant of FIP, dubbed as Fast FIP, which reduces the number of tunable parameters significantly and obtains an impressive runtime gain of almost $5\times$. Extensive experiments show that the proposed method achieves state-of-the-art (SOTA) performance on a wide range of backdoor defense benchmarks: 5 different tasks -- Image Recognition, Object Detection, Video Action Recognition, 3D point Cloud, Language Generation; 11 different datasets including ImageNet, PASCAL VOC, UCF101; diverse model architectures spanning both CNN and vision transformer; 14 different backdoor attacks, e.g., Dynamic, WaNet, LIRA, ISSBA, etc.
Authors: Sanjuksha Nirgude, Kevin DuCharme, Namrita Madhusoodanan
Abstract: The problem of cleaning a messy table using Deep Neural Networks is a very interesting problem in both social and industrial robotics. This project focuses on the social application of this technology. A neural network model that is capable of detecting and recognizing common tabletop objects, such as a mug, mouse, or stapler is developed. The model also predicts the angle at which these objects are placed on a table,with respect to some reference. Assuming each object has a fixed intended position and orientation on the tabletop, the orientation of a particular object predicted by the deep learning model can be used to compute the transformation matrix to move the object from its initial position to the intended position. This can be fed to a pick and place robot to carry out the transfer.This paper talks about the deep learning approaches used in this project for object detection and orientation estimation.
Authors: Sajib Acharjee Dip, Kazi Hasan Ibn Arif, Uddip Acharjee Shuvo, Ishtiaque Ahmed Khan, Na Meng
Abstract: In the realm of dermatology, the complexity of diagnosing skin conditions manually necessitates the expertise of dermatologists. Accurate identification of various skin ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly in accurately diagnosing diseases across diverse skin tones, with a notable performance gap in darker skin. Additionally, the scarcity of publicly available, unbiased datasets hampers the development of inclusive AI diagnostic tools. To tackle the challenges in accurately predicting skin conditions across diverse skin tones, we employ a transfer-learning approach that capitalizes on the rich, transferable knowledge from various image domains. Our method integrates multiple pre-trained models from a wide range of sources, including general and specific medical images, to improve the robustness and inclusiveness of the skin condition predictions. We rigorously evaluated the effectiveness of these models using the Diverse Dermatology Images (DDI) dataset, which uniquely encompasses both underrepresented and common skin tones, making it an ideal benchmark for assessing our approach. Among all methods, Med-ViT emerged as the top performer due to its comprehensive feature representation learned from diverse image sources. To further enhance performance, we conducted domain adaptation using additional skin image datasets such as HAM10000. This adaptation significantly improved model performance across all models.
Authors: Md Manjurul Ahsan, Benjamin Bevans, Chris Billings, Alexander Riensche, Yingtao Liu, Shivakumar Raman, Zahed Siddique
Abstract: Digital Twins (DTs) are becoming popular in Additive Manufacturing (AM) due to their ability to create virtual replicas of physical components of AM machines, which helps in real-time production monitoring. Advanced techniques such as Machine Learning (ML), Augmented Reality (AR), and simulation-based models play key roles in developing intelligent and adaptable DTs in manufacturing processes. However, questions remain regarding scalability, the integration of high-quality data, and the computational power required for real-time applications in developing DTs. Understanding the current state of DTs in AM is essential to address these challenges and fully utilize their potential in advancing AM processes. Considering this opportunity, this work aims to provide a comprehensive overview of DTs in AM by addressing the following four research questions: (1) What are the key types of DTs used in AM and their specific applications? (2) What are the recent developments and implementations of DTs? (3) How are DTs employed in process improvement and hybrid manufacturing? (4) How are DTs integrated with Industry 4.0 technologies? By discussing current applications and techniques, we aim to offer a better understanding and potential future research directions for researchers and practitioners in AM and DTs.
Authors: Deepak Dagar, Dinesh Kumar Vishwakarma
Abstract: The trustworthiness of multimedia is being increasingly evaluated by advanced Image Manipulation Localization (IML) techniques, resulting in the emergence of the IML field. An effective manipulation model necessitates the extraction of non-semantic differential features between manipulated and legitimate sections to utilize artifacts. This requires direct comparisons between the two regions.. Current models employ either feature approaches based on handcrafted features, convolutional neural networks (CNNs), or a hybrid approach that combines both. Handcrafted feature approaches presuppose tampering in advance, hence restricting their effectiveness in handling various tampering procedures, but CNNs capture semantic information, which is insufficient for addressing manipulation artifacts. In order to address these constraints, we have developed a dual-branch model that integrates manually designed feature noise with conventional CNN features. This model employs a dual-branch strategy, where one branch integrates noise characteristics and the other branch integrates RGB features using the hierarchical ConvNext Module. In addition, the model utilizes edge supervision loss to acquire boundary manipulation information, resulting in accurate localization at the edges. Furthermore, this architecture utilizes a feature augmentation module to optimize and refine the presentation of attributes. The shallowfakes dataset (CASIA, COVERAGE, COLUMBIA, NIST16) and deepfake dataset Faceforensics++ (FF++) underwent thorough testing to demonstrate their outstanding ability to extract features and their superior performance compared to other baseline models. The AUC score achieved an astounding 99%. The model is superior in comparison and easily outperforms the existing state-of-the-art (SoTA) models.
Authors: Jinhui Yi, Yanan Luo, Marion Deichmann, Gabriel Schaaf, Juergen Gall
Abstract: An early, non-invasive, and on-site detection of nutrient deficiencies is critical to enable timely actions to prevent major losses of crops caused by lack of nutrients. While acquiring labeled data is very expensive, collecting images from multiple views of a crop is straightforward. Despite its relevance for practical applications, unsupervised domain adaptation where multiple views are available for the labeled source domain as well as the unlabeled target domain is an unexplored research area. In this work, we thus propose an approach that leverages multiple camera views in the source and target domain for unsupervised domain adaptation. We evaluate the proposed approach on two nutrient deficiency datasets. The proposed method achieves state-of-the-art results on both datasets compared to other unsupervised domain adaptation methods. The dataset and source code are available at https://github.com/jh-yi/MV-Match.
Authors: Zhanwen Liu, Chao Li, Yang Wang, Nan Yang, Xing Fan, Jiaqi Ma, Xiangmo Zhao
Abstract: Motion prediction plays an essential role in autonomous driving systems, enabling autonomous vehicles to achieve more accurate local-path planning and driving decisions based on predictions of the surrounding vehicles. However, existing methods neglect the potential missing values caused by object occlusion, perception failures, etc., which inevitably degrades the trajectory prediction performance in real traffic scenarios. To address this limitation, we propose a novel end-to-end framework for incomplete vehicle trajectory prediction, named Multi-scale Temporal Fusion Transformer (MTFT), which consists of the Multi-scale Attention Head (MAH) and the Continuity Representation-guided Multi-scale Fusion (CRMF) module. Specifically, the MAH leverages the multi-head attention mechanism to parallelly capture multi-scale motion representation of trajectory from different temporal granularities, thus mitigating the adverse effect of missing values on prediction. Furthermore, the multi-scale motion representation is input into the CRMF module for multi-scale fusion to obtain the robust temporal feature of the vehicle. During the fusion process, the continuity representation of vehicle motion is first extracted across time steps to guide the fusion, ensuring that the resulting temporal feature incorporates both detailed information and the overall trend of vehicle motion, which facilitates the accurate decoding of future trajectory that is consistent with the vehicle's motion trend. We evaluate the proposed model on four datasets derived from highway and urban traffic scenarios. The experimental results demonstrate its superior performance in the incomplete vehicle trajectory prediction task compared with state-of-the-art models, e.g., a comprehensive performance improvement of more than 39% on the HighD dataset.
Authors: Chao Gu, Ke Lin, Yiyang Luo, Jiahui Hou, Xiang-Yang Li
Abstract: To accurately understand engineering drawings, it is essential to establish the correspondence between images and their description tables within the drawings. Existing document understanding methods predominantly focus on text as the main modality, which is not suitable for documents containing substantial image information. In the field of visual relation detection, the structure of the task inherently limits its capacity to assess relationships among all entity pairs in the drawings. To address this issue, we propose a vision-based relation detection model, named ViRED, to identify the associations between tables and circuits in electrical engineering drawings. Our model mainly consists of three parts: a vision encoder, an object encoder, and a relation decoder. We implement ViRED using PyTorch to evaluate its performance. To validate the efficacy of ViRED, we conduct a series of experiments. The experimental results indicate that, within the engineering drawing dataset, our approach attained an accuracy of 96\% in the task of relation prediction, marking a substantial improvement over existing methodologies. The results also show that ViRED can inference at a fast speed even when there are numerous objects in a single engineering drawing.
Authors: Liang Wu, Bertram E. Shi
Abstract: Multiple datasets have been created for training and testing appearance-based gaze estimators. Intuitively, more data should lead to better performance. However, combining datasets to train a single esti-mator rarely improves gaze estimation performance. One reason may be differences in the experimental protocols used to obtain the gaze sam-ples, resulting in differences in the distributions of head poses, gaze an-gles, illumination, etc. Another reason may be the inconsistency between methods used to define gaze angles (label mismatch). We propose two innovations to improve the performance of gaze estimation by leveraging multiple datasets, a change in the estimator architecture and the intro-duction of a gaze adaptation module. Most state-of-the-art estimators merge information extracted from images of the two eyes and the entire face either in parallel or combine information from the eyes first then with the face. Our proposed Two-stage Transformer-based Gaze-feature Fusion (TTGF) method uses transformers to merge information from each eye and the face separately and then merge across the two eyes. We argue that this improves head pose invariance since changes in head pose affect left and right eye images in different ways. Our proposed Gaze Adaptation Module (GAM) method handles annotation inconsis-tency by applying a Gaze Adaption Module for each dataset to correct gaze estimates from a single shared estimator. This enables us to combine information across datasets despite differences in labeling. Our experi-ments show that these innovations improve gaze estimation performance over the SOTA both individually and collectively (by 10% - 20%). Our code is available at https://github.com/HKUST-NISL/GazeSetMerge.
Authors: Yuxi Zhang, Xiang Chen, Jiazheng Wang, Min Liu, Yaonan Wang, Dongdong Liu, Renjiu Hu, Hang Zhang
Abstract: In this paper, we summarize the methods and experimental results we proposed for Task 2 in the learn2reg 2024 Challenge. This task focuses on unsupervised registration of anatomical structures in brain MRI images between different patients. The difficulty lies in: (1) without segmentation labels, and (2) a large amount of data. To address these challenges, we built an efficient backbone network and explored several schemes to further enhance registration accuracy. Under the guidance of the NCC loss function and smoothness regularization loss function, we obtained a smooth and reasonable deformation field. According to the leaderboard, our method achieved a Dice coefficient of 77.34%, which is 1.4% higher than the TransMorph. Overall, we won second place on the leaderboard for Task 2.
Authors: Nan Zhou, Ke Zou, Kai Ren, Mengting Luo, Linchao He, Meng Wang, Yidi Chen, Yi Zhang, Hu Chen, Huazhu Fu
Abstract: The Medical Segment Anything Model (MedSAM) has shown remarkable performance in medical image segmentation, drawing significant attention in the field. However, its sensitivity to varying prompt types and locations poses challenges. This paper addresses these challenges by focusing on the development of reliable prompts that enhance MedSAM's accuracy. We introduce MedSAM-U, an uncertainty-guided framework designed to automatically refine multi-prompt inputs for more reliable and precise medical image segmentation. Specifically, we first train a Multi-Prompt Adapter integrated with MedSAM, creating MPA-MedSAM, to adapt to diverse multi-prompt inputs. We then employ uncertainty-guided multi-prompt to effectively estimate the uncertainties associated with the prompts and their initial segmentation results. In particular, a novel uncertainty-guided prompts adaptation technique is then applied automatically to derive reliable prompts and their corresponding segmentation outcomes. We validate MedSAM-U using datasets from multiple modalities to train a universal image segmentation model. Compared to MedSAM, experimental results on five distinct modal datasets demonstrate that the proposed MedSAM-U achieves an average performance improvement of 1.7\% to 20.5\% across uncertainty-guided prompts.
Authors: Zhuolin Tan, Chenqiang Gao, Anyong Qin, Ruixin Chen, Tiecheng Song, Feng Yang, Deyu Meng
Abstract: Analyzing student actions is an important and challenging task in educational research. Existing efforts have been hampered by the lack of accessible datasets to capture the nuanced action dynamics in classrooms. In this paper, we present a new multi-label student action video (SAV) dataset for complex classroom scenes. The dataset consists of 4,324 carefully trimmed video clips from 758 different classrooms, each labeled with 15 different actions displayed by students in classrooms. Compared to existing behavioral datasets, our dataset stands out by providing a wide range of real classroom scenarios, high-quality video data, and unique challenges, including subtle movement differences, dense object engagement, significant scale differences, varied shooting angles, and visual occlusion. The increased complexity of the dataset brings new opportunities and challenges for benchmarking action detection. Innovatively, we also propose a new baseline method, a visual transformer for enhancing attention to key local details in small and dense object regions. Our method achieves excellent performance with mean Average Precision (mAP) of 67.9\% and 27.4\% on SAV and AVA, respectively. This paper not only provides the dataset but also calls for further research into AI-driven educational tools that may transform teaching methodologies and learning outcomes. The code and dataset will be released at https://github.com/Ritatanz/SAV.
Authors: Yixuan Zhou, Xing Xu, Zhe Sun, Jingkuan Song, Andrzej Cichocki, Heng Tao Shen
Abstract: Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of normalizing flows in multi-class anomaly detection, wherein the normal data is compounded with multiple classes without providing class labels. Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-Flow. Specifically, our VQ-Flow leverages hierarchical vector quantization to estimate two relative codebooks: a Conceptual Prototype Codebook (CPC) for concept distinction and its concomitant Concept-Specific Pattern Codebook (CSPC) to capture concept-specific normal patterns. The flow models in VQ-Flow are conditioned on the concept-specific patterns captured in CSPC, capable of modeling specific normal patterns associated with different concepts. Moreover, CPC further enables our VQ-Flow for concept-aware distribution modeling, faithfully mimicking the intricate multi-class normal distribution through a mixed Gaussian distribution reparametrized on the conceptual prototypes. Through the introduction of vector quantization, the proposed VQ-Flow advances the state-of-the-art in multi-class anomaly detection within a unified training scheme, yielding the Det./Loc. AUROC of 99.5%/98.3% on MVTec AD. The codebase is publicly available at https://github.com/cool-xuan/vqflow.
Authors: Yanfeng Zhou, Lingrui Li, Zichen Wang, Guole Liu, Ziwen Liu, Ge Yang
Abstract: XNet introduces a wavelet-based X-shaped unified architecture for fully- and semi-supervised biomedical segmentation. So far, however, XNet still faces the limitations, including performance degradation when images lack high-frequency (HF) information, underutilization of raw images and insufficient fusion. To address these issues, we propose XNet v2, a low- and high-frequency complementary model. XNet v2 performs wavelet-based image-level complementary fusion, using fusion results along with raw images inputs three different sub-networks to construct consistency loss. Furthermore, we introduce a feature-level fusion module to enhance the transfer of low-frequency (LF) information and HF information. XNet v2 achieves state-of-the-art in semi-supervised segmentation while maintaining competitve results in fully-supervised learning. More importantly, XNet v2 excels in scenarios where XNet fails. Compared to XNet, XNet v2 exhibits fewer limitations, better results and greater universality. Extensive experiments on three 2D and two 3D datasets demonstrate the effectiveness of XNet v2. Code is available at https://github.com/Yanfeng-Zhou/XNetv2 .
Authors: Ge Gao, Ho Man Kwan, Fan Zhang, David Bull
Abstract: Neural video compression has recently demonstrated significant potential to compete with conventional video codecs in terms of rate-quality performance. These learned video codecs are however associated with various issues related to decoding complexity (for autoencoder-based methods) and/or system delays (for implicit neural representation (INR) based models), which currently prevent them from being deployed in practical applications. In this paper, targeting a practical neural video codec, we propose a novel INR-based coding framework, PNVC, which innovatively combines autoencoder-based and overfitted solutions. Our approach benefits from several design innovations, including a new structural reparameterization-based architecture, hierarchical quality control, modulation-based entropy modeling, and scale-aware positional embedding. Supporting both low delay (LD) and random access (RA) configurations, PNVC outperforms existing INR-based codecs, achieving nearly 35%+ BD-rate savings against HEVC HM 18.0 (LD) - almost 10% more compared to one of the state-of-the-art INR-based codecs, HiNeRV and 5% more over VTM 20.0 (LD), while maintaining 20+ FPS decoding speeds for 1080p content. This represents an important step forward for INR-based video coding, moving it towards practical deployment. The source code will be available for public evaluation.
Authors: Sungjoon Park, Jaesub Yun, Donggeon Lee, Minsik Park
Abstract: Because videos in the wild can be out of sync for various reasons, a sync-net is used to bring the video back into sync for tasks that require synchronized videos. Previous state-of-the-art (SOTA) sync-nets use InfoNCE loss, rely on the transformer architecture, or both. Unfortunately, the former makes the model's output difficult to interpret, and the latter is unfriendly with large images, thus limiting the usefulness of sync-nets. In this work, we train a convolutional sync-net using the balanced BCE loss (BBCE), a loss inspired by the binary cross entropy (BCE) and the InfoNCE losses. In contrast to the InfoNCE loss, the BBCE loss does not require complicated sampling schemes. Our model can better handle larger images, and its output can be given a probabilistic interpretation. The probabilistic interpretation allows us to define metrics such as probability at offset and offscreen ratio to evaluate the sync quality of audio-visual (AV) speech datasets. Furthermore, our model achieves SOTA accuracy of $96.5\%$ on the LRS2 dataset and $93.8\%$ on the LRS3 dataset.
Authors: Fangcen Liu, Chenqiang Gao, Fang Chen, Pengcheng Li, Junjie Guo, Deyu Meng
Abstract: Infrared and visible dual-modality tasks such as semantic segmentation and object detection can achieve robust performance even in extreme scenes by fusing complementary information. Most current methods design task-specific frameworks, which are limited in generalization across multiple tasks. In this paper, we propose a fusion-guided infrared and visible general framework, IVGF, which can be easily extended to many high-level vision tasks. Firstly, we adopt the SOTA infrared and visible foundation models to extract the general representations. Then, to enrich the semantics information of these general representations for high-level vision tasks, we design the feature enhancement module and token enhancement module for feature maps and tokens, respectively. Besides, the attention-guided fusion module is proposed for effectively fusing by exploring the complementary information of two modalities. Moreover, we also adopt the cutout&mix augmentation strategy to conduct the data augmentation, which further improves the ability of the model to mine the regional complementary between the two modalities. Extensive experiments show that the IVGF outperforms state-of-the-art dual-modality methods in the semantic segmentation and object detection tasks. The detailed ablation studies demonstrate the effectiveness of each module, and another experiment explores the anti-missing modality ability of the proposed method in the dual-modality semantic segmentation task.
Authors: Zhenye Xu, Yao Guo
Abstract: This paper addresses the critical task of gait cycle segmentation using short sequences from ear-worn IMUs, a practical and non-invasive approach for home-based monitoring and rehabilitation of patients with impaired motor function. While previous studies have focused on IMUs positioned on the lower limbs, ear-worn IMUs offer a unique advantage in capturing gait dynamics with minimal intrusion. To address the challenges of gait cycle segmentation using short sequences, we introduce the Gait Characteristic Curve Regression and Restoration (GCCRR) method, a novel two-stage approach designed for fine-grained gait phase segmentation. The first stage transforms the segmentation task into a regression task on the Gait Characteristic Curve (GCC), which is a one-dimensional feature sequence incorporating periodic information. The second stage restores the gait cycle using peak detection techniques. Our method employs Bi-LSTM-based deep learning algorithms for regression to ensure reliable segmentation for short gait sequences. Evaluation on the HamlynGait dataset demonstrates that GCCRR achieves over 80\% Accuracy, with a Timestamp Error below one sampling interval. Despite its promising results, the performance lags behind methods using more extensive sensor systems, highlighting the need for larger, more diverse datasets. Future work will focus on data augmentation using motion capture systems and improving algorithmic generalizability.
Authors: Jeong Hun Yeo, Chae Won Kim, Hyunjun Kim, Hyeongseop Rha, Seunghee Han, Wen-Huang Cheng, Yong Man Ro
Abstract: Lip reading aims to predict spoken language by analyzing lip movements. Despite advancements in lip reading technologies, performance degrades when models are applied to unseen speakers due to their sensitivity to variations in visual information such as lip appearances. To address this challenge, speaker adaptive lip reading technologies have advanced by focusing on effectively adapting a lip reading model to target speakers in the visual modality. The effectiveness of adapting language information, such as vocabulary choice, of the target speaker has not been explored in the previous works. Moreover, existing datasets for speaker adaptation have limited vocabulary size and pose variations, limiting the validation of previous speaker-adaptive methods in real-world scenarios. To address these issues, we propose a novel speaker-adaptive lip reading method that adapts a pre-trained model to target speakers at both vision and language levels. Specifically, we integrate prompt tuning and the LoRA approach, applying them to a pre-trained lip reading model to effectively adapt the model to target speakers. In addition, to validate its effectiveness in real-world scenarios, we introduce a new dataset, VoxLRS-SA, derived from VoxCeleb2 and LRS3. It contains a vocabulary of approximately 100K words, offers diverse pose variations, and enables the validation of adaptation methods in wild, sentence-level lip reading for the first time. Through various experiments, we demonstrate that the existing speaker-adaptive method also improves performance in the wild at the sentence level. Moreover, with the proposed adaptation method, we show that the proposed method achieves larger improvements when applied to the target speaker, compared to the previous works.
Authors: Lening Guo, Jing Yu, Ning Zhang, Chuangbai Xiao
Abstract: Blind image deblurring is a challenging low-level vision task that involves estimating the unblurred image when the blur kernel is unknown. In this paper, we present a self-supervised multi-scale blind image deblurring method to jointly estimate the latent image and the blur kernel via alternating optimization. In the image estimation step, we construct a multi-scale generator network with multiple inputs and multiple outputs to collaboratively estimate latent images at various scales, supervised by an image pyramid constructed from only the blurred image. This generator places architectural constraints on the network and avoids the need for mathematical expression of image priors. In the blur kernel estimation step, the blur kernel at each scale is independently estimated with a direct solution to a quadratic regularized least-squares model for its flexible adaptation to the proposed multi-scale generator for image estimation. Thanks to the collaborative estimation across multiple scales, our method avoids the computationally intensive coarse-to-fine propagation and additional image deblurring processes used in traditional mathematical optimization-based methods. Quantitative and qualitative experimental results on synthetic and realistic datasets demonstrate the superior performance of our method, especially for handling large and real-world blurs.
Authors: Xiaobin Lu, Xiaobin Hu, Jun Luo, Ben Zhu, Yaping Ruan, Wenqi Ren
Abstract: Blind face restoration endeavors to restore a clear face image from a degraded counterpart. Recent approaches employing Generative Adversarial Networks (GANs) as priors have demonstrated remarkable success in this field. However, these methods encounter challenges in achieving a balance between realism and fidelity, particularly in complex degradation scenarios. To inherit the exceptional realism generative ability of the diffusion model and also constrained by the identity-aware fidelity, we propose a novel diffusion-based framework by embedding the 3D facial priors as structure and identity constraints into a denoising diffusion process. Specifically, in order to obtain more accurate 3D prior representations, the 3D facial image is reconstructed by a 3D Morphable Model (3DMM) using an initial restored face image that has been processed by a pretrained restoration network. A customized multi-level feature extraction method is employed to exploit both structural and identity information of 3D facial images, which are then mapped into the noise estimation process. In order to enhance the fusion of identity information into the noise estimation, we propose a Time-Aware Fusion Block (TAFB). This module offers a more efficient and adaptive fusion of weights for denoising, considering the dynamic nature of the denoising process in the diffusion model, which involves initial structure refinement followed by texture detail enhancement.Extensive experiments demonstrate that our network performs favorably against state-of-the-art algorithms on synthetic and real-world datasets for blind face restoration.
Authors: Qian Li, Shuojue Yang, Daiyun Shen, Yueming Jin
Abstract: Reconstructing endoscopic videos is crucial for high-fidelity visualization and the efficiency of surgical operations. Despite the importance, existing 3D reconstruction methods encounter several challenges, including stringent demands for accuracy, imprecise camera positioning, intricate dynamic scenes, and the necessity for rapid reconstruction. Addressing these issues, this paper presents the first camera-pose-free scene reconstruction framework, Free-DyGS, tailored for dynamic surgical videos, leveraging 3D Gaussian splatting technology. Our approach employs a frame-by-frame reconstruction strategy and is delineated into four distinct phases: Scene Initialization, Joint Learning, Scene Expansion, and Retrospective Learning. We introduce a Generalizable Gaussians Parameterization module within the Scene Initialization and Expansion phases to proficiently generate Gaussian attributes for each pixel from the RGBD frames. The Joint Learning phase is crafted to concurrently deduce scene deformation and camera pose, facilitated by an innovative flexible deformation module. In the scene expansion stage, the Gaussian points gradually grow as the camera moves. The Retrospective Learning phase is dedicated to enhancing the precision of scene deformation through the reassessment of prior frames. The efficacy of the proposed Free-DyGS is substantiated through experiments on two datasets: the StereoMIS and Hamlyn datasets. The experimental outcomes underscore that Free-DyGS surpasses conventional baseline models in both rendering fidelity and computational efficiency.
Authors: Xiaojie Xu, Tianshuo Xu, Fulong Ma, Yingcong Chen
Abstract: We explore Bird's-Eye View (BEV) generation, converting a BEV map into its corresponding multi-view street images. Valued for its unified spatial representation aiding multi-sensor fusion, BEV is pivotal for various autonomous driving applications. Creating accurate street-view images from BEV maps is essential for portraying complex traffic scenarios and enhancing driving algorithms. Concurrently, diffusion-based conditional image generation models have demonstrated remarkable outcomes, adept at producing diverse, high-quality, and condition-aligned results. Nonetheless, the training of these models demands substantial data and computational resources. Hence, exploring methods to fine-tune these advanced models, like Stable Diffusion, for specific conditional generation tasks emerges as a promising avenue. In this paper, we introduce a practical framework for generating images from a BEV layout. Our approach comprises two main components: the Neural View Transformation and the Street Image Generation. The Neural View Transformation phase converts the BEV map into aligned multi-view semantic segmentation maps by learning the shape correspondence between the BEV and perspective views. Subsequently, the Street Image Generation phase utilizes these segmentations as a condition to guide a fine-tuned latent diffusion model. This finetuning process ensures both view and style consistency. Our model leverages the generative capacity of large pretrained diffusion models within traffic contexts, effectively yielding diverse and condition-coherent street view images.
Authors: Ruojun Zhou, Lisha Qu, Lei Zhang, Ziming Li, Hongwei Yu, Bing Luo
Abstract: Deep learning-based techniques have been widely utilized for brain tumor segmentation using both single and multi-modal Magnetic Resonance Imaging (MRI) images. Most current studies focus on centralized training due to the intrinsic challenge of data sharing across clinics. To mitigate privacy concerns, researchers have introduced Federated Learning (FL) methods to brain tumor segmentation tasks. However, currently such methods are focusing on single modal MRI, with limited study on multi-modal MRI. The challenges include complex structure, large-scale parameters, and overfitting issues of the FL based methods using multi-modal MRI. To address the above challenges, we propose a novel multi-modal FL framework for brain tumor segmentation (Fed-MUnet) that is suitable for FL training. We evaluate our approach with the BraTS2022 datasets, which are publicly available. The experimental results demonstrate that our framework achieves FL nature of distributed learning and privacy preserving. For the enhancing tumor, tumor core and whole tumor, the mean of five major metrics were 87.5%, 90.6% and 92.2%, respectively, which were higher than SOTA methods while preserving privacy. In terms of parameters count, quantity of floating-point operations (FLOPs) and inference, Fed-MUnet is Pareto optimal compared with the state-of-the-art segmentation backbone while achieves higher performance and tackles privacy issue. Our codes are open-sourced at https://github.com/Arnold-Jun/Fed-MUnet.
Authors: Long Li, Nian Liu, Dingwen Zhang, Zhongyu Li, Salman Khan, Rao Anwer, Hisham Cholakkal, Junwei Han, Fahad Shahbaz Khan
Abstract: Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.
Authors: Gargi Panda, Soumitra Kundu, Saumik Bhattacharya, Aurobinda Routray
Abstract: Improving the quality of underwater images is essential for advancing marine research and technology. This work introduces a sparsity-driven interpretable neural network (SINET) for the underwater image enhancement (UIE) task. Unlike pure deep learning methods, our network architecture is based on a novel channel-specific convolutional sparse coding (CCSC) model, ensuring good interpretability of the underlying image enhancement process. The key feature of SINET is that it estimates the salient features from the three color channels using three sparse feature estimation blocks (SFEBs). The architecture of SFEB is designed by unrolling an iterative algorithm for solving the $\ell_1$ regulaized convolutional sparse coding (CSC) problem. Our experiments show that SINET surpasses state-of-the-art PSNR value by $1.05$ dB with $3873$ times lower computational complexity.
Authors: Jiahe Tian, Peng Chen, Cai Yu, Xiaomeng Fu, Xi Wang, Jiao Dai, Jizhong Han
Abstract: Locating manipulation maps, i.e., pixel-level annotation of forgery cues, is crucial for providing interpretable detection results in face forgery detection. Related learning objects have also been widely adopted as auxiliary tasks to improve the classification performance of detectors whereas they require comparisons between paired real and forged faces to obtain manipulation maps as supervision. This requirement restricts their applicability to unpaired faces and contradicts real-world scenarios. Moreover, the used comparison methods annotate all changed pixels, including noise introduced by compression and upsampling. Using such maps as supervision hinders the learning of exploitable cues and makes models prone to overfitting. To address these issues, we introduce a weakly supervised model in this paper, named Forgery Cue Discovery (FoCus), to locate forgery cues in unpaired faces. Unlike some detectors that claim to locate forged regions in attention maps, FoCus is designed to sidestep their shortcomings of capturing partial and inaccurate forgery cues. Specifically, we propose a classification attentive regions proposal module to locate forgery cues during classification and a complementary learning module to facilitate the learning of richer cues. The produced manipulation maps can serve as better supervision to enhance face forgery detectors. Visualization of the manipulation maps of the proposed FoCus exhibits superior interpretability and robustness compared to existing methods. Experiments on five datasets and four multi-task models demonstrate the effectiveness of FoCus in both in-dataset and cross-dataset evaluations.
Authors: Qihua Chen, Yue Ma, Hongfa Wang, Junkun Yuan, Wenzhe Zhao, Qi Tian, Hongmei Wang, Shaobo Min, Qifeng Chen, Wei Liu
Abstract: This paper explores higher-resolution video outpainting with extensive content generation. We point out common issues faced by existing methods when attempting to largely outpaint videos: the generation of low-quality content and limitations imposed by GPU memory. To address these challenges, we propose a diffusion-based method called \textit{Follow-Your-Canvas}. It builds upon two core designs. First, instead of employing the common practice of "single-shot" outpainting, we distribute the task across spatial windows and seamlessly merge them. It allows us to outpaint videos of any size and resolution without being constrained by GPU memory. Second, the source video and its relative positional relation are injected into the generation process of each window. It makes the generated spatial layout within each window harmonize with the source video. Coupling with these two designs enables us to generate higher-resolution outpainting videos with rich content while keeping spatial and temporal consistency. Follow-Your-Canvas excels in large-scale video outpainting, e.g., from 512X512 to 1152X2048 (9X), while producing high-quality and aesthetically pleasing results. It achieves the best quantitative results across various resolution and scale setups. The code is released on https://github.com/mayuelala/FollowYourCanvas
Authors: Yepeng Liu, Baosheng Yu, Tian Chen, Yuliang Gu, Bo Du, Yongchao Xu, Jun Cheng
Abstract: Retinal image registration plays an important role in the ophthalmological diagnosis process. Since there exist variances in viewing angles and anatomical structures across different retinal images, keypoint-based approaches become the mainstream methods for retinal image registration thanks to their robustness and low latency. These methods typically assume the retinal surfaces are planar, and adopt feature matching to obtain the homography matrix that represents the global transformation between images. Yet, such a planar hypothesis inevitably introduces registration errors since retinal surface is approximately curved. This limitation is more prominent when registering image pairs with significant differences in viewing angles. To address this problem, we propose a hybrid registration framework called HybridRetina, which progressively registers retinal images with global and local deformable transformations. For that, we use a keypoint detector and a deformation network called GAMorph to estimate the global transformation and local deformable transformation, respectively. Specifically, we integrate multi-level pixel relation knowledge to guide the training of GAMorph. Additionally, we utilize an edge attention module that includes the geometric priors of the images, ensuring the deformation field focuses more on the vascular regions of clinical interest. Experiments on two widely-used datasets, FIRE and FLoRI21, show that our proposed HybridRetina significantly outperforms some state-of-the-art methods. The code is available at https://github.com/lyp-deeplearning/awesome-retinal-registration.
URLs: https://github.com/lyp-deeplearning/awesome-retinal-registration.
Authors: Yuxuan Wang, Cihang Xie, Yang Liu, Zilong Zheng
Abstract: Recent advancements in large-scale video-language models have shown significant potential for real-time planning and detailed interactions. However, their high computational demands and the scarcity of annotated datasets limit their practicality for academic researchers. In this work, we introduce VideoLLaMB, a novel framework that utilizes temporal memory tokens within bridge layers to allow for the encoding of entire video sequences alongside historical visual data, effectively preserving semantic continuity and enhancing model performance across various tasks. This approach includes recurrent memory tokens and a SceneTilling algorithm, which segments videos into independent semantic units to preserve semantic integrity. Empirically, VideoLLaMB significantly outstrips existing video-language models, demonstrating a 5.5 points improvement over its competitors across three VideoQA benchmarks, and 2.06 points on egocentric planning. Comprehensive results on the MVBench show that VideoLLaMB-7B achieves markedly better results than previous 7B models of same LLM. Remarkably, it maintains robust performance as PLLaVA even as video length increases up to 8 times. Besides, the frame retrieval results on our specialized Needle in a Video Haystack (NIAVH) benchmark, further validate VideoLLaMB's prowess in accurately identifying specific frames within lengthy videos. Our SceneTilling algorithm also enables the generation of streaming video captions directly, without necessitating additional training. In terms of efficiency, VideoLLaMB, trained on 16 frames, supports up to 320 frames on a single Nvidia A100 GPU with linear GPU memory scaling, ensuring both high performance and cost-effectiveness, thereby setting a new foundation for long-form video-language models in both academic and practical applications.
Authors: Taorong Liu, Jing Xiao, Liang Liao, Chia-Wen Lin
Abstract: Online Domain Adaptation (OnDA) is designed to handle unforeseeable domain changes at minimal cost that occur during the deployment of the model, lacking clear boundaries between the domain, such as sudden weather events. However, existing OnDA methods that rely solely on the model itself to adapt to the current domain often misidentify ambiguous classes amidst continuous domain shifts and pass on this erroneous knowledge to the next domain. To tackle this, we propose \textbf{RODASS}, a \textbf{R}obust \textbf{O}nline \textbf{D}omain \textbf{A}daptive \textbf{S}emantic \textbf{S}egmentation framework, which dynamically detects domain shifts and adjusts hyper-parameters to minimize training costs and error propagation. Specifically, we introduce the \textbf{D}ynamic \textbf{A}mbiguous \textbf{P}atch \textbf{Mask} (\textbf{DAP Mask}) strategy, which dynamically selects highly disturbed regions and masks these regions, mitigating error accumulation in ambiguous classes and enhancing the model's robustness against external noise in dynamic natural environments. Additionally, we present the \textbf{D}ynamic \textbf{S}ource \textbf{C}lass \textbf{Mix} (\textbf{DSC Mix}), a domain-aware mix method that augments target domain scenes with class-level source buffers, reducing the high uncertainty and noisy labels, thereby accelerating adaptation and offering a more efficient solution for online domain adaptation. Our approach outperforms state-of-the-art methods on widely used OnDA benchmarks while maintaining approximately 40 frames per second (FPS).
Authors: Yuqi Liu, Wenqian Zhang, Sihan Ren, Chengyu Huang, Jingyi Yu, Lan Xu
Abstract: Sign languages, used by around 70 million Deaf individuals globally, are visual languages that convey visual and contextual information. Current methods in vision-based sign language recognition (SLR) and translation (SLT) struggle with dialogue scenes due to limited dataset diversity and the neglect of contextually relevant information. To address these challenges, we introduce SCOPE (Sign language Contextual Processing with Embedding from LLMs), a novel context-aware vision-based SLR and SLT framework. For SLR, we utilize dialogue contexts through a multi-modal encoder to enhance gloss-level recognition. For subsequent SLT, we further fine-tune a Large Language Model (LLM) by incorporating prior conversational context. We also contribute a new sign language dataset that contains 72 hours of Chinese sign language videos in contextual dialogues across various scenarios. Experimental results demonstrate that our SCOPE framework achieves state-of-the-art performance on multiple datasets, including Phoenix-2014T, CSL-Daily, and our SCOPE dataset. Moreover, surveys conducted with participants from the Deaf community further validate the robustness and effectiveness of our approach in real-world applications. Both our dataset and code will be open-sourced to facilitate further research.
Authors: Danilo Dordevic, Suryansh Kumar
Abstract: We introduce the Evidential Transformer, an uncertainty-driven transformer model for improved and robust image retrieval. In this paper, we make several contributions to content-based image retrieval (CBIR). We incorporate probabilistic methods into image retrieval, achieving robust and reliable results, with evidential classification surpassing traditional training based on multiclass classification as a baseline for deep metric learning. Furthermore, we improve the state-of-the-art retrieval results on several datasets by leveraging the Global Context Vision Transformer (GC ViT) architecture. Our experimental results consistently demonstrate the reliability of our approach, setting a new benchmark in CBIR in all test settings on the Stanford Online Products (SOP) and CUB-200-2011 datasets.
Authors: Xiaolong Wang, Zhi-Qi Cheng, Jue Wang, Xiaojiang Peng
Abstract: Fashion image editing is a crucial tool for designers to convey their creative ideas by visualizing design concepts interactively. Current fashion image editing techniques, though advanced with multimodal prompts and powerful diffusion models, often struggle to accurately identify editing regions and preserve the desired garment texture detail. To address these challenges, we introduce a new multimodal fashion image editing architecture based on latent diffusion models, called Detail-Preserved Diffusion Models (DPDEdit). DPDEdit guides the fashion image generation of diffusion models by integrating text prompts, region masks, human pose images, and garment texture images. To precisely locate the editing region, we first introduce Grounded-SAM to predict the editing region based on the user's textual description, and then combine it with other conditions to perform local editing. To transfer the detail of the given garment texture into the target fashion image, we propose a texture injection and refinement mechanism. Specifically, this mechanism employs a decoupled cross-attention layer to integrate textual descriptions and texture images, and incorporates an auxiliary U-Net to preserve the high-frequency details of generated garment texture. Additionally, we extend the VITON-HD dataset using a multimodal large language model to generate paired samples with texture images and textual descriptions. Extensive experiments show that our DPDEdit outperforms state-of-the-art methods in terms of image fidelity and coherence with the given multimodal inputs.
Authors: Yang Li, Jianli Xiao
Abstract: Accurate real-time object detection enhances the safety of advanced driver-assistance systems, making it an essential component in driving scenarios. With the rapid development of deep learning technology, CNN-based YOLO real-time object detectors have gained significant attention. However, the local focus of CNNs results in performance bottlenecks. To further enhance detector performance, researchers have introduced Transformer-based self-attention mechanisms to leverage global receptive fields, but their quadratic complexity incurs substantial computational costs. Recently, Mamba, with its linear complexity, has made significant progress through global selective scanning. Inspired by Mamba's outstanding performance, we propose a novel object detector: DS MYOLO. This detector captures global feature information through a simplified selective scanning fusion block (SimVSS Block) and effectively integrates the network's deep features. Additionally, we introduce an efficient channel attention convolution (ECAConv) that enhances cross-channel feature interaction while maintaining low computational complexity. Extensive experiments on the CCTSDB 2021 and VLD-45 driving scenarios datasets demonstrate that DS MYOLO exhibits significant potential and competitive advantage among similarly scaled YOLO series real-time object detectors.
Authors: Yingrui Wu, Mingyang Zhao, Weize Quan, Jian Shi, Xiaohong Jia, Dong-Ming Yan
Abstract: We present a robust refinement method for estimating oriented normals from unstructured point clouds. In contrast to previous approaches that either suffer from high computational complexity or fail to achieve desirable accuracy, our novel framework incorporates sign orientation and data augmentation in the feature space to refine the initial oriented normals, striking a balance between efficiency and accuracy. To address the issue of noise-caused direction inconsistency existing in previous approaches, we introduce a new metric called the Chamfer Normal Distance, which faithfully minimizes the estimation error by correcting the annotated normal with the closest point found on the potentially clean point cloud. This metric not only tackles the challenge but also aids in network training and significantly enhances network robustness against noise. Moreover, we propose an innovative dual-parallel architecture that integrates Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion, which enables the network to capture intricate geometric details more effectively and notably reduces ambiguity in scale selection. Extensive experiments demonstrate the superiority and versatility of our method in both unoriented and oriented normal estimation tasks across synthetic and real-world datasets among indoor and outdoor scenarios. The code is available at https://github.com/YingruiWoo/OCMG-Net.git.
Authors: Alberto Bacchin, Davide Allegro, Stefano Ghidoni, Emanuele Menegatti
Abstract: Out-of-Distribution (OOD) detection in computer vision is a crucial research area, with related benchmarks playing a vital role in assessing the generalizability of models and their applicability in real-world scenarios. However, existing OOD benchmarks in the literature suffer from two main limitations: (1) they often overlook semantic shift as a potential challenge, and (2) their scale is limited compared to the large datasets used to train modern models. To address these gaps, we introduce SOOD-ImageNet, a novel dataset comprising around 1.6M images across 56 classes, designed for common computer vision tasks such as image classification and semantic segmentation under OOD conditions, with a particular focus on the issue of semantic shift. We ensured the necessary scalability and quality by developing an innovative data engine that leverages the capabilities of modern vision-language models, complemented by accurate human checks. Through extensive training and evaluation of various models on SOOD-ImageNet, we showcase its potential to significantly advance OOD research in computer vision. The project page is available at https://github.com/bach05/SOODImageNet.git.
Authors: Zhihao Xu, Shengjie Gong, Jiapeng Tang, Lingyu Liang, Yining Huang, Haojie Li, Shuangping Huang
Abstract: We present a novel approach for synthesizing 3D facial motions from audio sequences using key motion embeddings. Despite recent advancements in data-driven techniques, accurately mapping between audio signals and 3D facial meshes remains challenging. Direct regression of the entire sequence often leads to over-smoothed results due to the ill-posed nature of the problem. To this end, we propose a progressive learning mechanism that generates 3D facial animations by introducing key motion capture to decrease cross-modal mapping uncertainty and learning complexity. Concretely, our method integrates linguistic and data-driven priors through two modules: the linguistic-based key motion acquisition and the cross-modal motion completion. The former identifies key motions and learns the associated 3D facial expressions, ensuring accurate lip-speech synchronization. The latter extends key motions into a full sequence of 3D talking faces guided by audio features, improving temporal coherence and audio-visual consistency. Extensive experimental comparisons against existing state-of-the-art methods demonstrate the superiority of our approach in generating more vivid and consistent talking face animations. Consistent enhancements in results through the integration of our proposed learning scheme with existing methods underscore the efficacy of our approach. Our code and weights will be at the project website: \url{https://github.com/ffxzh/KMTalk}.
Authors: Zhongyi Xia, Tianzhao Wu
Abstract: Monocular depth estimation is a critical function in computer vision applications. This paper shows that large language models (LLMs) can effectively interpret depth with minimal supervision, using efficient resource utilization and a consistent neural network architecture. We introduce LLM-MDE, a multimodal framework that deciphers depth through language comprehension. Specifically, LLM-MDE employs two main strategies to enhance the pretrained LLM's capability for depth estimation: cross-modal reprogramming and an adaptive prompt estimation module. These strategies align vision representations with text prototypes and automatically generate prompts based on monocular images, respectively. Comprehensive experiments on real-world MDE datasets confirm the effectiveness and superiority of LLM-MDE, which excels in few-/zero-shot tasks while minimizing resource use. The source code is available.
Authors: Tuong Vy Nguyen, Johannes Hoster, Alexander Glaser, Kristian Hildebrand, Felix Biessmann
Abstract: Generative deep learning architectures can produce realistic, high-resolution fake imagery -- with potentially drastic societal implications. A key question in this context is: How easy is it to generate realistic imagery, in particular for niche domains. The iterative process required to achieve specific image content is difficult to automate and control. Especially for rare classes, it remains difficult to assess fidelity, meaning whether generative approaches produce realistic imagery and alignment, meaning how (well) the generation can be guided by human input. In this work, we present a large-scale empirical evaluation of generative architectures which we fine-tuned to generate synthetic satellite imagery. We focus on nuclear power plants as an example of a rare object category - as there are only around 400 facilities worldwide, this restriction is exemplary for many other scenarios in which training and test data is limited by the restricted number of occurrences of real-world examples. We generate synthetic imagery by conditioning on two kinds of modalities, textual input and image input obtained from a game engine that allows for detailed specification of the building layout. The generated images are assessed by commonly used metrics for automatic evaluation and then compared with human judgement from our conducted user studies to assess their trustworthiness. Our results demonstrate that even for rare objects, generation of authentic synthetic satellite imagery with textual or detailed building layouts is feasible. In line with previous work, we find that automated metrics are often not aligned with human perception -- in fact, we find strong negative correlations between commonly used image quality metrics and human ratings.
Authors: Mingyuan Yao, Yukang Huo, Qingbin Tian, Jiayin Zhao, Xiao Liu, Ruifeng Wang, Haihua Wang
Abstract: Growth, abnormal behavior, and diseases of fish can be early detected by monitoring fish tracking through the method of image processing, which is of great significance for factory aquaculture. However, underwater reflections and some reasons with fish, such as the high similarity , rapid swimming caused by stimuli and multi-object occlusion bring challenges to multi-target tracking of fish. To address these challenges, this paper establishes a complex multi-scene sturgeon tracking dataset and proposes a real-time end-to-end fish tracking model, FMRFT. In this model, the Mamba In Mamba (MIM) architecture with low memory consumption is introduced into the tracking algorithm to realize multi-frame video timing memory and fast feature extraction, which improves the efficiency of correlation analysis for contiguous frames in multi-fish video. Additionally, the superior feature interaction and a priori frame processing capabilities of RT-DETR are leveraged to provide an effective tracking algorithm. By incorporating the QTSI query interaction processing module, the model effectively handles occluded objects and redundant tracking frames, resulting in more accurate and stable fish tracking. Trained and tested on the dataset, the model achieves an IDF1 score of 90.3% and a MOTA accuracy of 94.3%. Experimental results demonstrate that the proposed FMRFT model effectively addresses the challenges of high similarity and mutual occlusion in fish populations, enabling accurate tracking in factory farming environments.
Authors: Yueqian Wang, Jianxin Liang, Yuxuan Wang, Huishuai Zhang, Dongyan Zhao
Abstract: Hallucination is a common issue in Multimodal Large Language Models (MLLMs), yet the underlying principles remain poorly understood. In this paper, we investigate which components of MLLMs contribute to object hallucinations. To analyze image representations while completely avoiding the influence of all other factors other than the image representation itself, we propose a parametric-free representation alignment metric (Pfram) that can measure the similarities between any two representation systems without requiring additional training parameters. Notably, Pfram can also assess the alignment of a neural representation system with the human representation system, represented by ground-truth annotations of images. By evaluating the alignment with object annotations, we demonstrate that this metric shows strong and consistent correlations with object hallucination across a wide range of state-of-the-art MLLMs, spanning various model architectures and sizes. Furthermore, using this metric, we explore other key issues related to image representations in MLLMs, such as the role of different modules, the impact of textual instructions, and potential improvements including the use of alternative visual encoders. Our code is available at: https://github.com/yellow-binary-tree/Pfram.
Authors: Leqi Shen, Tianxiang Hao, Sicheng Zhao, Yifeng Zhang, Pengzhang Liu, Yongjun Bao, Guiguang Ding
Abstract: Most text-video retrieval methods utilize the text-image pre-trained CLIP as a backbone, incorporating complex modules that result in high computational overhead. As a result, many studies focus on efficient fine-tuning. The primary challenge in efficient adaption arises from the inherent differences between image and video modalities. Each sampled video frame must be processed by the image encoder independently, which increases complexity and complicates practical deployment. Although existing efficient methods fine-tune with small trainable parameters, they still incur high inference costs due to the large token number. In this work, we argue that temporal redundancy significantly contributes to the model's high complexity due to the repeated information in consecutive frames. Existing token compression methods for image models fail to solve the unique challenges, as they overlook temporal redundancy across frames. To tackle these problems, we propose Temporal Token Merging (TempMe) to reduce temporal redundancy. Specifically, we introduce a progressive multi-granularity framework. By gradually combining neighboring clips, we merge temporal tokens across different frames and learn video-level features, leading to lower complexity and better performance. Extensive experiments validate the superiority of our TempMe. Compared to previous efficient text-video retrieval methods, TempMe significantly reduces output tokens by 95% and GFLOPs by 51%, while achieving a 1.8X speedup and a 4.4% R-Sum improvement. Additionally, TempMe exhibits robust generalization capabilities by integrating effectively with both efficient and full fine-tuning methods. With full fine-tuning, TempMe achieves a significant 7.9% R-Sum improvement, trains 1.57X faster, and utilizes 75.2% GPU memory usage. Our code will be released.
Authors: Gaotong Yu, Yi Chen, Jian Xu
Abstract: Recently, multimodal large language models (MM-LLMs) have achieved great success in many multimodal tasks, but their high computational costs limit their further promotion and application. In the MM-LLMs framework, the main computational consumption step is the processing of concatenated text and visual tokens at the LLM layer. The length of the input token for LLM directly affects the overall training and inference efficiency. In response to this issue, we further studied the visual tokens of MM-LLMs. We found that the similarity between visual and CLS tokens in the visual encoder follows a long-tail distribution. In other words, only a few visual tokens are highly similar to CLS tokens. Therefore, we designed a dynamic pruning algorithm to address this issue. Firstly, for different input samples, we search for the inflection point of their visual CLS token similarity curve and use it as the corresponding segmentation point to trim the visual markers. This process mainly reduces the output of the visual encoder to accelerate the model. Then, in the LLM layer, the concatenated visual text tokens are pruned for the second time. During this process, due to the interaction between visual and textual features, visual and textual tokens with low text correlation are further filtered, achieving a balance between efficiency and performance. The results on multiple datasets show that our proposed method can achieve performance that competes with the original performance when using an average of 22% of the original token quantity. Our source code will be made publicly available following acceptance.
Authors: Hsin-Yi Chen, Chuan-Kai Fu, Jen-Hui Chuang
Abstract: Accurate calibration of camera intrinsic parameters is crucial to various computer vision-based applications in the fields of intelligent systems, autonomous vehicles, etc. However, existing calibration schemes are incompetent for finding general trend of the variation of camera parameters due to common physical changes. In this paper, it is demonstrated that major and minor variations due to changes in focal length and camera pose, respectively, can be identified with a recently proposed calibration method. It is readily observable from the experimental results that the former variations have different trends (directions) of principal point deviation for different types of camera, possibly due to different internal lens configurations, while the latter have very similar trends in the deviation which is most likely due to direction of gravity. Finally, to confirm the validity of such unprecedented findings, 3D to 2D reprojection errors are compared for different methods of camera calibration.
Authors: Yi Chen, Jian Xu, Xu-Yao Zhang, Wen-Zhuo Liu, Yang-Yang Liu, Cheng-Lin Liu
Abstract: With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current large-scale multimodal models achieve this by mapping visual features obtained from the visual encoder into a large language model and using them as inputs alongside text for downstream tasks. Therefore, the number of visual tokens directly affects the training and inference speed of the model. There has been significant work on token pruning for visual transformers, but for large multimodal models, only relying on visual information for token pruning or compression may lead to significant loss of important information. On the other hand, the textual input in the form of a question may contain valuable information that can aid in answering the question, providing additional knowledge to the model. To address the potential oversimplification and excessive pruning that can occur with most purely visual token pruning methods, we propose a text information-guided dynamic visual token recovery mechanism that does not require training. This mechanism leverages the similarity between the question text and visual tokens to recover visually meaningful tokens with important text information while merging other less important tokens. Experimental results demonstrate that our proposed method achieves comparable performance to the original approach while compressing the visual tokens to an average of 10% of the original quantity. Our source code will be made publicly available following acceptance.
Authors: Adrito Das, Danyal Z. Khan, Dimitrios Psychogyios, Yitong Zhang, John G. Hanrahan, Francisco Vasconcelos, You Pang, Zhen Chen, Jinlin Wu, Xiaoyang Zou, Guoyan Zheng, Abdul Qayyum, Moona Mazher, Imran Razzak, Tianbin Li, Jin Ye, Junjun He, Szymon P{\l}otka, Joanna Kaleta, Amine Yamlahi, Antoine Jund, Patrick Godau, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Dominik Rivoir, Alejandra P\'erez, Santiago Rodriguez, Pablo Arbel\'aez, Danail Stoyanov, Hani J. Marcus, Sophia Bano
Abstract: The field of computer vision applied to videos of minimally invasive surgery is ever-growing. Workflow recognition pertains to the automated recognition of various aspects of a surgery: including which surgical steps are performed; and which surgical instruments are used. This information can later be used to assist clinicians when learning the surgery; during live surgery; and when writing operation notes. The Pituitary Vision (PitVis) 2023 Challenge tasks the community to step and instrument recognition in videos of endoscopic pituitary surgery. This is a unique task when compared to other minimally invasive surgeries due to the smaller working space, which limits and distorts vision; and higher frequency of instrument and step switching, which requires more precise model predictions. Participants were provided with 25-videos, with results presented at the MICCAI-2023 conference as part of the Endoscopic Vision 2023 Challenge in Vancouver, Canada, on 08-Oct-2023. There were 18-submissions from 9-teams across 6-countries, using a variety of deep learning models. A commonality between the top performing models was incorporating spatio-temporal and multi-task methods, with greater than 50% and 10% macro-F1-score improvement over purely spacial single-task models in step and instrument recognition respectively. The PitVis-2023 Challenge therefore demonstrates state-of-the-art computer vision models in minimally invasive surgery are transferable to a new dataset, with surgery specific techniques used to enhance performance, progressing the field further. Benchmark results are provided in the paper, and the dataset is publicly available at: https://doi.org/10.5522/04/26531686.
Authors: Liuhan Chen, Zongjian Li, Bin Lin, Bin Zhu, Qian Wang, Shenghai Yuan, Xing Zhou, Xinghua Cheng, Li Yuan
Abstract: Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstruction quality, the more sufficient the VAE's compression for videos is, the more efficient the LVDMs are. However, most LVDMs utilize 2D image VAE, whose compression for videos is only in the spatial dimension and often ignored in the temporal dimension. How to conduct temporal compression for videos in a VAE to obtain more concise latent representations while promising accurate reconstruction is seldom explored. To fill this gap, we propose an omni-dimension compression VAE, named OD-VAE, which can temporally and spatially compress videos. Although OD-VAE's more sufficient compression brings a great challenge to video reconstruction, it can still achieve high reconstructed accuracy by our fine design. To obtain a better trade-off between video reconstruction quality and compression speed, four variants of OD-VAE are introduced and analyzed. In addition, a novel tail initialization is designed to train OD-VAE more efficiently, and a novel inference strategy is proposed to enable OD-VAE to handle videos of arbitrary length with limited GPU memory. Comprehensive experiments on video reconstruction and LVDM-based video generation demonstrate the effectiveness and efficiency of our proposed methods.
Authors: Zewen Chen, Sunhan Xu, Yun Zeng, Haochen Guo, Jian Guo, Shuai Liu, Juan Wang, Bing Li, Weiming Hu, Dehua Liu, Hesong Li
Abstract: With the rising demand for high-resolution (HR) images, No-Reference Image Quality Assessment (NR-IQA) gains more attention, as it can ecaluate image quality in real-time on mobile devices and enhance user experience. However, existing NR-IQA methods often resize or crop the HR images into small resolution, which leads to a loss of important details. And most of them are of high computational complexity, which hinders their application on mobile devices due to limited computational resources. To address these challenges, we propose MobileIQA, a novel approach that utilizes lightweight backbones to efficiently assess image quality while preserving image details through high-resolution input. MobileIQA employs the proposed multi-view attention learning (MAL) module to capture diverse opinions, simulating subjective opinions provided by different annotators during the dataset annotation process. The model uses a teacher model to guide the learning of a student model through knowledge distillation. This method significantly reduces computational complexity while maintaining high performance. Experiments demonstrate that MobileIQA outperforms novel IQA methods on evaluation metrics and computational efficiency. The code is available at https://github.com/chencn2020/MobileIQA.
Authors: Luoyu Mei, Shuai Wang, Yun Cheng, Ruofeng Liu, Zhimeng Yin, Wenchao Jiang, Shuai Wang, Wei Gong
Abstract: Semantic recognition is pivotal in virtual reality (VR) applications, enabling immersive and interactive experiences. A promising approach is utilizing millimeter-wave (mmWave) signals to generate point clouds. However, the high computational and memory demands of current mmWave point cloud models hinder their efficiency and reliability. To address this limitation, our paper introduces ESP-PCT, a novel Enhanced Semantic Performance Point Cloud Transformer with a two-stage semantic recognition framework tailored for VR applications. ESP-PCT takes advantage of the accuracy of sensory point cloud data and optimizes the semantic recognition process, where the localization and focus stages are trained jointly in an end-to-end manner. We evaluate ESP-PCT on various VR semantic recognition conditions, demonstrating substantial enhancements in recognition efficiency. Notably, ESP-PCT achieves a remarkable accuracy of 93.2% while reducing the computational requirements (FLOPs) by 76.9% and memory usage by 78.2% compared to the existing Point Transformer model simultaneously. These underscore ESP-PCT's potential in VR semantic recognition by achieving high accuracy and reducing redundancy. The code and data of this project are available at \url{https://github.com/lymei-SEU/ESP-PCT}.
Authors: Kim Jinwoo
Abstract: Image retrieval is a crucial research topic in computer vision, with broad application prospects ranging from online product searches to security surveillance systems. In recent years, the accuracy and efficiency of image retrieval have significantly improved due to advancements in deep learning. However, existing methods still face numerous challenges, particularly in handling large-scale datasets, cross-domain retrieval, and image perturbations that can arise from real-world conditions such as variations in lighting, occlusion, and viewpoint. Data augmentation techniques and adversarial learning methods have been widely applied in the field of image retrieval to address these challenges. Data augmentation enhances the model's generalization ability and robustness by generating more diverse training samples, simulating real-world variations, and reducing overfitting. Meanwhile, adversarial attacks and defenses introduce perturbations during training to improve the model's robustness against potential attacks, ensuring reliability in practical applications. This review comprehensively summarizes the latest research advancements in image retrieval, with a particular focus on the roles of data augmentation and adversarial learning techniques in enhancing retrieval performance. Future directions and potential challenges are also discussed.
Authors: Kangdao Liu, Tianhao Sun, Hao Zeng, Yongshan Zhang, Chi-Man Pun, Chi-Man Vong
Abstract: Hyperspectral image (HSI) classification involves assigning specific labels to each pixel to identify various land cover categories. Although deep classifiers have shown high predictive accuracy in this field, quantifying their uncertainty remains a significant challenge, which hinders their application in critical contexts. This study first theoretically evaluates the applicability of \textit{Conformal Prediction} (CP), an emerging technique for uncertainty quantification, in the context of HSI classification. We then propose a conformal procedure that provides HSI classifiers with trustworthy prediction sets, offering coverage guarantees that ensure these sets contain the true labels with a user-specified probability. Building on this foundation, we introduce \textit{Spatial-Aware Conformal Prediction} (\texttt{SACP}), which incorporates essential spatial information inherent in HSIs by aggregating non-conformity scores of pixels with high spatial correlation. Both theoretical and empirical results demonstrate that \texttt{SACP} outperforms standard CP in HSI classification. The source code is accessible at \url{https://github.com/J4ckLiu/SACP}.
Authors: Haicheng Liao, Yongkang Li, Chengyue Wang, Songning Lai, Zhenning Li, Zilin Bian, Jaeyoung Lee, Zhiyong Cui, Guohui Zhang, Chengzhong Xu
Abstract: The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances the prediction capabilities beyond the current state-of-the-art (SOTA) 2D-based methods by incorporating monocular depth cues for sophisticated 3D scene modeling. Addressing the prevalent challenge of skewed data distribution in traffic accident datasets, we propose the Binary Adaptive Loss for Early Anticipation (BA-LEA). This novel loss function, together with a multi-task learning strategy, shifts the focus of the predictive model towards the critical moments preceding an accident. {We rigorously evaluate the performance of our framework on three benchmark datasets--Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D), and DADA-2000 Dataset--demonstrating its superior predictive accuracy through key metrics such as Average Precision (AP) and mean Time-To-Accident (mTTA).
Authors: German F. Torres, Jussi Kalliola, Soumya Tripathy, Erman Acar, Joni-Kristian K\"am\"ar\"ainen
Abstract: Video deblurring aims at recovering sharp details from a sequence of blurry frames. Despite the proliferation of depth sensors in mobile phones and the potential of depth information to guide deblurring, depth-aware deblurring has received only limited attention. In this work, we introduce the 'Depth-Aware VIdeo DEblurring' (DAVIDE) dataset to study the impact of depth information in video deblurring. The dataset comprises synchronized blurred, sharp, and depth videos. We investigate how the depth information should be injected into the existing deep RGB video deblurring models, and propose a strong baseline for depth-aware video deblurring. Our findings reveal the significance of depth information in video deblurring and provide insights into the use cases where depth cues are beneficial. In addition, our results demonstrate that while the depth improves deblurring performance, this effect diminishes when models are provided with a longer temporal context. Project page: https://germanftv.github.io/DAVIDE.github.io/ .
Authors: Haiju Fan, Xiaona Qin, Shuang Chen, Hubert P. H. Shum, Ming Li
Abstract: To improve storage and transmission, images are generally compressed. Vector quantization (VQ) is a popular compression method as it has a high compression ratio that suppresses other compression techniques. Despite this, existing adversarial attack methods on image classification are mostly performed in the pixel domain with few exceptions in the compressed domain, making them less applicable in real-world scenarios. In this paper, we propose a novel one-index attack method in the VQ domain to generate adversarial images by a differential evolution algorithm, successfully resulting in image misclassification in victim models. The one-index attack method modifies a single index in the compressed data stream so that the decompressed image is misclassified. It only needs to modify a single VQ index to realize an attack, which limits the number of perturbed indexes. The proposed method belongs to a semi-black-box attack, which is more in line with the actual attack scenario. We apply our method to attack three popular image classification models, i.e., Resnet, NIN, and VGG16. On average, 55.9% and 77.4% of the images in CIFAR-10 and Fashion MNIST, respectively, are successfully attacked, with a high level of misclassification confidence and a low level of image perturbation.
Authors: Sebastian G. Gruber, Pascal Tobias Ziegler, Florian Buettner
Abstract: The evaluation of image generators remains a challenge due to the limitations of traditional metrics in providing nuanced insights into specific image regions. This is a critical problem as not all regions of an image may be learned with similar ease. In this work, we propose a novel approach to disentangle the cosine similarity of mean embeddings into the product of cosine similarities for individual pixel clusters via central kernel alignment. Consequently, we can quantify the contribution of the cluster-wise performance to the overall image generation performance. We demonstrate how this enhances the explainability and the likelihood of identifying pixel regions of model misbehavior across various real-world use cases.
Authors: Maximilian Mueller, Matthias Hein
Abstract: In realistic medical settings, the data are often inherently long-tailed, with most samples concentrated in a few classes and a long tail of rare classes, usually containing just a few samples. This distribution presents a significant challenge because rare conditions are critical to detect and difficult to classify due to limited data. In this paper, rather than attempting to classify rare classes, we aim to detect these as out-of-distribution data reliably. We leverage low-rank adaption (LoRA) and diffusion guidance to generate targeted synthetic data for the detection problem. We significantly improve the OOD detection performance on a challenging histopathological task with only ten samples per tail class without losing classification accuracy on the head classes.
Authors: Vadim Titov, Madina Khalmatova, Alexandra Ivanova, Dmitry Vetrov, Aibek Alanov
Abstract: Despite recent advances in large-scale text-to-image generative models, manipulating real images with these models remains a challenging problem. The main limitations of existing editing methods are that they either fail to perform with consistent quality on a wide range of image edits or require time-consuming hyperparameter tuning or fine-tuning of the diffusion model to preserve the image-specific appearance of the input image. We propose a novel approach that is built upon a modified diffusion sampling process via the guidance mechanism. In this work, we explore the self-guidance technique to preserve the overall structure of the input image and its local regions appearance that should not be edited. In particular, we explicitly introduce layout-preserving energy functions that are aimed to save local and global structures of the source image. Additionally, we propose a noise rescaling mechanism that allows to preserve noise distribution by balancing the norms of classifier-free guidance and our proposed guiders during generation. Such a guiding approach does not require fine-tuning the diffusion model and exact inversion process. As a result, the proposed method provides a fast and high-quality editing mechanism. In our experiments, we show through human evaluation and quantitative analysis that the proposed method allows to produce desired editing which is more preferable by humans and also achieves a better trade-off between editing quality and preservation of the original image. Our code is available at https://github.com/FusionBrainLab/Guide-and-Rescale.
Authors: Yang Zhang, Rui Zhang, Xuecheng Nie, Haochen Li, Jikun Chen, Yifan Hao, Xin Zhang, Luoqi Liu, Ling Li
Abstract: Recent text-to-image models have achieved remarkable success in generating high-quality images. However, when tasked with multi-concept generation which creates images containing multiple characters or objects, existing methods often suffer from attribute confusion, resulting in severe text-image inconsistency. We found that attribute confusion occurs when a certain region of the latent features attend to multiple or incorrect prompt tokens. In this work, we propose novel Semantic Protection Diffusion (SPDiffusion) to protect the semantics of regions from the influence of irrelevant tokens, eliminating the confusion of non-corresponding attributes. In the SPDiffusion framework, we design a Semantic Protection Mask (SP-Mask) to represent the relevance of the regions and the tokens, and propose a Semantic Protection Cross-Attention (SP-Attn) to shield the influence of irrelevant tokens on specific regions in the generation process. To evaluate our method, we created a diverse multi-concept benchmark, and SPDiffusion achieves state-of-the-art results on this benchmark, proving its effectiveness. Our method can be combined with many other application methods or backbones, such as ControlNet, Story Diffusion, PhotoMaker and PixArt-alpha to enhance their multi-concept capabilities, demonstrating strong compatibility and scalability.
Authors: Iulian Emil Tampu, Per Nyman, Christoforos Spyretos, Ida Blystad, Alia Shamikh, Gabriela Prochazka, Teresita D\'iaz de St{\aa}hl, Johanna Sandgren, Peter Lundberg, Neda Haj-Hosseini
Abstract: Brain tumors are the most common solid tumors in children and young adults, but the scarcity of large histopathology datasets has limited the application of computational pathology in this group. This study implements two weakly supervised multiple-instance learning (MIL) approaches on patch-features obtained from state-of-the-art histology-specific foundation models to classify pediatric brain tumors in hematoxylin and eosin whole slide images (WSIs) from a multi-center Swedish cohort. WSIs from 540 subjects (age 8.5$\pm$4.9 years) diagnosed with brain tumor were gathered from the six Swedish university hospitals. Instance (patch)-level features were obtained from WSIs using three pre-trained feature extractors: ResNet50, UNI and CONCH. Instances were aggregated using attention-based MIL (ABMIL) or clustering-constrained attention MIL (CLAM) for patient-level classification. Models were evaluated on three classification tasks based on the hierarchical classification of pediatric brain tumors: tumor category, family and type. Model generalization was assessed by training on data from two of the centers and testing on data from four other centers. Model interpretability was evaluated through attention-mapping. The highest classification performance was achieved using UNI features and AMBIL aggregation, with Matthew's correlation coefficient of 0.86$\pm$0.04, 0.63$\pm$0.04, and 0.53$\pm$0.05, for tumor category, family and type classification, respectively. When evaluating generalization, models utilizing UNI and CONCH features outperformed those using ResNet50. However, the drop in performance from the in-site to out-of-site testing was similar across feature extractors. These results show the potential of state-of-the-art computational pathology methods in diagnosing pediatric brain tumors at different hierarchical levels with fair generalizability on a multi-center national dataset.
Authors: Siqi Luo, Yi Xin, Yuntao Du, Zhongwei Wan, Tao Tan, Guangtao Zhai, Xiaohong Liu
Abstract: Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data. Although these methods offer some relief, they lack a reliable mechanism for domain shift correction, which can often be erratic in real-world applications. In response, we develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA. Adhering to the principle of few inputs, big gains, FS-TTA reduces blind exploration in unseen target domains. Furthermore, we propose a two-stage framework to tackle FS-TTA, including (i) fine-tuning the pre-trained source model with few-shot support set, along with using feature diversity augmentation module to avoid overfitting, (ii) implementing test time adaptation based on prototype memory bank guidance to produce high quality pseudo-label for model adaptation. Through extensive experiments on three cross-domain classification benchmarks, we demonstrate the superior performance and reliability of our FS-TTA and framework.
Authors: Cunzheng Wang, Ziyuan Guo, Yuxuan Duan, Huaxia Li, Nemo Chen, Xu Tang, Yao Hu
Abstract: Consistency distillation methods have demonstrated significant success in accelerating generative tasks of diffusion models. However, since previous consistency distillation methods use simple and straightforward strategies in selecting target timesteps, they usually struggle with blurs and detail losses in generated images. To address these limitations, we introduce Target-Driven Distillation (TDD), which (1) adopts a delicate selection strategy of target timesteps, increasing the training efficiency; (2) utilizes decoupled guidances during training, making TDD open to post-tuning on guidance scale during inference periods; (3) can be optionally equipped with non-equidistant sampling and x0 clipping, enabling a more flexible and accurate way for image sampling. Experiments verify that TDD achieves state-of-the-art performance in few-step generation, offering a better choice among consistency distillation models.
Authors: Guanglei Zhou, Bhargav Korrapati, Gaurav Rajavendra Reddy, Jiang Hu, Yiran Chen, Dipto G. Thakurta
Abstract: Generation of VLSI layout patterns is essential for a wide range of Design For Manufacturability (DFM) studies. In this study, we investigate the potential of generative machine learning models for creating design rule legal metal layout patterns. Our results demonstrate that the proposed model can generate legal patterns in complex design rule settings and achieves a high diversity score. The designed system, with its flexible settings, supports both pattern generation with localized changes, and design rule violation correction. Our methodology is validated on Intel 18A Process Design Kit (PDK) and can produce a wide range of DRC-compliant pattern libraries with only 20 starter patterns.
Authors: Yunfei Xie, Cihang Xie, Alan Yuille, Jieru Mei
Abstract: In this paper, we introduce a hierarchical transformer-based model designed for sophisticated image segmentation tasks, effectively bridging the granularity of part segmentation with the comprehensive scope of object segmentation. At the heart of our approach is a multi-level representation strategy, which systematically advances from individual pixels to superpixels, and ultimately to cohesive group formations. This architecture is underpinned by two pivotal aggregation strategies: local aggregation and global aggregation. Local aggregation is employed to form superpixels, leveraging the inherent redundancy of the image data to produce segments closely aligned with specific parts of the object, guided by object-level supervision. In contrast, global aggregation interlinks these superpixels, organizing them into larger groups that correlate with entire objects and benefit from part-level supervision. This dual aggregation framework ensures a versatile adaptation to varying supervision inputs while maintaining computational efficiency. Our methodology notably improves the balance between adaptability across different supervision modalities and computational manageability, culminating in significant enhancement in segmentation performance. When tested on the PartImageNet dataset, our model achieves a substantial increase, outperforming the previous state-of-the-art by 2.8% and 0.8% in mIoU scores for part and object segmentation, respectively. Similarly, on the Pascal Part dataset, it records performance enhancements of 1.5% and 2.0% for part and object segmentation, respectively.
Authors: Sushant Gautam, Andrea Stor{\aa}s, Cise Midoglu, Steven A. Hicks, Vajira Thambawita, P{\aa}l Halvorsen, Michael A. Riegler
Abstract: We introduce Kvasir-VQA, an extended dataset derived from the HyperKvasir and Kvasir-Instrument datasets, augmented with question-and-answer annotations to facilitate advanced machine learning tasks in Gastrointestinal (GI) diagnostics. This dataset comprises 6,500 annotated images spanning various GI tract conditions and surgical instruments, and it supports multiple question types including yes/no, choice, location, and numerical count. The dataset is intended for applications such as image captioning, Visual Question Answering (VQA), text-based generation of synthetic medical images, object detection, and classification. Our experiments demonstrate the dataset's effectiveness in training models for three selected tasks, showcasing significant applications in medical image analysis and diagnostics. We also present evaluation metrics for each task, highlighting the usability and versatility of our dataset. The dataset and supporting artifacts are available at https://datasets.simula.no/kvasir-vqa.
Authors: Ishan Rajendrakumar Dave, Fabian Caba Heilbron, Mubarak Shah, Simon Jenni
Abstract: Temporal video alignment aims to synchronize the key events like object interactions or action phase transitions in two videos. Such methods could benefit various video editing, processing, and understanding tasks. However, existing approaches operate under the restrictive assumption that a suitable video pair for alignment is given, significantly limiting their broader applicability. To address this, we re-pose temporal alignment as a search problem and introduce the task of Alignable Video Retrieval (AVR). Given a query video, our approach can identify well-alignable videos from a large collection of clips and temporally synchronize them to the query. To achieve this, we make three key contributions: 1) we introduce DRAQ, a video alignability indicator to identify and re-rank the best alignable video from a set of candidates; 2) we propose an effective and generalizable frame-level video feature design to improve the alignment performance of several off-the-shelf feature representations, and 3) we propose a novel benchmark and evaluation protocol for AVR using cycle-consistency metrics. Our experiments on 3 datasets, including large-scale Kinetics700, demonstrate the effectiveness of our approach in identifying alignable video pairs from diverse datasets. Project Page: https://daveishan.github.io/avr-webpage/.
Authors: Ishan Rajendrakumar Dave, Mamshad Nayeem Rizve, Mubarak Shah
Abstract: Real-life applications of action recognition often require a fine-grained understanding of subtle movements, e.g., in sports analytics, user interactions in AR/VR, and surgical videos. Although fine-grained actions are more costly to annotate, existing semi-supervised action recognition has mainly focused on coarse-grained action recognition. Since fine-grained actions are more challenging due to the absence of scene bias, classifying these actions requires an understanding of action-phases. Hence, existing coarse-grained semi-supervised methods do not work effectively. In this work, we for the first time thoroughly investigate semi-supervised fine-grained action recognition (FGAR). We observe that alignment distances like dynamic time warping (DTW) provide a suitable action-phase-aware measure for comparing fine-grained actions, a concept previously unexploited in FGAR. However, since regular DTW distance is pairwise and assumes strict alignment between pairs, it is not directly suitable for classifying fine-grained actions. To utilize such alignment distances in a limited-label setting, we propose an Alignability-Verification-based Metric learning technique to effectively discriminate between fine-grained action pairs. Our learnable alignability score provides a better phase-aware measure, which we use to refine the pseudo-labels of the primary video encoder. Our collaborative pseudo-labeling-based framework `\textit{FinePseudo}' significantly outperforms prior methods on four fine-grained action recognition datasets: Diving48, FineGym99, FineGym288, and FineDiving, and shows improvement on existing coarse-grained datasets: Kinetics400 and Something-SomethingV2. We also demonstrate the robustness of our collaborative pseudo-labeling in handling novel unlabeled classes in open-world semi-supervised setups. Project Page: https://daveishan.github.io/finepsuedo-webpage/.
Authors: Meiyu Qiu, Yun Li, Wenjun Huang, Haoyun Zhang, Weiping Zheng, Wenbin Lei, Xiaomao Fan
Abstract: Laryngeal cancer is a malignant disease with a high morality rate in otorhinolaryngology, posing an significant threat to human health. Traditionally larygologists manually visual-inspect laryngeal cancer in laryngoscopic videos, which is quite time-consuming and subjective. In this study, we propose a novel automatic framework via 3D-large-scale pretrained models termed 3D-LSPTM for laryngeal cancer detection. Firstly, we collect 1,109 laryngoscopic videos from the First Affiliated Hospital Sun Yat-sen University with the approval of the Ethics Committee. Then we utilize the 3D-large-scale pretrained models of C3D, TimeSformer, and Video-Swin-Transformer, with the merit of advanced featuring videos, for laryngeal cancer detection with fine-tuning techniques. Extensive experiments show that our proposed 3D-LSPTM can achieve promising performance on the task of laryngeal cancer detection. Particularly, 3D-LSPTM with the backbone of Video-Swin-Transformer can achieve 92.4% accuracy, 95.6% sensitivity, 94.1% precision, and 94.8% F_1.
Authors: Xuanrui Zeng
Abstract: Weakly supervised image segmentation (WSSS) from image tags remains challenging due to its under-constraint nature. Most mainstream work focus on the extraction of class activation map (CAM) and imposing various additional regularization. Contrary to the mainstream, we propose to frame WSSS as a problem of reconstruction from decomposition of the image using its mask, under which most regularization are embedded implicitly within the framework of the new problem. Our approach has demonstrated promising results on initial experiments, and shown robustness against the problem of background ambiguity. Our code is available at \url{https://github.com/xuanrui-work/WSSSByRec}.
Authors: Ansh Sharma, Albert Xiao, Praneet Rathi, Rohit Kundu, Albert Zhai, Yuan Shen, Shenlong Wang
Abstract: In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple resolutions. Pairing this concept with a tiled generation method yields a scalable system that can generate thousands of square kilometers of realistic Earth surfaces at high resolution. We evaluate our method on a dataset collected from Bing Maps and show that it outperforms super-resolution baselines on the extreme super-resolution task of 1024x zoom. We also demonstrate its ability to create diverse and coherent scenes via an interactive gigapixel-scale generated map. Finally, we demonstrate how our system can be extended to enable novel content creation applications including controllable world generation and 3D scene generation.
Authors: Ryan Wen Liu, Yuxu Lu, Yuan Gao, Yu Guo, Wenqi Ren, Fenghua Zhu, Fei-Yue Wang
Abstract: The visible-light camera, which is capable of environment perception and navigation assistance, has emerged as an essential imaging sensor for marine surface vessels in intelligent waterborne transportation systems (IWTS). However, the visual imaging quality inevitably suffers from several kinds of degradations (e.g., limited visibility, low contrast, color distortion, etc.) under complex weather conditions (e.g., haze, rain, and low-lightness). The degraded visual information will accordingly result in inaccurate environment perception and delayed operations for navigational risk. To promote the navigational safety of vessels, many computational methods have been presented to perform visual quality enhancement under poor weather conditions. However, most of these methods are essentially specific-purpose implementation strategies, only available for one specific weather type. To overcome this limitation, we propose to develop a general-purpose multi-scene visibility enhancement method, i.e., edge reparameterization- and attention-guided neural network (ERANet), to adaptively restore the degraded images captured under different weather conditions. In particular, our ERANet simultaneously exploits the channel attention, spatial attention, and reparameterization technology to enhance the visual quality while maintaining low computational cost. Extensive experiments conducted on standard and IWTS-related datasets have demonstrated that our ERANet could outperform several representative visibility enhancement methods in terms of both imaging quality and computational efficiency. The superior performance of IWTS-related object detection and scene segmentation could also be steadily obtained after ERANet-based visibility enhancement under complex weather conditions.
Authors: Zhangsihao Yang, Mengyi Shan, Mohammad Farazi, Wenhui Zhu, Yanxi Chen, Xuanzhao Dong, Yalin Wang
Abstract: Human video generation task has gained significant attention with the advancement of deep generative models. Generating realistic videos with human movements is challenging in nature, due to the intricacies of human body topology and sensitivity to visual artifacts. The extensively studied 2D media generation methods take advantage of massive human media datasets, but struggle with 3D-aware control; whereas 3D avatar-based approaches, while offering more freedom in control, lack photorealism and cannot be harmonized seamlessly with background scene. We propose AMG, a method that combines the 2D photorealism and 3D controllability by conditioning video diffusion models on controlled rendering of 3D avatars. We additionally introduce a novel data processing pipeline that reconstructs and renders human avatar movements from dynamic camera videos. AMG is the first method that enables multi-person diffusion video generation with precise control over camera positions, human motions, and background style. We also demonstrate through extensive evaluation that it outperforms existing human video generation methods conditioned on pose sequences or driving videos in terms of realism and adaptability.
Authors: David Vinicius da Silva, Valter Estevam, David Menotti
Abstract: The limited amount of labeled data for training the Brazilian Sign Language (Libras) to Portuguese Translation models is a challenging problem due to video collection and annotation costs. This paper proposes generating sign language content by concatenating short clips containing isolated signals for training Sign Language Translation models. We employ the V-LIBRASIL dataset, composed of 4,089 sign videos for 1,364 signs, interpreted by at least three persons, to create hundreds of thousands of sentences with their respective Libras translation, and then, to feed the model. More specifically, we propose several experiments varying the vocabulary size and sentence structure, generating datasets with approximately 170K, 300K, and 500K videos. Our results achieve meaningful scores of 9.2% and 26.2% for BLEU-4 and METEOR, respectively. Our technique enables the creation or extension of existing datasets at a much lower cost than the collection and annotation of thousands of sentences providing clear directions for future works.
Authors: David S. Bolme, Deniz Aykac, Ryan Shivers, Joel Brogan, Nell Barber, Bob Zhang, Laura Davies, David Cornett III
Abstract: This paper examines covariate effects on fused whole body biometrics performance in the IARPA BRIAR dataset, specifically focusing on UAV platforms, elevated positions, and distances up to 1000 meters. The dataset includes outdoor videos compared with indoor images and controlled gait recordings. Normalized raw fusion scores relate directly to predicted false accept rates (FAR), offering an intuitive means for interpreting model results. A linear model is developed to predict biometric algorithm scores, analyzing their performance to identify the most influential covariates on accuracy at altitude and range. Weather factors like temperature, wind speed, solar loading, and turbulence are also investigated in this analysis. The study found that resolution and camera distance best predicted accuracy and findings can guide future research and development efforts in long-range/elevated/UAV biometrics and support the creation of more reliable and robust systems for national security and other critical domains.
Authors: Yifei Yang, Zikai Huang, Chenshu Xu, Shengfeng He
Abstract: Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise motion representations, which capture only static spatial details and overlook temporal dynamics. This approach leads to significant redundancy across the temporal dimension, complicating the generation of effective long-term motion. To overcome these limitations, we introduce the novel concept of Lagrangian Motion Fields, specifically designed for long-term motion generation. By treating each joint as a Lagrangian particle with uniform velocity over short intervals, our approach condenses motion representations into a series of "supermotions" (analogous to superpixels). This method seamlessly integrates static spatial information with interpretable temporal dynamics, transcending the limitations of existing network architectures and motion sequence content types. Our solution is versatile and lightweight, eliminating the need for neural network preprocessing. Our approach excels in tasks such as long-term music-to-dance generation and text-to-motion generation, offering enhanced efficiency, superior generation quality, and greater diversity compared to existing methods. Additionally, the adaptability of Lagrangian Motion Fields extends to applications like infinite motion looping and fine-grained controlled motion generation, highlighting its broad utility. Video demonstrations are available at \url{https://plyfager.github.io/LaMoG}.
Authors: Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Abstract: We propose a new strategy called think twice before recognizing to improve fine-grained traffic sign recognition (TSR). Fine-grained TSR in the wild is difficult due to the complex road conditions, and existing approaches particularly struggle with cross-country TSR when data is lacking. Our strategy achieves effective fine-grained TSR by stimulating the multiple-thinking capability of large multimodal models (LMM). We introduce context, characteristic, and differential descriptions to design multiple thinking processes for the LMM. The context descriptions with center coordinate prompt optimization help the LMM to locate the target traffic sign in the original road images containing multiple traffic signs and filter irrelevant answers through the proposed prior traffic sign hypothesis. The characteristic description is based on few-shot in-context learning of template traffic signs, which decreases the cross-domain difference and enhances the fine-grained recognition capability of the LMM. The differential descriptions of similar traffic signs optimize the multimodal thinking capability of the LMM. The proposed method is independent of training data and requires only simple and uniform instructions. We conducted extensive experiments on three benchmark datasets and two real-world datasets from different countries, and the proposed method achieves state-of-the-art TSR results on all five datasets.
Authors: Deniz Aykac, Joel Brogan, Nell Barber, Ryan Shivers, Bob Zhang, Dallas Sacca, Ryan Tipton, Gavin Jager, Austin Garret, Matthew Love, Jim Goddard, David Cornett III, David S. Bolme
Abstract: The considerable body of data available for evaluating biometric recognition systems in Research and Development (R\&D) environments has contributed to the increasingly common problem of target performance mismatch. Biometric algorithms are frequently tested against data that may not reflect the real world applications they target. From a Testing and Evaluation (T\&E) standpoint, this domain mismatch causes difficulty assessing when improvements in State-of-the-Art (SOTA) research actually translate to improved applied outcomes. This problem can be addressed with thoughtful preparation of data and experimental methods to reflect specific use-cases and scenarios. To that end, this paper evaluates research solutions for identifying individuals at ranges and altitudes, which could support various application areas such as counterterrorism, protection of critical infrastructure facilities, military force protection, and border security. We address challenges including image quality issues and reliance on face recognition as the sole biometric modality. By fusing face and body features, we propose developing robust biometric systems for effective long-range identification from both the ground and steep pitch angles. Preliminary results show promising progress in whole-body recognition. This paper presents these early findings and discusses potential future directions for advancing long-range biometric identification systems based on mission-driven metrics.
Authors: Erjin Bao, Ching-Chun Chang, Hanrui Wang, Isao Echizen
Abstract: With the proliferation of AI agents in various domains, protecting the ownership of AI models has become crucial due to the significant investment in their development. Unauthorized use and illegal distribution of these models pose serious threats to intellectual property, necessitating effective copyright protection measures. Model watermarking has emerged as a key technique to address this issue, embedding ownership information within models to assert rightful ownership during copyright disputes. This paper presents several contributions to model watermarking: a self-authenticating black-box watermarking protocol using hash techniques, a study on evidence forgery attacks using adversarial perturbations, a proposed defense involving a purification step to counter adversarial attacks, and a purification-agnostic proxy learning method to enhance watermark reliability and model performance. Experimental results demonstrate the effectiveness of these approaches in improving the security, reliability, and performance of watermarked models.
Authors: Zhiheng Peng, Kai Zhao, Xiaoran Chen, Li Ma, Siyu Xia, Changjie Fan, Weijian Shang, Wei Jing
Abstract: Efficient, accurate and low-cost estimation of human skeletal information is crucial for a range of applications such as biology education and human-computer interaction. However, current simple skeleton models, which are typically based on 2D-3D joint points, fall short in terms of anatomical fidelity, restricting their utility in fields. On the other hand, more complex models while anatomically precise, are hindered by sophisticate multi-stage processing and the need for extra data like skin meshes, making them unsuitable for real-time applications. To this end, we propose the EA-RAS (Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton), a single-stage, lightweight, and plug-and-play anatomical skeleton estimator that can provide real-time, accurate anatomically realistic skeletons with arbitrary pose using only a single RGB image input. Additionally, EA-RAS estimates the conventional human-mesh model explicitly, which not only enhances the functionality but also leverages the outside skin information by integrating features into the inside skeleton modeling process. In this work, we also develop a progressive training strategy and integrated it with an enhanced optimization process, enabling the network to obtain initial weights using only a small skin dataset and achieve self-supervision in skeleton reconstruction. Besides, we also provide an optional lightweight post-processing optimization strategy to further improve accuracy for scenarios that prioritize precision over real-time processing. The experiments demonstrated that our regression method is over 800 times faster than existing methods, meeting real-time requirements. Additionally, the post-processing optimization strategy provided can enhance reconstruction accuracy by over 50% and achieve a speed increase of more than 7 times.
Authors: Chengqian Zhao, Zhao Yao, Zhaoyu Hu, Yuanxin Xie, Yafang Zhang, Yuanyuan Wang, Shuo Li, Jianhua Zhou, Jianqiao Zhou, Yin Wang, Jinhua Yu
Abstract: In the intelligent diagnosis of bimodal (gray-scale and contrast-enhanced) ultrasound videos, medical domain knowledge such as the way sonographers browse videos, the particular areas they emphasize, and the features they pay special attention to, plays a decisive role in facilitating precise diagnosis. Embedding medical knowledge into the deep learning network can not only enhance performance but also boost clinical confidence and reliability of the network. However, it is an intractable challenge to automatically focus on these person- and disease-specific features in videos and to enable networks to encode bimodal information comprehensively and efficiently. This paper proposes a novel Tri-Attention Selective Learning Network (TASL-Net) to tackle this challenge and automatically embed three types of diagnostic attention of sonographers into a mutual transformer framework for intelligent diagnosis of bimodal ultrasound videos. Firstly, a time-intensity-curve-based video selector is designed to mimic the temporal attention of sonographers, thus removing a large amount of redundant information while improving computational efficiency of TASL-Net. Then, to introduce the spatial attention of the sonographers for contrast-enhanced video analysis, we propose the earliest-enhanced position detector based on structural similarity variation, on which the TASL-Net is made to focus on the differences of perfusion variation inside and outside the lesion. Finally, by proposing a mutual encoding strategy that combines convolution and transformer, TASL-Net possesses bimodal attention to structure features on gray-scale videos and to perfusion variations on contrast-enhanced videos. These modules work collaboratively and contribute to superior performance. We conduct a detailed experimental validation of TASL-Net's performance on three datasets, including lung, breast, and liver.
Authors: Bin Fu, Qiyang Wan, Jialin Li, Ruiping Wang, Xilin Chen
Abstract: Categorization, a core cognitive ability in humans that organizes objects based on common features, is essential to cognitive science as well as computer vision. To evaluate the categorization ability of visual AI models, various proxy tasks on recognition from datasets to open world scenarios have been proposed. Recent development of Large Multimodal Models (LMMs) has demonstrated impressive results in high-level visual tasks, such as visual question answering, video temporal reasoning, etc., utilizing the advanced architectures and large-scale multimodal instruction tuning. Previous researchers have developed holistic benchmarks to measure the high-level visual capability of LMMs, but there is still a lack of pure and in-depth quantitative evaluation of the most fundamental categorization ability. According to the research on human cognitive process, categorization can be seen as including two parts: category learning and category use. Inspired by this, we propose a novel, challenging, and efficient benchmark based on composite blocks, called ComBo, which provides a disentangled evaluation framework and covers the entire categorization process from learning to use. By analyzing the results of multiple evaluation tasks, we find that although LMMs exhibit acceptable generalization ability in learning new categories, there are still gaps compared to humans in many ways, such as fine-grained perception of spatial relationship and abstract category understanding. Through the study of categorization, we can provide inspiration for the further development of LMMs in terms of interpretability and generalization.
Authors: Shiting Xiao, Yuhang Li, Youngeun Kim, Donghyun Lee, Priyadarshini Panda
Abstract: Spiking Neural Networks (SNNs) have emerged as a compelling, energy-efficient alternative to traditional Artificial Neural Networks (ANNs) for static image tasks such as image classification and segmentation. However, in the more complex video classification domain, SNN-based methods fall considerably short of ANN-based benchmarks due to the challenges in processing dense frame sequences. To bridge this gap, we propose ReSpike, a hybrid framework that synergizes the strengths of ANNs and SNNs to tackle action recognition tasks with high accuracy and low energy cost. By decomposing film clips into spatial and temporal components, i.e., RGB image Key Frames and event-like Residual Frames, ReSpike leverages ANN for learning spatial information and SNN for learning temporal information. In addition, we propose a multi-scale cross-attention mechanism for effective feature fusion. Compared to state-of-the-art SNN baselines, our ReSpike hybrid architecture demonstrates significant performance improvements (e.g., >30% absolute accuracy improvement on HMDB-51, UCF-101, and Kinetics-400). Furthermore, ReSpike achieves comparable performance with prior ANN approaches while bringing better accuracy-energy tradeoff.
Authors: Liutao Yang, Jiahao Huang, Guang Yang, Daoqiang Zhang
Abstract: Sparse views X-ray computed tomography has emerged as a contemporary technique to mitigate radiation dose. Because of the reduced number of projection views, traditional reconstruction methods can lead to severe artifacts. Recently, research studies utilizing deep learning methods has made promising progress in removing artifacts for Sparse-View Computed Tomography (SVCT). However, given the limitations on the generalization capability of deep learning models, current methods usually train models on fixed sampling rates, affecting the usability and flexibility of model deployment in real clinical settings. To address this issue, our study proposes a adaptive reconstruction method to achieve high-performance SVCT reconstruction at any sampling rate. Specifically, we design a novel imaging degradation operator in the proposed sampling diffusion model for SVCT (CT-SDM) to simulate the projection process in the sinogram domain. Thus, the CT-SDM can gradually add projection views to highly undersampled measurements to generalize the full-view sinograms. By choosing an appropriate starting point in diffusion inference, the proposed model can recover the full-view sinograms from any sampling rate with only one trained model. Experiments on several datasets have verified the effectiveness and robustness of our approach, demonstrating its superiority in reconstructing high-quality images from sparse-view CT scans across various sampling rates.
Authors: Hamza Farooq, Zuhair Zafar, Ahsan Saadat, Tariq M Khan, Shahzaib Iqbal, Imran Razzak
Abstract: Accurate segmentation of skin lesions within dermoscopic images plays a crucial role in the timely identification of skin cancer for computer-aided diagnosis on mobile platforms. However, varying shapes of the lesions, lack of defined edges, and the presence of obstructions such as hair strands and marker colors make this challenge more complex. \textcolor{red}Additionally, skin lesions often exhibit subtle variations in texture and color that are difficult to differentiate from surrounding healthy skin, necessitating models that can capture both fine-grained details and broader contextual information. Currently, melanoma segmentation models are commonly based on fully connected networks and U-Nets. However, these models often struggle with capturing the complex and varied characteristics of skin lesions, such as the presence of indistinct boundaries and diverse lesion appearances, which can lead to suboptimal segmentation performance.To address these challenges, we propose a novel lightweight network specifically designed for skin lesion segmentation utilizing mobile devices, featuring a minimal number of learnable parameters (only 0.8 million). This network comprises an encoder-decoder architecture that incorporates conformer-based focal modulation attention, self-aware local and global spatial attention, and split channel-shuffle. The efficacy of our model has been evaluated on four well-established benchmark datasets for skin lesion segmentation: ISIC 2016, ISIC 2017, ISIC 2018, and PH2. Empirical findings substantiate its state-of-the-art performance, notably reflected in a high Jaccard index.
Authors: Liang Geng
Abstract: Apples growing in natural environments often face severe visual obstructions from leaves and branches. This significantly increases the risk of false detections in object detection tasks, thereby escalating the challenge. Addressing this issue, we introduce a technique called "Occlusion-Enhanced Distillation" (OED). This approach utilizes occlusion information to regularize the learning of semantically aligned features on occluded datasets and employs Exponential Moving Average (EMA) to enhance training stability. Specifically, we first design an occlusion-enhanced dataset that integrates Grounding DINO and SAM methods to extract occluding elements such as leaves and branches from each sample, creating occlusion examples that reflect the natural growth state of fruits. Additionally, we propose a multi-scale knowledge distillation strategy, where the student network uses images with increased occlusions as inputs, while the teacher network employs images without natural occlusions. Through this setup, the strategy guides the student network to learn from the teacher across scales of semantic and local features alignment, effectively narrowing the feature distance between occluded and non-occluded targets and enhancing the robustness of object detection. Lastly, to improve the stability of the student network, we introduce the EMA strategy, which aids the student network in learning more generalized feature expressions that are less affected by the noise of individual image occlusions. Our method significantly outperforms current state-of-the-art techniques through extensive comparative experiments.
Authors: Muye Huang, Lai Han, Xinyu Zhang, Wenjun Wu, Jie Ma, Lingling Zhang, Jun Liu
Abstract: Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs' capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models' chart comprehension abilities in real-world scenarios. Specifically, EvoChart is a unique self-training data synthesis approach that simultaneously produces high-quality training corpus and a high-performance chart understanding model. EvoChart-QA consists of 650 distinct real-world charts collected from 140 different websites and 1,250 expert-curated questions that focus on chart understanding. Experimental results on various open-source and proprietary VLMs tested on EvoChart-QA demonstrate that even the best proprietary model, GPT-4o, achieves only 49.8% accuracy. Moreover, the EvoChart method significantly boosts the performance of open-source VLMs on real-world chart understanding tasks, achieving 54.2% accuracy on EvoChart-QA.
Authors: Sohan Anisetty, James Hays
Abstract: Our research presents a novel motion generation framework designed to produce whole-body motion sequences conditioned on multiple modalities simultaneously, specifically text and audio inputs. Leveraging Vector Quantized Variational Autoencoders (VQVAEs) for motion discretization and a bidirectional Masked Language Modeling (MLM) strategy for efficient token prediction, our approach achieves improved processing efficiency and coherence in the generated motions. By integrating spatial attention mechanisms and a token critic we ensure consistency and naturalness in the generated motions. This framework expands the possibilities of motion generation, addressing the limitations of existing approaches and opening avenues for multimodal motion synthesis.
Authors: Junpeng Jiang, Gangyi Hong, Lijun Zhou, Enhui Ma, Hengtong Hu, Xia Zhou, Jie Xiang, Fan Liu, Kaicheng Yu, Haiyang Sun, Kun Zhan, Peng Jia, Miao Zhang
Abstract: Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned problem, i.e. models built on top of Diffusion Transformers (DiT), works are still missing which are targeted on exploring the potential for multi-view videos generation scenarios. Noticeably, we propose the first DiT-based framework specifically designed for generating temporally and multi-view consistent videos which precisely match the given bird's-eye view layouts control. Specifically, the proposed framework leverages a parameter-free spatial view-inflated attention mechanism to guarantee the cross-view consistency, where joint cross-attention modules and ControlNet-Transformer are integrated to further improve the precision of control. To demonstrate our advantages, we extensively investigate the qualitative comparisons on nuScenes dataset, particularly in some most challenging corner cases. In summary, the effectiveness of our proposed method in producing long, controllable, and highly consistent videos under difficult conditions is proven to be effective.
Authors: Ruben D. Fonnegra, Maria Liliana Hern\'andez, Juan C. Caicedo, Gloria M. D\'iaz
Abstract: Contrast-enhancement pattern analysis is critical in breast magnetic resonance imaging (MRI) to distinguish benign from probably malignant tumors. However, contrast-enhanced image acquisitions are time-consuming and very expensive. As an alternative to physical acquisition, this paper proposes a comprehensive pipeline for the generation of accurate long-term (late) contrast-enhanced breast MRI from the early counterpart. The proposed strategy focuses on preserving the contrast agent pattern in the enhanced regions while maintaining visual properties in the entire synthesized images. To that end, a novel loss function that leverages the biological behavior of contrast agent (CA) in tissue, given by the Time-Intensity (TI) enhancement curve, is proposed to optimize a pixel-attention based generative model. In addition, unlike traditional normalization and standardization methods, we developed a new normalization strategy that maintains the contrast enhancement pattern across the image sequences at multiple timestamps. This ensures the prevalence of the CA pattern after image preprocessing, unlike conventional approaches. Furthermore, in order to objectively evaluate the clinical quality of the synthesized images, two metrics are also introduced to measure the differences between the TI curves of enhanced regions of the acquired and synthesized images. The experimental results showed that the proposed strategy generates images that significantly outperform diagnostic quality in contrast-enhanced regions while maintaining the spatial features of the entire image. This results suggest a potential use of synthetic late enhanced images generated via deep learning in clinical scenarios.
Authors: Weichao Pan, Jiaju Kang, Xu Wang, Zhihao Chen, Yiyuan Ge
Abstract: Current road damage detection methods, relying on manual inspections or sensor-mounted vehicles, are inefficient, limited in coverage, and often inaccurate, especially for minor damages, leading to delays and safety hazards. To address these issues and enhance real-time road damage detection using street view image data (SVRDD), we propose DAPONet, a model incorporating three key modules: a dual attention mechanism combining global and local attention, a multi-scale partial over-parameterization module, and an efficient downsampling module. DAPONet achieves a mAP50 of 70.1% on the SVRDD dataset, outperforming YOLOv10n by 10.4%, while reducing parameters to 1.6M and FLOPs to 1.7G, representing reductions of 41% and 80%, respectively. On the MS COCO2017 val dataset, DAPONet achieves an mAP50-95 of 33.4%, 0.8% higher than EfficientDet-D1, with a 74% reduction in both parameters and FLOPs.
Authors: Qinghui Hong, Haoyou Jiang, Pingdan Xiao, Sichun Du, Tao Li
Abstract: Edge detection in images is the foundation of many complex tasks in computer graphics. Due to the feature loss caused by multi-layer convolution and pooling architectures, learning-based edge detection models often produce thick edges and struggle to detect the edges of small objects in images. Inspired by state space models, this paper presents an edge detection algorithm which effectively addresses the aforementioned issues. The presented algorithm obtains state space variables of the image from dual-input channels with minimal down-sampling processes and utilizes these state variables for real-time learning and memorization of image text. Additionally, to achieve precise edges while filtering out false edges, a post-processing algorithm called wind erosion has been designed to handle the binary edge map. To further enhance the processing speed of the algorithm, we have designed parallel computing circuits for the most computationally intensive parts of presented algorithm, significantly improving computational speed and efficiency. Experimental results demonstrate that the proposed algorithm achieves precise thin edge localization and exhibits noise suppression capabilities across various types of images. With the parallel computing circuits, the algorithm to achieve processing speeds exceeds 30 FPS on 5K images.
Authors: Yearim Kim, Sangyu Han, Sangbum Han, Nojun Kwak
Abstract: In the field of eXplainable AI (XAI) in language models, the progression from local explanations of individual decisions to global explanations with high-level concepts has laid the groundwork for mechanistic interpretability, which aims to decode the exact operations. However, this paradigm has not been adequately explored in image models, where existing methods have primarily focused on class-specific interpretations. This paper introduces a novel approach to systematically trace the entire pathway from input through all intermediate layers to the final output within the whole dataset. We utilize Pointwise Feature Vectors (PFVs) and Effective Receptive Fields (ERFs) to decompose model embeddings into interpretable Concept Vectors. Then, we calculate the relevance between concept vectors with our Generalized Integrated Gradients (GIG), enabling a comprehensive, dataset-wide analysis of model behavior. We validate our method of concept extraction and concept attribution in both qualitative and quantitative evaluations. Our approach advances the understanding of semantic significance within image models, offering a holistic view of their operational mechanics.
Authors: Hyejin Park, Dongbo Min
Abstract: In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework directly tackles the challenge of differential sample importance, with a keen focus on rectifying the teacher model's misclassifications. DGAD employs Misclassification-Aware Partitioning (MAP) to dynamically tailor the distillation focus, optimizing the learning process by steering towards the most reliable teacher predictions. Additionally, our Error-corrective Label Swapping (ELS) corrects misclassifications of the teacher on both clean and adversarially perturbed inputs, refining the quality of knowledge transfer. Further, Predictive Consistency Regularization (PCR) guarantees consistent performance of the student model across both clean and adversarial inputs, significantly enhancing its overall robustness. By integrating these methodologies, DGAD significantly improves upon the accuracy of clean data and fortifies the model's defenses against sophisticated adversarial threats. Our experimental validation on CIFAR10, CIFAR100, and Tiny ImageNet datasets, employing various model architectures, demonstrates the efficacy of DGAD, establishing it as a promising approach for enhancing both the robustness and accuracy of student models in adversarial settings.
Authors: Kun Zhou, Xinyu Lin, Wenbo Li, Xiaogang Xu, Yuanhao Cai, Zhonghang Liu, Xiaoguang Han, Jiangbo Lu
Abstract: Previous low-light image enhancement (LLIE) approaches, while employing frequency decomposition techniques to address the intertwined challenges of low frequency (e.g., illumination recovery) and high frequency (e.g., noise reduction), primarily focused on the development of dedicated and complex networks to achieve improved performance. In contrast, we reveal that an advanced disentanglement paradigm is sufficient to consistently enhance state-of-the-art methods with minimal computational overhead. Leveraging the image Laplace decomposition scheme, we propose a novel low-frequency consistency method, facilitating improved frequency disentanglement optimization. Our method, seamlessly integrating with various models such as CNNs, Transformers, and flow-based and diffusion models, demonstrates remarkable adaptability. Noteworthy improvements are showcased across five popular benchmarks, with up to 7.68dB gains on PSNR achieved for six state-of-the-art models. Impressively, our approach maintains efficiency with only 88K extra parameters, setting a new standard in the challenging realm of low-light image enhancement.
Authors: Haodong Wang, Chongyu Wang, Yinghui Quan, Di Wang
Abstract: Expanding the receptive field in a deep learning model for large-scale 3D point cloud segmentation is an effective technique for capturing rich contextual information, which consequently enhances the network's ability to learn meaningful features. However, this often leads to increased computational complexity and risk of overfitting, challenging the efficiency and effectiveness of the learning paradigm. To address these limitations, we propose the Local Split Attention Pooling (LSAP) mechanism to effectively expand the receptive field through a series of local split operations, thus facilitating the acquisition of broader contextual knowledge. Concurrently, it optimizes the computational workload associated with attention-pooling layers to ensure a more streamlined processing workflow. Based on LSAP, a Parallel Aggregation Enhancement (PAE) module is introduced to enable parallel processing of data using both 2D and 3D neighboring information to further enhance contextual representations within the network. In light of the aforementioned designs, we put forth a novel framework, designated as LSNet, for large-scale point cloud semantic segmentation. Extensive evaluations demonstrated the efficacy of seamlessly integrating the proposed PAE module into existing frameworks, yielding significant improvements in mean intersection over union (mIoU) metrics, with a notable increase of up to 11%. Furthermore, LSNet demonstrated superior performance compared to state-of-the-art semantic segmentation networks on three benchmark datasets, including S3DIS, Toronto3D, and SensatUrban. It is noteworthy that our method achieved a substantial speedup of approximately 38.8% compared to those employing similar-sized receptive fields, which serves to highlight both its computational efficiency and practical utility in real-world large-scale scenes.
Authors: Muye Huang, Lingling Zhang, Lai Han, Wenjun Wu, Xinyu Zhang, Jun Liu
Abstract: Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to interpret, and chart-related questions often involve complex logical and numerical reasoning, which hinders the performance of existing models. This paper introduces VProChart, a novel framework designed to address these challenges in CQA by integrating a lightweight Visual Perception Alignment Agent (VPAgent) and a Programmatic Solution Reasoning approach. VPAgent aligns and models chart elements based on principles of human visual perception, enhancing the understanding of chart context. The Programmatic Solution Reasoning approach leverages large language models (LLMs) to transform natural language reasoning questions into structured solution programs, facilitating precise numerical and logical reasoning. Extensive experiments on benchmark datasets such as ChartQA and PlotQA demonstrate that VProChart significantly outperforms existing methods, highlighting its capability in understanding and reasoning with charts.
Authors: Avraham Chapman, Haiming Xu, Lingqiao Liu
Abstract: Training a fine-grained image recognition model with limited data presents a significant challenge, as the subtle differences between categories may not be easily discernible amidst distracting noise patterns. One commonly employed strategy is to leverage pretrained neural networks, which can generate effective feature representations for constructing an image classification model with a restricted dataset. However, these pretrained neural networks are typically trained for different tasks than the fine-grained visual recognition (FGVR) task at hand, which can lead to the extraction of less relevant features. Moreover, in the context of building FGVR models with limited data, these irrelevant features can dominate the training process, overshadowing more useful, generalizable discriminative features. Our research has identified a surprisingly simple solution to this challenge: we introduce a regularization technique to ensure that the magnitudes of the extracted features are evenly distributed. This regularization is achieved by maximizing the uniformity of feature magnitude distribution, measured through the entropy of the normalized features. The motivation behind this regularization is to remove bias in feature magnitudes from pretrained models, where some features may be more prominent and, consequently, more likely to be used for classification. Additionally, we have developed a dynamic weighting mechanism to adjust the strength of this regularization throughout the learning process. Despite its apparent simplicity, our approach has demonstrated significant performance improvements across various fine-grained visual recognition datasets.
Authors: Hyungkeun Park, Jong-seok Lee
Abstract: Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by effectively delivering the probability distribution for the non-target classes from the teacher model, which is known as `implicit (dark) knowledge', to the student model. Through gradient analysis, we first show that this actually has an effect of adaptively controlling the learning of implicit knowledge. Then, we propose a new loss that enables the student to learn explicit knowledge (i.e., the teacher's confidence about the target class) along with implicit knowledge in an adaptive manner. Furthermore, we propose to separate the classification and distillation tasks for effective distillation and inter-class relationship modeling. Experimental results demonstrate that the proposed method, called adaptive explicit knowledge transfer (AEKT) method, achieves improved performance compared to the state-of-the-art KD methods on the CIFAR-100 and ImageNet datasets.
Authors: Yanguang Sun, Chunyan Xu, Jian Yang, Hanyu Xuan, Lei Luo
Abstract: Camouflaged object detection has attracted a lot of attention in computer vision. The main challenge lies in the high degree of similarity between camouflaged objects and their surroundings in the spatial domain, making identification difficult. Existing methods attempt to reduce the impact of pixel similarity by maximizing the distinguishing ability of spatial features with complicated design, but often ignore the sensitivity and locality of features in the spatial domain, leading to sub-optimal results. In this paper, we propose a new approach to address this issue by jointly exploring the representation in the frequency and spatial domains, introducing the Frequency-Spatial Entanglement Learning (FSEL) method. This method consists of a series of well-designed Entanglement Transformer Blocks (ETB) for representation learning, a Joint Domain Perception Module for semantic enhancement, and a Dual-domain Reverse Parser for feature integration in the frequency and spatial domains. Specifically, the ETB utilizes frequency self-attention to effectively characterize the relationship between different frequency bands, while the entanglement feed-forward network facilitates information interaction between features of different domains through entanglement learning. Our extensive experiments demonstrate the superiority of our FSEL over 21 state-of-the-art methods, through comprehensive quantitative and qualitative comparisons in three widely-used datasets. The source code is available at: https://github.com/CSYSI/FSEL.
Authors: Ada-Astrid Balauca, Danda Pani Paudel, Kristina Toutanova, Luc Van Gool
Abstract: CLIP is a powerful and widely used tool for understanding images in the context of natural language descriptions to perform nuanced tasks. However, it does not offer application-specific fine-grained and structured understanding, due to its generic nature. In this work, we aim to adapt CLIP for fine-grained and structured -- in the form of tabular data -- visual understanding of museum exhibits. To facilitate such understanding we (a) collect, curate, and benchmark a dataset of 200K+ image-table pairs, and (b) develop a method that allows predicting tabular outputs for input images. Our dataset is the first of its kind in the public domain. At the same time, the proposed method is novel in leveraging CLIP's powerful representations for fine-grained and tabular understanding. The proposed method (MUZE) learns to map CLIP's image embeddings to the tabular structure by means of a proposed transformer-based parsing network (parseNet). More specifically, parseNet enables prediction of missing attribute values while integrating context from known attribute-value pairs for an input image. We show that this leads to significant improvement in accuracy. Through exhaustive experiments, we show the effectiveness of the proposed method on fine-grained and structured understanding of museum exhibits, by achieving encouraging results in a newly established benchmark. Our dataset and source-code can be found at: https://github.com/insait-institute/MUZE
Authors: Yifan Liu, Wuyang Li, Cheng Wang, Hui Chen, Yixuan Yuan
Abstract: Tooth point cloud segmentation is a fundamental task in many orthodontic applications. Current research mainly focuses on fully supervised learning which demands expensive and tedious manual point-wise annotation. Although recent weakly-supervised alternatives are proposed to use weak labels for 3D segmentation and achieve promising results, they tend to fail when the labels are extremely sparse. Inspired by the powerful promptable segmentation capability of the Segment Anything Model (SAM), we propose a framework named SAMTooth that leverages such capacity to complement the extremely sparse supervision. To automatically generate appropriate point prompts for SAM, we propose a novel Confidence-aware Prompt Generation strategy, where coarse category predictions are aggregated with confidence-aware filtering. Furthermore, to fully exploit the structural and shape clues in SAM's outputs for assisting the 3D feature learning, we advance a Mask-guided Representation Learning that re-projects the generated tooth masks of SAM into 3D space and constrains these points of different teeth to possess distinguished representations. To demonstrate the effectiveness of the framework, we conduct experiments on the public dataset and surprisingly find with only 0.1\% annotations (one point per tooth), our method can surpass recent weakly supervised methods by a large margin, and the performance is even comparable to the recent fully-supervised methods, showcasing the significant potential of applying SAM to 3D perception tasks with sparse labels. Code is available at https://github.com/CUHK-AIM-Group/SAMTooth.
Authors: Jun Hao Koh, Sy-Tuyen Ho, Ngoc-Bao Nguyen, Ngai-man Cheung
Abstract: Skip connections are fundamental architecture designs for modern deep neural networks (DNNs) such as CNNs and ViTs. While they help improve model performance significantly, we identify a vulnerability associated with skip connections to Model Inversion (MI) attacks, a type of privacy attack that aims to reconstruct private training data through abusive exploitation of a model. In this paper, as a pioneer work to understand how DNN architectures affect MI, we study the impact of skip connections on MI. We make the following discoveries: 1) Skip connections reinforce MI attacks and compromise data privacy. 2) Skip connections in the last stage are the most critical to attack. 3) RepVGG, an approach to remove skip connections in the inference-time architectures, could not mitigate the vulnerability to MI attacks. 4) Based on our findings, we propose MI-resilient architecture designs for the first time. Without bells and whistles, we show in extensive experiments that our MI-resilient architectures can outperform state-of-the-art (SOTA) defense methods in MI robustness. Furthermore, our MI-resilient architectures are complementary to existing MI defense methods. Our project is available at https://Pillowkoh.github.io/projects/RoLSS/
Authors: Haoran Wei, Chenglong Liu, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, Chunrui Han, Xiangyu Zhang
Abstract: Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper, we collectively refer to all artificial optical signals (e.g., plain texts, math/molecular formulas, tables, charts, sheet music, and even geometric shapes) as "characters" and propose the General OCR Theory along with an excellent model, namely GOT, to promote the arrival of OCR-2.0. The GOT, with 580M parameters, is a unified, elegant, and end-to-end model, consisting of a high-compression encoder and a long-contexts decoder. As an OCR-2.0 model, GOT can handle all the above "characters" under various OCR tasks. On the input side, the model supports commonly used scene- and document-style images in slice and whole-page styles. On the output side, GOT can generate plain or formatted results (markdown/tikz/smiles/kern) via an easy prompt. Besides, the model enjoys interactive OCR features, i.e., region-level recognition guided by coordinates or colors. Furthermore, we also adapt dynamic resolution and multi-page OCR technologies to GOT for better practicality. In experiments, we provide sufficient results to prove the superiority of our model.
Authors: Daosong Hu, Ruomeng Wang, Liang Zhao, Mingyue Cui, Song Ding, Kai Huang
Abstract: The three-dimensional vascular model reconstructed from CT images is widely used in medical diagnosis. At different phases, the beating of the heart can cause deformation of vessels, resulting in different vascular imaging states and false positive diagnostic results. The 4D model can simulate a complete cardiac cycle. Due to the dose limitation of contrast agent injection in patients, it is valuable to synthesize a 4D coronary artery trees through finite phases imaging. In this paper, we propose a method for generating a 4D coronary artery trees, which maps the systole to the diastole through deformation field prediction, interpolates on the timeline, and the motion trajectory of points are obtained. Specifically, the centerline is used to represent vessels and to infer deformation fields using cube-based sorting and neural networks. Adjacent vessel points are aggregated and interpolated based on the deformation field of the centerline point to obtain displacement vectors of different phases. Finally, the proposed method is validated through experiments to achieve the registration of non-rigid vascular points and the generation of 4D coronary trees.
Authors: Qi Zhang, Kaiyi Zhang, Antoni B. Chan, Hui Huang
Abstract: Multi-view crowd localization predicts the ground locations of all people in the scene. Typical methods usually estimate the crowd density maps on the ground plane first, and then obtain the crowd locations. However, the performance of existing methods is limited by the ambiguity of the density maps in crowded areas, where local peaks can be smoothed away. To mitigate the weakness of density map supervision, optimal transport-based point supervision methods have been proposed in the single-image crowd localization tasks, but have not been explored for multi-view crowd localization yet. Thus, in this paper, we propose a novel Mahalanobis distance-based multi-view optimal transport (M-MVOT) loss specifically designed for multi-view crowd localization. First, we replace the Euclidean-based transport cost with the Mahalanobis distance, which defines elliptical iso-contours in the cost function whose long-axis and short-axis directions are guided by the view ray direction. Second, the object-to-camera distance in each view is used to adjust the optimal transport cost of each location further, where the wrong predictions far away from the camera are more heavily penalized. Finally, we propose a strategy to consider all the input camera views in the model loss (M-MVOT) by computing the optimal transport cost for each ground-truth point based on its closest camera. Experiments demonstrate the advantage of the proposed method over density map-based or common Euclidean distance-based optimal transport loss on several multi-view crowd localization datasets. Project page: https://vcc.tech/research/2024/MVOT.
Authors: Ke Cao, Xuanhua He, Tao Hu, Chengjun Xie, Jie Zhang, Man Zhou, Danfeng Hong
Abstract: Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are proficient in long-range modeling with linear complexity, most Mamba-based approaches use fixed scanning strategies, which can introduce biased prior information. To mitigate this issue, we propose a novel Bayesian-inspired scanning strategy called Random Shuffle, supplemented by an theoretically-feasible inverse shuffle to maintain information coordination invariance, aiming to eliminate biases associated with fixed sequence scanning. Based on this transformation pair, we customized the Shuffle Mamba Framework, penetrating modality-aware information representation and cross-modality information interaction across spatial and channel axes to ensure robust interaction and an unbiased global receptive field for multi-modal image fusion. Furthermore, we develop a testing methodology based on Monte-Carlo averaging to ensure the model's output aligns more closely with expected results. Extensive experiments across multiple multi-modal image fusion tasks demonstrate the effectiveness of our proposed method, yielding excellent fusion quality over state-of-the-art alternatives. Code will be available upon acceptance.
Authors: Brent Zoomers, Maarten Wijnants, Ivan Molenaers, Joni Vanherck, Jeroen Put, Lode Jorissen, Nick Michiels
Abstract: Over the past year, 3D Gaussian Splatting (3DGS) has received significant attention for its ability to represent 3D scenes in a perceptually accurate manner. However, it can require a substantial amount of storage since each splat's individual data must be stored. While compression techniques offer a potential solution by reducing the memory footprint, they still necessitate retrieving the entire scene before any part of it can be rendered. In this work, we introduce a novel approach for progressively rendering such scenes, aiming to display visible content that closely approximates the final scene as early as possible without loading the entire scene into memory. This approach benefits both on-device rendering applications limited by memory constraints and streaming applications where minimal bandwidth usage is preferred. To achieve this, we approximate the contribution of each Gaussian to the final scene and construct an order of prioritization on their inclusion in the rendering process. Additionally, we demonstrate that our approach can be combined with existing compression methods to progressively render (and stream) 3DGS scenes, optimizing bandwidth usage by focusing on the most important splats within a scene. Overall, our work establishes a foundation for making remotely hosted 3DGS content more quickly accessible to end-users in over-the-top consumption scenarios, with our results showing significant improvements in quality across all metrics compared to existing methods.
Authors: Eero Lehtonen, Tuomo Komulainen, Ari Paasio, Mika Laiho
Abstract: The current event cameras are bio-inspired sensors that respond to brightness changes in the scene asynchronously and independently for every pixel, and transmit these changes as ternary event streams. Event cameras have several benefits over conventional digital cameras, such as significantly higher temporal resolution and pixel bandwidth resulting in reduced motion blur, and very high dynamic range. However, they also introduce challenges such as the difficulty of applying existing computer vision algorithms to the output event streams, and the flood of uninformative events in the presence of oscillating light sources. Here we propose a new type of event, the gradient event, which benefits from the same properties as a conventional brightness event, but which is by design much less sensitive to oscillating light sources, and which enables considerably better grayscale frame reconstruction. We show that the gradient event -based video reconstruction outperforms existing state-of-the-art brightness event -based methods by a significant margin, when evaluated on publicly available event-to-video datasets. Our results show how gradient information can be used to significantly improve the acquisition of visual information by an event camera.
Authors: Wenlin Li, Yucheng Xu, Xiaoqing Zheng, Suoya Han, Jun Wang, Xiaobo Sun
Abstract: Sparse and noisy images (SNIs), like those in spatial gene expression data, pose significant challenges for effective representation learning and clustering, which are essential for thorough data analysis and interpretation. In response to these challenges, we propose Dual Advancement of Representation Learning and Clustering (DARLC), an innovative framework that leverages contrastive learning to enhance the representations derived from masked image modeling. Simultaneously, DARLC integrates cluster assignments in a cohesive, end-to-end approach. This integrated clustering strategy addresses the "class collision problem" inherent in contrastive learning, thus improving the quality of the resulting representations. To generate more plausible positive views for contrastive learning, we employ a graph attention network-based technique that produces denoised images as augmented data. As such, our framework offers a comprehensive approach that improves the learning of representations by enhancing their local perceptibility, distinctiveness, and the understanding of relational semantics. Furthermore, we utilize a Student's t mixture model to achieve more robust and adaptable clustering of SNIs. Extensive experiments, conducted across 12 different types of datasets consisting of SNIs, demonstrate that DARLC surpasses the state-of-the-art methods in both image clustering and generating image representations that accurately capture gene interactions. Code is available at https://github.com/zipging/DARLC.
Authors: Qingxuan Lv, Junyu Dong, Yuezun Li, Sheng Chen, Hui Yu, Shu Zhang, Wenhan Wang
Abstract: Despite recent advances in stereo matching, the extension to intricate underwater settings remains unexplored, primarily owing to: 1) the reduced visibility, low contrast, and other adverse effects of underwater images; 2) the difficulty in obtaining ground truth data for training deep learning models, i.e. simultaneously capturing an image and estimating its corresponding pixel-wise depth information in underwater environments. To enable further advance in underwater stereo matching, we introduce a large synthetic dataset called UWStereo. Our dataset includes 29,568 synthetic stereo image pairs with dense and accurate disparity annotations for left view. We design four distinct underwater scenes filled with diverse objects such as corals, ships and robots. We also induce additional variations in camera model, lighting, and environmental effects. In comparison with existing underwater datasets, UWStereo is superior in terms of scale, variation, annotation, and photo-realistic image quality. To substantiate the efficacy of the UWStereo dataset, we undertake a comprehensive evaluation compared with nine state-of-the-art algorithms as benchmarks. The results indicate that current models still struggle to generalize to new domains. Hence, we design a new strategy that learns to reconstruct cross domain masked images before stereo matching training and integrate a cross view attention enhancement module that aggregates long-range content information to enhance the generalization ability.
Authors: Zhen Zhou, Yunkai Ma, Junfeng Fan, Shaolin Zhang, Fengshui Jing, Min Tan
Abstract: Panoptic 3D reconstruction from a monocular video is a fundamental perceptual task in robotic scene understanding. However, existing efforts suffer from inefficiency in terms of inference speed and accuracy, limiting their practical applicability. We present EPRecon, an efficient real-time panoptic 3D reconstruction framework. Current volumetric-based reconstruction methods usually utilize multi-view depth map fusion to obtain scene depth priors, which is time-consuming and poses challenges to real-time scene reconstruction. To end this, we propose a lightweight module to directly estimate scene depth priors in a 3D volume for reconstruction quality improvement by generating occupancy probabilities of all voxels. In addition, to infer richer panoptic features from occupied voxels, EPRecon extracts panoptic features from both voxel features and corresponding image features, obtaining more detailed and comprehensive instance-level semantic information and achieving more accurate segmentation results. Experimental results on the ScanNetV2 dataset demonstrate the superiority of EPRecon over current state-of-the-art methods in terms of both panoptic 3D reconstruction quality and real-time inference. Code is available at https://github.com/zhen6618/EPRecon.
Authors: Tommaso Apicella, Alessio Xompero, Paolo Gastaldo, Andrea Cavallaro
Abstract: Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size datasets. However, experimental setups are often not reproducible, thus leading to unfair and inconsistent comparisons. In this work, we benchmark these methods under a reproducible setup on two single objects scenarios, tabletop without occlusions and hand-held containers, to facilitate future comparisons. We include a version of a recent architecture, Mask2Former, re-trained for affordance segmentation and show that this model is the best-performing on most testing sets of both scenarios. Our analysis shows that models are not robust to scale variations when object resolutions differ from those in the training set.
Authors: Jinqing Zhang, Yanan Zhang, Yunlong Qi, Zehua Fu, Qingjie Liu, Yunhong Wang
Abstract: Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation, leaving it in a low-resolution state and failing to restore the authentic geometric information of the scene. In this paper, we identify the reasons why previous approaches are constrained by low BEV representation resolution and propose Radial-Cartesian BEV Sampling (RC-Sampling), enabling efficient generation of high-resolution dense BEV representations without the need for complex operators. Additionally, we design a novel In-Box Label to substitute the traditional depth label generated from the LiDAR points. This label reflects the actual geometric structure of objects rather than just their surfaces, injecting real-world geometric information into the BEV representation. Furthermore, in conjunction with the In-Box Label, a Centroid-Aware Inner Loss (CAI Loss) is developed to capture the fine-grained inner geometric structure of objects. Finally, we integrate the aforementioned modules into a novel multi-view 3D object detection framework, dubbed GeoBEV. Extensive experiments on the nuScenes dataset exhibit that GeoBEV achieves state-of-the-art performance, highlighting its effectiveness.
Authors: Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Tsung-Yi Ho
Abstract: Adapting pre-trained models to new tasks can exhibit varying effectiveness across datasets. Visual prompting, a state-of-the-art parameter-efficient transfer learning method, can significantly improve the performance of out-of-distribution tasks. On the other hand, linear probing, a standard transfer learning method, can sometimes become the best approach. We propose a log-likelihood ratio (LLR) approach to analyze the comparative benefits of visual prompting and linear probing. By employing the LLR score alongside resource-efficient visual prompts approximations, our cost-effective measure attains up to a 100-fold reduction in run time compared to full training, while achieving prediction accuracies up to $91\%$. The source code is available at $\href{https://github.com/IBM/VP-LLR}{\texttt{VP-LLR}}$.
Authors: Amirreza Dolatpour Fathkouhi, Geoffrey Charles Fox
Abstract: Redshift prediction is a fundamental task in astronomy, essential for understanding the expansion of the universe and determining the distances of astronomical objects. Accurate redshift prediction plays a crucial role in advancing our knowledge of the cosmos. Machine learning (ML) methods, renowned for their precision and speed, offer promising solutions for this complex task. However, traditional ML algorithms heavily depend on labeled data and task-specific feature extraction. To overcome these limitations, we introduce AstroMAE, an innovative approach that pretrains a vision transformer encoder using a masked autoencoder method on Sloan Digital Sky Survey (SDSS) images. This technique enables the encoder to capture the global patterns within the data without relying on labels. To the best of our knowledge, AstroMAE represents the first application of a masked autoencoder to astronomical data. By ignoring labels during the pretraining phase, the encoder gathers a general understanding of the data. The pretrained encoder is subsequently fine-tuned within a specialized architecture tailored for redshift prediction. We evaluate our model against various vision transformer architectures and CNN-based models, demonstrating the superior performance of AstroMAEs pretrained model and fine-tuning architecture.
Authors: Soumitri Chattopadhyay, Sanket Biswas, Emanuele Vivoli, Josep Llad\'os
Abstract: Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models trained on one domain do not generalize well on a different domain without fine-tuning. We attribute these to the limitations of the VLM's semantic representations and attempt to improve their fine-grained visual awareness using generative modeling. Specifically, we propose two novel methods: Generative Class Prompt Learning (GCPL) and Contrastive Multi-class Prompt Learning (CoMPLe). Utilizing text-to-image diffusion models, GCPL significantly improves the visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation during the generative optimization process. Our empirical results demonstrate that such a generative class prompt learning approach substantially outperform existing methods, offering a better alternative to few shot image recognition challenges. The source code will be made available at: https://github.com/soumitri2001/GCPL.
Authors: Tingchen Ma, Yongsheng Ou, Sheng Xu
Abstract: The Bundle Adjustment (BA) algorithm is a widely used nonlinear optimization technique in the backend of Simultaneous Localization and Mapping (SLAM) systems. By leveraging the co-view relationships of landmarks from multiple perspectives, it constructs a joint estimation model for both poses and landmarks, enabling the system to generate refined maps and reduce front-end localization errors. However, applying BA to LiDAR data presents unique challenges due to the large volume of 3D points typically present in point clouds, making robust and accurate model solving more complex. In this work, we propose a novel mean square group metric (MSGM). This metric applies mean square transformation to uniformly process the measurement of plane landmarks from a single perspective. The transformed metric ensures scale interpretability while avoiding the time-consuming point-by-point calculations. By integrating a robust kernel function, the metrics involved in the BA model are reweighted, enhancing the robustness of the solution process. On the basis of the proposed robust LiDAR BA model, we derived an explicit second-order estimator (RSO-BA). This estimator employs analytical formulas for Hessian and gradient calculations, ensuring the precision of the BA solution. We evaluated the proposed RSO-BA estimator against existing implicit second-order and explicit approximate second-order estimators using the publicly available datasets. The experimental results demonstrate that the RSO-BA estimator outperforms its counterparts regarding registration accuracy and robustness, particularly in large-scale or complex unstructured environments.
Authors: Salah Eddine Laidoudi, Madjid Maidi, Samir Otmane
Abstract: Real-time object detection in indoor settings is a challenging area of computer vision, faced with unique obstacles such as variable lighting and complex backgrounds. This field holds significant potential to revolutionize applications like augmented and mixed realities by enabling more seamless interactions between digital content and the physical world. However, the scarcity of research specifically fitted to the intricacies of indoor environments has highlighted a clear gap in the literature. To address this, our study delves into the evaluation of existing datasets and computational models, leading to the creation of a refined dataset. This new dataset is derived from OpenImages v7, focusing exclusively on 32 indoor categories selected for their relevance to real-world applications. Alongside this, we present an adaptation of a CNN detection model, incorporating an attention mechanism to enhance the model's ability to discern and prioritize critical features within cluttered indoor scenes. Our findings demonstrate that this approach is not just competitive with existing state-of-the-art models in accuracy and speed but also opens new avenues for research and application in the field of real-time indoor object detection.
Authors: Francesco Pasti, Marina Ceccon, Davide Dalle Pezze, Francesco Paissan, Elisabetta Farella, Gian Antonio Susto, Nicola Bellotto
Abstract: While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to new data while maintaining performance on previous data. This is particularly pertinent for edge devices, common in dynamic environments like automotive and robotics. In this work, we address the memory and computation constraints of edge devices in the Continual Learning for Object Detection (CLOD) scenario. Specifically, (i) we investigate the suitability of an open-source, lightweight, and fast detector, namely NanoDet, for CLOD on edge devices, improving upon larger architectures used in the literature. Moreover, (ii) we propose a novel CL method, called Latent Distillation~(LD), that reduces the number of operations and the memory required by state-of-the-art CL approaches without significantly compromising detection performance. Our approach is validated using the well-known VOC and COCO benchmarks, reducing the distillation parameter overhead by 74\% and the Floating Points Operations~(FLOPs) by 56\% per model update compared to other distillation methods.
Authors: Gaojie Lin, Jianwen Jiang, Chao Liang, Tianyun Zhong, Jiaqi Yang, Yanbo Zheng
Abstract: Diffusion-based video generation technology has advanced significantly, catalyzing a proliferation of research in human animation. However, the majority of these studies are confined to same-modality driving settings, with cross-modality human body animation remaining relatively underexplored. In this paper, we introduce, an end-to-end audio-driven human animation framework that ensures hand integrity, identity consistency, and natural motion. The key design of CyberHost is the Region Codebook Attention mechanism, which improves the generation quality of facial and hand animations by integrating fine-grained local features with learned motion pattern priors. Furthermore, we have developed a suite of human-prior-guided training strategies, including body movement map, hand clarity score, pose-aligned reference feature, and local enhancement supervision, to improve synthesis results. To our knowledge, CyberHost is the first end-to-end audio-driven human diffusion model capable of facilitating zero-shot video generation within the scope of human body. Extensive experiments demonstrate that CyberHost surpasses previous works in both quantitative and qualitative aspects.
Authors: Irene Ballester, Ond\v{r}ej Peterka, Martin Kampel
Abstract: 3D Human Pose Estimation (HPE) is the task of locating keypoints of the human body in 3D space from 2D or 3D representations such as RGB images, depth maps or point clouds. Current HPE methods from depth and point clouds predominantly rely on single-frame estimation and do not exploit temporal information from sequences. This paper presents SPiKE, a novel approach to 3D HPE using point cloud sequences. Unlike existing methods that process frames of a sequence independently, SPiKE leverages temporal context by adopting a Transformer architecture to encode spatio-temporal relationships between points across the sequence. By partitioning the point cloud into local volumes and using spatial feature extraction via point spatial convolution, SPiKE ensures efficient processing by the Transformer while preserving spatial integrity per timestamp. Experiments on the ITOP benchmark for 3D HPE show that SPiKE reaches 89.19% mAP, achieving state-of-the-art performance with significantly lower inference times. Extensive ablations further validate the effectiveness of sequence exploitation and our algorithmic choices. Code and models are available at: https://github.com/iballester/SPiKE
Authors: Maxime Zanella, Fereshteh Shakeri, Yunshi Huang, Houda Bahig, Ismail Ben Ayed
Abstract: The development of vision-language models (VLMs) for histo-pathology has shown promising new usages and zero-shot performances. However, current approaches, which decompose large slides into smaller patches, focus solely on inductive classification, i.e., prediction for each patch is made independently of the other patches in the target test data. We extend the capability of these large models by introducing a transductive approach. By using text-based predictions and affinity relationships among patches, our approach leverages the strong zero-shot capabilities of these new VLMs without any additional labels. Our experiments cover four histopathology datasets and five different VLMs. Operating solely in the embedding space (i.e., in a black-box setting), our approach is highly efficient, processing $10^5$ patches in just a few seconds, and shows significant accuracy improvements over inductive zero-shot classification. Code available at https://github.com/FereshteShakeri/Histo-TransCLIP.
Authors: Oline Ranum, Gomer Otterspeer, Jari I. Andersen, Robert G. Belleman, Floris Roelofsen
Abstract: In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, and attains an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5% over using no handshape annotations, and by 1% over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.
Authors: Imanol Solano, Alejandro Pe\~na, Aythami Morales, Julian Fierrez, Ruben Tolosana, Francisco Zamora-Martinez, Javier San Agustin
Abstract: We present a novel metric designed, among other applications, to quantify biased behaviors of machine learning models. As its core, the metric consists of a new similarity metric between score distributions that balances both their general shapes and tails' probabilities. In that sense, our proposed metric may be useful in many application areas. Here we focus on and apply it to the operational evaluation of face recognition systems, with special attention to quantifying demographic biases; an application where our metric is especially useful. The topic of demographic bias and fairness in biometric recognition systems has gained major attention in recent years. The usage of these systems has spread in society, raising concerns about the extent to which these systems treat different population groups. A relevant step to prevent and mitigate demographic biases is first to detect and quantify them. Traditionally, two approaches have been studied to quantify differences between population groups in machine learning literature: 1) measuring differences in error rates, and 2) measuring differences in recognition score distributions. Our proposed Comprehensive Equity Index (CEI) trade-offs both approaches combining both errors from distribution tails and general distribution shapes. This new metric is well suited to real-world scenarios, as measured on NIST FRVT evaluations, involving high-performance systems and realistic face databases including a wide range of covariates and demographic groups. We first show the limitations of existing metrics to correctly assess the presence of biases in realistic setups and then propose our new metric to tackle these limitations. We tested the proposed metric with two state-of-the-art models and four widely used databases, showing its capacity to overcome the main flaws of previous bias metrics.
Authors: Yixuan Ye, Ce Wang, Wanjie Sun, Zhenzhong Chen
Abstract: Remote-sensing (RS) image compression at extremely low bitrates has always been a challenging task in practical scenarios like edge device storage and narrow bandwidth transmission. Generative models including VAEs and GANs have been explored to compress RS images into extremely low-bitrate streams. However, these generative models struggle to reconstruct visually plausible images due to the highly ill-posed nature of extremely low-bitrate image compression. To this end, we propose an image compression framework that utilizes a pre-trained diffusion model with powerful natural image priors to achieve high-realism reconstructions. However, diffusion models tend to hallucinate small structures and textures due to the significant information loss at limited bitrates. Thus, we introduce vector maps as semantic and structural guidance and propose a novel image compression approach named Map-Assisted Generative Compression (MAGC). MAGC employs a two-stage pipeline to compress and decompress RS images at extremely low bitrates. The first stage maps an image into a latent representation, which is then further compressed in a VAE architecture to save bitrates and serves as implicit guidance in the subsequent diffusion process. The second stage conducts a conditional diffusion model to generate a visually pleasing and semantically accurate result using implicit guidance and explicit semantic guidance. Quantitative and qualitative comparisons show that our method outperforms standard codecs and other learning-based methods in terms of perceptual quality and semantic accuracy. The dataset and code will be publicly available at https://github.com/WHUyyx/MAGC.
Authors: Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung
Abstract: Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these models often struggle to differentiate between visually distinct images that have similar captions, resulting in suboptimal performance for image-based similarity searches. This paper addresses the challenge of optimizing CLIP models for various image-based similarity search scenarios, while maintaining their effectiveness in text-based search tasks such as text-to-image retrieval and zero-shot classification. We propose and evaluate two novel methods aimed at refining the retrieval capabilities of CLIP without compromising the alignment between text and image embeddings. The first method involves a sequential fine-tuning process: initially optimizing the image encoder for more precise image retrieval and subsequently realigning the text encoder to these optimized image embeddings. The second approach integrates pseudo-captions during the retrieval-optimization phase to foster direct alignment within the embedding space. Through comprehensive experiments, we demonstrate that these methods enhance CLIP's performance on various benchmarks, including image retrieval, k-NN classification, and zero-shot text-based classification, while maintaining robustness in text-to-image retrieval. Our optimized models permit maintaining a single embedding per image, significantly simplifying the infrastructure needed for large-scale multi-modal similarity search systems.
Authors: Yuhao Chen, Jiangpeng He, Chris Czarnecki, Gautham Vinod, Talha Ibn Mahmud, Siddeshwar Raghavan, Jinge Ma, Dayou Mao, Saeejith Nair, Pengcheng Xi, Alexander Wong, Edward Delp, Fengqing Zhu
Abstract: Food computing is both important and challenging in computer vision (CV). It significantly contributes to the development of CV algorithms due to its frequent presence in datasets across various applications, ranging from classification and instance segmentation to 3D reconstruction. The polymorphic shapes and textures of food, coupled with high variation in forms and vast multimodal information, including language descriptions and nutritional data, make food computing a complex and demanding task for modern CV algorithms. 3D food modeling is a new frontier for addressing food-related problems, due to its inherent capability to deal with random camera views and its straightforward representation for calculating food portion size. However, the primary hurdle in the development of algorithms for food object analysis is the lack of nutrition values in existing 3D datasets. Moreover, in the broader field of 3D research, there is a critical need for domain-specific test datasets. To bridge the gap between general 3D vision and food computing research, we propose MetaFood3D. This dataset consists of 637 meticulously labeled 3D food objects across 108 categories, featuring detailed nutrition information, weight, and food codes linked to a comprehensive nutrition database. The dataset emphasizes intra-class diversity and includes rich modalities such as textured mesh files, RGB-D videos, and segmentation masks. Experimental results demonstrate our dataset's significant potential for improving algorithm performance, highlight the challenging gap between video captures and 3D scanned data, and show the strength of the MetaFood3D dataset in high-quality data generation, simulation, and augmentation.
Authors: Nico Uhlemann, Yipeng Zhou, Tobias Mohr, Markus Lienkamp
Abstract: This paper explores pedestrian trajectory prediction in urban traffic while focusing on both model accuracy and real-world applicability. While promising approaches exist, they are often not publicly available, revolve around pedestrian datasets excluding traffic-related information, or resemble architectures that are either not real-time capable or robust. To address these limitations, we first introduce a dedicated benchmark based on Argoverse 2, specifically targeting pedestrians in urban settings. Following this, we present Snapshot, a modular, feed-forward neural network that outperforms the current state of the art while utilizing significantly less information. Despite its agent-centric encoding scheme, Snapshot demonstrates scalability, real-time performance, and robustness to varying motion histories. Moreover, by integrating Snapshot into a modular autonomous driving software stack, we showcase its real-world applicability
Authors: Muchammad Daniyal Kautsar, Ridwan Akmal, Afra Majida Hariono
Abstract: Indonesia ranks fourth globally in the number of deaf cases. Individuals with hearing impairments often find communication challenging, necessitating the use of sign language. However, there are limited public services that offer such inclusivity. On the other hand, advancements in artificial intelligence (AI) present promising solutions to overcome communication barriers faced by the deaf. This study aims to explore the application of AI in developing models for a simplified sign language translation app and dictionary, designed for integration into public service facilities, to facilitate communication for individuals with hearing impairments, thereby enhancing inclusivity in public services. The researchers compared the performance of LSTM and 1D CNN + Transformer (1DCNNTrans) models for sign language recognition. Through rigorous testing and validation, it was found that the LSTM model achieved an accuracy of 94.67%, while the 1DCNNTrans model achieved an accuracy of 96.12%. Model performance evaluation indicated that although the LSTM exhibited lower inference latency, it showed weaknesses in classifying classes with similar keypoints. In contrast, the 1DCNNTrans model demonstrated greater stability and higher F1 scores for classes with varying levels of complexity compared to the LSTM model. Both models showed excellent performance, exceeding 90% validation accuracy and demonstrating rapid classification of 50 sign language gestures.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: This study addresses the computational inefficiencies in point cloud classification by introducing novel MLP-based architectures inspired by recent advances in CNN optimization. Traditional neural networks heavily rely on multiplication operations, which are computationally expensive. To tackle this, we propose Add-MLP and Shift-MLP, which replace multiplications with addition and shift operations, respectively, significantly enhancing computational efficiency. Building on this, we introduce SA-MLP, a hybrid model that intermixes alternately distributed shift and adder layers to replace MLP layers, maintaining the original number of layers without freezing shift layer weights. This design contrasts with the ShiftAddNet model from previous literature, which replaces convolutional layers with shift and adder layers, leading to a doubling of the number of layers and limited representational capacity due to frozen shift weights. Moreover, SA-MLP optimizes learning by setting distinct learning rates and optimizers specifically for the adder and shift layers, fully leveraging their complementary strengths. Extensive experiments demonstrate that while Add-MLP and Shift-MLP achieve competitive performance, SA-MLP significantly surpasses the multiplication-based baseline MLP model and achieves performance comparable to state-of-the-art MLP-based models. This study offers an efficient and effective solution for point cloud classification, balancing performance with computational efficiency.
Authors: Frances Fengyi Yang, Michele Sasdelli, Tat-Jun Chin
Abstract: Gate quantum computers generate significant interest due to their potential to solve certain difficult problems such as prime factorization in polynomial time. Computer vision researchers have long been attracted to the power of quantum computers. Robust fitting, which is fundamentally important to many computer vision pipelines, has recently been shown to be amenable to gate quantum computing. The previous proposed solution was to compute Boolean influence as a measure of outlyingness using the Bernstein-Vazirani quantum circuit. However, the method assumed a quantum implementation of an $\ell_\infty$ feasibility test, which has not been demonstrated. In this paper, we take a big stride towards quantum robust fitting: we propose a quantum circuit to solve the $\ell_\infty$ feasibility test in the 1D case, which allows to demonstrate for the first time quantum robust fitting on a real gate quantum computer, the IonQ Aria. We also show how 1D Boolean influences can be accumulated to compute Boolean influences for higher-dimensional non-linear models, which we experimentally validate on real benchmark datasets.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: Advances in self-supervised learning are essential for enhancing feature extraction and understanding in point cloud processing. This paper introduces PMT-MAE (Point MLP-Transformer Masked Autoencoder), a novel self-supervised learning framework for point cloud classification. PMT-MAE features a dual-branch architecture that integrates Transformer and MLP components to capture rich features. The Transformer branch leverages global self-attention for intricate feature interactions, while the parallel MLP branch processes tokens through shared fully connected layers, offering a complementary feature transformation pathway. A fusion mechanism then combines these features, enhancing the model's capacity to learn comprehensive 3D representations. Guided by the sophisticated teacher model Point-M2AE, PMT-MAE employs a distillation strategy that includes feature distillation during pre-training and logit distillation during fine-tuning, ensuring effective knowledge transfer. On the ModelNet40 classification task, achieving an accuracy of 93.6\% without employing voting strategy, PMT-MAE surpasses the baseline Point-MAE (93.2\%) and the teacher Point-M2AE (93.4\%), underscoring its ability to learn discriminative 3D point cloud representations. Additionally, this framework demonstrates high efficiency, requiring only 40 epochs for both pre-training and fine-tuning. PMT-MAE's effectiveness and efficiency render it well-suited for scenarios with limited computational resources, positioning it as a promising solution for practical point cloud analysis.
Authors: Felipe Duque-Quiceno, Grzegorz Sarapata, Yuriy Dushin, Miles Allen, Jonathan O'Keeffe
Abstract: Accurate assessment of Parkinsonian tremor is vital for monitoring disease progression and evaluating treatment efficacy. We introduce a pixel-based deep learning model designed to analyse postural tremor in Parkinson's disease (PD) from video data, overcoming the limitations of traditional pose estimation techniques. Trained on 2,742 assessments from five specialised movement disorder centres across two continents, the model demonstrated robust concordance with clinical evaluations. It effectively predicted treatment effects for levodopa and deep brain stimulation (DBS), detected lateral asymmetry of symptoms, and differentiated between different tremor severities. Feature space analysis revealed a non-linear, structured distribution of tremor severity, with low-severity scores occupying a larger portion of the feature space. The model also effectively identified outlier videos, suggesting its potential for adaptive learning and quality control in clinical settings. Our approach offers a scalable and objective method for tremor scoring, with potential integration into other MDS-UPDRS motor assessments, including bradykinesia and gait. The system's adaptability and performance underscore its promise for high-frequency, longitudinal monitoring of PD symptoms, complementing clinical expertise and enhancing decision-making in patient management. Future work will extend this pixel-based methodology to other cardinal symptoms of PD, aiming to develop a comprehensive, multi-symptom model for automated Parkinson's disease severity assessment.
Authors: Bobby Azad, Pourya Adibfar, Kaiqun Fu
Abstract: In healthcare, medical image segmentation is crucial for accurate disease diagnosis and the development of effective treatment strategies. Early detection can significantly aid in managing diseases and potentially prevent their progression. Machine learning, particularly deep convolutional neural networks, has emerged as a promising approach to addressing segmentation challenges. Traditional methods like U-Net use encoding blocks for local representation modeling and decoding blocks to uncover semantic relationships. However, these models often struggle with multi-scale objects exhibiting significant variations in texture and shape, and they frequently fail to capture long-range dependencies in the input data. Transformers designed for sequence-to-sequence predictions have been proposed as alternatives, utilizing global self-attention mechanisms. Yet, they can sometimes lack precise localization due to insufficient granular details. To overcome these limitations, we introduce TransDAE: a novel approach that reimagines the self-attention mechanism to include both spatial and channel-wise associations across the entire feature space, while maintaining computational efficiency. Additionally, TransDAE enhances the skip connection pathway with an inter-scale interaction module, promoting feature reuse and improving localization accuracy. Remarkably, TransDAE outperforms existing state-of-the-art methods on the Synaps multi-organ dataset, even without relying on pre-trained weights.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: The rapid advancement in point cloud processing technologies has significantly increased the demand for efficient and compact models that achieve high-accuracy classification. Knowledge distillation has emerged as a potent model compression technique. However, traditional KD often requires extensive computational resources for forward inference of large teacher models, thereby reducing training efficiency for student models and increasing resource demands. To address these challenges, we introduce an innovative offline recording strategy that avoids the simultaneous loading of both teacher and student models, thereby reducing hardware demands. This approach feeds a multitude of augmented samples into the teacher model, recording both the data augmentation parameters and the corresponding logit outputs. By applying shape-level augmentation operations such as random scaling and translation, while excluding point-level operations like random jittering, the size of the records is significantly reduced. Additionally, to mitigate the issue of small student model over-imitating the teacher model's outputs and converging to suboptimal solutions, we incorporate a negative-weight self-distillation strategy. Experimental results demonstrate that the proposed distillation strategy enables the student model to achieve performance comparable to state-of-the-art models while maintaining lower parameter count. This approach strikes an optimal balance between performance and complexity. This study highlights the potential of our method to optimize knowledge distillation for point cloud classification tasks, particularly in resource-constrained environments, providing a novel solution for efficient point cloud analysis.
Authors: Chenghao Qian, Mahdi Rezaei, Saeed Anwar, Wenjing Li, Tanveer Hussain, Mohsen Azarmi, Wei Wang
Abstract: Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essential computer vision tasks, such as semantic segmentation, and often focus on only one specific condition, such as removing rain or translating nighttime images into daytime ones. To address these limitations, we propose a method to improve the visual quality and clarity degraded by such adverse conditions. Our method, AllWeather-Net, utilizes a novel hierarchical architecture to enhance images across all adverse conditions. This architecture incorporates information at three semantic levels: scene, object, and texture, by discriminating patches at each level. Furthermore, we introduce a Scaled Illumination-aware Attention Mechanism (SIAM) that guides the learning towards road elements critical for autonomous driving perception. SIAM exhibits robustness, remaining unaffected by changes in weather conditions or environmental scenes. AllWeather-Net effectively transforms images into normal weather and daytime scenes, demonstrating superior image enhancement results and subsequently enhancing the performance of semantic segmentation, with up to a 5.3% improvement in mIoU in the trained domain. We also show our model's generalization ability by applying it to unseen domains without re-training, achieving up to 3.9% mIoU improvement. Code can be accessed at: https://github.com/Jumponthemoon/AllWeatherNet.
Authors: Hu Wang, David Butler, Yuan Zhang, Jodie Avery, Steven Knox, Congbo Ma, Louise Hull, Gustavo Carneiro
Abstract: Endometriosis, affecting about 10\% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs of the disease using either laparoscopic surgery or the analysis of T1/T2 MRI images, with the latter being quicker and cheaper but less accurate. A key diagnostic sign of endometriosis is the obliteration of the Pouch of Douglas (POD). However, even experienced clinicians struggle with accurately classifying POD obliteration from MRI images, which complicates the training of reliable AI models. In this paper, we introduce the \underline{H}uman-\underline{AI} \underline{Co}llaborative \underline{M}ulti-modal \underline{M}ulti-rater Learning (HAICOMM) methodology to address the challenge above. HAICOMM is the first method that explores three important aspects of this problem: 1) multi-rater learning to extract a cleaner label from the multiple ``noisy'' labels available per training sample; 2) multi-modal learning to leverage the presence of T1/T2 MRI images for training and testing; and 3) human-AI collaboration to build a system that leverages the predictions from clinicians and the AI model to provide more accurate classification than standalone clinicians and AI models. Presenting results on the multi-rater T1/T2 MRI endometriosis dataset that we collected to validate our methodology, the proposed HAICOMM model outperforms an ensemble of clinicians, noisy-label learning models, and multi-rater learning methods.
Authors: Wangbo Yu, Jinbo Xing, Li Yuan, Wenbo Hu, Xiaoyu Li, Zhipeng Huang, Xiangjun Gao, Tien-Tsin Wong, Ying Shan, Yonghong Tian
Abstract: Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. In this work, we propose \textbf{ViewCrafter}, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images with the prior of video diffusion model. Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control. To further enlarge the generation range of novel views, we tailored an iterative view synthesis strategy together with a camera trajectory planning algorithm to progressively extend the 3D clues and the areas covered by the novel views. With ViewCrafter, we can facilitate various applications, such as immersive experiences with real-time rendering by efficiently optimizing a 3D-GS representation using the reconstructed 3D points and the generated novel views, and scene-level text-to-3D generation for more imaginative content creation. Extensive experiments on diverse datasets demonstrate the strong generalization capability and superior performance of our method in synthesizing high-fidelity and consistent novel views.
Authors: Ruixin Shi, Weijia Guo, Shiming Ge
Abstract: Low-resolution face recognition is a challenging task due to the missing of informative details. Recent approaches based on knowledge distillation have proven that high-resolution clues can well guide low-resolution face recognition via proper knowledge transfer. However, due to the distribution difference between training and testing faces, the learned models often suffer from poor adaptability. To address that, we split the knowledge transfer process into distillation and adaptation steps, and propose an adaptable instance-relation distillation approach to facilitate low-resolution face recognition. In the approach, the student distills knowledge from high-resolution teacher in both instance level and relation level, providing sufficient cross-resolution knowledge transfer. Then, the learned student can be adaptable to recognize low-resolution faces with adaptive batch normalization in inference. In this manner, the capability of recovering missing details of familiar low-resolution faces can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.
Authors: Subhajit Paul, Sahil Kumawat, Ashutosh Gupta, Deepak Mishra
Abstract: Recent progress in image deblurring techniques focuses mainly on operating in both frequency and spatial domains using the Fourier transform (FT) properties. However, their performance is limited due to the dependency of FT on stationary signals and its lack of capability to extract spatial-frequency properties. In this paper, we propose a novel approach based on the Fractional Fourier Transform (FRFT), a unified spatial-frequency representation leveraging both spatial and frequency components simultaneously, making it ideal for processing non-stationary signals like images. Specifically, we introduce a Fractional Fourier Transformer (F2former), where we combine the classical fractional Fourier based Wiener deconvolution (F2WD) as well as a multi-branch encoder-decoder transformer based on a new fractional frequency aware transformer block (F2TB). We design F2TB consisting of a fractional frequency aware self-attention (F2SA) to estimate element-wise product attention based on important frequency components and a novel feed-forward network based on frequency division multiplexing (FM-FFN) to refine high and low frequency features separately for efficient latent clear image restoration. Experimental results for the cases of both motion deblurring as well as defocus deblurring show that the performance of our proposed method is superior to other state-of-the-art (SOTA) approaches.
Authors: Kishor Datta Gupta, Marufa Kamal, Rakib Hossain Rifat, Mohd Ariful Haque, Roy George
Abstract: The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neural Networks (PGNNs) have emerged to address these limitations by integrating scientific principles and real-world knowledge, enhancing model interpretability and efficiency. This paper proposes a novel Physics-Guided CNN (PGCNN) architecture that incorporates dynamic, trainable, and automated LLM-generated, widely recognized rules integrated into the model as custom layers to address challenges like limited data and low confidence scores. The PGCNN is evaluated on multiple datasets, demonstrating superior performance compared to a baseline CNN model. Key improvements include a significant reduction in false positives and enhanced confidence scores for true detection. The results highlight the potential of PGCNNs to improve CNN performance for broader application areas.
Authors: Wenbo Hu, Xiangjun Gao, Xiaoyu Li, Sijie Zhao, Xiaodong Cun, Yong Zhang, Long Quan, Ying Shan
Abstract: Despite significant advancements in monocular depth estimation for static images, estimating video depth in the open world remains challenging, since open-world videos are extremely diverse in content, motion, camera movement, and length. We present DepthCrafter, an innovative method for generating temporally consistent long depth sequences with intricate details for open-world videos, without requiring any supplementary information such as camera poses or optical flow. DepthCrafter achieves generalization ability to open-world videos by training a video-to-depth model from a pre-trained image-to-video diffusion model, through our meticulously designed three-stage training strategy with the compiled paired video-depth datasets. Our training approach enables the model to generate depth sequences with variable lengths at one time, up to 110 frames, and harvest both precise depth details and rich content diversity from realistic and synthetic datasets. We also propose an inference strategy that processes extremely long videos through segment-wise estimation and seamless stitching. Comprehensive evaluations on multiple datasets reveal that DepthCrafter achieves state-of-the-art performance in open-world video depth estimation under zero-shot settings. Furthermore, DepthCrafter facilitates various downstream applications, including depth-based visual effects and conditional video generation.
Authors: Songhua Liu, Weihao Yu, Zhenxiong Tan, Xinchao Wang
Abstract: Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this existing paradigm faces significant challenges in generating high-resolution visual content due to its quadratic time and memory complexity with respect to the number of spatial tokens. To address this limitation, we aim at a novel linear attention mechanism as an alternative in this paper. Specifically, we begin our exploration from recently introduced models with linear complexity, e.g., Mamba, Mamba2, and Gated Linear Attention, and identify two key features-attention normalization and non-causal inference-that enhance high-resolution visual generation performance. Building on these insights, we introduce a generalized linear attention paradigm, which serves as a low-rank approximation of a wide spectrum of popular linear token mixers. To save the training cost and better leverage pre-trained models, we initialize our models and distill the knowledge from pre-trained StableDiffusion (SD). We find that the distilled model, termed LinFusion, achieves performance on par with or superior to the original SD after only modest training, while significantly reducing time and memory complexity. Extensive experiments on SD-v1.5, SD-v2.1, and SD-XL demonstrate that LinFusion delivers satisfactory zero-shot cross-resolution generation performance, generating high-resolution images like 16K resolution. Moreover, it is highly compatible with pre-trained SD components, such as ControlNet and IP-Adapter, requiring no adaptation efforts. Codes are available at https://github.com/Huage001/LinFusion.
Authors: Jiaqi Xu, Mengyang Wu, Xiaowei Hu, Chi-Wing Fu, Qi Dou, Pheng-Ann Heng
Abstract: This paper addresses the limitations of adverse weather image restoration approaches trained on synthetic data when applied to real-world scenarios. We formulate a semi-supervised learning framework employing vision-language models to enhance restoration performance across diverse adverse weather conditions in real-world settings. Our approach involves assessing image clearness and providing semantics using vision-language models on real data, serving as supervision signals for training restoration models. For clearness enhancement, we use real-world data, utilizing a dual-step strategy with pseudo-labels assessed by vision-language models and weather prompt learning. For semantic enhancement, we integrate real-world data by adjusting weather conditions in vision-language model descriptions while preserving semantic meaning. Additionally, we introduce an effective training strategy to bootstrap restoration performance. Our approach achieves superior results in real-world adverse weather image restoration, demonstrated through qualitative and quantitative comparisons with state-of-the-art works.
Authors: Jenny Seidenschwarz, Qunjie Zhou, Bardienus Duisterhof, Deva Ramanan, Laura Leal-Taix\'e
Abstract: Reconstructing scenes and tracking motion are two sides of the same coin. Tracking points allow for geometric reconstruction [14], while geometric reconstruction of (dynamic) scenes allows for 3D tracking of points over time [24, 39]. The latter was recently also exploited for 2D point tracking to overcome occlusion ambiguities by lifting tracking directly into 3D [38]. However, above approaches either require offline processing or multi-view camera setups both unrealistic for real-world applications like robot navigation or mixed reality. We target the challenge of online 2D and 3D point tracking from unposed monocular camera input introducing Dynamic Online Monocular Reconstruction (DynOMo). We leverage 3D Gaussian splatting to reconstruct dynamic scenes in an online fashion. Our approach extends 3D Gaussians to capture new content and object motions while estimating camera movements from a single RGB frame. DynOMo stands out by enabling emergence of point trajectories through robust image feature reconstruction and a novel similarity-enhanced regularization term, without requiring any correspondence-level supervision. It sets the first baseline for online point tracking with monocular unposed cameras, achieving performance on par with existing methods. We aim to inspire the community to advance online point tracking and reconstruction, expanding the applicability to diverse real-world scenarios.
Authors: Xiaowei Hu, Zhenghao Xing, Tianyu Wang, Chi-Wing Fu, Pheng-Ann Heng
Abstract: Shadows are formed when light encounters obstacles, leading to areas of diminished illumination. In computer vision, shadow detection, removal, and generation are crucial for enhancing scene understanding, refining image quality, ensuring visual consistency in video editing, and improving virtual environments. This paper presents a comprehensive survey of shadow detection, removal, and generation in images and videos within the deep learning landscape over the past decade, covering tasks, deep models, datasets, and evaluation metrics. Our key contributions include a comprehensive survey of shadow analysis, standardization of experimental comparisons, exploration of the relationships among model size, speed, and performance, a cross-dataset generalization study, identification of open issues and future directions, and provision of publicly available resources to support further research.
Authors: Zhe Fu, Kanlun Wang, Wangjiaxuan Xin, Lina Zhou, Shi Chen, Yaorong Ge, Daniel Janies, Dongsong Zhang
Abstract: The landscape of social media content has evolved significantly, extending from text to multimodal formats. This evolution presents a significant challenge in combating misinformation. Previous research has primarily focused on single modalities or text-image combinations, leaving a gap in detecting multimodal misinformation. While the concept of entity consistency holds promise in detecting multimodal misinformation, simplifying the representation to a scalar value overlooks the inherent complexities of high-dimensional representations across different modalities. To address these limitations, we propose a Multimedia Misinformation Detection (MultiMD) framework for detecting misinformation from video content by leveraging cross-modal entity consistency. The proposed dual learning approach allows for not only enhancing misinformation detection performance but also improving representation learning of entity consistency across different modalities. Our results demonstrate that MultiMD outperforms state-of-the-art baseline models and underscore the importance of each modality in misinformation detection. Our research provides novel methodological and technical insights into multimodal misinformation detection.
Authors: Ahmad Mohammad Saber, Alaa Selim, Mohamed M. Hammad, Amr Youssef, Deepa Kundur, Ehab El-Saadany
Abstract: With the rapid integration of electronically interfaced renewable energy resources and loads into smart grids, there is increasing interest in power quality disturbances (PQD) classification to enhance the security and efficiency of these grids. This paper introduces a new approach to PQD classification based on the Vision Transformer (ViT) model. When a PQD occurs, the proposed approach first converts the power quality signal into an image and then utilizes a pre-trained ViT to accurately determine the class of the PQD. Unlike most previous works, which were limited to a few disturbance classes or small datasets, the proposed method is trained and tested on a large dataset with 17 disturbance classes. Our experimental results show that the proposed ViT-based approach achieves PQD classification precision and recall of 98.28% and 97.98%, respectively, outperforming recently proposed techniques applied to the same dataset.
Authors: Timbwaoga A. J. Ouermi, Jixian Li, Zachary Morrow, Bart van Bloemen Waanders, Chris R. Johnson
Abstract: Uncertainty is inherent to most data, including vector field data, yet it is often omitted in visualizations and representations. Effective uncertainty visualization can enhance the understanding and interpretability of vector field data. For instance, in the context of severe weather events such as hurricanes and wildfires, effective uncertainty visualization can provide crucial insights about fire spread or hurricane behavior and aid in resource management and risk mitigation. Glyphs are commonly used for representing vector uncertainty but are often limited to 2D. In this work, we present a glyph-based technique for accurately representing 3D vector uncertainty and a comprehensive framework for visualization, exploration, and analysis using our new glyphs. We employ hurricane and wildfire examples to demonstrate the efficacy of our glyph design and visualization tool in conveying vector field uncertainty.
Authors: Christopher Klugmann, Rafid Mahmood, Guruprasad Hegde, Amit Kale, Daniel Kondermann
Abstract: Labeling visual data is expensive and time-consuming. Crowdsourcing systems promise to enable highly parallelizable annotations through the participation of monetarily or otherwise motivated workers, but even this approach has its limits. The solution: replace manual work with machine work. But how reliable are machine annotators? Sacrificing data quality for high throughput cannot be acceptable, especially in safety-critical applications such as autonomous driving. In this paper, we present a framework that enables quality checking of visual data at large scales without sacrificing the reliability of the results. We ask annotators simple questions with discrete answers, which can be highly automated using a convolutional neural network trained to predict crowd responses. Unlike the methods of previous work, which aim to directly predict soft labels to address human uncertainty, we use per-task posterior distributions over soft labels as our training objective, leveraging a Dirichlet prior for analytical accessibility. We demonstrate our approach on two challenging real-world automotive datasets, showing that our model can fully automate a significant portion of tasks, saving costs in the high double-digit percentage range. Our model reliably predicts human uncertainty, allowing for more accurate inspection and filtering of difficult examples. Additionally, we show that the posterior distributions over soft labels predicted by our model can be used as priors in further inference processes, reducing the need for numerous human labelers to approximate true soft labels accurately. This results in further cost reductions and more efficient use of human resources in the annotation process.
Authors: Muyao Chen, Mathieu Ch\^ateauvert, Jonathan Ethier
Abstract: This paper discusses recent advancements made in the fast prediction of signal power in mmWave communications environments. Using machine learning (ML) it is possible to train models that provide power estimates with both good accuracy and with real-time simulation speeds. Work involving improved training data pre-processing as well as 3D predictions with arbitrary transmitter height is discussed.
Authors: Sagar Srinivas Sakhinana, Geethan Sannidhi, Venkataramana Runkana
Abstract: In the chemical and process industries, Process Flow Diagrams (PFDs) and Piping and Instrumentation Diagrams (P&IDs) are critical for design, construction, and maintenance. Recent advancements in Generative AI, such as Large Multimodal Models (LMMs) like GPT4 (Omni), have shown promise in understanding and interpreting process diagrams for Visual Question Answering (VQA). However, proprietary models pose data privacy risks, and their computational complexity prevents knowledge editing for domain-specific customization on consumer hardware. To overcome these challenges, we propose a secure, on-premises enterprise solution using a hierarchical, multi-agent Retrieval Augmented Generation (RAG) framework for open-domain question answering (ODQA) tasks, offering enhanced data privacy, explainability, and cost-effectiveness. Our novel multi-agent framework employs introspective and specialized sub-agents using open-source, small-scale multimodal models with the ReAct (Reason+Act) prompting technique for PFD and P&ID analysis, integrating multiple information sources to provide accurate and contextually relevant answers. Our approach, supported by iterative self-correction, aims to deliver superior performance in ODQA tasks. We conducted rigorous experimental studies, and the empirical results validated the proposed approach effectiveness.
Authors: Aishik Nagar, Shantanu Jaiswal, Cheston Tan
Abstract: Vision-language models (VLMs) have shown impressive zero- and few-shot performance on real-world visual question answering (VQA) benchmarks, alluding to their capabilities as visual reasoning engines. However, the benchmarks being used conflate "pure" visual reasoning with world knowledge, and also have questions that involve a limited number of reasoning steps. Thus, it remains unclear whether a VLM's apparent visual reasoning performance is due to its world knowledge, or due to actual visual reasoning capabilities. To clarify this ambiguity, we systematically benchmark and dissect the zero-shot visual reasoning capabilities of VLMs through synthetic datasets that require minimal world knowledge, and allow for analysis over a broad range of reasoning steps. We focus on two novel aspects of zero-shot visual reasoning: i) evaluating the impact of conveying scene information as either visual embeddings or purely textual scene descriptions to the underlying large language model (LLM) of the VLM, and ii) comparing the effectiveness of chain-of-thought prompting to standard prompting for zero-shot visual reasoning. We find that the underlying LLMs, when provided textual scene descriptions, consistently perform better compared to being provided visual embeddings. In particular, 18% higher accuracy is achieved on the PTR dataset. We also find that CoT prompting performs marginally better than standard prompting only for the comparatively large GPT-3.5-Turbo (175B) model, and does worse for smaller-scale models. This suggests the emergence of CoT abilities for visual reasoning in LLMs at larger scales even when world knowledge is limited. Overall, we find limitations in the abilities of VLMs and LLMs for more complex visual reasoning, and highlight the important role that LLMs can play in visual reasoning.
Authors: Gerardo Altamirano-G\'omez, Carlos Gershenson
Abstract: In recent years, several models using Quaternion-Valued Convolutional Neural Networks (QCNNs) for different problems have been proposed. Although the definition of the quaternion convolution layer is the same, there are different adaptations of other atomic components to the quaternion domain, e.g., pooling layers, activation functions, fully connected layers, etc. However, the effect of selecting a specific type of these components and the way in which their interactions affect the performance of the model still unclear. Understanding the impact of these choices on model performance is vital for effectively utilizing QCNNs. This paper presents a statistical analysis carried out on experimental data to compare the performance of existing components for the image classification problem. In addition, we introduce a novel Fully Quaternion ReLU activation function, which exploits the unique properties of quaternion algebra to improve model performance.
Authors: Guoyang Xu, Junqi Xue, Zhenxi Song, Yuxin Liu, Zirui Wang, Min Zhang, Zhiguo Zhang
Abstract: Multimodal sentiment recognition aims to learn representations from different modalities to identify human emotions. However, previous works does not suppresses the frame-level redundancy inherent in continuous time series, resulting in incomplete modality representations with noise. To address this issue, we propose the Temporal-invariant learning, which minimizes the distributional differences between time steps to effectively capture smoother time series patterns, thereby enhancing the quality of the representations and robustness of the model. To fully exploit the rich semantic information in textual knowledge, we propose a Text-Driven Fusion Module (TDFM). To guide cross-modal interactions, TDFM evaluates the correlations between different modality through modality-invariant representations. Furthermore, we introduce a modality discriminator to disentangle modality-invariant and modality-specific subspaces. Experimental results on two public datasets demonstrate the superiority of our model.
Authors: Zeyu Zhang, Nengmin Yi, Shengbo Tan, Ying Cai, Yi Yang, Lei Xu, Qingtai Li, Zhang Yi, Daji Ergu, Yang Zhao
Abstract: Cervical disc herniation (CDH) is a prevalent musculoskeletal disorder that significantly impacts health and requires labor-intensive analysis from experts. Despite advancements in automated detection of medical imaging, two significant challenges hinder the real-world application of these methods. First, the computational complexity and resource demands present a significant gap for real-time application. Second, noise in MRI reduces the effectiveness of existing methods by distorting feature extraction. To address these challenges, we propose three key contributions: Firstly, we introduced MedDet, which leverages the multi-teacher single-student knowledge distillation for model compression and efficiency, meanwhile integrating generative adversarial training to enhance performance. Additionally, we customize the second-order nmODE to improve the model's resistance to noise in MRI. Lastly, we conducted comprehensive experiments on the CDH-1848 dataset, achieving up to a 5% improvement in mAP compared to previous methods. Our approach also delivers over 5 times faster inference speed, with approximately 67.8% reduction in parameters and 36.9% reduction in FLOPs compared to the teacher model. These advancements significantly enhance the performance and efficiency of automated CDH detection, demonstrating promising potential for future application in clinical practice. See project website https://steve-zeyu-zhang.github.io/MedDet
Authors: Spencer Whitehead, Jacob Phillips, Sean Hendryx
Abstract: Multimodal language models can exhibit hallucinations in their outputs, which limits their reliability. The ability to automatically detect these errors is important for mitigating them, but has been less explored and existing efforts do not localize hallucinations, instead framing this as a classification task. In this work, we first pose multimodal hallucination detection as a sequence labeling task where models must localize hallucinated text spans and present a strong baseline model. Given the high cost of human annotations for this task, we propose an approach to improve the sample efficiency of these models by creating corrupted grounding data, which we use for pre-training. Leveraging phrase grounding data, we generate hallucinations to replace grounded spans and create hallucinated text. Experiments show that pre-training on this data improves sample efficiency when fine-tuning, and that the learning signal from the grounding data plays an important role in these improvements.
Authors: Hossein Khalili, Seongbin Park, Vincent Li, Brandan Bright, Ali Payani, Ramana Rao Kompella, Nader Sehatbakhsh
Abstract: Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbations can significantly impact outcomes. Common countermeasures involve adversarial training and/or data or network transformation. These methods, though effective, require full access to typically proprietary classifiers and are costly for large models. Recent solutions propose purification models, which add a "purification" layer before classification, eliminating the need to modify the classifier directly. Despite their effectiveness, these methods are compute-intensive, making them unsuitable for mobile systems where resources are limited and low latency is essential. This paper introduces LightPure, a new method that enhances adversarial image purification. It improves the accuracy of existing purification methods and provides notable enhancements in speed and computational efficiency, making it suitable for mobile devices with limited resources. Our approach uses a two-step diffusion and one-shot Generative Adversarial Network (GAN) framework, prioritizing latency without compromising robustness. We propose several new techniques to achieve a reasonable balance between classification accuracy and adversarial robustness while maintaining desired latency. We design and implement a proof-of-concept on a Jetson Nano board and evaluate our method using various attack scenarios and datasets. Our results show that LightPure can outperform existing methods by up to 10x in terms of latency while achieving higher accuracy and robustness for various attack scenarios. This method offers a scalable and effective solution for real-world mobile systems.
Authors: Seyedeh Fahimeh Hosseini, Faezeh Shalbafzadeh, Behzad Amanpour-Gharaei
Abstract: Radiological images, such as magnetic resonance imaging (MRI) and computed tomography (CT) images, typically consist of a body part and a dark background. For many analyses, it is necessary to separate the body part region from the background. In this article, we present a Python code designed to separate body and background regions in 2D and 3D radiological images. We tested the algorithm on various MRI and CT images of different body parts, including the brain, neck, and abdominal regions. Additionally, we introduced a method for intensity normalization and outlier restriction, adjusted for data conversion into 8-bit unsigned integer (UINT8) format, and examined its effects on body-background separation. Our Python code is available for use with proper citation.
Authors: Haonan Chang, Kowndinya Boyalakuntla, Yuhan Liu, Xinyu Zhang, Liam Schramm, Abdeslam Boularias
Abstract: Solving storage problem: where objects must be accurately placed into containers with precise orientations and positions, presents a distinct challenge that extends beyond traditional rearrangement tasks. These challenges are primarily due to the need for fine-grained 6D manipulation and the inherent multi-modality of solution spaces, where multiple viable goal configurations exist for the same storage container. We present a novel Diffusion-based Affordance Prediction (DAP) pipeline for the multi-modal object storage problem. DAP leverages a two-step approach, initially identifying a placeable region on the container and then precisely computing the relative pose between the object and that region. Existing methods either struggle with multi-modality issues or computation-intensive training. Our experiments demonstrate DAP's superior performance and training efficiency over the current state-of-the-art RPDiff, achieving remarkable results on the RPDiff benchmark. Additionally, our experiments showcase DAP's data efficiency in real-world applications, an advancement over existing simulation-driven approaches. Our contribution fills a gap in robotic manipulation research by offering a solution that is both computationally efficient and capable of handling real-world variability. Code and supplementary material can be found at: https://github.com/changhaonan/DPS.git.
Authors: Aref Farhadipour, Masoumeh Chapariniya, Teodora Vukovic, Volker Dellwo
Abstract: Multimodal learning involves integrating information from various modalities to enhance learning and comprehension. We compare three modality fusion strategies in person identification and verification by processing two modalities: voice and face. In this paper, a one-dimensional convolutional neural network is employed for x-vector extraction from voice, while the pre-trained VGGFace2 network and transfer learning are utilized for face modality. In addition, gammatonegram is used as speech representation in engagement with the Darknet19 pre-trained network. The proposed systems are evaluated using the K-fold cross-validation technique on the 118 speakers of the test set of the VoxCeleb2 dataset. The comparative evaluations are done for single-modality and three proposed multimodal strategies in equal situations. Results demonstrate that the feature fusion strategy of gammatonegram and facial features achieves the highest performance, with an accuracy of 98.37% in the person identification task. However, concatenating facial features with the x-vector reaches 0.62% for EER in verification tasks.
Authors: Yangfan Deng, Hamad Albidah, Ahmed Dallal, Jijun Yin, Zhi-Hong Mao
Abstract: Sleep is crucial for human health, and EEG signals play a significant role in sleep research. Due to the high-dimensional nature of EEG signal data sequences, data visualization and clustering of different sleep stages have been challenges. To address these issues, we propose a two-stage hierarchical and explainable feature selection framework by incorporating a feature selection algorithm to improve the performance of dimensionality reduction. Inspired by topological data analysis, which can analyze the structure of high-dimensional data, we extract topological features from the EEG signals to compensate for the structural information loss that happens in traditional spectro-temporal data analysis. Supported by the topological visualization of the data from different sleep stages and the classification results, the proposed features are proven to be effective supplements to traditional features. Finally, we compare the performances of three dimensionality reduction algorithms: Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP). Among them, t-SNE achieved the highest accuracy of 79.8%, but considering the overall performance in terms of computational resources and metrics, UMAP is the optimal choice.
Authors: Jiantong Jiang, Ajmal Mian
Abstract: Hyperparameter optimization (HPO) and neural architecture search (NAS) are powerful in attaining state-of-the-art machine learning models, with Bayesian optimization (BO) standing out as a mainstream method. Extending BO into the multi-fidelity setting has been an emerging research topic, but faces the challenge of determining an appropriate fidelity for each hyperparameter configuration to fit the surrogate model. To tackle the challenge, we propose a multi-fidelity BO method named FastBO, which adaptively decides the fidelity for each configuration and efficiently offers strong performance. The advantages are achieved based on the novel concepts of efficient point and saturation point for each configuration.We also show that our adaptive fidelity identification strategy provides a way to extend any single-fidelity method to the multi-fidelity setting, highlighting its generality and applicability.
Authors: Zhengcong Fei, Mingyuan Fan, Changqian Yu, Junshi Huang
Abstract: This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic. Generally, along with design in advanced Flux\footnote{https://github.com/black-forest-labs/flux} model, we transfers it into a latent VAE space of mel-spectrum. It involves first applying a sequence of independent attention to the double text-music stream, followed by a stacked single music stream for denoised patch prediction. We employ multiple pre-trained text encoders to sufficiently capture caption semantic information as well as inference flexibility. In between, coarse textual information, in conjunction with time step embeddings, is utilized in a modulation mechanism, while fine-grained textual details are concatenated with the music patch sequence as inputs. Through an in-depth study, we demonstrate that rectified flow training with an optimized architecture significantly outperforms established diffusion methods for the text-to-music task, as evidenced by various automatic metrics and human preference evaluations. Our experimental data, code, and model weights are made publicly available at: \url{https://github.com/feizc/FluxMusic}.
URLs: https://github.com/black-forest-labs/flux, https://github.com/feizc/FluxMusic
Authors: Sina Derakhshandeh, Ali Mahloojifar
Abstract: Segmentation is one of the most significant steps in image processing. Segmenting an image is a technique that makes it possible to separate a digital image into various areas based on the different characteristics of pixels in the image. In particular, segmentation of breast ultrasound images is widely used for cancer identification. As a result of image segmentation, it is possible to make early diagnoses of diseases via medical images in a very effective way. Due to various ultrasound artifacts and noises, including speckle noise, low signal-to-noise ratio, and intensity heterogeneity, the process of accurately segmenting medical images, such as ultrasound images, is still a challenging task. In this paper, we present a new method to improve the accuracy and effectiveness of breast ultrasound image segmentation. More precisely, we propose a Neural Network (NN) based on U-Net and an encoder-decoder architecture. By taking U-Net as the basis, both encoder and decoder parts are developed by combining U-Net with other Deep Neural Networks (Res-Net and MultiResUNet) and introducing a new approach and block (Co-Block), which preserves as much as possible the low-level and the high-level features. The designed network is evaluated using the Breast Ultrasound Images (BUSI) Dataset. It consists of 780 images and the images are categorized into three classes, which are normal, benign, and malignant. According to our extensive evaluations of a public breast ultrasound dataset, the designed network segments the breast lesions more accurately than other state-of-the-art deep learning methods. With only 8.88M parameters, our network (CResU-Net) obtained 76.88%, 71.5%, 90.3%, and 97.4% in terms of Dice similarity coefficients (DSC), Intersection over Union (IoU), Area under curve (AUC), and global accuracy (ACC), respectively, on BUSI dataset.
Authors: Linda Wei, Shengyi Hua, Shaoting Zhang, Xiaofan Zhang
Abstract: Breast cancer is a highly fatal disease among cancers in women, and early detection is crucial for treatment. HER2 status, a valuable diagnostic marker based on Immunohistochemistry (IHC) staining, is instrumental in determining breast cancer status. The high cost of IHC staining and the ubiquity of Hematoxylin and Eosin (H&E) staining make the conversion from H&E to IHC staining essential. In this article, we propose a destain-restain framework for converting H&E staining to IHC staining, leveraging the characteristic that H&E staining and IHC staining of the same tissue sections share the Hematoxylin channel. We further design loss functions specifically for Hematoxylin and Diaminobenzidin (DAB) channels to generate IHC images exploiting insights from separated staining channels. Beyond the benchmark metrics on BCI contest, we have developed semantic information metrics for the HER2 level. The experimental results demonstrated that our method outperforms previous open-sourced methods in terms of image intrinsic property and semantic information.
Authors: Pragya Gupta, Subhamoy Mandal, Debashree Guha, Debjani Chakraborty
Abstract: Automatic diagnosis techniques have evolved to identify age-related macular degeneration (AMD) by employing single modality Fundus images or optical coherence tomography (OCT). To classify ocular diseases, fundus and OCT images are the most crucial imaging modalities used in the clinical setting. Most deep learning-based techniques are established on a single imaging modality, which contemplates the ocular disorders to a specific extent and disregards other modality that comprises exhaustive information among distinct imaging modalities. This paper proposes a modality-specific multiscale color space embedding integrated with the attention mechanism based on transfer learning for classification (MCGAEc), which can efficiently extract the distinct modality information at various scales using the distinct color spaces. In this work, we first introduce the modality-specific multiscale color space encoder model, which includes diverse feature representations by integrating distinct characteristic color spaces on a multiscale into a unified framework. The extracted features from the prior encoder module are incorporated with the attention mechanism to extract the global features representation, which is integrated with the prior extracted features and transferred to the random forest classifier for the classification of AMD. To analyze the performance of the proposed MCGAEc method, a publicly available multi-modality dataset from Project Macula for AMD is utilized and compared with the existing models.
Authors: Pandiyaraju V, Shravan Venkatraman, Abeshek A, Pavan Kumar S, Aravintakshan S A
Abstract: Brain tumors are abnormalities that can severely impact a patient's health, leading to life-threatening conditions such as cancer. These can result in various debilitating effects, including neurological issues, cognitive impairment, motor and sensory deficits, as well as emotional and behavioral changes. These symptoms significantly affect a patient's quality of life, making early diagnosis and timely treatment essential to prevent further deterioration. However, accurately segmenting the tumor region from medical images, particularly MRI scans, is a challenging and time-consuming task that requires the expertise of radiologists. Manual segmentation can also be prone to human errors. To address these challenges, this research leverages the synergy of SeNet and ResNet architectures within an encoder-decoder framework, designed specifically for glioma detection and segmentation. The proposed model incorporates the power of SeResNet-152 as the backbone, integrated into a robust encoder-decoder structure to enhance feature extraction and improve segmentation accuracy. This novel approach significantly reduces the dependency on manual tasks and improves the precision of tumor identification. Evaluation of the model demonstrates strong performance, achieving 87% in Dice Coefficient, 89.12% in accuracy, 88% in IoU score, and 82% in mean IoU score, showcasing its effectiveness in tackling the complex problem of brain tumor segmentation.
Authors: Wangang Cheng, Guanghua He, Keli Hu, Mingyu Fang, Liang Dong, Zhong Li, Hancan Zhu
Abstract: Deep learning methods have significantly advanced medical image segmentation, yet their success hinges on large volumes of manually annotated data, which require specialized expertise for accurate labeling. Additionally, these methods often demand substantial computational resources, particularly for three-dimensional medical imaging tasks. Consequently, applying deep learning techniques for medical image segmentation with limited annotated data and computational resources remains a critical challenge. In this paper, we propose a novel parameter-efficient fine-tuning strategy, termed HyPS, which employs a hybrid parallel and serial architecture. HyPS updates a minimal subset of model parameters, thereby retaining the pre-trained model's original knowledge tructure while enhancing its ability to learn specific features relevant to downstream tasks. We apply this strategy to the state-of-the-art SwinUNETR model for medical image segmentation. Initially, the model is pre-trained on the BraTs2021 dataset, after which the HyPS method is employed to transfer it to three distinct hippocampus datasets.Extensive experiments demonstrate that HyPS outperforms baseline methods, especially in scenarios with limited training samples. Furthermore, based on the segmentation results, we calculated the hippocampal volumes of subjects from the ADNI dataset and combined these with metadata to classify disease types. In distinguishing Alzheimer's disease (AD) from cognitively normal (CN) individuals, as well as early mild cognitive impairment (EMCI) from late mild cognitive impairment (LMCI), HyPS achieved classification accuracies of 83.78% and 64.29%, respectively. These findings indicate that the HyPS method not only facilitates effective hippocampal segmentation using pre-trained models but also holds potential for aiding Alzheimer's disease detection. Our code is publicly available.
Authors: Zoey Chen, Zhao Mandi, Homanga Bharadhwaj, Mohit Sharma, Shuran Song, Abhishek Gupta, Vikash Kumar
Abstract: Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to generalize despite these challenges, it is essential to leverage sources of data or priors beyond the robot's direct experience. In this work, we posit that image-text generative models, which are pre-trained on large corpora of web-scraped data, can serve as such a data source. These generative models encompass a broad range of real-world scenarios beyond a robot's direct experience and can synthesize novel synthetic experiences that expose robotic agents to additional world priors aiding real-world generalization at no extra cost. In particular, our approach leverages pre-trained generative models as an effective tool for data augmentation. We propose a generative augmentation framework for semantically controllable augmentations and rapidly multiplying robot datasets while inducing rich variations that enable real-world generalization. Based on diverse augmentations of robot data, we show how scalable robot manipulation policies can be trained and deployed both in simulation and in unseen real-world environments such as kitchens and table-tops. By demonstrating the effectiveness of image-text generative models in diverse real-world robotic applications, our generative augmentation framework provides a scalable and efficient path for boosting generalization in robot learning at no extra human cost.
Authors: Boda Li, Shichao Zhou, Qinwei Ma, Shaopeng Ma
Abstract: Digital Image Correlation (DIC) is a key technique in experimental mechanics for full-field deformation measurement, traditionally relying on subset matching to determine displacement fields. However, selecting optimal parameters like shape functions and subset size can be challenging in non-uniform deformation scenarios. Recent deep learning-based DIC approaches, both supervised and unsupervised, use neural networks to map speckle images to deformation fields, offering precise measurements without manual tuning. However, these methods require complex network architectures to extract speckle image features, which does not guarantee solution accuracy This paper introduces PINN-DIC, a novel DIC method based on Physics-Informed Neural Networks (PINNs). Unlike traditional approaches, PINN-DIC uses a simple fully connected neural network that takes the coordinate domain as input and outputs the displacement field. By integrating the DIC governing equation into the loss function, PINN-DIC directly extracts the displacement field from reference and deformed speckle images through iterative optimization. Evaluations on simulated and real experiments demonstrate that PINN-DIC maintains the accuracy of deep learning-based DIC in non-uniform fields while offering three distinct advantages: 1) enhanced precision with a simpler network by directly fitting the displacement field from coordinates, 2) effective handling of irregular boundary displacement fields with minimal parameter adjustments, and 3) easy integration with other neural network-based mechanical analysis methods for comprehensive DIC result analysis.
Authors: Yingfa Chen, Chenlong Hu, Cong Feng, Chenyang Song, Shi Yu, Xu Han, Zhiyuan Liu, Maosong Sun
Abstract: This study presents a multi-modal multi-granularity tokenizer specifically designed for analyzing ancient Chinese scripts, focusing on the Chu bamboo slip (CBS) script used during the Spring and Autumn and Warring States period (771-256 BCE) in Ancient China. Considering the complex hierarchical structure of ancient Chinese scripts, where a single character may be a combination of multiple sub-characters, our tokenizer first adopts character detection to locate character boundaries, and then conducts character recognition at both the character and sub-character levels. Moreover, to support the academic community, we have also assembled the first large-scale dataset of CBSs with over 100K annotated character image scans. On the part-of-speech tagging task built on our dataset, using our tokenizer gives a 5.5% relative improvement in F1-score compared to mainstream sub-word tokenizers. Our work not only aids in further investigations of the specific script but also has the potential to advance research on other forms of ancient Chinese scripts.
Authors: Mevan Ekanayake, Zhifeng Chen, Gary Egan, Mehrtash Harandi, Zhaolin Chen
Abstract: Implicit Neural Representations (INRs) have recently advanced the field of deep learning due to their ability to learn continuous representations of signals without the need for large training datasets. Although INR methods have been studied for medical image super-resolution, their adaptability to localized priors in medical images has not been extensively explored. Medical images contain rich anatomical divisions that could provide valuable local prior information to enhance the accuracy and robustness of INRs. In this work, we propose a novel framework, referred to as the Semantically Conditioned INR (SeCo-INR), that conditions an INR using local priors from a medical image, enabling accurate model fitting and interpolation capabilities to achieve super-resolution. Our framework learns a continuous representation of the semantic segmentation features of a medical image and utilizes it to derive the optimal INR for each semantic region of the image. We tested our framework using several medical imaging modalities and achieved higher quantitative scores and more realistic super-resolution outputs compared to state-of-the-art methods.
Authors: Chongjie Si, Zhiyi Shi, Shifan Zhang, Xiaokang Yang, Hanspeter Pfister, Wei Shen
Abstract: Large language models demonstrate impressive performance on downstream tasks, yet requiring extensive resource consumption when fully fine-tuning all parameters. To mitigate this, Parameter Efficient Fine-Tuning (PEFT) strategies, such as LoRA, have been developed. In this paper, we delve into the concept of task-specific directions--critical for transitioning large models from pre-trained states to task-specific enhancements in PEFT. We propose a framework to clearly define these directions and explore their properties, and practical utilization challenges. We then introduce a novel approach, LoRA-Dash, which aims to maximize the impact of task-specific directions during the fine-tuning process, thereby enhancing model performance on targeted tasks. Extensive experiments have conclusively demonstrated the effectiveness of LoRA-Dash, and in-depth analyses further reveal the underlying mechanisms of LoRA-Dash. The code is available at https://github.com/Chongjie-Si/Subspace-Tuning.
Authors: Yu Xiang Tan, Malika Meghjani
Abstract: GPS-based vehicle localization and tracking suffers from unstable positional information commonly experienced in tunnel segments and in dense urban areas. Also, both Visual Odometry (VO) and Visual Inertial Odometry (VIO) are susceptible to adverse weather conditions that causes occlusions or blur on the visual input. In this paper, we propose a novel approach for vehicle localization that uses street network based map information to correct drifting odometry estimates and intermittent GPS measurements especially, in adversarial scenarios such as driving in rain and tunnels. Specifically, our approach is a flexible fusion algorithm that integrates intermittent GPS, drifting IMU and VO estimates together with 2D map information for robust vehicle localization and tracking. We refer to our approach as Map-Fusion. We robustly evaluate our proposed approach on four geographically diverse datasets from different countries ranging across clear and rain weather conditions. These datasets also include challenging visual segments in tunnels and underpasses. We show that with the integration of the map information, our Map-Fusion algorithm reduces the error of the state-of-the-art VO and VIO approaches across all datasets. We also validate our proposed algorithm in a real-world environment and in real-time on a hardware constrained mobile robot. Map-Fusion achieved 2.46m error in clear weather and 6.05m error in rain weather for a 150m route.
Authors: Viet-Hung Tran, Ngoc-Bao Nguyen, Son T. Mai, Hans Vandierendonck, Ngai-man Cheung
Abstract: Model Inversion (MI) is a type of privacy violation that focuses on reconstructing private training data through abusive exploitation of machine learning models. To defend against MI attacks, state-of-the-art (SOTA) MI defense methods rely on regularizations that conflict with the training loss, creating explicit tension between privacy protection and model utility. In this paper, we present a new method to defend against MI attacks. Our method takes a new perspective and focuses on training data. Our idea is based on a novel insight on Random Erasing (RE), which has been applied in the past as a data augmentation technique to improve the model accuracy under occlusion. In our work, we instead focus on applying RE for degrading MI attack accuracy. Our key insight is that MI attacks require significant amount of private training data information encoded inside the model in order to reconstruct high-dimensional private images. Therefore, we propose to apply RE to reduce private information presented to the model during training. We show that this can lead to substantial degradation in MI reconstruction quality and attack accuracy. Meanwhile, natural accuracy of the model is only moderately affected. Our method is very simple to implement and complementary to existing defense methods. Our extensive experiments of 23 setups demonstrate that our method can achieve SOTA performance in balancing privacy and utility of the models. The results consistently demonstrate the superiority of our method over existing defenses across different MI attacks, network architectures, and attack configurations.
Authors: Jinglin Liang, Jin Zhong, Hanlin Gu, Zhongqi Lu, Xingxing Tang, Gang Dai, Shuangping Huang, Lixin Fan, Qiang Yang
Abstract: Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue that has been explored to some extent in Continual Learning (CL). However, due to privacy preservation requirements, some conventional methods, such as experience replay, are not directly applicable to FCCL.Existing FCCL methods mitigate forgetting by generating historical data through federated training of GANs or data-free knowledge distillation. However, these approaches often suffer from unstable training of generators or low-quality generated data, limiting their guidance for the model.To address this challenge, we propose a novel method of data replay based on diffusion models. Instead of training a diffusion model, we employ a pre-trained conditional diffusion model to reverse-engineer each class, searching the corresponding input conditions for each class within the model's input space, significantly reducing computational resources and time consumption while ensuring effective generation. Furthermore, we enhance the classifier's domain generalization ability on generated and real data through contrastive learning, indirectly improving the representational capability of generated data for real data. Comprehensive experiments demonstrate that our method significantly outperforms existing baselines.Code is available at https://github.com/jinglin-liang/DDDR.
Authors: Andrija Djurisic, Rosanne Liu, Mladen Nikolic
Abstract: The safe deployment of machine learning and AI models in open-world settings hinges critically on the ability to detect out-of-distribution (OOD) data accurately, data samples that contrast vastly from what the model was trained with. Current approaches to OOD detection often require further training the model, and/or statistics about the training data which may no longer be accessible. Additionally, many existing OOD detection methods struggle to maintain performance when transferred across different architectures. Our research tackles these issues by proposing a simple, post-hoc method that does not require access to the training data distribution, keeps a trained network intact, and holds strong performance across a variety of architectures. Our method, Logit Scaling (LTS), as the name suggests, simply scales the logits in a manner that effectively distinguishes between in-distribution (ID) and OOD samples. We tested our method on benchmarks across various scales, including CIFAR-10, CIFAR-100, ImageNet and OpenOOD. The experiments cover 3 ID and 14 OOD datasets, as well as 9 model architectures. Overall, we demonstrate state-of-the-art performance, robustness and adaptability across different architectures, paving the way towards a universally applicable solution for advanced OOD detection.
Authors: Rizhong Lin, Hamza Kebiri, Ali Gholipour, Yufei Chen, Jean-Philippe Thiran, Davood Karimi, Meritxell Bach Cuadra
Abstract: Diffusion Magnetic Resonance Imaging (dMRI) is a non-invasive method for depicting brain microstructure in vivo. Fiber orientation distributions (FODs) are mathematical representations extensively used to map white matter fiber configurations. Recently, FOD estimation with deep neural networks has seen growing success, in particular, those of neonates estimated with fewer diffusion measurements. These methods are mostly trained on target FODs reconstructed with multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD), which might not be the ideal ground truth for developing brains. Here, we investigate this hypothesis by training a state-of-the-art model based on the U-Net architecture on both MSMT-CSD and single-shell three-tissue constrained spherical deconvolution (SS3T-CSD). Our results suggest that SS3T-CSD might be more suited for neonatal brains, given that the ratio between single and multiple fiber-estimated voxels with SS3T-CSD is more realistic compared to MSMT-CSD. Additionally, increasing the number of input gradient directions significantly improves performance with SS3T-CSD over MSMT-CSD. Finally, in an age domain-shift setting, SS3T-CSD maintains robust performance across age groups, indicating its potential for more accurate neonatal brain imaging.
Authors: Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio, Giorgio Giacinto, Fabio Roli
Abstract: Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a misclassification. These methods, which we refer to as adversarial pruning methods, involve complex and articulated designs, making it difficult to analyze the differences and establish a fair and accurate comparison. In this work, we overcome these issues by surveying current adversarial pruning methods and proposing a novel taxonomy to categorize them based on two main dimensions: the pipeline, defining when to prune; and the specifics, defining how to prune. We then highlight the limitations of current empirical analyses and propose a novel, fair evaluation benchmark to address them. We finally conduct an empirical re-evaluation of current adversarial pruning methods and discuss the results, highlighting the shared traits of top-performing adversarial pruning methods, as well as common issues. We welcome contributions in our publicly-available benchmark at https://github.com/pralab/AdversarialPruningBenchmark
Authors: Lucas Lange, Maurice-Maximilian Heykeroth, Erhard Rahm
Abstract: Machine Learning (ML) is crucial in many sectors, including computer vision. However, ML models trained on sensitive data face security challenges, as they can be attacked and leak information. Privacy-Preserving Machine Learning (PPML) addresses this by using Differential Privacy (DP) to balance utility and privacy. This study identifies image dataset characteristics that affect the utility and vulnerability of private and non-private Convolutional Neural Network (CNN) models. Through analyzing multiple datasets and privacy budgets, we find that imbalanced datasets increase vulnerability in minority classes, but DP mitigates this issue. Datasets with fewer classes improve both model utility and privacy, while high entropy or low Fisher Discriminant Ratio (FDR) datasets deteriorate the utility-privacy trade-off. These insights offer valuable guidance for practitioners and researchers in estimating and optimizing the utility-privacy trade-off in image datasets, helping to inform data and privacy modifications for better outcomes based on dataset characteristics.
Authors: Haocheng Yuan, Adrien Bousseau, Hao Pan, Chengquan Zhang, Niloy J. Mitra, Changjian Li
Abstract: Differentiable rendering is a key ingredient for inverse rendering and machine learning, as it allows to optimize scene parameters (shape, materials, lighting) to best fit target images. Differentiable rendering requires that each scene parameter relates to pixel values through differentiable operations. While 3D mesh rendering algorithms have been implemented in a differentiable way, these algorithms do not directly extend to Constructive-Solid-Geometry (CSG), a popular parametric representation of shapes, because the underlying boolean operations are typically performed with complex black-box mesh-processing libraries. We present an algorithm, DiffCSG, to render CSG models in a differentiable manner. Our algorithm builds upon CSG rasterization, which displays the result of boolean operations between primitives without explicitly computing the resulting mesh and, as such, bypasses black-box mesh processing. We describe how to implement CSG rasterization within a differentiable rendering pipeline, taking special care to apply antialiasing along primitive intersections to obtain gradients in such critical areas. Our algorithm is simple and fast, can be easily incorporated into modern machine learning setups, and enables a range of applications for computer-aided design, including direct and image-based editing of CSG primitives. Code and data: https://yyyyyhc.github.io/DiffCSG/.
Authors: Chukwudubem Umeano, Stefano Scali, Oleksandr Kyriienko
Abstract: We consider the problem of distinguishing two vectors (visualized as images or barcodes) and learning if they are related to one another. For this, we develop a geometric quantum machine learning (GQML) approach with embedded symmetries that allows for the classification of similar and dissimilar pairs based on global correlations, and enables generalization from just a few samples. Unlike GQML algorithms developed to date, we propose to focus on symmetry-aware measurement adaptation that outperforms unitary parametrizations. We compare GQML for similarity testing against classical deep neural networks and convolutional neural networks with Siamese architectures. We show that quantum networks largely outperform their classical counterparts. We explain this difference in performance by analyzing correlated distributions used for composing our dataset. We relate the similarity testing with problems that showcase a proven maximal separation between the BQP complexity class and the polynomial hierarchy. While the ability to achieve advantage largely depends on how data are loaded, we discuss how similar problems can benefit from quantum machine learning.
Authors: Joel Brogan, Olivera Kotevska, Anibely Torres, Sumit Jha, Mark Adams
Abstract: Signal analysis and classification is fraught with high levels of noise and perturbation. Computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, these methods aren't designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring.
Authors: Liutao Yang, Jiahao Huang, Yingying Fang, Angelica I Aviles-Rivero, Carola-Bibiane Schonlieb, Daoqiang Zhang, Guang Yang
Abstract: Sparse-View Computed Tomography (SVCT) offers low-dose and fast imaging but suffers from severe artifacts. Optimizing the sampling strategy is an essential approach to improving the imaging quality of SVCT. However, current methods typically optimize a universal sampling strategy for all types of scans, overlooking the fact that the optimal strategy may vary depending on the specific scanning task, whether it involves particular body scans (e.g., chest CT scans) or downstream clinical applications (e.g., disease diagnosis). The optimal strategy for one scanning task may not perform as well when applied to other tasks. To address this problem, we propose a deep learning framework that learns task-specific sampling strategies with a multi-task approach to train a unified reconstruction network while tailoring optimal sampling strategies for each individual task. Thus, a task-specific sampling strategy can be applied for each type of scans to improve the quality of SVCT imaging and further assist in performance of downstream clinical usage. Extensive experiments across different scanning types provide validation for the effectiveness of task-specific sampling strategies in enhancing imaging quality. Experiments involving downstream tasks verify the clinical value of learned sampling strategies, as evidenced by notable improvements in downstream task performance. Furthermore, the utilization of a multi-task framework with a shared reconstruction network facilitates deployment on current imaging devices with switchable task-specific modules, and allows for easily integrate new tasks without retraining the entire model.
Authors: Zach Eidex, Mojtaba Safari, Richard L. J. Qiu, David S. Yu, Hui-Kuo Shu, Hui Mao, Xiaofeng Yang
Abstract: Objective: Gadolinium-based contrast agents (GBCAs) are commonly used in MRI scans of patients with gliomas to enhance brain tumor characterization using T1-weighted (T1W) MRI. However, there is growing concern about GBCA toxicity. This study develops a deep-learning framework to generate T1-postcontrast (T1C) from pre-contrast multiparametric MRI. Approach: We propose the tumor-aware vision transformer (TA-ViT) model that predicts high-quality T1C images. The predicted tumor region is significantly improved (P < .001) by conditioning the transformer layers from predicted segmentation maps through adaptive layer norm zero mechanism. The predicted segmentation maps were generated with the multi-parametric residual (MPR) ViT model and transformed into a latent space to produce compressed, feature-rich representations. The TA-ViT model predicted T1C MRI images of 501 glioma cases. Selected patients were split into training (N=400), validation (N=50), and test (N=51) sets. Main Results: Both qualitative and quantitative results demonstrate that the TA-ViT model performs superior against the benchmark MRP-ViT model. Our method produces synthetic T1C MRI with high soft tissue contrast and more accurately reconstructs both the tumor and whole brain volumes. The synthesized T1C images achieved remarkable improvements in both tumor and healthy tissue regions compared to the MRP-ViT model. For healthy tissue and tumor regions, the results were as follows: NMSE: 8.53 +/- 4.61E-4; PSNR: 31.2 +/- 2.2; NCC: 0.908 +/- .041 and NMSE: 1.22 +/- 1.27E-4, PSNR: 41.3 +/- 4.7, and NCC: 0.879 +/- 0.042, respectively. Significance: The proposed method generates synthetic T1C images that closely resemble real T1C images. Future development and application of this approach may enable contrast-agent-free MRI for brain tumor patients, eliminating the risk of GBCA toxicity and simplifying the MRI scan protocol.
Authors: Wenlong Huang, Chen Wang, Yunzhu Li, Ruohan Zhang, Li Fei-Fei
Abstract: Representing robotic manipulation tasks as constraints that associate the robot and the environment is a promising way to encode desired robot behaviors. However, it remains unclear how to formulate the constraints such that they are 1) versatile to diverse tasks, 2) free of manual labeling, and 3) optimizable by off-the-shelf solvers to produce robot actions in real-time. In this work, we introduce Relational Keypoint Constraints (ReKep), a visually-grounded representation for constraints in robotic manipulation. Specifically, ReKep is expressed as Python functions mapping a set of 3D keypoints in the environment to a numerical cost. We demonstrate that by representing a manipulation task as a sequence of Relational Keypoint Constraints, we can employ a hierarchical optimization procedure to solve for robot actions (represented by a sequence of end-effector poses in SE(3)) with a perception-action loop at a real-time frequency. Furthermore, in order to circumvent the need for manual specification of ReKep for each new task, we devise an automated procedure that leverages large vision models and vision-language models to produce ReKep from free-form language instructions and RGB-D observations. We present system implementations on a wheeled single-arm platform and a stationary dual-arm platform that can perform a large variety of manipulation tasks, featuring multi-stage, in-the-wild, bimanual, and reactive behaviors, all without task-specific data or environment models. Website at https://rekep-robot.github.io.
Authors: Bokang Zhang, Yanglin Zhang, Zhikun Zhang, Jinglan Yang, Lingying Huang, Junfeng Wu
Abstract: Neural Radiance Fields (NeRF) have revolutionized 3D computer vision and graphics, facilitating novel view synthesis and influencing sectors like extended reality and e-commerce. However, NeRF's dependence on extensive data collection, including sensitive scene image data, introduces significant privacy risks when users upload this data for model training. To address this concern, we first propose SplitNeRF, a training framework that incorporates split learning (SL) techniques to enable privacy-preserving collaborative model training between clients and servers without sharing local data. Despite its benefits, we identify vulnerabilities in SplitNeRF by developing two attack methods, Surrogate Model Attack and Scene-aided Surrogate Model Attack, which exploit the shared gradient data and a few leaked scene images to reconstruct private scene information. To counter these threats, we introduce $S^2$NeRF, secure SplitNeRF that integrates effective defense mechanisms. By introducing decaying noise related to the gradient norm into the shared gradient information, $S^2$NeRF preserves privacy while maintaining a high utility of the NeRF model. Our extensive evaluations across multiple datasets demonstrate the effectiveness of $S^2$NeRF against privacy breaches, confirming its viability for secure NeRF training in sensitive applications.
Authors: Md Jobayer, Md. Mehedi Hasan Shawon, Tasfin Mahmud, Md. Borhan Uddin Antor, Arshad M. Chowdhury
Abstract: Sleep stages play an essential role in the identification of sleep patterns and the diagnosis of sleep disorders. In this study, we present an automated sleep stage classifier termed the Attentive Dilated Convolutional Neural Network (AttDiCNN), which uses deep learning methodologies to address challenges related to data heterogeneity, computational complexity, and reliable automatic sleep staging. We employed a force-directed layout based on the visibility graph to capture the most significant information from the EEG signals, representing the spatial-temporal features. The proposed network consists of three compositors: the Localized Spatial Feature Extraction Network (LSFE), the Spatio-Temporal-Temporal Long Retention Network (S2TLR), and the Global Averaging Attention Network (G2A). The LSFE is tasked with capturing spatial information from sleep data, the S2TLR is designed to extract the most pertinent information in long-term contexts, and the G2A reduces computational overhead by aggregating information from the LSFE and S2TLR. We evaluated the performance of our model on three comprehensive and publicly accessible datasets, achieving state-of-the-art accuracy of 98.56%, 99.66%, and 99.08% for the EDFX, HMC, and NCH datasets, respectively, yet maintaining a low computational complexity with 1.4 M parameters. The results substantiate that our proposed architecture surpasses existing methodologies in several performance metrics, thus proving its potential as an automated tool in clinical settings.
Authors: Paolo Rabino, Tatiana Tommasi
Abstract: Interacting with real-world cluttered scenes pose several challenges to robotic agents that need to understand complex spatial dependencies among the observed objects to determine optimal pick sequences or efficient object retrieval strategies. Existing solutions typically manage simplified scenarios and focus on predicting pairwise object relationships following an initial object detection phase, but often overlook the global context or struggle with handling redundant and missing object relations. In this work, we present a modern take on visual relational reasoning for grasp planning. We introduce D3GD, a novel testbed that includes bin picking scenes with up to 35 objects from 97 distinct categories. Additionally, we propose D3G, a new end-to-end transformer-based dependency graph generation model that simultaneously detects objects and produces an adjacency matrix representing their spatial relationships. Recognizing the limitations of standard metrics, we employ the Average Precision of Relationships for the first time to evaluate model performance, conducting an extensive experimental benchmark. The obtained results establish our approach as the new state-of-the-art for this task, laying the foundation for future research in robotic manipulation. We publicly release the code and dataset at https://paolotron.github.io/d3g.github.io.
Authors: Guangyin Bao, Duoqian Miao
Abstract: Exploring the mysteries of the human brain is a long-term research topic in neuroscience. With the help of deep learning, decoding visual information from human brain activity fMRI has achieved promising performance. However, these decoding models require centralized storage of fMRI data to conduct training, leading to potential privacy security issues. In this paper, we focus on privacy preservation in multi-individual brain visual decoding. To this end, we introduce a novel framework called FedMinds, which utilizes federated learning to protect individuals' privacy during model training. In addition, we deploy individual adapters for each subject, thus allowing personalized visual decoding. We conduct experiments on the authoritative NSD datasets to evaluate the performance of the proposed framework. The results demonstrate that our framework achieves high-precision visual decoding along with privacy protection.
Authors: Yihao Luo, Dario Sesia, Fanwen Wang, Yinzhe Wu, Wenhao Ding, Jiahao Huang, Fadong Shi Anoop Shah, Amit Kaural, Jamil Mayet, Guang Yang, ChoonHwai Yap
Abstract: Mesh reconstruction of the cardiac anatomy from medical images is useful for shape and motion measurements and biophysics simulations to facilitate the assessment of cardiac function and health. However, 3D medical images are often acquired as 2D slices that are sparsely sampled and noisy, and mesh reconstruction on such data is a challenging task. Traditional voxel-based approaches rely on pre- and post-processing that compromises image fidelity, while mesh-level deep learning approaches require mesh annotations that are difficult to get. Therefore, direct cross-domain supervision from 2D images to meshes is a key technique for advancing 3D learning in medical imaging, but it has not been well-developed. While there have been attempts to approximate the optimized meshes' slicing, few existing methods directly use 2D slices to supervise mesh reconstruction in a differentiable manner. Here, we propose a novel explicit differentiable voxelization and slicing (DVS) algorithm that allows gradient backpropagation to a mesh from its slices, facilitating refined mesh optimization directly supervised by the losses defined on 2D images. Further, we propose an innovative framework for extracting patient-specific left ventricle (LV) meshes from medical images by coupling DVS with a graph harmonic deformation (GHD) mesh morphing descriptor of cardiac shape that naturally preserves mesh quality and smoothness during optimization. Experimental results demonstrate that our method achieves state-of-the-art performance in cardiac mesh reconstruction tasks from CT and MRI, with an overall Dice score of 90% on multi-datasets, outperforming existing approaches. The proposed method can further quantify clinically useful parameters such as ejection fraction and global myocardial strains, closely matching the ground truth and surpassing the traditional voxel-based approach in sparse images.
Authors: Mazeyu Ji, Ri-Zhao Qiu, Xueyan Zou, Xiaolong Wang
Abstract: The ability for robots to perform efficient and zero-shot grasping of object parts is crucial for practical applications and is becoming prevalent with recent advances in Vision-Language Models (VLMs). To bridge the 2D-to-3D gap for representations to support such a capability, existing methods rely on neural fields (NeRFs) via differentiable rendering or point-based projection methods. However, we demonstrate that NeRFs are inappropriate for scene changes due to their implicitness and point-based methods are inaccurate for part localization without rendering-based optimization. To amend these issues, we propose GraspSplats. Using depth supervision and a novel reference feature computation method, GraspSplats generates high-quality scene representations in under 60 seconds. We further validate the advantages of Gaussian-based representation by showing that the explicit and optimized geometry in GraspSplats is sufficient to natively support (1) real-time grasp sampling and (2) dynamic and articulated object manipulation with point trackers. With extensive experiments on a Franka robot, we demonstrate that GraspSplats significantly outperforms existing methods under diverse task settings. In particular, GraspSplats outperforms NeRF-based methods like F3RM and LERF-TOGO, and 2D detection methods.
Authors: Saeed Anwar, Muhammad Tahir, Chongyi Li, Ajmal Mian, Fahad Shahbaz Khan, Abdul Wahab Muzaffar
Abstract: Image colorization estimates RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality. Over the last decade, deep learning techniques for image colorization have significantly progressed, necessitating a systematic survey and benchmarking of these techniques. This article presents a comprehensive survey of recent state-of-the-art deep learning-based image colorization techniques, describing their fundamental block architectures, inputs, optimizers, loss functions, training protocols, training data, etc. It categorizes the existing colorization techniques into seven classes and discusses important factors governing their performance, such as benchmark datasets and evaluation metrics. We highlight the limitations of existing datasets and introduce a new dataset specific to colorization. We perform an extensive experimental evaluation of existing image colorization methods using both existing datasets and our proposed one. Finally, we discuss the limitations of existing methods and recommend possible solutions and future research directions for this rapidly evolving topic of deep image colorization. The dataset and codes for evaluation are publicly available at https://github.com/saeed-anwar/ColorSurvey.
Authors: Eslam Mohamed, Abdelrahman Shaker, Ahmad El-Sallab, Mayada Hadhoud
Abstract: Instance segmentation has gained recently huge attention in various computer vision applications. It aims at providing different IDs to different object of the scene, even if they belong to the same class. This is useful in various scenarios, especially in occlusions. Instance segmentation is usually performed as a two-stage pipeline. First, an object is detected, then semantic segmentation within the detected box area. This process involves costly up-sampling, especially for the segmentation part. Moreover, for some applications, such as LiDAR point clouds and aerial object detection, it is often required to predict oriented boxes, which add extra complexity to the two-stage pipeline. In this paper, we propose Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation. The proposed model is inspired by the YOLO one-shot object detector, with the box regression loss is replaced with polynomial regression in the localization head. This modification enables us to skip the segmentation up-sampling decoder altogether and produces the instance segmentation contour from the polynomial output coefficients. In addition, this architecture is a natural fit for oriented objects. We evaluate our model on three datasets, namely, Carnva, Cityscapes and Airbus. The results show our model achieves competitive accuracy in terms of mAP with significant improvement in speed by 2x on GTX-1080 GPU.
Authors: Zhijian Liu, Haotian Tang, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela Rus, Song Han
Abstract: Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view (BEV) representation space, which nicely preserves both geometric and semantic information. To achieve this, we diagnose and lift key efficiency bottlenecks in the view transformation with optimized BEV pooling, reducing latency by more than 40x. BEVFusion is fundamentally task-agnostic and seamlessly supports different 3D perception tasks with almost no architectural changes. It establishes the new state of the art on nuScenes, achieving 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower computation cost. Code to reproduce our results is available at https://github.com/mit-han-lab/bevfusion.
Authors: Anique Akhtar, Zhu Li, Geert Van der Auwera
Abstract: Efficient point cloud compression is essential for applications like virtual and mixed reality, autonomous driving, and cultural heritage. This paper proposes a deep learning-based inter-frame encoding scheme for dynamic point cloud geometry compression. We propose a lossy geometry compression scheme that predicts the latent representation of the current frame using the previous frame by employing a novel feature space inter-prediction network. The proposed network utilizes sparse convolutions with hierarchical multiscale 3D feature learning to encode the current frame using the previous frame. The proposed method introduces a novel predictor network for motion compensation in the feature domain to map the latent representation of the previous frame to the coordinates of the current frame to predict the current frame's feature embedding. The framework transmits the residual of the predicted features and the actual features by compressing them using a learned probabilistic factorized entropy model. At the receiver, the decoder hierarchically reconstructs the current frame by progressively rescaling the feature embedding. The proposed framework is compared to the state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based Point Cloud Compression (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG). The proposed method achieves more than 88% BD-Rate (Bjontegaard Delta Rate) reduction against G-PCCv20 Octree, more than 56% BD-Rate savings against G-PCCv20 Trisoup, more than 62% BD-Rate reduction against V-PCC intra-frame encoding mode, and more than 52% BD-Rate savings against V-PCC P-frame-based inter-frame encoding mode using HEVC. These significant performance gains are cross-checked and verified in the MPEG working group.
Authors: Jichao Zhang, Aliaksandr Siarohin, Yahui Liu, Hao Tang, Nicu Sebe, Wei Wang
Abstract: Generative Neural Radiance Fields (GNeRF)-based 3D-aware GANs have showcased remarkable prowess in crafting high-fidelity images while upholding robust 3D consistency, particularly face generation. However, specific existing models prioritize view consistency over disentanglement, leading to constrained semantic or attribute control during the generation process. While many methods have explored incorporating semantic masks or leveraging 3D Morphable Models (3DMM) priors to imbue models with semantic control, these methods often demand training from scratch, entailing significant computational overhead. In this paper, we propose a novel approach: a conditional GNeRF model that integrates specific attribute labels as input, thus amplifying the controllability and disentanglement capabilities of 3D-aware generative models. Our approach builds upon a pre-trained 3D-aware face model, and we introduce a Training as Init and Optimizing for Tuning (TRIOT) method to train a conditional normalized flow module to enable the facial attribute editing, then optimize the latent vector to improve attribute-editing precision further. Our extensive experiments substantiate the efficacy of our model, showcasing its ability to generate high-quality edits with enhanced view consistency while safeguarding non-target regions. The code for our model is publicly available at https://github.com/zhangqianhui/TT-GNeRF.
Authors: Weijie Wang, Nicu Sebe, Bruno Lepri
Abstract: Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation. To simplify the learning paradigm, most previous methods convert ambiguous annotation results into precise one-hot annotations and train FER models in an end-to-end supervised manner. In this paper, we rethink the existing training paradigm and propose that it is better to use weakly supervised strategies to train FER models with original ambiguous annotation.
Authors: Jochem Loedeman, Maarten C. Stol, Tengda Han, Yuki M. Asano
Abstract: With the introduction of the transformer architecture in computer vision, increasing model scale has been demonstrated as a clear path to achieving performance and robustness gains. However, with model parameter counts reaching the billions, classical finetuning approaches are becoming increasingly limiting and even unfeasible when models become hosted as inference APIs, as in NLP. Visual input-prompt learning, an adaptation technique in which additional inputs in visual (RGB) space are learned, has emerged as a potential solution for adapting frozen and cloud-hosted models, requiring neither access to the forward pass, nor post-processing. Yet so far, these constraints have deteriorated adaptation performances significantly. To this end, we propose the Prompt Generation Network (PGN) that generates a different prompt for every data point, which is then used to adapt a frozen pretrained vision model to a target task. We show that the PGN effectively adapts pretrained models to various new datasets: It surpasses previous methods by a large margin on 12/12 datasets and even outperforms full-finetuning on 5/12, while requiring 100x fewer parameters. Lastly, we introduce the "prompt inversion" trick, with which PGNs can be efficiently trained in a latent space but deployed in RGB input space for inference.
Authors: Xiangtai Li, Shilin Xu, Yibo Yang, Haobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Ming-Hsuan Yang, Dacheng Tao
Abstract: Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions without shared computation and task association. We aim to unify these tasks at the architectural level, designing the first end-to-end unified framework, Panoptic-PartFormer. Moreover, we find the previous metric PartPQ biases to PQ. To handle both issues, we first design a meta-architecture that decouples part features and things/stuff features, respectively. We model things, stuff, and parts as object queries and directly learn to optimize all three forms of prediction as a unified mask prediction and classification problem. We term our model as Panoptic-PartFormer. Second, we propose a new metric Part-Whole Quality (PWQ), better to measure this task from pixel-region and part-whole perspectives. It also decouples the errors for part segmentation and panoptic segmentation. Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further. We design a new part-whole interaction method using masked cross attention. Finally, extensive ablation studies and analysis demonstrate the effectiveness of both Panoptic-PartFormer and Panoptic-PartFormer++. Compared with previous Panoptic-PartFormer, our Panoptic-PartFormer++ achieves 2% PartPQ and 3% PWQ improvements on the Cityscapes PPS dataset and 5% PartPQ on the Pascal Context PPS dataset. On both datasets, Panoptic-PartFormer++ achieves new state-of-the-art results. Our models can serve as a strong baseline and aid future research in PPS. The source code and trained models will be available at~\url{https://github.com/lxtGH/Panoptic-PartFormer}.
Authors: Christopher K. I. Williams
Abstract: This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the contents of the image(s) are causally explained in terms of models of instantiated objects, each with their own type, shape, appearance and pose, along with global variables like scene lighting and camera parameters. This approach also requires scene models which account for the co-occurrences and inter-relationships of objects in a scene. The SGM approach has the merits that it is compositional and generative, which lead to interpretability and editability. \\\\ To pursue the SGM agenda, we need models for objects and scenes, and approaches to carry out inference. We first review models for objects, which include ``things'' (object categories that have a well defined shape), and ``stuff'' (categories which have amorphous spatial extent). We then move on to review \emph{scene models} which describe the inter-relationships of objects. Perhaps the most challenging problem for SGMs is \emph{inference} of the objects, lighting and camera parameters, and scene inter-relationships from input consisting of a single or multiple images. We conclude with a discussion of issues that need addressing to advance the SGM agenda.
Authors: Bochen Xie, Yongjian Deng, Zhanpeng Shao, Qingsong Xu, Youfu Li
Abstract: Event cameras are neuromorphic vision sensors that record a scene as sparse and asynchronous event streams. Most event-based methods project events into dense frames and process them using conventional vision models, resulting in high computational complexity. A recent trend is to develop point-based networks that achieve efficient event processing by learning sparse representations. However, existing works may lack robust local information aggregators and effective feature interaction operations, thus limiting their modeling capabilities. To this end, we propose an attention-aware model named Event Voxel Set Transformer (EVSTr) for efficient spatiotemporal representation learning on event streams. It first converts the event stream into voxel sets and then hierarchically aggregates voxel features to obtain robust representations. The core of EVSTr is an event voxel transformer encoder that consists of two well-designed components, including the Multi-Scale Neighbor Embedding Layer (MNEL) for local information aggregation and the Voxel Self-Attention Layer (VSAL) for global feature interaction. Enabling the network to incorporate a long-range temporal structure, we introduce a segment modeling strategy (S$^{2}$TM) to learn motion patterns from a sequence of segmented voxel sets. The proposed model is evaluated on two recognition tasks, including object classification and action recognition. To provide a convincing model evaluation, we present a new event-based action recognition dataset (NeuroHAR) recorded in challenging scenarios. Comprehensive experiments show that EVSTr achieves state-of-the-art performance while maintaining low model complexity.
Authors: Jingyao Li, Pengguang Chen, Shengju Qian, Shu Liu, Jiaya Jia
Abstract: Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify input pixels from unseen classes, leading to confusion between novel classes and semantically similar ones. In this work, we propose a novel approach, TagCLIP (Trusty-aware guided CLIP), to address this issue. We disentangle the ill-posed optimization problem into two parallel processes: semantic matching performed individually and reliability judgment for improving discrimination ability. Building on the idea of special tokens in language modeling representing sentence-level embeddings, we introduce a trusty token that enables distinguishing novel classes from known ones in prediction. To evaluate our approach, we conduct experiments on two benchmark datasets, PASCAL VOC 2012, COCO-Stuff 164K and PASCAL Context. Our results show that TagCLIP improves the Intersection over Union (IoU) of unseen classes by 7.4%, 1.7% and 2.1%, respectively, with negligible overheads. The code is available at https://github.com/dvlab-research/TagCLIP.
Authors: Sourav Das, Guglielmo Camporese, Shaokang Cheng, Lamberto Ballan
Abstract: Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics. One fundamental difficulty stands in the evolution of the trajectory that becomes more and more uncertain and unpredictable as the time horizon grows, subsequently increasing the complexity of the problem. To overcome this issue, in this paper, we propose Di-Long, a new method that employs the distillation of a short-term trajectory model forecaster that guides a student network for long-term trajectory prediction during the training process. Given a total sequence length that comprehends the allowed observation for the student network and the complementary target sequence, we let the student and the teacher solve two different related tasks defined over the same full trajectory: the student observes a short sequence and predicts a long trajectory, whereas the teacher observes a longer sequence and predicts the remaining short target trajectory. The teacher's task is less uncertain, and we use its accurate predictions to guide the student through our knowledge distillation framework, reducing long-term future uncertainty. Our experiments show that our proposed Di-Long method is effective for long-term forecasting and achieves state-of-the-art performance on the Intersection Drone Dataset (inD) and the Stanford Drone Dataset (SDD).
Authors: Xu Zhang, Zhedong Zheng, Linchao Zhu, Yi Yang
Abstract: Composed image retrieval extends content-based image retrieval systems by enabling users to search using reference images and captions that describe their intention. Despite great progress in developing image-text compositors to extract discriminative visual-linguistic features, we identify a hitherto overlooked issue, triplet ambiguity, which impedes robust feature extraction. Triplet ambiguity refers to a type of semantic ambiguity that arises between the reference image, the relative caption, and the target image. It is mainly due to the limited representation of the annotated text, resulting in many noisy triplets where multiple visually dissimilar candidate images can be matched to an identical reference pair (i.e., a reference image + a relative caption). To address this challenge, we propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings, fostering complementary feature extraction and mitigating dependence on any single, potentially biased compositor; (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions to promote consensual outputs. During evaluation, the decisions of the four compositors are combined through a weighting scheme, enhancing overall agreement. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its competitiveness in addressing the fundamental limitations of existing methods.
Authors: Yonglin Li, Jing Zhang, Xiao Teng, Long Lan, Xinwang Liu
Abstract: The Segment Anything Model (SAM) has gained significant attention for its impressive performance in image segmentation. However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive prompts and a limited understanding of different modalities, such as language and vision. This paper presents the RefSAM model, which explores the potential of SAM for RVOS by incorporating multi-view information from diverse modalities and successive frames at different timestamps in an online manner. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-Modal MLP that projects the text embedding of the referring expression into sparse and dense embeddings, serving as user-interactive prompts. Additionally, we have introduced the hierarchical dense attention module to fuse hierarchical visual semantic information with sparse embeddings to obtain fine-grained dense embeddings, and an implicit tracking module to generate a tracking token and provide historical information for the mask decoder. Furthermore, we employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively. Through comprehensive ablation studies, we demonstrate our model's practical and effective design choices. Extensive experiments conducted on Refer-Youtube-VOS, Ref-DAVIS17, and three referring image segmentation datasets validate the superiority and effectiveness of our RefSAM model over existing methods.
Authors: Ziwei Wang, Timothy Molloy, Pieter van Goor, Robert Mahony
Abstract: Event-based cameras are popular for tracking fast-moving objects due to their high temporal resolution, low latency, and high dynamic range. In this paper, we propose a novel algorithm for tracking event blobs using raw events asynchronously in real time. We introduce the concept of an event blob as a spatio-temporal likelihood of event occurrence where the conditional spatial likelihood is blob-like. Many real-world objects such as car headlights or any quickly moving foreground objects generate event blob data. The proposed algorithm uses a nearest neighbour classifier with a dynamic threshold criteria for data association coupled with an extended Kalman filter to track the event blob state. Our algorithm achieves highly accurate blob tracking, velocity estimation, and shape estimation even under challenging lighting conditions and high-speed motions (> 11000 pixels/s). The microsecond time resolution achieved means that the filter output can be used to derive secondary information such as time-to-contact or range estimation, that will enable applications to real-world problems such as collision avoidance in autonomous driving.
Authors: Shreyas Vaidya, Arvind Kumar Sharma, Prajwal Gatti, Anand Mishra
Abstract: In this work, we study the task of ``visually'' translating scene text from a source language (e.g., Hindi) to a target language (e.g., English). Visual translation involves not just the recognition and translation of scene text but also the generation of the translated image that preserves visual features of the source scene text, such as font, size, and background. There are several challenges associated with this task, such as translation with limited context, deciding between translation and transliteration, accommodating varying text lengths within fixed spatial boundaries, and preserving the font and background styles of the source scene text in the target language. To address this problem, we make the following contributions: (i) We study visual translation as a standalone problem for the first time in the literature. (ii) We present a cascaded framework for visual translation that combines state-of-the-art modules for scene text recognition, machine translation, and scene text synthesis as a baseline for the task. (iii) We propose a set of task-specific design enhancements to design a variant of the baseline to obtain performance improvements. (iv) Currently, the existing related literature lacks any comprehensive performance evaluation for this novel task. To fill this gap, we introduce several automatic and user-assisted evaluation metrics designed explicitly for evaluating visual translation. Further, we evaluate presented baselines for translating scene text between Hindi and English. Our experiments demonstrate that although we can effectively perform visual translation over a large collection of scene text images, the presented baseline only partially addresses challenges posed by visual translation tasks. We firmly believe that this new task and the limitations of existing models, as reported in this paper, should encourage further research in visual translation.
Authors: Weijian Huang, Cheng Li, Hong-Yu Zhou, Hao Yang, Jiarun Liu, Yong Liang, Hairong Zheng, Shaoting Zhang, Shanshan Wang
Abstract: Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained knowledge understanding in computer-aided diagnosis and the capability of utilizing very limited or even no task-specific labeled data in real-world clinical applications. In this study, we present MaCo, a masked contrastive chest X-ray foundation model that tackles these challenges. MaCo explores masked contrastive learning to simultaneously achieve fine-grained image understanding and zero-shot learning for a variety of medical imaging tasks. It designs a correlation weighting mechanism to adjust the correlation between masked chest X-ray image patches and their corresponding reports, thereby enhancing the model's representation learning capabilities. To evaluate the performance of MaCo, we conducted extensive experiments using 6 well-known open-source X-ray datasets. The experimental results demonstrate the superiority of MaCo over 10 state-of-the-art approaches across tasks such as classification, segmentation, detection, and phrase grounding. These findings highlight the significant potential of MaCo in advancing a wide range of medical image analysis tasks.
Authors: Chi-en Amy Tai, Matthew Keller, Saeejith Nair, Yuhao Chen, Yifan Wu, Olivia Markham, Krish Parmar, Pengcheng Xi, Heather Keller, Sharon Kirkpatrick, Alexander Wong
Abstract: Accurate dietary intake estimation is critical for informing policies and programs to support healthy eating, as malnutrition has been directly linked to decreased quality of life. However self-reporting methods such as food diaries suffer from substantial bias. Other conventional dietary assessment techniques and emerging alternative approaches such as mobile applications incur high time costs and may necessitate trained personnel. Recent work has focused on using computer vision and machine learning to automatically estimate dietary intake from food images, but the lack of comprehensive datasets with diverse viewpoints, modalities and food annotations hinders the accuracy and realism of such methods. To address this limitation, we introduce NutritionVerse-Synth, the first large-scale dataset of 84,984 photorealistic synthetic 2D food images with associated dietary information and multimodal annotations (including depth images, instance masks, and semantic masks). Additionally, we collect a real image dataset, NutritionVerse-Real, containing 889 images of 251 dishes to evaluate realism. Leveraging these novel datasets, we develop and benchmark NutritionVerse, an empirical study of various dietary intake estimation approaches, including indirect segmentation-based and direct prediction networks. We further fine-tune models pretrained on synthetic data with real images to provide insights into the fusion of synthetic and real data. Finally, we release both datasets (NutritionVerse-Synth, NutritionVerse-Real) on https://www.kaggle.com/nutritionverse/datasets as part of an open initiative to accelerate machine learning for dietary sensing.
Authors: Zeqi Xiao, Tai Wang, Jingbo Wang, Jinkun Cao, Wenwei Zhang, Bo Dai, Dahua Lin, Jiangmiao Pang
Abstract: Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. Despite advancements in motion quality and physical plausibility, two pivotal factors, versatile interaction control and the development of a user-friendly interface, require further exploration before the practical application of HSI. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands. This framework is built upon the definition of interaction as Chain of Contacts (CoC): steps of human joint-object part pairs, which is inspired by the strong correlation between interaction types and human-object contact regions. Based on the definition, UniHSI constitutes a Large Language Model (LLM) Planner to translate language prompts into task plans in the form of CoC, and a Unified Controller that turns CoC into uniform task execution. To facilitate training and evaluation, we collect a new dataset named ScenePlan that encompasses thousands of task plans generated by LLMs based on diverse scenarios. Comprehensive experiments demonstrate the effectiveness of our framework in versatile task execution and generalizability to real scanned scenes. The project page is at https://github.com/OpenRobotLab/UniHSI .
Authors: Karim Radouane, Julien Lagarde, Sylvie Ranwez, Andon Tchechmedjiev
Abstract: Diverse and extensive work has recently been conducted on text-conditioned human motion generation. However, progress in the reverse direction, motion captioning, has seen less comparable advancement. In this paper, we introduce a novel architecture design that enhances text generation quality by emphasizing interpretability through spatio-temporal and adaptive attention mechanisms. To encourage human-like reasoning, we propose methods for guiding attention during training, emphasizing relevant skeleton areas over time and distinguishing motion-related words. We discuss and quantify our model's interpretability using relevant histograms and density distributions. Furthermore, we leverage interpretability to derive fine-grained information about human motion, including action localization, body part identification, and the distinction of motion-related words. Finally, we discuss the transferability of our approaches to other tasks. Our experiments demonstrate that attention guidance leads to interpretable captioning while enhancing performance compared to higher parameter-count, non-interpretable state-of-the-art systems. The code is available at: https://github.com/rd20karim/M2T-Interpretable.
Authors: Jun Wu, Sicheng Li, Sihui Ji, Yifei Yang, Yue Wang, Rong Xiong, Yiyi Liao
Abstract: Recovering 3D geometry and textures of individual objects is crucial for many robotics applications, such as manipulation, pose estimation, and autonomous driving. However, decomposing a target object from a complex background is challenging. Most existing approaches rely on costly manual labels to acquire object instance perception. Recent advancements in 2D self-supervised learning offer new prospects for identifying objects of interest, yet leveraging such noisy 2D features for clean decomposition remains difficult. In this paper, we propose a Decomposed Object Reconstruction (DORec) network based on neural implicit representations. Our key idea is to use 2D self-supervised features to create two levels of masks for supervision: a binary mask for foreground regions and a K-cluster mask for semantically similar regions. These complementary masks result in robust decomposition. Experimental results on different datasets show DORec's superiority in segmenting and reconstructing diverse foreground objects from varied backgrounds enabling downstream tasks such as pose estimation.
Authors: Andrea Boscolo Camiletto, Alfredo Bochicchio, Alexander Liniger, Dengxin Dai, Abel Gawel
Abstract: Efficient relocalization is essential for intelligent vehicles when GPS reception is insufficient or sensor-based localization fails. Recent advances in Bird's-Eye-View (BEV) segmentation allow for accurate estimation of local scene appearance and in turn, can benefit the relocalization of the vehicle. However, one downside of BEV methods is the heavy computation required to leverage the geometric constraints. This paper presents U-BEV, a U-Net inspired architecture that extends the current state-of-the-art by allowing the BEV to reason about the scene on multiple height layers before flattening the BEV features. We show that this extension boosts the performance of the U-BEV by up to 4.11 IoU. Additionally, we combine the encoded neural BEV with a differentiable template matcher to perform relocalization on neural SD-map data. The model is fully end-to-end trainable and outperforms transformer-based BEV methods of similar computational complexity by 1.7 to 2.8 mIoU and BEV-based relocalization by over 26% Recall Accuracy on the nuScenes dataset.
Authors: Junwei You, Ying Chen, Zhuoyu Jiang, Zhangchi Liu, Zilin Huang, Yifeng Ding, Bin Ran
Abstract: Effective classification of autonomous vehicle (AV) driving behavior emerges as a critical area for diagnosing AV operation faults, enhancing autonomous driving algorithms, and reducing accident rates. This paper presents the Gramian Angular Field Vision Transformer (GAF-ViT) model, designed to analyze AV driving behavior. The proposed GAF-ViT model consists of three key components: GAF Transformer Module, Channel Attention Module, and Multi-Channel ViT Module. These modules collectively convert representative sequences of multivariate behavior into multi-channel images and employ image recognition techniques for behavior classification. A channel attention mechanism is applied to multi-channel images to discern the impact of various driving behavior features. Experimental evaluation on the Waymo Open Dataset of trajectories demonstrates that the proposed model achieves state-of-the-art performance. Furthermore, an ablation study effectively substantiates the efficacy of individual modules within the model.
Authors: Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Josh Susskind, Navdeep Jaitly
Abstract: Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges. Existing methods often resort to training cascaded models in pixel space or using a downsampled latent space of a separately trained auto-encoder. In this paper, we introduce Matryoshka Diffusion Models(MDM), an end-to-end framework for high-resolution image and video synthesis. We propose a diffusion process that denoises inputs at multiple resolutions jointly and uses a NestedUNet architecture where features and parameters for small-scale inputs are nested within those of large scales. In addition, MDM enables a progressive training schedule from lower to higher resolutions, which leads to significant improvements in optimization for high-resolution generation. We demonstrate the effectiveness of our approach on various benchmarks, including class-conditioned image generation, high-resolution text-to-image, and text-to-video applications. Remarkably, we can train a single pixel-space model at resolutions of up to 1024x1024 pixels, demonstrating strong zero-shot generalization using the CC12M dataset, which contains only 12 million images. Our code is released at https://github.com/apple/ml-mdm
Authors: Dan Song, Xuanpu Zhang, Juan Zhou, Weizhi Nie, Ruofeng Tong, Mohan Kankanhalli, An-An Liu
Abstract: Image-based virtual try-on aims to synthesize a naturally dressed person image with a clothing image, which revolutionizes online shopping and inspires related topics within image generation, showing both research significance and commercial potential. However, there is a gap between current research progress and commercial applications and an absence of comprehensive overview of this field to accelerate the development.In this survey, we provide a comprehensive analysis of the state-of-the-art techniques and methodologies in aspects of pipeline architecture, person representation and key modules such as try-on indication, clothing warping and try-on stage. We additionally apply CLIP to assess the semantic alignment of try-on results, and evaluate representative methods with uniformly implemented evaluation metrics on the same dataset.In addition to quantitative and qualitative evaluation of current open-source methods, unresolved issues are highlighted and future research directions are prospected to identify key trends and inspire further exploration. The uniformly implemented evaluation metrics, dataset and collected methods will be made public available at https://github.com/little-misfit/Survey-Of-Virtual-Try-On.
URLs: https://github.com/little-misfit/Survey-Of-Virtual-Try-On.
Authors: Wei Yao, Hongwen Zhang, Yunlian Sun, Jinhui Tang
Abstract: Previous methods for 3D human motion recovery from monocular images often fall short due to reliance on camera coordinates, leading to inaccuracies in real-world applications where complex shooting conditions are prevalent. The limited availability and diversity of focal length labels further exacerbate misalignment issues in reconstructed 3D human bodies. To address these challenges, we introduce W-HMR, a weak-supervised calibration method that predicts "reasonable" focal lengths based on body distortion information, eliminating the need for precise focal length labels. Our approach enhances 2D supervision precision and recovery accuracy. Additionally, we present the OrientCorrect module, which corrects body orientation for plausible reconstructions in world space, avoiding the error accumulation associated with inaccurate camera rotation predictions. Our contributions include a novel weak-supervised camera calibration technique, an effective orientation correction module, and a decoupling strategy that significantly improves the generalizability and accuracy of human motion recovery in both camera and world coordinates. The robustness of W-HMR is validated through extensive experiments on various datasets, showcasing its superiority over existing methods. Codes and demos have been released on the project page https://yw0208.github.io/w-hmr/.
Authors: Dongho Lee, Jongseo Lee, Jinwoo Choi
Abstract: Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input. Our proposed bottleneck cross-attention mechanism enables the spatial and temporal expert models to exchange information and make synergistic predictions, leading to improved performance. We validate the proposed method with extensive experiments on public benchmarks with different characteristics: EPIC-KITCHENS-100, Something-Something-V2, and Kinetics-400. Our method consistently shows favorable performance across these datasets, while the performance of existing methods fluctuates depending on the dataset characteristics.
Authors: Yuntao Shou, Wei Ai, Tao Meng, Nan Yin, Keqin Li
Abstract: The age estimation task aims to predict the age of an individual by analyzing facial features in an image. The development of age estimation can improve the efficiency and accuracy of various applications (e.g., age verification and secure access control, etc.). In recent years, contrastive language-image pre-training (CLIP) has been widely used in various multimodal tasks and has made some progress in the field of age estimation. However, existing CLIP-based age estimation methods require high memory usage (quadratic complexity) when globally modeling images, and lack an error feedback mechanism to prompt the model about the quality of age prediction results. To tackle the above issues, we propose a novel CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation (CILF-CIAE). Specifically, we first introduce the CLIP model to extract image features and text semantic information respectively, and map them into a highly semantically aligned high-dimensional feature space. Next, we designed a new Transformer architecture (i.e., FourierFormer) to achieve channel evolution and spatial interaction of images, and to fuse image and text semantic information. Compared with the quadratic complexity of the attention mechanism, the proposed Fourierformer is of linear log complexity. To further narrow the semantic gap between image and text features, we utilize an efficient contrastive multimodal learning module that supervises the multimodal fusion process of FourierFormer through contrastive loss for image-text matching, thereby improving the interaction effect between different modalities. Finally, we introduce reversible age estimation, which uses end-to-end error feedback to reduce the error rate of age predictions. Through extensive experiments on multiple data sets, CILF-CIAE has achieved better age prediction results.
Authors: Yuntao Shou, Wei Ai, Tao Meng, Nan Yin
Abstract: Remote sensing segmentation has a wide range of applications in environmental protection, and urban change detection, etc. Despite the success of deep learning-based remote sensing segmentation methods (e.g., CNN and Transformer), they are not flexible enough to model irregular objects. In addition, existing graph contrastive learning methods usually adopt the way of maximizing mutual information to keep the node representations consistent between different graph views, which may cause the model to learn task-independent redundant information. To tackle the above problems, this paper treats images as graph structures and introduces a simple contrastive vision GNN (SC-ViG) architecture for remote sensing segmentation. Specifically, we construct a node-masked and edge-masked graph view to obtain an optimal graph structure representation, which can adaptively learn whether to mask nodes and edges. Furthermore, this paper innovatively introduces information bottleneck theory into graph contrastive learning to maximize task-related information while minimizing task-independent redundant information. Finally, we replace the convolutional module in UNet with the SC-ViG module to complete the segmentation and classification tasks of remote sensing images. Extensive experiments on publicly available real datasets demonstrate that our method outperforms state-of-the-art remote sensing image segmentation methods.
Authors: Junhyuk So, Jungwon Lee, Eunhyeok Park
Abstract: The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted to address this issue by reducing the number of score function evaluations (NFE) using advanced ODE solvers without fine-tuning, the decreased number of denoising iterations misses the opportunity to update fine details, resulting in noticeable quality degradation. In our work, we introduce an advanced acceleration technique that leverages the temporal redundancy inherent in diffusion models. Reusing feature maps with high temporal similarity opens up a new opportunity to save computation resources without compromising output quality. To realize the practical benefits of this intuition, we conduct an extensive analysis and propose a novel method, FRDiff. FRDiff is designed to harness the advantages of both reduced NFE and feature reuse, achieving a Pareto frontier that balances fidelity and latency trade-offs in various generative tasks.
Authors: Qian Qiao, Yu Xie, Ziyin Zeng, Fanzhang Li
Abstract: Few-shot image classification aims to classify images from unseen novel classes with few samples. Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features. However, most existing methods solely rely on either employing all local descriptors or directly utilizing partial descriptors, potentially resulting in the loss of crucial information. Moreover, these methods primarily emphasize the selection of query descriptors while overlooking support descriptors. In this paper, we propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net), which exhibits the capacity for adaptive selection of task-aware support descriptors and query descriptors. Specifically, we compare the similarity of each local support descriptor with other local support descriptors to obtain the optimal support descriptor subset and then compare the query descriptors with the optimal support subset to obtain discriminative query descriptors. Extensive experiments demonstrate that our TALDS-Net outperforms state-of-the-art methods on both general and fine-grained datasets.
Authors: Zhaochen Li, Fengheng Li, Wei Feng, Honghe Zhu, Yaoyu Li, Zheng Zhang, Jingjing Lv, Junjie Shen, Zhangang Lin, Jingping Shao, Zhenglu Yang
Abstract: Product poster generation significantly optimizes design efficiency and reduces production costs. Prevailing methods predominantly rely on image-inpainting methods to generate clean background images for given products. Subsequently, poster layout generation methods are employed to produce corresponding layout results. However, the background images may not be suitable for accommodating textual content due to their complexity, and the fixed location of products limits the diversity of layout results. To alleviate these issues, we propose a novel product poster generation framework based on diffusion models named P\&R. The P\&R draws inspiration from the workflow of designers in creating posters, which consists of two stages: Planning and Rendering. At the planning stage, we propose a PlanNet to generate the layout of the product and other visual components considering both the appearance features of the product and semantic features of the text, which improves the diversity and rationality of the layouts. At the rendering stage, we propose a RenderNet to generate the background for the product while considering the generated layout, where a spatial fusion module is introduced to fuse the layout of different visual components. To foster the advancement of this field, we propose the first product poster generation dataset PPG30k, comprising 30k exquisite product poster images along with comprehensive image and text annotations. Our method outperforms the state-of-the-art product poster generation methods on PPG30k. The PPG30k will be released soon.
Authors: Rub\`en Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, Joonas J\"alk\"o, Vincent Poulain D'Andecy, Aurelie Joseph, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
Abstract: Document Visual Question Answering (DocVQA) has quickly grown into a central task of document understanding. But despite the fact that documents contain sensitive or copyrighted information, none of the current DocVQA methods offers strong privacy guarantees. In this work, we explore privacy in the domain of DocVQA for the first time, highlighting privacy issues in state of the art multi-modal LLM models used for DocVQA, and explore possible solutions. Specifically, we focus on invoice processing as a realistic document understanding scenario, and propose a large scale DocVQA dataset comprising invoice documents and associated questions and answers. We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the data of the invoice provider is the sensitive information to be protected. We demonstrate that non-private models tend to memorise, a behaviour that can lead to exposing private information. We then evaluate baseline training schemes employing federated learning and differential privacy in this multi-modal scenario, where the sensitive information might be exposed through either or both of the two input modalities: vision (document image) or language (OCR tokens). Finally, we design attacks exploiting the memorisation effect of the model, and demonstrate their effectiveness in probing a representative DocVQA models.
Authors: Xiao Wang, Jiandong Jin, Chenglong Li, Jin Tang, Cheng Zhang, Wei Wang
Abstract: Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the relations between pedestrian images and attribute labels. In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels. Specifically, the attribute phrases are first expanded into sentences, and then the pre-trained vision-language model CLIP is adopted as our backbone for feature embedding of visual images and attribute descriptions. The contrastive learning objective connects the vision and language modalities well in the CLIP-based feature space, and the Transformer layers used in CLIP can capture the long-range relations between pixels. Then, a multi-modal Transformer is adopted to fuse the dual features effectively and feed-forward network is used to predict attributes. To optimize our network efficiently, we propose the region-aware prompt tuning technique to adjust very few parameters (i.e., only the prompt vectors and classification heads) and fix both the pre-trained VL model and multi-modal Transformer. Our proposed PAR algorithm only adjusts 0.75% learnable parameters compared with the fine-tuning strategy. It also achieves new state-of-the-art performance on both standard and zero-shot settings for PAR, including RAPv1, RAPv2, WIDER, PA100K, and PETA-ZS, RAP-ZS datasets. The source code and pre-trained models will be released on https://github.com/Event-AHU/OpenPAR.
Authors: Yunqi Gu, Tao Zhou, Yizhe Zhang, Yi Zhou, Kelei He, Chen Gong, Huazhu Fu
Abstract: Medical image segmentation plays a crucial role in computer-aided diagnosis. However, existing methods heavily rely on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations. Moreover, accurately segmenting lesions poses challenges due to variations in shape, size, and location. To address these issues, we propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image Segmentation (DEC-Seg). First, we propose a Cross-level Feature Aggregation (CFA) module that integrates cross-level adjacent layers to enhance the feature representation ability across different resolutions. To address scale variation, we present a scale-enhanced consistency constraint, which ensures consistency in the segmentation maps generated from the same input image at different scales. This constraint helps handle variations in lesion sizes and improves the robustness of the model. Furthermore, we propose a cross-generative consistency scheme, in which the original and perturbed images can be reconstructed using cross-segmentation maps. This consistency constraint allows us to mine effective feature representations and boost the segmentation performance. To further exploit the scale information, we propose a Dual-scale Complementary Fusion (DCF) module that integrates features from two scale-specific decoders operating at different scales to help produce more accurate segmentation maps. Extensive experimental results on multiple medical segmentation tasks (polyp, skin lesion, and brain glioma) demonstrate the effectiveness of our DEC-Seg against other state-of-the-art semi-supervised segmentation approaches. The implementation code will be released at https://github.com/taozh2017/DECSeg.
Authors: Zhen Zhou, Junfeng Fan, Yunkai Ma, Sihan Zhao, Fengshui Jing, Min Tan
Abstract: Instance segmentation in unmanned aerial vehicle measurement is a long-standing challenge. Since horizontal bounding boxes introduce many interference objects, oriented bounding boxes (OBBs) are usually used for instance identification. However, based on ``segmentation within bounding box'' paradigm, current instance segmentation methods using OBBs are overly dependent on bounding box detection performance. To tackle this, this paper proposes OBSeg, an efficient instance segmentation framework using OBBs. OBSeg is based on box prompt-based segmentation foundation models (BSMs), e.g., Segment Anything Model. Specifically, OBSeg first detects OBBs to distinguish instances and provide coarse localization information. Then, it predicts OBB prompt-related masks for fine segmentation. Since OBBs only serve as prompts, OBSeg alleviates the over-dependence on bounding box detection performance of current instance segmentation methods using OBBs. In addition, to enable BSMs to handle OBB prompts, we propose a novel OBB prompt encoder. To make OBSeg more lightweight and further improve the performance of lightweight distilled BSMs, a Gaussian smoothing-based knowledge distillation method is introduced. Experiments demonstrate that OBSeg outperforms current instance segmentation methods on multiple public datasets. The code is available at https://github.com/zhen6618/OBBInstanceSegmentation.
Authors: Qiao Jin, Fangyuan Chen, Yiliang Zhou, Ziyang Xu, Justin M. Cheung, Robert Chen, Ronald M. Summers, Justin F. Rousseau, Peiyun Ni, Marc J Landsman, Sally L. Baxter, Subhi J. Al'Aref, Yijia Li, Alex Chen, Josef A. Brejt, Michael F. Chiang, Yifan Peng, Zhiyong Lu
Abstract: Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI models into clinical workflows.
Authors: Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Puhua Chen
Abstract: Real-world data are long-tailed, the lack of tail samples leads to a significant limitation in the generalization ability of the model. Although numerous approaches of class re-balancing perform well for moderate class imbalance problems, additional knowledge needs to be introduced to help the tail class recover the underlying true distribution when the observed distribution from a few tail samples does not represent its true distribution properly, thus allowing the model to learn valuable information outside the observed domain. In this work, we propose to leverage the geometric information of the feature distribution of the well-represented head class to guide the model to learn the underlying distribution of the tail class. Specifically, we first systematically define the geometry of the feature distribution and the similarity measures between the geometries, and discover four phenomena regarding the relationship between the geometries of different feature distributions. Then, based on four phenomena, feature uncertainty representation is proposed to perturb the tail features by utilizing the geometry of the head class feature distribution. It aims to make the perturbed features cover the underlying distribution of the tail class as much as possible, thus improving the model's generalization performance in the test domain. Finally, we design a three-stage training scheme enabling feature uncertainty modeling to be successfully applied. Experiments on CIFAR-10/100-LT, ImageNet-LT, and iNaturalist2018 show that our proposed approach outperforms other similar methods on most metrics. In addition, the experimental phenomena we discovered are able to provide new perspectives and theoretical foundations for subsequent studies.
Authors: F. Xavier Gaya-Morey, Cristina Manresa-Yee, Jose M. Buades-Rubio
Abstract: As the percentage of elderly people in developed countries increases worldwide, the healthcare of this collective is a worrying matter, especially if it includes the preservation of their autonomy. In this direction, many studies are being published on Ambient Assisted Living (AAL) systems, which help to reduce the preoccupations raised by the independent living of the elderly. In this study, a systematic review of the literature is presented on fall detection and Human Activity Recognition (HAR) for the elderly, as the two main tasks to solve to guarantee the safety of elderly people living alone. To address the current tendency to perform these two tasks, the review focuses on the use of Deep Learning (DL) based approaches on computer vision data. In addition, different collections of data like DL models, datasets or hardware (e.g. depth or thermal cameras) are gathered from the reviewed studies and provided for reference in future studies. Strengths and weaknesses of existing approaches are also discussed and, based on them, our recommendations for future works are provided.
Authors: F. Xavier Gaya-Morey, Silvia Ramis-Guarinos, Cristina Manresa-Yee, Jose M. Buades-Rubio
Abstract: Facial expression recognition is vital for human behavior analysis, and deep learning has enabled models that can outperform humans. However, it is unclear how closely they mimic human processing. This study aims to explore the similarity between deep neural networks and human perception by comparing twelve different networks, including both general object classifiers and FER-specific models. We employ an innovative global explainable AI method to generate heatmaps, revealing crucial facial regions for the twelve networks trained on six facial expressions. We assess these results both quantitatively and qualitatively, comparing them to ground truth masks based on Friesen and Ekman's description and among them. We use Intersection over Union (IoU) and normalized correlation coefficients for comparisons. We generate 72 heatmaps to highlight critical regions for each expression and architecture. Qualitatively, models with pre-trained weights show more similarity in heatmaps compared to those without pre-training. Specifically, eye and nose areas influence certain facial expressions, while the mouth is consistently important across all models and expressions. Quantitatively, we find low average IoU values (avg. 0.2702) across all expressions and architectures. The best-performing architecture averages 0.3269, while the worst-performing one averages 0.2066. Dendrograms, built with the normalized correlation coefficient, reveal two main clusters for most expressions: models with pre-training and models without pre-training. Findings suggest limited alignment between human and AI facial expression recognition, with network architectures influencing the similarity, as similar architectures prioritize similar facial regions.
Authors: Fei Xie, Wankou Yang, Chunyu Wang, Lei Chu, Yue Cao, Chao Ma, Wenjun Zeng
Abstract: Developing robust and discriminative appearance models has been a long-standing research challenge in visual object tracking. In the prevalent Siamese-based paradigm, the features extracted by the Siamese-like networks are often insufficient to model the tracked targets and distractor objects, thereby hindering them from being robust and discriminative simultaneously. While most Siamese trackers focus on designing robust correlation operations, we propose a novel single-branch tracking framework inspired by the transformer. Unlike the Siamese-like feature extraction, our tracker deeply embeds cross-image feature correlation in multiple layers of the feature network. By extensively matching the features of the two images through multiple layers, it can suppress non-target features, resulting in target-aware feature extraction. The output features can be directly used for predicting target locations without additional correlation steps. Thus, we reformulate the two-branch Siamese tracking as a conceptually simple, fully transformer-based Single-Branch Tracking pipeline, dubbed SBT. After conducting an in-depth analysis of the SBT baseline, we summarize many effective design principles and propose an improved tracker dubbed SuperSBT. SuperSBT adopts a hierarchical architecture with a local modeling layer to enhance shallow-level features. A unified relation modeling is proposed to remove complex handcrafted layer pattern designs. SuperSBT is further improved by masked image modeling pre-training, integrating temporal modeling, and equipping with dedicated prediction heads. Thus, SuperSBT outperforms the SBT baseline by 4.7%,3.0%, and 4.5% AUC scores in LaSOT, TrackingNet, and GOT-10K. Notably, SuperSBT greatly raises the speed of SBT from 37 FPS to 81 FPS. Extensive experiments show that our method achieves superior results on eight VOT benchmarks.
Authors: Pengjie Wang, Kaile Zhang, Xinyu Wang, Shengwei Han, Yongge Liu, Jinpeng Wan, Haisu Guan, Zhebin Kuang, Lianwen Jin, Xiang Bai, Yuliang Liu
Abstract: Oracle bone script, one of the earliest known forms of ancient Chinese writing, presents invaluable research materials for scholars studying the humanities and geography of the Shang Dynasty, dating back 3,000 years. The immense historical and cultural significance of these writings cannot be overstated. However, the passage of time has obscured much of their meaning, presenting a significant challenge in deciphering these ancient texts. With the advent of Artificial Intelligence (AI), employing AI to assist in deciphering Oracle Bone Characters (OBCs) has become a feasible option. Yet, progress in this area has been hindered by a lack of high-quality datasets. To address this issue, this paper details the creation of the HUST-OBC dataset. This dataset encompasses 77,064 images of 1,588 individual deciphered characters and 62,989 images of 9,411 undeciphered characters, with a total of 140,053 images, compiled from diverse sources. The hope is that this dataset could inspire and assist future research in deciphering those unknown OBCs. All the codes and datasets are available at https://github.com/Yuliang-Liu/Open-Oracle.
Authors: Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, Jiachen Lu, Li Zhang
Abstract: Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, traditional simulation systems, which often heavily rely on manual modeling and 2D image editing, struggled with scaling to extensive scenes and generating realistic simulation data. In this study, we present S-NeRF++, an innovative autonomous driving simulation system based on neural reconstruction. Trained on widely-used self-driving datasets such as nuScenes and Waymo, S-NeRF++ can generate a large number of realistic street scenes and foreground objects with high rendering quality as well as offering considerable flexibility in manipulation and simulation. Specifically, S-NeRF++ is an enhanced neural radiance field for synthesizing large-scale scenes and moving vehicles, with improved scene parameterization and camera pose learning. The system effectively utilizes noisy and sparse LiDAR data to refine training and address depth outliers, ensuring high-quality reconstruction and novel-view rendering. It also provides a diverse foreground asset bank by reconstructing and generating different foreground vehicles to support comprehensive scenario creation.Moreover, we have developed an advanced foreground-background fusion pipeline that skillfully integrates illumination and shadow effects, further enhancing the realism of our simulations. With the high-quality simulated data provided by our S-NeRF++, we found the perception methods enjoy performance boosts on several autonomous driving downstream tasks, further demonstrating our proposed simulator's effectiveness.
Authors: Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu, Feng Wen, Wei Zhang, Li Zhang
Abstract: The extraction of road network is essential for the generation of high-definition maps since it enables the precise localization of road landmarks and their interconnections. However, generating road network poses a significant challenge due to the conflicting underlying combination of Euclidean (e.g., road landmarks location) and non-Euclidean (e.g., road topological connectivity) structures. Existing methods struggle to merge the two types of data domains effectively, but few of them address it properly. Instead, our work establishes a unified representation of both types of data domain by projecting both Euclidean and non-Euclidean data into an integer series called RoadNet Sequence. Further than modeling an auto-regressive sequence-to-sequence Transformer model to understand RoadNet Sequence, we decouple the dependency of RoadNet Sequence into a mixture of auto-regressive and non-autoregressive dependency. Building on this, our proposed non-autoregressive sequence-to-sequence approach leverages non-autoregressive dependencies while fixing the gap towards auto-regressive dependencies, resulting in success on both efficiency and accuracy. We further identify two main bottlenecks in the current RoadNetTransformer on a non-overfitting split of the dataset: poor landmark detection limited by the BEV Encoder and error propagation to topology reasoning. Therefore, we propose Topology-Inherited Training to inherit better topology knowledge into RoadNetTransformer. Additionally, we collect SD-Maps from open-source map datasets and use this prior information to significantly improve landmark detection and reachability. Extensive experiments on nuScenes dataset demonstrate the superiority of RoadNet Sequence representation and the non-autoregressive approach compared to existing state-of-the-art alternatives.
Authors: Jin Liu, Bo Wang, Chuanming Wang, Huiyuan Fu, Huadong Ma
Abstract: Exposure correction aims to enhance visual data suffering from improper exposures, which can greatly improve satisfactory visual effects. However, previous methods mainly focus on the image modality, and the video counterpart is less explored in the literature. Directly applying prior image-based methods to videos results in temporal incoherence with low visual quality. Through thorough investigation, we find that the development of relevant communities is limited by the absence of a benchmark dataset. Therefore, in this paper, we construct the first real-world paired video dataset, including both underexposure and overexposure dynamic scenes. To achieve spatial alignment, we utilize two DSLR cameras and a beam splitter to simultaneously capture improper and normal exposure videos. Additionally, we propose an end-to-end video exposure correction network, in which a dual-stream module is designed to deal with both underexposure and overexposure factors, enhancing the illumination based on Retinex theory. The extensive experiments based on various metrics and user studies demonstrate the significance of our dataset and the effectiveness of our method. The code and dataset are available at https://github.com/kravrolens/VECNet.
Authors: Lingchen Yang, Gaspard Zoss, Prashanth Chandran, Markus Gross, Barbara Solenthaler, Eftychios Sifakis, Derek Bradley
Abstract: Physically-based simulation is a powerful approach for 3D facial animation as the resulting deformations are governed by physical constraints, allowing to easily resolve self-collisions, respond to external forces and perform realistic anatomy edits. Today's methods are data-driven, where the actuations for finite elements are inferred from captured skin geometry. Unfortunately, these approaches have not been widely adopted due to the complexity of initializing the material space and learning the deformation model for each character separately, which often requires a skilled artist followed by lengthy network training. In this work, we aim to make physics-based facial animation more accessible by proposing a generalized physical face model that we learn from a large 3D face dataset. Once trained, our model can be quickly fit to any unseen identity and produce a ready-to-animate physical face model automatically. Fitting is as easy as providing a single 3D face scan, or even a single face image. After fitting, we offer intuitive animation controls, as well as the ability to retarget animations across characters. All the while, the resulting animations allow for physical effects like collision avoidance, gravity, paralysis, bone reshaping and more.
Authors: Chenchen Tao, Xiaohao Peng, Chong Wang, Jiafei Wu, Puning Zhao, Jun Wang, Jiangbo Qian
Abstract: Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. However, the ambiguous nature of anomaly definitions across contexts may introduce inaccuracy in discriminating abnormal and normal events. To show the model what is anomalous, a novel framework is proposed to guide the learning of suspected anomalies from event prompts. Given a textual prompt dictionary of potential anomaly events and the captions generated from anomaly videos, the semantic anomaly similarity between them could be calculated to identify the suspected events for each video snippet. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos, as well as provides a new way to label pseudo anomalies for self-training. To demonstrate its effectiveness, comprehensive experiments and detailed ablation studies are conducted on four datasets, namely XD-Violence, UCF-Crime, TAD, and ShanghaiTech. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC (86.5\%, \hl{90.4}\%, 94.4\%, and 97.4\%). Furthermore, it shows promising performance in open-set and cross-dataset cases. The data, code, and models can be found at: \url{https://github.com/shiwoaz/lap}.
Authors: Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, Baobao Chang
Abstract: In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat and Video-LLaVA. We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs, suggesting a need for a sparser approach compared to textual data handling. To this end, we introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency by learning adaptive attention patterns in early layers and pruning visual tokens in subsequent ones. Our evaluations demonstrate FastV's ability to dramatically reduce computational costs (e.g., a 45 reduction in FLOPs for LLaVA-1.5-13B) without sacrificing performance in a wide range of image and video understanding tasks. The computational efficiency and performance trade-off of FastV are highly customizable and pareto-efficient. It can compress the FLOPs of a 13B-parameter model to achieve a lower budget than that of a 7B-parameter model, while still maintaining superior performance. We believe FastV has practical values for deployment of LVLMs in edge devices and commercial models. Code is released at https://github.com/pkunlp-icler/FastV.
Authors: Yifei Gao, Jiaqi Wang, Zhiyu Lin, Jitao Sang
Abstract: The evolution of Artificial Intelligence Generated Contents (AIGCs) is advancing towards higher quality. The growing interactions with AIGCs present a new challenge to the data-driven AI community: While AI-generated contents have played a crucial role in a wide range of AI models, the potential hidden risks they introduce have not been thoroughly examined. Beyond human-oriented forgery detection, AI-generated content poses potential issues for AI models originally designed to process natural data. In this study, we underscore the exacerbated hallucination phenomena in Large Vision-Language Models (LVLMs) caused by AI-synthetic images. Remarkably, our findings shed light on a consistent AIGC \textbf{hallucination bias}: the object hallucinations induced by synthetic images are characterized by a greater quantity and a more uniform position distribution, even these synthetic images do not manifest unrealistic or additional relevant visual features compared to natural images. Moreover, our investigations on Q-former and Linear projector reveal that synthetic images may present token deviations after visual projection, thereby amplifying the hallucination bias.
Authors: Zhihao Chen, Yiyuan Ge, Ziyang Wang, Jiaju Kang, Mingya Zhang
Abstract: The study of Cloth-Changing Person Re-identification (CC-ReID) focuses on retrieving specific pedestrians when their clothing has changed, typically under the assumption that the entire pedestrian images are visible. Pedestrian images in real-world scenarios, however, are often partially obscured by obstacles, presenting a significant challenge to existing CC-ReID systems. In this paper, we introduce a more challenging task termed Occluded Cloth-Changing Person Re-Identification ($OC^4-ReID$), which simultaneously addresses two challenges of clothing changes and occlusion. Concretely, we construct two new datasets, Occ-LTCC and Occ-PRCC, based on original CC-ReID datasets to include random occlusions of key pedestrians components (e.g., head, torso). Moreover, a novel benchmark is proposed for $OC^4-ReID$ incorporating a Train-Test Micro Granularity Screening ($T^2MGS$) module to mitigate the influence of occlusion and proposing a Part-Robust Triplet (PRT) loss for partial features learning. Comprehensive experiments on the proposed datasets, as well as on two CC-ReID benchmark datasets demonstrate the superior performance of proposed method against other state-of-the-art methods. The codes and datasets are available at: https://github.com/1024AILab/OC4-ReID.
Authors: Tianyi Zhang, Kaining Huang, Weiming Zhi, Matthew Johnson-Roberson
Abstract: Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this same capability. In this paper, we tackle the challenge of constructing a photorealistic scene representation under poorly illuminated conditions and with a moving light source. We approach the task of modeling illumination as a learning problem, and utilize the developed illumination model to aid in scene reconstruction. We introduce an innovative framework that uses a data-driven approach, Neural Light Simulators (NeLiS), to model and calibrate the camera-light system. Furthermore, we present DarkGS, a method that applies NeLiS to create a relightable 3D Gaussian scene model capable of real-time, photorealistic rendering from novel viewpoints. We show the applicability and robustness of our proposed simulator and system in a variety of real-world environments.
Authors: Datao Tang, Xiangyong Cao, Xingsong Hou, Zhongyuan Jiang, Junmin Liu, Deyu Meng
Abstract: The emergence of generative models has revolutionized the field of remote sensing (RS) image generation. Despite generating high-quality images, existing methods are limited in relying mainly on text control conditions, and thus do not always generate images accurately and stably. In this paper, we propose CRS-Diff, a new RS generative framework specifically tailored for RS image generation, leveraging the inherent advantages of diffusion models while integrating more advanced control mechanisms. Specifically, CRS-Diff can simultaneously support text-condition, metadata-condition, and image-condition control inputs, thus enabling more precise control to refine the generation process. To effectively integrate multiple condition control information, we introduce a new conditional control mechanism to achieve multi-scale feature fusion, thus enhancing the guiding effect of control conditions. To our knowledge, CRS-Diff is the first multiple-condition controllable RS generative model. Experimental results in single-condition and multiple-condition cases have demonstrated the superior ability of our CRS-Diff to generate RS images both quantitatively and qualitatively compared with previous methods. Additionally, our CRS-Diff can serve as a data engine that generates high-quality training data for downstream tasks, e.g., road extraction. The code is available at https://github.com/Sonettoo/CRS-Diff.
Authors: Yiming Ji, Yang Liu, Guanghu Xie, Boyu Ma, Zongwu Xie
Abstract: We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we propose a Spatially Consistent Feature Fusion model to reduce the effect of erroneous estimates from pre-trained segmentation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping. Additionally, we employ a lightweight encoder-decoder to compress the high-dimensional semantic features into a compact 3D Gaussian representation, mitigating the burden of excessive memory consumption. Furthermore, we leverage the advantage of 3D Gaussian splatting, which enables efficient and differentiable novel view rendering, and propose a Virtual Camera View Pruning method to eliminate outlier gaussians, thereby effectively enhancing the quality of scene representations. Our NEDS-SLAM method demonstrates competitive performance over existing dense semantic SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in 3D dense semantic mapping.
Authors: Ali Karami, Thi Kieu Khanh Ho, Narges Armanfard
Abstract: Skeleton-based video anomaly detection (SVAD) is a crucial task in computer vision. Accurately identifying abnormal patterns or events enables operators to promptly detect suspicious activities, thereby enhancing safety. Achieving this demands a comprehensive understanding of human motions, both at body and region levels, while also accounting for the wide variations of performing a single action. However, existing studies fail to simultaneously address these crucial properties. This paper introduces a novel, practical and lightweight framework, namely Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection (GiCiSAD) to overcome the challenges associated with SVAD. GiCiSAD consists of three novel modules: the Graph Attention-based Forecasting module to capture the spatio-temporal dependencies inherent in the data, the Graph-level Jigsaw Puzzle Maker module to distinguish subtle region-level discrepancies between normal and abnormal motions, and the Graph-based Conditional Diffusion model to generate a wide spectrum of human motions. Extensive experiments on four widely used skeleton-based video datasets show that GiCiSAD outperforms existing methods with significantly fewer training parameters, establishing it as the new state-of-the-art.
Authors: Dingchen Yang, Bowen Cao, Guang Chen, Changjun Jiang
Abstract: Multi-modal Large Language Models (MLLMs) demonstrate remarkable success across various vision-language tasks. However, they suffer from visual hallucination, where the generated responses diverge from the provided image. Are MLLMs oblivious to the accurate visual cues when they hallucinate? Our investigation reveals that the visual branch may equally advocate both accurate and erroneous content. To address this issue, we propose Pensieve, a training-free method that leverages the analogous visual hallucinations, which are induced by images sharing common semantic and appearance characteristics, to mitigate hallucination. Specifically, Pensieve enables MLLMs to retrospect relevant images as references and compare their visual content with the test image via confidence score subtraction. Moreover, our paradigm balances the effects of addressing errors from both the visual and textual branches by adaptively scaling the subtracted scores. Experiments on Whoops, LLaVA Bench, POPE, and MME demonstrate the efficacy of Pensieve in mitigating visual hallucination, surpassing other advanced decoding strategies. Pensieve also aids MLLMs in identifying visual details and enhance the specificity of generated image descriptions.
Authors: Yufu Wang, Ziyun Wang, Lingjie Liu, Kostas Daniilidis
Abstract: We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos. TRAM robustifies SLAM to recover the camera motion in the presence of dynamic humans and uses the scene background to derive the motion scale. Using the recovered camera as a metric-scale reference frame, we introduce a video transformer model (VIMO) to regress the kinematic body motion of a human. By composing the two motions, we achieve accurate recovery of 3D humans in the world space, reducing global motion errors by a large margin from prior work. https://yufu-wang.github.io/tram4d/
Authors: Abdelrahman Shaker, Syed Talal Wasim, Martin Danelljan, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan
Abstract: Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand the memory bank every few frames. We propose a transformer-based approach, named MAVOS, that introduces an optimized and dynamic long-term modulated cross-attention (MCA) memory to model temporal smoothness without requiring frequent memory expansion. The proposed MCA effectively encodes both local and global features at various levels of granularity while efficiently maintaining consistent speed regardless of the video length. Extensive experiments on multiple benchmarks, LVOS, Long-Time Video, and DAVIS 2017, demonstrate the effectiveness of our proposed contributions leading to real-time inference and markedly reduced memory demands without any degradation in segmentation accuracy on long videos. Compared to the best existing transformer-based approach, our MAVOS increases the speed by 7.6x, while significantly reducing the GPU memory by 87% with comparable segmentation performance on short and long video datasets. Notably on the LVOS dataset, our MAVOS achieves a J&F score of 63.3% while operating at 37 frames per second (FPS) on a single V100 GPU. Our code and models will be publicly available at: https://github.com/Amshaker/MAVOS.
Authors: Jing Liang, Zhuo Deng, Zheming Zhou, Omid Ghasemalizadeh, Dinesh Manocha, Min Sun, Cheng-Hao Kuo, Arnie Sen
Abstract: We present a novel end-to-end algorithm (PoCo) for the indoor RGB-D place recognition task, aimed at identifying the most likely match for a given query frame within a reference database. The task presents inherent challenges attributed to the constrained field of view and limited range of perception sensors. We propose a new network architecture, which generalizes the recent Context of Clusters (CoCs) to extract global descriptors directly from the noisy point clouds through end-to-end learning. Moreover, we develop the architecture by integrating both color and geometric modalities into the point features to enhance the global descriptor representation. We conducted evaluations on public datasets ScanNet-PR and ARKit with 807 and 5047 scenarios, respectively. PoCo achieves SOTA performance: on ScanNet-PR, we achieve R@1 of 64.63%, a 5.7% improvement from the best-published result CGis (61.12%); on Arkit, we achieve R@1 of 45.12%, a 13.3% improvement from the best-published result CGis (39.82%). In addition, PoCo shows higher efficiency than CGis in inference time (1.75X-faster), and we demonstrate the effectiveness of PoCo in recognizing places within a real-world laboratory environment.
Authors: Richard E. Neddo, Zander W. Blasingame, Chen Liu
Abstract: Face morphing attacks pose an increasing threat to face recognition (FR) systems. A morphed photo contains biometric information from two different subjects to take advantage of vulnerabilities in FRs. These systems are particularly susceptible to attacks when the morphs are subjected to print-scanning to mask the artifacts generated during the morphing process. We investigate the impact of print-scanning on morphing attack detection through a series of evaluations on heterogeneous morphing attack scenarios. Our experiments show that we can increase the Mated Morph Presentation Match Rate (MMPMR) by up to 8.48%. Furthermore, when a Single-image Morphing Attack Detection (S-MAD) algorithm is not trained to detect print-scanned morphs the Morphing Attack Classification Error Rate (MACER) can increase by up to 96.12%, indicating significant vulnerability.
Authors: Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu
Abstract: Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks, and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing, hindering their clinical utility across diverse resource-constrained scenarios in practice. In this paper, we propose a novel and lightweight framework Med-MoE (Mixture-of-Experts) that tackles both discriminative and generative multimodal medical tasks. The learning of Med-MoE consists of three steps: multimodal medical alignment, instruction tuning and routing, and domain-specific MoE tuning. After aligning multimodal medical images with LLM tokens, we then enable the model for different multimodal medical tasks with instruction tuning, together with a trainable router tailored for expert selection across input modalities. Finally, the model is tuned by integrating the router with multiple domain-specific experts, which are selectively activated and further empowered by meta expert. Comprehensive experiments on both open- and close-end medical question answering (Med-VQA) and image classification tasks across datasets such as VQA-RAD, SLAKE and Path-VQA demonstrate that our model can achieve performance superior to or on par with state-of-the-art baselines, while only requiring approximately 30\%-50\% of activated model parameters. Extensive analysis and ablations corroborate the effectiveness and practical utility of our method.
Authors: Mykola Lavreniuk
Abstract: Self-supervised monocular depth estimation has garnered considerable attention for its applications in autonomous driving and robotics. While recent methods have made strides in leveraging techniques like the Self Query Layer (SQL) to infer depth from motion, they often overlook the potential of strengthening pose information. In this paper, we introduce SPIdepth, a novel approach that prioritizes enhancing the pose network for improved depth estimation. Building upon the foundation laid by SQL, SPIdepth emphasizes the importance of pose information in capturing fine-grained scene structures. By enhancing the pose network's capabilities, SPIdepth achieves remarkable advancements in scene understanding and depth estimation. Experimental results on benchmark datasets such as KITTI, Cityscapes, and Make3D showcase SPIdepth's state-of-the-art performance, surpassing previous methods by significant margins. Specifically, SPIdepth tops the self-supervised KITTI benchmark. Additionally, SPIdepth achieves the lowest AbsRel (0.029), SqRel (0.069), and RMSE (1.394) on KITTI, establishing new state-of-the-art results. On Cityscapes, SPIdepth shows improvements over SQLdepth of 21.7% in AbsRel, 36.8% in SqRel, and 16.5% in RMSE, even without using motion masks. On Make3D, SPIdepth in zero-shot outperforms all other models. Remarkably, SPIdepth achieves these results using only a single image for inference, surpassing even methods that utilize video sequences for inference, thus demonstrating its efficacy and efficiency in real-world applications. Our approach represents a significant leap forward in self-supervised monocular depth estimation, underscoring the importance of strengthening pose information for advancing scene understanding in real-world applications. The code and pre-trained models are publicly available at https://github.com/Lavreniuk/SPIdepth.
Authors: Xu Han, Yuan Tang, Zhaoxuan Wang, Xianzhi Li
Abstract: Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM), outperforms Transformer in multiple areas with only linear complexity. However, the straightforward adoption of Mamba does not achieve satisfactory performance on point cloud tasks. In this work, we present Mamba3D, a state space model tailored for point cloud learning to enhance local feature extraction, achieving superior performance, high efficiency, and scalability potential. Specifically, we propose a simple yet effective Local Norm Pooling (LNP) block to extract local geometric features. Additionally, to obtain better global features, we introduce a bidirectional SSM (bi-SSM) with both a token forward SSM and a novel backward SSM that operates on the feature channel. Extensive experimental results show that Mamba3D surpasses Transformer-based counterparts and concurrent works in multiple tasks, with or without pre-training. Notably, Mamba3D achieves multiple SoTA, including an overall accuracy of 92.6% (train from scratch) on the ScanObjectNN and 95.1% (with single-modal pre-training) on the ModelNet40 classification task, with only linear complexity. Our code and weights are available at https://github.com/xhanxu/Mamba3D.
Authors: Zhenrong Zhang, Jianan Liu, Xi Zhou, Tao Huang, Qing-Long Han, Jingxin Liu, Hongbin Liu
Abstract: Cooperative perception is essential to enhance the efficiency and safety of future transportation systems, requiring extensive data sharing among vehicles on the road, which raises significant privacy concerns. Federated learning offers a promising solution by enabling data privacy-preserving collaborative enhancements in perception, decision-making, and planning among connected and autonomous vehicles (CAVs). However, federated learning is impeded by significant challenges arising from data heterogeneity across diverse clients, potentially diminishing model accuracy and prolonging convergence periods. This study introduces a specialized federated learning framework for CP, termed the federated dynamic weighted aggregation (FedDWA) algorithm, facilitated by dynamic adjusting loss (DALoss) function. This framework employs dynamic client weighting to direct model convergence and integrates a novel loss function that utilizes Kullback-Leibler divergence (KLD) to counteract the detrimental effects of non-independently and identically distributed (Non-IID) and unbalanced data. Utilizing the BEV transformer as the primary model, our rigorous testing on the OpenV2V dataset, augmented with FedBEVT data, demonstrates significant improvements in the average intersection over union (IoU). These results highlight the substantial potential of our federated learning framework to address data heterogeneity challenges in CP, thereby enhancing the accuracy of environmental perception models and facilitating more robust and efficient collaborative learning solutions in the transportation sector.
Authors: Peijin Jia, Tuopu Wen, Ziang Luo, Mengmeng Yang, Kun Jiang, Zhiquan Lei, Xuewei Tang, Ziyuan Liu, Le Cui, Bo Zhang, Long Huang, Diange Yang
Abstract: Constructing high-definition (HD) maps is a crucial requirement for enabling autonomous driving. In recent years, several map segmentation algorithms have been developed to address this need, leveraging advancements in Bird's-Eye View (BEV) perception. However, existing models still encounter challenges in producing realistic and consistent semantic map layouts. One prominent issue is the limited utilization of structured priors inherent in map segmentation masks. In light of this, we propose DiffMap, a novel approach specifically designed to model the structured priors of map segmentation masks using latent diffusion model. By incorporating this technique, the performance of existing semantic segmentation methods can be significantly enhanced and certain structural errors present in the segmentation outputs can be effectively rectified. Notably, the proposed module can be seamlessly integrated into any map segmentation model, thereby augmenting its capability to accurately delineate semantic information. Furthermore, through extensive visualization analysis, our model demonstrates superior proficiency in generating results that more accurately reflect real-world map layouts, further validating its efficacy in improving the quality of the generated maps.
Authors: Charles Gaydon, Michel Daab, Floryne Roche
Abstract: Mapping agencies are increasingly adopting Aerial Lidar Scanning (ALS) as a new tool to map buildings and other above-ground structures. Processing ALS data at scale requires efficient point classification methods that perform well over highly diverse territories. Large annotated Lidar datasets are needed to evaluate these classification methods, however, current Lidar benchmarks have restricted scope and often cover a single urban area. To bridge this data gap, we introduce the FRench ALS Clouds from TArgeted Landscapes (FRACTAL) dataset: an ultra-large-scale aerial Lidar dataset made of 100,000 dense point clouds with high quality labels for 7 semantic classes and spanning 250 km$^2$. FRACTAL achieves high spatial and semantic diversity by explicitly sampling rare classes and challenging landscapes from five different regions of France. We describe the data collection, annotation, and curation process of the dataset. We provide baseline semantic segmentation results using a state of the art 3D point cloud classification model. FRACTAL aims to support the development of 3D deep learning approaches for large-scale land monitoring.
Authors: Junzhuo Chen
Abstract: Large unlabeled data and difficult-to-identify anomalies are the urgent issues need to overcome in most industrial scene. In order to address this issue, a new meth-odology for detecting surface defects in in-dustrial settings is introduced, referred to as Memory Augmentation and Pseudo-Labeling(MAPL). The methodology first in-troduces an anomaly simulation strategy, which significantly improves the model's ability to recognize rare or unknown anom-aly types by generating simulated anomaly samples. To cope with the problem of the lack of labeling of anomalous simulated samples, a pseudo-labeler method based on a one-classifier ensemble was employed in this study, which enhances the robustness of the model in the case of limited labeling data by automatically selecting key pseudo-labeling hyperparameters. Meanwhile, a memory-enhanced learning mechanism is introduced to effectively predict abnormal regions by analyzing the difference be-tween the input samples and the normal samples in the memory pool. An end-to-end learning framework is employed by MAPL to identify the abnormal regions directly from the input data, which optimizes the ef-ficiency and real-time performance of de-tection. By conducting extensive trials on the recently developed BHAD dataset (in-cluding MVTec AD [1], Visa [2], and MDPP [3]), MAPL achieves an average im-age-level AUROC score of 86.2%, demon-strating a 5.1% enhancement compared to the original MemSeg [4] model. The source code is available at https://github.com/jzc777/MAPL.
Authors: Jianhua Zhu, Liangcai Gao, Wenqi Zhao
Abstract: Significant progress has been made in the field of handwritten mathematical expression recognition, while existing encoder-decoder methods are usually difficult to model global information in $LaTeX$. Therefore, this paper introduces a novel approach, Implicit Character-Aided Learning (ICAL), to mine the global expression information and enhance handwritten mathematical expression recognition. Specifically, we propose the Implicit Character Construction Module (ICCM) to predict implicit character sequences and use a Fusion Module to merge the outputs of the ICCM and the decoder, thereby producing corrected predictions. By modeling and utilizing implicit character information, ICAL achieves a more accurate and context-aware interpretation of handwritten mathematical expressions. Experimental results demonstrate that ICAL notably surpasses the state-of-the-art(SOTA) models, improving the expression recognition rate (ExpRate) by 2.25\%/1.81\%/1.39\% on the CROHME 2014/2016/2019 datasets respectively, and achieves a remarkable 69.06\% on the challenging HME100k test set. We make our code available on the GitHub: https://github.com/qingzhenduyu/ICAL
Authors: Zhiqiang Shen, Peng Cao, Junming Su, Jinzhu Yang, Osmar R. Zaiane
Abstract: This paper investigates an extremely challenging problem: barely-supervised volumetric medical image segmentation (BSS). A BSS training dataset consists of two parts: 1) a barely-annotated labeled set, where each labeled image contains only a single-slice annotation, and 2) an unlabeled set comprising numerous unlabeled volumetric images. State-of-the-art BSS methods employ a registration-based paradigm, which uses inter-slice image registration to propagate single-slice annotations into volumetric pseudo labels, constructing a completely annotated labeled set, to which a semi-supervised segmentation scheme can be applied. However, the paradigm has a critical limitation: the pseudo-labels generated by image registration are unreliable and noisy. Motivated by this, we propose a new perspective: instead of solving BSS within a semi-supervised learning scheme, this work formulates BSS as an unsupervised domain adaptation problem. To this end, we propose a novel BSS framework, \textbf{B}arely-supervised learning \textbf{via} unsupervised domain \textbf{A}daptation (BvA), as an alternative to the dominant registration paradigm. Specifically, we first design a novel noise-free labeled data construction algorithm (NFC) for slice-to-volume labeled data synthesis. Then, we introduce a frequency and spatial Mix-Up strategy (FSX) to mitigate the domain shifts. Extensive experiments demonstrate that our method provides a promising alternative for BSS. Remarkably, the proposed method, trained on the left atrial segmentation dataset with \textbf{only one} barely-labeled image, achieves a Dice score of 81.20%, outperforming the state-of-the-art by 61.71%. The code is available at \href{https://github.com/Senyh/BvA}{\textit{\texttt{https://github.com/Senyh/BvA}}}.
URLs: https://github.com/Senyh/BvA, https://github.com/Senyh/BvA
Authors: Zeyu Zhang, Yiran Wang, Biao Wu, Shuo Chen, Zhiyuan Zhang, Shiya Huang, Wenbo Zhang, Meng Fang, Ling Chen, Yang Zhao
Abstract: In recent years, there has been significant interest in creating 3D avatars and motions, driven by their diverse applications in areas like film-making, video games, AR/VR, and human-robot interaction. However, current efforts primarily concentrate on either generating the 3D avatar mesh alone or producing motion sequences, with integrating these two aspects proving to be a persistent challenge. Additionally, while avatar and motion generation predominantly target humans, extending these techniques to animals remains a significant challenge due to inadequate training data and methods. To bridge these gaps, our paper presents three key contributions. Firstly, we proposed a novel agent-based approach named Motion Avatar, which allows for the automatic generation of high-quality customizable human and animal avatars with motions through text queries. The method significantly advanced the progress in dynamic 3D character generation. Secondly, we introduced a LLM planner that coordinates both motion and avatar generation, which transforms a discriminative planning into a customizable Q&A fashion. Lastly, we presented an animal motion dataset named Zoo-300K, comprising approximately 300,000 text-motion pairs across 65 animal categories and its building pipeline ZooGen, which serves as a valuable resource for the community. See project website https://steve-zeyu-zhang.github.io/MotionAvatar/
Authors: Qingdong He, Jiangning Zhang, Jinlong Peng, Haoyang He, Xiangtai Li, Yabiao Wang, Chengjie Wang
Abstract: Transformers have revolutionized the point cloud learning task, but the quadratic complexity hinders its extension to long sequence and makes a burden on limited computational resources. The recent advent of RWKV, a fresh breed of deep sequence models, has shown immense potential for sequence modeling in NLP tasks. In this paper, we present PointRWKV, a model of linear complexity derived from the RWKV model in the NLP field with necessary modifications for point cloud learning tasks. Specifically, taking the embedded point patches as input, we first propose to explore the global processing capabilities within PointRWKV blocks using modified multi-headed matrix-valued states and a dynamic attention recurrence mechanism. To extract local geometric features simultaneously, we design a parallel branch to encode the point cloud efficiently in a fixed radius near-neighbors graph with a graph stabilizer. Furthermore, we design PointRWKV as a multi-scale framework for hierarchical feature learning of 3D point clouds, facilitating various downstream tasks. Extensive experiments on different point cloud learning tasks show our proposed PointRWKV outperforms the transformer- and mamba-based counterparts, while significantly saving about 42\% FLOPs, demonstrating the potential option for constructing foundational 3D models.
Authors: \'Alvaro Becerra, Javier Irigoyen, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez, Mutlu Cukurova
Abstract: In this article, we explore computer vision approaches to detect abnormal head pose during e-learning sessions and we introduce a study on the effects of mobile phone usage during these sessions. We utilize behavioral data collected from 120 learners monitored while participating in a MOOC learning sessions. Our study focuses on the influence of phone-usage events on behavior and physiological responses, specifically attention, heart rate, and meditation, before, during, and after phone usage. Additionally, we propose an approach for estimating head pose events using images taken by the webcam during the MOOC learning sessions to detect phone-usage events. Our hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-learning sessions. We propose an approach designed to detect deviations in head posture from the average observed during a learner's session, operating as a semi-supervised method. This system flags events indicating alterations in head posture for subsequent human review and selection of mobile phone usage occurrences with a sensitivity over 90%.
Authors: Miriam Navarro, \'Alvaro Becerra, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez
Abstract: In this paper, we present an approach in the Multimodal Learning Analytics field. Within this approach, we have developed a tool to visualize and analyze eye movement data collected during learning sessions in online courses. The tool is named VAAD, an acronym for Visual Attention Analysis Dashboard. These eye movement data have been gathered using an eye-tracker and subsequently processed and visualized for interpretation. The purpose of the tool is to conduct a descriptive analysis of the data by facilitating its visualization, enabling the identification of differences and learning patterns among various learner populations. Additionally, it integrates a predictive module capable of anticipating learner activities during a learning session. Consequently, VAAD holds the potential to offer valuable insights into online learning behaviors from both descriptive and predictive perspectives.
Authors: Zehui Lin, Zhuoneng Zhang, Xindi Hu, Zhifan Gao, Xin Yang, Yue Sun, Dong Ni, Tao Tan
Abstract: Ultrasound is widely used in clinical practice due to its affordability, portability, and safety. However, current AI research often overlooks combined disease prediction and tissue segmentation. We propose UniUSNet, a universal framework for ultrasound image classification and segmentation. This model handles various ultrasound types, anatomical positions, and input formats, excelling in both segmentation and classification tasks. Trained on a comprehensive dataset with over 9.7K annotations from 7 distinct anatomical positions, our model matches state-of-the-art performance and surpasses single-dataset and ablated models. Zero-shot and fine-tuning experiments show strong generalization and adaptability with minimal fine-tuning. We plan to expand our dataset and refine the prompting mechanism, with model weights and code available at (https://github.com/Zehui-Lin/UniUSNet).
Authors: Yuxin Hong, Xiao Zhang, Xin Zhang, Joey Tianyi Zhou
Abstract: In the medical field, managing high-dimensional massive medical imaging data and performing reliable medical analysis from it is a critical challenge, especially in resource-limited environments such as remote medical facilities and mobile devices. This necessitates effective dataset compression techniques to reduce storage, transmission, and computational cost. However, existing coreset selection methods are primarily designed for natural image datasets, and exhibit doubtful effectiveness when applied to medical image datasets due to challenges such as intra-class variation and inter-class similarity. In this paper, we propose a novel coreset selection strategy termed as Evolution-aware VAriance (EVA), which captures the evolutionary process of model training through a dual-window approach and reflects the fluctuation of sample importance more precisely through variance measurement. Extensive experiments on medical image datasets demonstrate the effectiveness of our strategy over previous SOTA methods, especially at high compression rates. EVA achieves 98.27% accuracy with only 10% training data, compared to 97.20% for the full training set. None of the compared baseline methods can exceed Random at 5% selection rate, while EVA outperforms Random by 5.61%, showcasing its potential for efficient medical image analysis.
Authors: Jiawei Mao, Juncheng Wu, Yuyin Zhou, Xuesong Yin, Yuanqi Chang
Abstract: There are many excellent solutions in image restoration.However, most methods require on training separate models to restore images with different types of degradation.Although existing all-in-one models effectively address multiple types of degradation simultaneously, their performance in real-world scenarios is still constrained by the task confusion problem.In this work, we attempt to address this issue by introducing \textbf{Restorer}, a novel Transformer-based all-in-one image restoration model.To effectively address the complex degradation present in real-world images, we propose All-Axis Attention (AAA), a mechanism that simultaneously models long-range dependencies across both spatial and channel dimensions, capturing potential correlations along all axes.Additionally, we introduce textual prompts in Restorer to incorporate explicit task priors, enabling the removal of specific degradation types based on user instructions. By iterating over these prompts, Restorer can handle composite degradation in real-world scenarios without requiring additional training.Based on these designs, Restorer with one set of parameters demonstrates state-of-the-art performance in multiple image restoration tasks compared to existing all-in-one and even single-task models.Additionally, Restorer is efficient during inference, suggesting the potential in real-world applications.
Authors: Jialang Xu, Nazir Sirajudeen, Matthew Boal, Nader Francis, Danail Stoyanov, Evangelos Mazomenos
Abstract: Automated detection of surgical errors can improve robotic-assisted surgery. Despite promising progress, existing methods still face challenges in capturing rich temporal context to establish long-term dependencies while maintaining computational efficiency. In this paper, we propose a novel hierarchical model named SEDMamba, which incorporates the selective state space model (SSM) into surgical error detection, facilitating efficient long sequence modelling with linear complexity. SEDMamba enhances selective SSM with a bottleneck mechanism and fine-to-coarse temporal fusion (FCTF) to detect and temporally localize surgical errors in long videos. The bottleneck mechanism compresses and restores features within their spatial dimension, thereby reducing computational complexity. FCTF utilizes multiple dilated 1D convolutional layers to merge temporal information across diverse scale ranges, accommodating errors of varying duration. Our work also contributes the first-of-its-kind, frame-level, in-vivo surgical error dataset to support error detection in real surgical cases. Specifically, we deploy the clinically validated observational clinical human reliability assessment tool (OCHRA) to annotate the errors during suturing tasks in an open-source radical prostatectomy dataset (SAR-RARP50). Experimental results demonstrate that our SEDMamba outperforms state-of-the-art methods with at least 1.82% AUC and 3.80% AP performance gains with significantly reduced computational complexity. The corresponding error annotations, code and models will be released at https://github.com/wzjialang/SEDMamba.
Authors: Jiaxin Zhang, Wentao Yang, Songxuan Lai, Zecheng Xie, Lianwen Jin
Abstract: Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layouts typical of document images. These characteristics demand a high level of detail perception ability from MLLMs. While increasing input resolution improves detail perception capability, it also leads to longer sequences of visual tokens, increasing computational costs and straining the models' ability to handle long contexts. To address these challenges, we introduce DocKylin, a document-centric MLLM that performs visual content slimming at both the pixel and token levels, thereby reducing token sequence length in VDU scenarios. We introduce an Adaptive Pixel Slimming (APS) preprocessing module to perform pixel-level slimming, increasing the proportion of informative pixels. Moreover, we propose a novel Dynamic Token Slimming (DTS) module to conduct token-level slimming, filtering essential tokens and removing others to adaptively create a more compact visual sequence. Experiments demonstrate DocKylin's promising performance across various VDU benchmarks and the effectiveness of each component.
Authors: Kirolos Ataallah, Chenhui Gou, Eslam Abdelrahman, Khushbu Pahwa, Jian Ding, Mohamed Elhoseiny
Abstract: Understanding long videos, ranging from tens of minutes to several hours, presents unique challenges in video comprehension. Despite the increasing importance of long-form video content, existing benchmarks primarily focus on shorter clips. To address this gap, we introduce InfiniBench a comprehensive benchmark for very long video understanding which presents 1)The longest video duration, averaging 52.59 minutes per video 2) The largest number of question-answer pairs, 108.2K 3) Diversity in questions that examine nine different skills and include both multiple-choice questions and open-ended questions 4) Human-centric, as the video sources come from movies and daily TV shows, with specific human-level question designs such as Movie Spoiler Questions that require critical thinking and comprehensive understanding. Using InfiniBench, we comprehensively evaluate existing Large Multi-Modality Models (LMMs) on each skill, including the commercial models such as GPT-4o and Gemini 1.5 Flash and the open-source models. The evaluation shows significant challenges in our benchmark. Our findings reveal that even leading AI models like GPT-4o and Gemini 1.5 Flash face challenges in achieving high performance in long video understanding, with average accuracies of just 49.16\% and 42.72\%, and average scores of 3.22 and 2.71 out of 5, respectively. We hope this benchmark will stimulate the LMMs community towards long video and human-level understanding. Our benchmark can be accessed at https://vision-cair.github.io/InfiniBench/
Authors: Chih-Chung Hsu, Shao-Ning Chen, Mei-Hsuan Wu, Yi-Fang Wang, Chia-Ming Lee, Yi-Shiuan Chou
Abstract: As DeepFake video manipulation techniques escalate, posing profound threats, the urgent need to develop efficient detection strategies is underscored. However, one particular issue lies with facial images being mis-detected, often originating from degraded videos or adversarial attacks, leading to unexpected temporal artifacts that can undermine the efficacy of DeepFake video detection techniques. This paper introduces a novel method for robust DeepFake video detection, harnessing the power of the proposed Graph-Regularized Attentive Convolutional Entanglement (GRACE) based on the graph convolutional network with graph Laplacian to address the aforementioned challenges. First, conventional Convolution Neural Networks are deployed to perform spatiotemporal features for the entire video. Then, the spatial and temporal features are mutually entangled by constructing a graph with sparse constraint, enforcing essential features of valid face images in the noisy face sequences remaining, thus augmenting stability and performance for DeepFake video detection. Furthermore, the Graph Laplacian prior is proposed in the graph convolutional network to remove the noise pattern in the feature space to further improve the performance. Comprehensive experiments are conducted to illustrate that our proposed method delivers state-of-the-art performance in DeepFake video detection under noisy face sequences. The source code is available at https://github.com/ming053l/GRACE.
Authors: Yibo Miao, Yifan Zhu, Yinpeng Dong, Lijia Yu, Jun Zhu, Xiao-Shan Gao
Abstract: The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its security risks. The generated videos may contain illegal or unethical content, and there is a lack of comprehensive quantitative understanding of their safety, posing a challenge to their reliability and practical deployment. Previous evaluations primarily focus on the quality of video generation. While some evaluations of text-to-image models have considered safety, they cover fewer aspects and do not address the unique temporal risk inherent in video generation. To bridge this research gap, we introduce T2VSafetyBench, a new benchmark designed for conducting safety-critical assessments of text-to-video models. We define 12 critical aspects of video generation safety and construct a malicious prompt dataset including real-world prompts, LLM-generated prompts and jailbreak attack-based prompts. Based on our evaluation results, we draw several important findings, including: 1) no single model excels in all aspects, with different models showing various strengths; 2) the correlation between GPT-4 assessments and manual reviews is generally high; 3) there is a trade-off between the usability and safety of text-to-video generative models. This indicates that as the field of video generation rapidly advances, safety risks are set to surge, highlighting the urgency of prioritizing video safety. We hope that T2VSafetyBench can provide insights for better understanding the safety of video generation in the era of generative AI.
Authors: Huafeng Qin, Xin Jin, Hongyu Zhu, Hongchao Liao, Moun\^im A. El-Yacoubi, Xinbo Gao
Abstract: Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image with patches from another to generate the mixed image. Similarly, the corresponding labels are linearly combined by a fixed ratio $\lambda$ by l. The objects in two images may be overlapped during the mixing process, so some semantic information is corrupted in the mixed samples. In this case, the mixed image does not match the mixed label information. Besides, such a label may mislead the deep learning model training, which results in poor performance. To solve this problem, we proposed a novel approach named SUMix to learn the mixing ratio as well as the uncertainty for the mixed samples during the training process. First, we design a learnable similarity function to compute an accurate mix ratio. Second, an approach is investigated as a regularized term to model the uncertainty of the mixed samples. We conduct experiments on five image benchmarks, and extensive experimental results imply that our method is capable of improving the performance of classifiers with different cutting-based mixup approaches. The source code is available at https://github.com/JinXins/SUMix.
Authors: Linh Van Ma, Tran Thien Dat Nguyen, Changbeom Shim, Du Yong Kim, Namkoo Ha, Moongu Jeon
Abstract: This paper proposes an online visual multi-object tracking (MOT) algorithm that resolves object appearance-reappearance and occlusion. Our solution is based on the labeled random finite set (LRFS) filtering approach, which in principle, addresses disappearance, appearance, reappearance, and occlusion via a single Bayesian recursion. However, in practice, existing numerical approximations cause reappearing objects to be initialized as new tracks, especially after long periods of being undetected. In occlusion handling, the filter's efficacy is dictated by trade-offs between the sophistication of the occlusion model and computational demand. Our contribution is a novel modeling method that exploits object features to address reappearing objects whilst maintaining a linear complexity in the number of detections. Moreover, to improve the filter's occlusion handling, we propose a fuzzy detection model that takes into consideration the overlapping areas between tracks and their sizes. We also develop a fast version of the filter to further reduce the computational time. The source code is publicly available at https://github.com/linh-gist/mv-glmb-ab.
Authors: Milena T. Bagdasarian, Paul Knoll, Florian Barthel, Anna Hilsmann, Peter Eisert, Wieland Morgenstern
Abstract: We present a work-in-progress survey on 3D Gaussian Splatting compression methods, focusing on their statistical performance across various benchmarks. This survey aims to facilitate comparability by summarizing key statistics of different compression approaches in a tabulated format. The datasets evaluated include TanksAndTemples, MipNeRF360, DeepBlending, and SyntheticNeRF. For each method, we report the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), and the resultant size in megabytes (MB), as provided by the respective authors. This is an ongoing, open project, and we invite contributions from the research community as GitHub issues or pull requests. Please visit http://w-m.github.io/3dgs-compression-survey/ for more information and a sortable version of the table.
Authors: Youssef Zahran, Gertjan Burghouts, Yke Bauke Eisma
Abstract: Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Compositional Zero-Shot Learning (CZSL) mainly focus on image classification. This paper aims to enhance CZSL in object detection without forgetting prior learned knowledge. We use Grounding DINO and incorporate Compositional Soft Prompting (CSP) into it and extend it with Compositional Anticipation. We achieve a 70.5% improvement over CSP on the harmonic mean (HM) between seen and unseen compositions on the CLEVR dataset. Furthermore, we introduce Contrastive Prompt Tuning to incrementally address model confusion between similar compositions. We demonstrate the effectiveness of this method and achieve an increase of 14.5% in HM across the pretrain, increment, and unseen sets. Collectively, these methods provide a framework for learning various compositions with limited data, as well as improving the performance of underperforming compositions when additional data becomes available.
Authors: Chang Liu, Giulia Rizzoli, Pietro Zanuttigh, Fu Li, Yi Niu
Abstract: Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this work, we argue that widely available web images can also be considered for the learning of new classes. To achieve this, firstly we introduce a strategy to select web images which are similar to previously seen examples in the latent space using a Fourier-based domain discriminator. Then, an effective caption-driven reharsal strategy is proposed to preserve previously learnt classes. To our knowledge, this is the first work to rely solely on web images for both the learning of new concepts and the preservation of the already learned ones in WILSS. Experimental results show that the proposed approach can reach state-of-the-art performances without using manually selected and annotated data in the incremental steps.
Authors: Decheng Liu, Zongqi Wang, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
Abstract: Due to the successful development of deep image generation technology, forgery detection plays a more important role in social and economic security. Racial bias has not been explored thoroughly in the deep forgery detection field. In the paper, we first contribute a dedicated dataset called the Fair Forgery Detection (FairFD) dataset, where we prove the racial bias of public state-of-the-art (SOTA) methods. Different from existing forgery detection datasets, the self-constructed FairFD dataset contains a balanced racial ratio and diverse forgery generation images with the largest-scale subjects. Additionally, we identify the problems with naive fairness metrics when benchmarking forgery detection models. To comprehensively evaluate fairness, we design novel metrics including Approach Averaged Metric and Utility Regularized Metric, which can avoid deceptive results. We also present an effective and robust post-processing technique, Bias Pruning with Fair Activations (BPFA), which improves fairness without requiring retraining or weight updates. Extensive experiments conducted with 12 representative forgery detection models demonstrate the value of the proposed dataset and the reasonability of the designed fairness metrics. By applying the BPFA to the existing fairest detector, we achieve a new SOTA. Furthermore, we conduct more in-depth analyses to offer more insights to inspire researchers in the community.
Authors: Chenshu Hou, Liang Peng, Xiaopei Wu, Xiaofei He, Wenxiao Wang
Abstract: 3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment to determine whether the descriptions are met. Most previous works attempt to accomplish both tasks within the same module, which can easily lead to a distraction of attention. To this end, we propose PD-APE, a dual-branch decoding framework that separately decodes target object attributes and surrounding layouts. Specifically, in the target object branch, the decoder processes text tokens that describe features of the target object (e.g., category and color), guiding the queries to pay attention to the target object itself. In the surrounding branch, the queries align with other text tokens that carry surrounding environment information, making the attention maps accurately capture the layout described in the text. Benefiting from the proposed dual-branch design, the queries are allowed to focus on points relevant to each branch's specific objective. Moreover, we design an adaptive position encoding method for each branch respectively. In the target object branch, the position encoding relies on the relative positions between seed points and predicted 3D boxes. In the surrounding branch, the attention map is additionally guided by the confidence between visual and text features, enabling the queries to focus on points that have valuable layout information. Extensive experiments demonstrate that we surpass the state-of-the-art on two widely adopted 3D visual grounding datasets, ScanRefer and Nr3D.
Authors: Qiao Li, Kanlun Tan, Qiao Liu, Di Yuan, Xin Li, Yunpeng Liu
Abstract: Due to the lack of large-scale labeled Thermal InfraRed (TIR) training datasets, most existing TIR trackers are trained directly on RGB datasets. However, tracking methods trained on RGB datasets suffer a significant drop-off in TIR data due to the domain shift issue. To this end, in this work, we propose a Progressive Domain Adaptation framework for TIR Tracking (PDAT), which transfers useful knowledge learned from RGB tracking to TIR tracking. The framework makes full use of large-scale labeled RGB datasets without requiring time-consuming and labor-intensive labeling of large-scale TIR data. Specifically, we first propose an adversarial-based global domain adaptation module to reduce domain gap on the feature level coarsely. Second, we design a clustering-based subdomain adaptation method to further align the feature distributions of the RGB and TIR datasets finely. These two domain adaptation modules gradually eliminate the discrepancy between the two domains, and thus learn domain-invariant fine-grained features through progressive training. Additionally, we collect a largescale TIR dataset with over 1.48 million unlabeled TIR images for training the proposed domain adaptation framework. Experimental results on five TIR tracking benchmarks show that the proposed method gains a nearly 6% success rate, demonstrating its effectiveness.
Authors: Sungmin Kang, Jaeha Song, Jihie Kim
Abstract: Understanding the morphological structure of medical images and precisely segmenting the region of interest or abnormality is an important task that can assist in diagnosis. However, the unique properties of medical imaging make clear segmentation difficult,and the high cost and time-consuming task of labeling leads to a coarse-grained representation of ground truth. Facing with these problems, we propose a novel Diffusion Transformer Segmentation (DTS) model for robust segmentation in the presence of noise. We propose an alternative to the dominant Denoising U-Net encoder through experiments applying a transformer architecture, which captures global dependency through self-attention. Additionally, we propose k-neighbor label smoothing, reverse boundary attention, and self-supervised learning with morphology-driven learning to improve the ability to identify complex structures. Our model, which analyzes the morphological representation of images, shows better results than the previous models in various medical imaging modalities, including CT, MRI, and lesion images.
Authors: Haochen Zhao, Hui Meng, Deqian Yang, Xiaozheng Xie, Xiaoze Wu, Qingfeng Li, Jianwei Niu
Abstract: Semi-supervised multi-organ medical image segmentation aids physicians in improving disease diagnosis and treatment planning and reduces the time and effort required for organ annotation.Existing state-of-the-art methods train the labeled data with ground truths and train the unlabeled data with pseudo-labels. However, the two training flows are separate, which does not reflect the interrelationship between labeled and unlabeled data.To address this issue, we propose a semi-supervised multi-organ segmentation method called GuidedNet, which leverages the knowledge from labeled data to guide the training of unlabeled data. The primary goals of this study are to improve the quality of pseudo-labels for unlabeled data and to enhance the network's learning capability for both small and complex organs.A key concept is that voxel features from labeled and unlabeled data that are close to each other in the feature space are more likely to belong to the same class.On this basis, a 3D Consistent Gaussian Mixture Model (3D-CGMM) is designed to leverage the feature distributions from labeled data to rectify the generated pseudo-labels.Furthermore, we introduce a Knowledge Transfer Cross Pseudo Supervision (KT-CPS) strategy, which leverages the prior knowledge obtained from the labeled data to guide the training of the unlabeled data, thereby improving the segmentation accuracy for both small and complex organs. Extensive experiments on two public datasets, FLARE22 and AMOS, demonstrated that GuidedNet is capable of achieving state-of-the-art performance. The source code with our proposed model are available at https://github.com/kimjisoo12/GuidedNet.
Authors: Long Bai, Guankun Wang, Mobarakol Islam, Lalithkumar Seenivasan, An Wang, Hongliang Ren
Abstract: Medical visual question answering (VQA) bridges the gap between visual information and clinical decision-making, enabling doctors to extract understanding from clinical images and videos. In particular, surgical VQA can enhance the interpretation of surgical data, aiding in accurate diagnoses, effective education, and clinical interventions. However, the inability of VQA models to visually indicate the regions of interest corresponding to the given questions results in incomplete comprehension of the surgical scene. To tackle this, we propose the surgical visual question localized-answering (VQLA) for precise and context-aware responses to specific queries regarding surgical images. Furthermore, to address the strong demand for safety in surgical scenarios and potential corruptions in image acquisition and transmission, we propose a novel approach called Calibrated Co-Attention Gated Vision-Language (C$^2$G-ViL) embedding to integrate and align multimodal information effectively. Additionally, we leverage the adversarial sample-based contrastive learning strategy to boost our performance and robustness. We also extend our EndoVis-18-VQLA and EndoVis-17-VQLA datasets to broaden the scope and application of our data. Extensive experiments on the aforementioned datasets demonstrate the remarkable performance and robustness of our solution. Our solution can effectively combat real-world image corruption. Thus, our proposed approach can serve as an effective tool for assisting surgical education, patient care, and enhancing surgical outcomes.
Authors: Sarah Barrington, Matyas Bohacek, Hany Farid
Abstract: We describe a large-scale dataset--DeepSpeak--of real and deepfake footage of people talking and gesturing in front of their webcams. The real videos in this first version of the dataset consist of 17 hours of footage from 220 diverse individuals. Constituting more than 26 hours of footage, the fake videos consist of a range of different state-of-the-art face-swap and lip-sync deepfakes with natural and AI-generated voices. We expect to release future versions of this dataset with different and updated deepfake technologies. This dataset is made freely available for research and non-commercial uses; requests for commercial use will be considered.
Authors: Shishir Reddy Vutukur, Mengkejiergeli Ba, Benjamin Busam, Matthias Kayser, Gurprit Singh
Abstract: In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the 6D pose of the object in the embedding space by learning shape representation at a given pose. This model enables us to learn pose by performing shape representation at a target pose from RGB image input. We perform shape representation as an auxiliary task which helps us in learning rotations space for an object based on 2D images. An image encoder predicts the rotation in the embedding space and the DeepSDF based decoder learns to represent the object's shape at the given pose. As our approach is shape based, the pipeline is suitable for any type of object irrespective of the symmetry. Moreover, we need only a CAD model of the objects to train SABER. Our pipeline is synthetic data based and can also handle symmetric objects without symmetry labels and, thus, no additional labeled training data is needed. The experimental evaluation shows that our method achieves close to benchmark results for both symmetric objects and asymmetric objects on Occlusion-LineMOD, and T-LESS datasets.
Authors: Yecheng Zhang, Huimin Zhao, Ying Long
Abstract: Rapidly acquiring three-dimensional (3D) building data, including geometric attributes like rooftop, height and orientations, as well as indicative attributes like function, quality, and age, is essential for accurate urban analysis, simulations, and policy updates. Current building datasets suffer from incomplete coverage of building multi-attributes. This paper introduces a geospatial artificial intelligence (GeoAI) framework for large-scale building modeling, presenting the first national-scale Multi-Attribute Building dataset (CMAB), covering 3,667 spatial cities, 29 million buildings, and 21.3 billion square meters of rooftops with an F1-Score of 89.93% in OCRNet-based extraction, totaling 337.7 billion cubic meters of building stock. We trained bootstrap aggregated XGBoost models with city administrative classifications, incorporating features such as morphology, location, and function. Using multi-source data, including billions of high-resolution Google Earth images and 60 million street view images (SVIs), we generated rooftop, height, function, age, and quality attributes for each building. Accuracy was validated through model benchmarks, existing similar products, and manual SVI validation, mostly above 80%. Our dataset and results are crucial for global SDGs and urban planning.
Authors: Shizhou Zhang, Wenlong Luo, De Cheng, Qingchun Yang, Lingyan Ran, Yinghui Xing, Yanning Zhang
Abstract: In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185,907 images and 5,576 tracklets, featuring 2,788 distinct identities. To our knowledge, this is the first dataset for video ReID under Ground-to-Aerial scenarios. G2A-VReID dataset has the following characteristics: 1) Drastic view changes; 2) Large number of annotated identities; 3) Rich outdoor scenarios; 4) Huge difference in resolution. Additionally, we propose a new benchmark approach for cross-platform ReID by transforming the cross-platform visual alignment problem into visual-semantic alignment through vision-language model (i.e., CLIP) and applying a parameter-efficient Video Set-Level-Adapter module to adapt image-based foundation model to video ReID tasks, termed VSLA-CLIP. Besides, to further reduce the great discrepancy across the platforms, we also devise the platform-bridge prompts for efficient visual feature alignment. Extensive experiments demonstrate the superiority of the proposed method on all existing video ReID datasets and our proposed G2A-VReID dataset.
Authors: Zhongliang Guo, Lei Fang, Jingyu Lin, Yifei Qian, Shuai Zhao, Zeyu Wang, Junhao Dong, Cunjian Chen, Ognjen Arandjelovi\'c, Chun Pong Lau
Abstract: Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have revolutionized image synthesis and manipulation. However, these generative techniques raises concerns about data misappropriation and intellectual property infringement. Adversarial attacks on machine learning models have been extensively studied, and a well-established body of research has extended these techniques as a benign metric to prevent the underlying misuse of generative AI. Current approaches to safeguarding images from manipulation by LDMs are limited by their reliance on model-specific knowledge and their inability to significantly degrade semantic quality of generated images. In response to these shortcomings, we propose the Posterior Collapse Attack (PCA) based on the observation that VAEs suffer from posterior collapse during training. Our method minimizes dependence on the white-box information of target models to get rid of the implicit reliance on model-specific knowledge. By accessing merely a small amount of LDM parameters, in specific merely the VAE encoder of LDMs, our method causes a substantial semantic collapse in generation quality, particularly in perceptual consistency, and demonstrates strong transferability across various model architectures. Experimental results show that PCA achieves superior perturbation effects on image generation of LDMs with lower runtime and VRAM. Our method outperforms existing techniques, offering a more robust and generalizable solution that is helpful in alleviating the socio-technical challenges posed by the rapidly evolving landscape of generative AI.
Authors: Minhyeok Lee, Suhwan Cho, Chajin Shin, Jungho Lee, Sunghun Yang, Sangyoun Lee
Abstract: Propagation-based video inpainting using optical flow at the pixel or feature level has recently garnered significant attention. However, it has limitations such as the inaccuracy of optical flow prediction and the propagation of noise over time. These issues result in non-uniform noise and time consistency problems throughout the video, which are particularly pronounced when the removed area is large and involves substantial movement. To address these issues, we propose a novel First Frame Filling Video Diffusion Inpainting model (FFF-VDI). We design FFF-VDI inspired by the capabilities of pre-trained image-to-video diffusion models that can transform the first frame image into a highly natural video. To apply this to the video inpainting task, we propagate the noise latent information of future frames to fill the masked areas of the first frame's noise latent code. Next, we fine-tune the pre-trained image-to-video diffusion model to generate the inpainted video. The proposed model addresses the limitations of existing methods that rely on optical flow quality, producing much more natural and temporally consistent videos. This proposed approach is the first to effectively integrate image-to-video diffusion models into video inpainting tasks. Through various comparative experiments, we demonstrate that the proposed model can robustly handle diverse inpainting types with high quality.
Authors: Can Qin, Congying Xia, Krithika Ramakrishnan, Michael Ryoo, Lifu Tu, Yihao Feng, Manli Shu, Honglu Zhou, Anas Awadalla, Jun Wang, Senthil Purushwalkam, Le Xue, Yingbo Zhou, Huan Wang, Silvio Savarese, Juan Carlos Niebles, Zeyuan Chen, Ran Xu, Caiming Xiong
Abstract: We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM) architecture and introduce a video variational autoencoder (VidVAE). VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens and the computational demands associated with generating long-sequence videos. To further address the computational costs, we propose a divide-and-merge strategy that maintains temporal consistency across video segments. Our Diffusion Transformer (DiT) model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios. We have devised a data processing pipeline from the very beginning and collected over 13M high-quality video-text pairs. The pipeline includes multiple steps such as clipping, text detection, motion estimation, aesthetics scoring, and dense captioning based on our in-house video-LLM model. Training the VidVAE and DiT models required approximately 40 and 642 H100 days, respectively. Our model supports over 14-second 720p video generation in an end-to-end way and demonstrates competitive performance against state-of-the-art T2V models.
Authors: Luyang Luo, Mingxiang Wu, Mei Li, Yi Xin, Qiong Wang, Varut Vardhanabhuti, Winnie CW Chu, Zhenhui Li, Juan Zhou, Pranav Rajpurkar, Hao Chen
Abstract: Breast magnetic resonance imaging (MRI) is the imaging technique with the highest sensitivity for detecting breast cancer and is routinely used for women at high risk. Despite the comprehensive multiparametric protocol of breast MRI, existing artificial intelligence-based studies predominantly rely on single sequences and have limited validation. Here we report a large mixture-of-modality-experts model (MOME) that integrates multiparametric MRI information within a unified structure, offering a noninvasive method for personalized breast cancer management. We have curated the largest multiparametric breast MRI dataset, involving 5,205 patients from three hospitals in the north, southeast, and southwest of China, for the development and extensive evaluation of our model. MOME demonstrated accurate and robust identification of breast cancer. It achieved comparable performance for malignancy recognition to that of four senior radiologists and significantly outperformed a junior radiologist, with 0.913 AUROC, 0.948 AUPRC, 0.905 F1 score, and 0.723 MCC. Our findings suggest that MOME could reduce the need for biopsies in BI-RADS 4 patients with a ratio of 7.3%, classify triple-negative breast cancer with an AUROC of 0.709, and predict pathological complete response to neoadjuvant chemotherapy with an AUROC of 0.694. The model further supports scalable and interpretable inference, adapting to missing modalities and providing decision explanations by highlighting lesions and measuring modality contributions. MOME exemplifies a discriminative, robust, scalable, and interpretable multimodal model, paving the way for noninvasive, personalized management of breast cancer patients based on multiparametric breast imaging data.
Authors: Wenhao Li, Yichao Cao, Xiu Su, Xi Lin, Shan You, Mingkai Zheng, Yi Chen, Chang Xu
Abstract: Video generation models hold substantial potential in areas such as filmmaking. However, current video diffusion models need high computational costs and produce suboptimal results due to high complexity of video generation task. In this paper, we propose \textbf{ConFiner}, an efficient high-quality video generation framework that decouples video generation into easier subtasks: structure \textbf{con}trol and spatial-temporal re\textbf{fine}ment. It can generate high-quality videos with chain of off-the-shelf diffusion model experts, each expert responsible for a decoupled subtask. During the refinement, we introduce coordinated denoising, which can merge multiple diffusion experts' capabilities into a single sampling. Furthermore, we design ConFiner-Long framework, which can generate long coherent video with three constraint strategies on ConFiner. Experimental results indicate that with only 10\% of the inference cost, our ConFiner surpasses representative models like Lavie and Modelscope across all objective and subjective metrics. And ConFiner-Long can generate high-quality and coherent videos with up to 600 frames.
Authors: Zhuoyue Wang, Yiyi Tao, Danqing Ma, Jiajing Chen
Abstract: In this paper, a color edge detection strategy based on collaborative filtering combined with multiscale gradient fusion is proposed. The block-matching and 3D (BM3D) filter are used to enhance the sparse representation in the transform domain and achieve the effect of denoising, whereas the multiscale gradient fusion makes up for the defect of loss of details in single-scale edge detection and improves the edge detection resolution and quality. First, the RGB images in the dataset are converted to XYZ color space images through mathematical operations. Second, the colored block-matching and 3D (CBM3D) filter are used on the sparse images and to remove noise interference. Then, the vector gradients of the color image and the anisotropic Gaussian directional derivative of the two scale parameters are calculated and averaged pixel-by-pixel to obtain a new edge strength map. Finally, the edge features are enhanced by image normalization and non-maximum suppression technology, and on that basis, the edge contour is obtained by double threshold selection and a new morphological refinement method. Through an experimental analysis of the edge detection dataset, the method proposed has good noise robustness and high edge quality, which is better than the Color Sobel, Color Canny, SE and Color AGDD as shown by the PR curve, AUC, PSNR, MSE, and FOM indicators.
Authors: Kunpeng Wang, Danying Lin, Chenglong Li, Zhengzheng Tu, Bin Luo
Abstract: Although most existing multi-modal salient object detection (SOD) methods demonstrate effectiveness through training models from scratch, the limited multi-modal data hinders these methods from reaching optimality. In this paper, we propose a novel framework to explore and exploit the powerful feature representation and zero-shot generalization ability of the pre-trained Segment Anything Model (SAM) for multi-modal SOD. Despite serving as a recent vision fundamental model, driving the class-agnostic SAM to comprehend and detect salient objects accurately is non-trivial, especially in challenging scenes. To this end, we develop \underline{SAM} with se\underline{m}antic f\underline{e}ature fu\underline{s}ion guidanc\underline{e} (Sammese), which incorporates multi-modal saliency-specific knowledge into SAM to adapt SAM to multi-modal SOD tasks. However, it is difficult for SAM trained on single-modal data to directly mine the complementary benefits of multi-modal inputs and comprehensively utilize them to achieve accurate saliency prediction. To address these issues, we first design a multi-modal complementary fusion module to extract robust multi-modal semantic features by integrating information from visible and thermal or depth image pairs. Then, we feed the extracted multi-modal semantic features into both the SAM image encoder and mask decoder for fine-tuning and prompting, respectively. Specifically, in the image encoder, a multi-modal adapter is proposed to adapt the single-modal SAM to multi-modal information. In the mask decoder, a semantic-geometric prompt generation strategy is proposed to produce corresponding embeddings with various saliency cues. Extensive experiments on both RGB-D and RGB-T SOD benchmarks show the effectiveness of the proposed framework. The code will be available at \url{https://github.com/Angknpng/Sammese}.
Authors: Yu-Hsuan Hsieh, Shang-Hong Lai
Abstract: To improve logical anomaly detection, some previous works have integrated segmentation techniques with conventional anomaly detection methods. Although these methods are effective, they frequently lead to unsatisfactory segmentation results and require manual annotations. To address these drawbacks, we develop an unsupervised component segmentation technique that leverages foundation models to autonomously generate training labels for a lightweight segmentation network without human labeling. Integrating this new segmentation technique with our proposed Patch Histogram module and the Local-Global Student-Teacher (LGST) module, we achieve a detection AUROC of 95.3% in the MVTec LOCO AD dataset, which surpasses previous SOTA methods. Furthermore, our proposed method provides lower latency and higher throughput than most existing approaches.
Authors: Michael G. DeMoor, John J. Prevost
Abstract: Deep Metric Learning (DML) loss functions traditionally aim to control the forces of separability and compactness within an embedding space so that the same class data points are pulled together and different class ones are pushed apart. Within the context of DML, a softmax operation will typically normalize distances into a probability for optimization, thus coupling all the push/pull forces together. This paper proposes a potential new class of loss functions that operate within a euclidean domain and aim to take full advantage of the coupled forces governing embedding space formation under a softmax. These forces of compactness and separability can be boosted or mitigated within controlled locations at will by using a warping function. In this work, we provide a simple example of a warping function and use it to achieve competitive, state-of-the-art results on various metric learning benchmarks.
Authors: Qian Wang, Zhaoyang Bu, Jiaxuan Mao, Wenyu Zhu, Jingya Zhao, Wei Du, Guochao Shi, Min Zhou, Si Chen, Jieming Qu
Abstract: Recent advancements in deep learning techniques have sparked performance boosts in various real-world applications including disease diagnosis based on multi-modal medical data. Cough sound data-based respiratory disease (e.g., COVID-19 and Chronic Obstructive Pulmonary Disease) diagnosis has also attracted much attention. However, existing works usually utilise traditional machine learning or deep models of moderate scales. On the other hand, the developed approaches are trained and evaluated on small-scale data due to the difficulty of curating and annotating clinical data on scale. To address these issues in prior works, we create a unified framework to evaluate various deep models from lightweight Convolutional Neural Networks (e.g., ResNet18) to modern vision transformers and compare their performance in respiratory disease classification. Based on the observations from such an extensive empirical study, we propose a novel approach to cough-based disease classification based on both self-supervised and supervised learning on a large-scale cough data set. Experimental results demonstrate our proposed approach outperforms prior arts consistently on two benchmark datasets for COVID-19 diagnosis and a proprietary dataset for COPD/non-COPD classification with an AUROC of 92.5%.
Authors: Dilermando Queiroz, Anderson Carlos, Ma\'ira Fatoretto, Luis Filipe Nakayama, Andr\'e Anjos, Lilian Berton
Abstract: Foundation models have emerged as robust models with label efficiency in diverse domains. In medical imaging, these models contribute to the advancement of medical diagnoses due to the difficulty in obtaining labeled data. However, it is unclear whether using a large amount of unlabeled data, biased by the presence of sensitive attributes during pre-training, influences the fairness of the model. This research examines the bias in the Foundation model (RetFound) when it is applied to fine-tune the Brazilian Multilabel Ophthalmological Dataset (BRSET), which has a different population than the pre-training dataset. The model evaluation, in comparison with supervised learning, shows that the Foundation Model has the potential to reduce the gap between the maximum AUC and minimum AUC evaluations across gender and age groups. However, in a data-efficient generalization, the model increases the bias when the data amount decreases. These findings suggest that when deploying a Foundation Model in real-life scenarios with limited data, the possibility of fairness issues should be considered.
Authors: Pardis Afshar, Sajjad Hashembeiki, Pouya Khani, Emad Fatemizadeh, Mohammad Hossein Rohban
Abstract: Histopathological image analysis is crucial for accurate cancer diagnosis and treatment planning. While deep learning models, especially convolutional neural networks, have advanced this field, their "black-box" nature raises concerns about interpretability and trustworthiness. Explainable Artificial Intelligence (XAI) techniques aim to address these concerns, but evaluating their effectiveness remains challenging. A significant issue with current occlusion-based XAI methods is that they often generate Out-of-Distribution (OoD) samples, leading to inaccurate evaluations. In this paper, we introduce Inpainting-Based Occlusion (IBO), a novel occlusion strategy that utilizes a Denoising Diffusion Probabilistic Model to inpaint occluded regions in histopathological images. By replacing cancerous areas with realistic, non-cancerous tissue, IBO minimizes OoD artifacts and preserves data integrity. We evaluate our method on the CAMELYON16 dataset through two phases: first, by assessing perceptual similarity using the Learned Perceptual Image Patch Similarity (LPIPS) metric, and second, by quantifying the impact on model predictions through Area Under the Curve (AUC) analysis. Our results demonstrate that IBO significantly improves perceptual fidelity, achieving nearly twice the improvement in LPIPS scores compared to the best existing occlusion strategy. Additionally, IBO increased the precision of XAI performance prediction from 42% to 71% compared to traditional methods. These results demonstrate IBO's potential to provide more reliable evaluations of XAI techniques, benefiting histopathology and other applications. The source code for this study is available at https://github.com/a-fsh-r/IBO.
Authors: Zhirui Gao, Renjiao Yi, Chenyang Zhu, Ke Zhuang, Wei Chen, Kai Xu
Abstract: Radiance fields including NeRFs and 3D Gaussians demonstrate great potential in high-fidelity rendering and scene reconstruction, while they require a substantial number of posed images as inputs. COLMAP is frequently employed for preprocessing to estimate poses, while it necessitates a large number of feature matches to operate effectively, and it struggles with scenes characterized by sparse features, large baselines between images, or a limited number of input images. We aim to tackle few-view NeRF reconstruction using only 3 to 6 unposed scene images. Traditional methods often use calibration boards but they are not common in images. We propose a novel idea of utilizing everyday objects, commonly found in both images and real life, as "pose probes". The probe object is automatically segmented by SAM, whose shape is initialized from a cube. We apply a dual-branch volume rendering optimization (object NeRF and scene NeRF) to constrain the pose optimization and jointly refine the geometry. Specifically, object poses of two views are first estimated by PnP matching in an SDF representation, which serves as initial poses. PnP matching, requiring only a few features, is suitable for feature-sparse scenes. Additional views are incrementally incorporated to refine poses from preceding views. In experiments, PoseProbe achieves state-of-the-art performance in both pose estimation and novel view synthesis across multiple datasets. We demonstrate its effectiveness, particularly in few-view and large-baseline scenes where COLMAP struggles. In ablations, using different objects in a scene yields comparable performance. Our project page is available at: \href{https://zhirui-gao.github.io/PoseProbe.github.io/}{this https URL}
Authors: Theodoros Kouzelis, Manos Plitsis, Mihalis A. Nicolaou, Yannis Panagakis
Abstract: Recent advances in Diffusion Models (DMs) have led to significant progress in visual synthesis and editing tasks, establishing them as a strong competitor to Generative Adversarial Networks (GANs). However, the latent space of DMs is not as well understood as that of GANs. Recent research has focused on unsupervised semantic discovery in the latent space of DMs by leveraging the bottleneck layer of the denoising network, which has been shown to exhibit properties of a semantic latent space. However, these approaches are limited to discovering global attributes. In this paper we address, the challenge of local image manipulation in DMs and introduce an unsupervised method to factorize the latent semantics learned by the denoising network of pre-trained DMs. Given an arbitrary image and defined regions of interest, we utilize the Jacobian of the denoising network to establish a relation between the regions of interest and their corresponding subspaces in the latent space. Furthermore, we disentangle the joint and individual components of these subspaces to identify latent directions that enable local image manipulation. Once discovered, these directions can be applied to different images to produce semantically consistent edits, making our method suitable for practical applications. Experimental results on various datasets demonstrate that our method can produce semantic edits that are more localized and have better fidelity compared to the state-of-the-art.
Authors: Chun Tong Lei, Hon Ming Yam, Zhongliang Guo, Chun Pong Lau
Abstract: Neural networks, despite their remarkable performance in widespread applications, including image classification, are also known to be vulnerable to subtle adversarial noise. Although some diffusion-based purification methods have been proposed, for example, DiffPure, those methods are time-consuming. In this paper, we propose One Step Control Purification (OSCP), a diffusion-based purification model that can purify the adversarial image in one Neural Function Evaluation (NFE) in diffusion models. We use Latent Consistency Model (LCM) and ControlNet for our one-step purification. OSCP is computationally friendly and time efficient compared to other diffusion-based purification methods; we achieve defense success rate of 74.19\% on ImageNet, only requiring 0.1s for each purification. Moreover, there is a fundamental incongruence between consistency distillation and adversarial perturbation. To address this ontological dissonance, we propose Gaussian Adversarial Noise Distillation (GAND), a novel consistency distillation framework that facilitates a more nuanced reconciliation of the latent space dynamics, effectively bridging the natural and adversarial manifolds. Our experiments show that the GAND does not need a Full Fine Tune (FFT); PEFT, e.g., LoRA is sufficient.
Authors: Avideep Mukherjee, Soumya Banerjee, Piyush Rai, Vinay P. Namboodiri
Abstract: Diffusion-based models demonstrate impressive generation capabilities. However, they also have a massive number of parameters, resulting in enormous model sizes, thus making them unsuitable for deployment on resource-constraint devices. Block-wise generation can be a promising alternative for designing compact-sized (parameter-efficient) deep generative models since the model can generate one block at a time instead of generating the whole image at once. However, block-wise generation is also considerably challenging because ensuring coherence across generated blocks can be non-trivial. To this end, we design a retrieval-augmented generation (RAG) approach and leverage the corresponding blocks of the images retrieved by the RAG module to condition the training and generation stages of a block-wise denoising diffusion model. Our conditioning schemes ensure coherence across the different blocks during training and, consequently, during generation. While we showcase our approach using the latent diffusion model (LDM) as the base model, it can be used with other variants of denoising diffusion models. We validate the solution of the coherence problem through the proposed approach by reporting substantive experiments to demonstrate our approach's effectiveness in compact model size and excellent generation quality.
Authors: Shuyi Ouyang, Jinyang Zhang, Xiangye Lin, Xilai Wang, Qingqing Chen, Yen-Wei Chen, Lanfen Lin
Abstract: Conventional medical image segmentation methods have been found inadequate in facilitating physicians with the identification of specific lesions for diagnosis and treatment. Given the utility of text as an instructional format, we introduce a novel task termed Medical Image Referring Segmentation (MIRS), which requires segmenting specified lesions in images based on the given language expressions. Due to the varying object scales in medical images, MIRS demands robust vision-language modeling and comprehensive multi-scale interaction for precise localization and segmentation under linguistic guidance. However, existing medical image segmentation methods fall short in meeting these demands, resulting in insufficient segmentation accuracy. In response, we propose an approach named Language-guided Scale-aware MedSegmentor (LSMS), incorporating two appealing designs: (1)~a Scale-aware Vision-Language Attention module that leverages diverse convolutional kernels to acquire rich visual knowledge and interact closely with linguistic features, thereby enhancing lesion localization capability; (2)~a Full-Scale Decoder that globally models multi-modal features across various scales, capturing complementary information between scales to accurately outline lesion boundaries. Addressing the lack of suitable datasets for MIRS, we constructed a vision-language medical dataset called Reference Hepatic Lesion Segmentation (RefHL-Seg). This dataset comprises 2,283 abdominal CT slices from 231 cases, with corresponding textual annotations and segmentation masks for various liver lesions in images. We validated the performance of LSMS for MIRS and conventional medical image segmentation tasks across various datasets. Our LSMS consistently outperforms on all datasets with lower computational costs. The code and datasets will be released.
Authors: Naoki Wake, Atsushi Kanehira, Kazuhiro Sasabuchi, Jun Takamatsu, Katsushi Ikeuchi
Abstract: Video action localization aims to find timings of a specific action from a long video. Although existing learning-based approaches have been successful, those require annotating videos that come with a considerable labor cost. This paper proposes a learning-free, open-vocabulary approach based on emerging off-the-shelf vision-language models (VLM). The challenge stems from the fact that VLMs are neither designed to process long videos nor tailored for finding actions. We overcome these problems by extending an iterative visual prompting technique. Specifically, we sample video frames into a concatenated image with frame index labels, making a VLM guess a frame that is considered to be closest to the start/end of the action. Iterating this process by narrowing a sampling time window results in finding a specific frame of start and end of an action. We demonstrate that this sampling technique yields reasonable results, illustrating a practical extension of VLMs for understanding videos. A sample code is available at https://microsoft.github.io/VLM-Video-Action-Localization/.
URLs: https://microsoft.github.io/VLM-Video-Action-Localization/.
Authors: Somdyuti Paul, Andrey Norkin, Alan C. Bovik
Abstract: Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection requires a video shot to be pre-encoded with multiple encoding parameters to find the optimal operating points given by the convex hull of the resulting rate-quality curves. However, this pre-encoding step is equivalent to an exhaustive search process over the space of possible encoding parameters, which causes significant overhead in terms of both computation and time expenditure. To reduce this overhead, we propose a deep learning based method of content aware convex hull prediction. We employ a recurrent convolutional network (RCN) to implicitly analyze the spatiotemporal complexity of video shots in order to predict their convex hulls. A two-step transfer learning scheme is adopted to train our proposed RCN-Hull model, which ensures sufficient content diversity to analyze scene complexity, while also making it possible to capture the scene statistics of pristine source videos. Our experimental results reveal that our proposed model yields better approximations of the optimal convex hulls, and offers competitive time savings as compared to existing approaches. On average, the pre-encoding time was reduced by 53.8% by our method, while the average Bjontegaard delta bitrate (BD-rate) of the predicted convex hulls against ground truth was 0.26%, and the mean absolute deviation of the BD-rate distribution was 0.57%.
Authors: Yulin Yang, Patrick Geneva, Guoquan Huang
Abstract: In this paper, we study state estimation of multi-visual-inertial systems (MVIS) and develop sensor fusion algorithms to optimally fuse an arbitrary number of asynchronous inertial measurement units (IMUs) or gyroscopes and global and(or) rolling shutter cameras. We are especially interested in the full calibration of the associated visual-inertial sensors, including the IMU or camera intrinsics and the IMU-IMU(or camera) spatiotemporal extrinsics as well as the image readout time of rolling-shutter cameras (if used). To this end, we develop a new analytic combined IMU integration with intrinsics-termed ACI3-to preintegrate IMU measurements, which is leveraged to fuse auxiliary IMUs and(or) gyroscopes alongside a base IMU. We model the multi-inertial measurements to include all the necessary inertial intrinsic and IMU-IMU spatiotemporal extrinsic parameters, while leveraging IMU-IMU rigid-body constraints to eliminate the necessity of auxiliary inertial poses and thus reducing computational complexity. By performing observability analysis of MVIS, we prove that the standard four unobservable directions remain - no matter how many inertial sensors are used, and also identify, for the first time, degenerate motions for IMU-IMU spatiotemporal extrinsics and auxiliary inertial intrinsics. In addition to the extensive simulations that validate our analysis and algorithms, we have built our own MVIS sensor rig and collected over 25 real-world datasets to experimentally verify the proposed calibration against the state-of-the-art calibration method such as Kalibr. We show that the proposed MVIS calibration is able to achieve competing accuracy with improved convergence and repeatability, which is open sourced to better benefit the community.
Authors: Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Hao Bai, Yuexiang Zhai, Benjamin D. Haeffele, Yi Ma
Abstract: In this paper, we contend that a natural objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a low-dimensional Gaussian mixture supported on incoherent subspaces. The goodness of such a representation can be evaluated by a principled measure, called sparse rate reduction, that simultaneously maximizes the intrinsic information gain and extrinsic sparsity of the learned representation. From this perspective, popular deep network architectures, including transformers, can be viewed as realizing iterative schemes to optimize this measure. Particularly, we derive a transformer block from alternating optimization on parts of this objective: the multi-head self-attention operator compresses the representation by implementing an approximate gradient descent step on the coding rate of the features, and the subsequent multi-layer perceptron sparsifies the features. This leads to a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable. We show, by way of a novel connection between denoising and compression, that the inverse to the aforementioned compressive encoding can be realized by the same class of CRATE architectures. Thus, the so-derived white-box architectures are universal to both encoders and decoders. Experiments show that these networks, despite their simplicity, indeed learn to compress and sparsify representations of large-scale real-world image and text datasets, and achieve performance very close to highly engineered transformer-based models: ViT, MAE, DINO, BERT, and GPT2. We believe the proposed computational framework demonstrates great potential in bridging the gap between theory and practice of deep learning, from a unified perspective of data compression. Code is available at: https://ma-lab-berkeley.github.io/CRATE .
Authors: Haoxiang Gao, Yaqian Li, Kaiwen Long, Ming Yang, Yiqing Shen
Abstract: The advent of foundation models has revolutionized the fields of natural language processing and computer vision, paving the way for their application in autonomous driving (AD). This survey presents a comprehensive review of more than 40 research papers, demonstrating the role of foundation models in enhancing AD. Large language models contribute to planning and simulation in AD, particularly through their proficiency in reasoning, code generation and translation. In parallel, vision foundation models are increasingly adapted for critical tasks such as 3D object detection and tracking, as well as creating realistic driving scenarios for simulation and testing. Multi-modal foundation models, integrating diverse inputs, exhibit exceptional visual understanding and spatial reasoning, crucial for end-to-end AD. This survey not only provides a structured taxonomy, categorizing foundation models based on their modalities and functionalities within the AD domain but also delves into the methods employed in current research. It identifies the gaps between existing foundation models and cutting-edge AD approaches, thereby charting future research directions and proposing a roadmap for bridging these gaps.
Authors: Yiqiao Jin, Minje Choi, Gaurav Verma, Jindong Wang, Srijan Kumar
Abstract: Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces. Multimodal Large Language Models (MLLMs) have emerged as a promising solution to these challenges, yet they struggle to accurately interpret human emotions and complex content such as misinformation. This paper introduces MM-Soc, a comprehensive benchmark designed to evaluate MLLMs' understanding of multimodal social media content. MM-Soc compiles prominent multimodal datasets and incorporates a novel large-scale YouTube tagging dataset, targeting a range of tasks from misinformation detection, hate speech detection, and social context generation. Through our exhaustive evaluation on ten size-variants of four open-source MLLMs, we have identified significant performance disparities, highlighting the need for advancements in models' social understanding capabilities. Our analysis reveals that, in a zero-shot setting, various types of MLLMs generally exhibit difficulties in handling social media tasks. However, MLLMs demonstrate performance improvements post fine-tuning, suggesting potential pathways for improvement. Our code and data are available at https://github.com/claws-lab/MMSoc.git.
Authors: Kevin Xu, Yeganeh Kordi, Tanay Nayak, Ado Asija, Yizhong Wang, Kate Sanders, Adam Byerly, Jingyu Zhang, Benjamin Van Durme, Daniel Khashabi
Abstract: Can advanced multi-modal models effectively tackle complex web-based tasks? Such tasks are often found on crowdsourcing platforms, where crowdworkers engage in challenging micro-tasks within web-based environments. Building on this idea, we present TurkingBench, a benchmark consisting of tasks presented as web pages with textual instructions and multi-modal contexts. Unlike previous approaches that rely on artificially synthesized web pages, our benchmark uses natural HTML pages originally designed for crowdsourcing workers to perform various annotation tasks. Each task's HTML instructions are instantiated with different values derived from crowdsourcing tasks, creating diverse instances. This benchmark includes 32.2K instances spread across 158 tasks. To support the evaluation of TurkingBench, we have developed a framework that links chatbot responses to actions on web pages (e.g., modifying a text box, selecting a radio button). We assess the performance of cutting-edge private and open-source models, including language-only and vision-language models (such as GPT4 and InternVL), on this benchmark. Our results show that while these models outperform random chance, there is still significant room for improvement. We hope that this benchmark will drive progress in the evaluation and development of web-based agents.
Authors: Jindong Gu
Abstract: In recent years, generative AI (GenAI), like large language models and text-to-image models, has received significant attention across various domains. However, ensuring the responsible generation of content by these models is crucial for their real-world applicability. This raises an interesting question: What should responsible GenAI generate, and what should it not? To answer the question, this paper investigates the practical responsible requirements of both textual and visual generative models, outlining five key considerations: generating truthful content, avoiding toxic content, refusing harmful instruction, leaking no training data-related content, and ensuring generated content identifiable. Specifically, we review recent advancements and challenges in addressing these requirements. Besides, we discuss and emphasize the importance of responsible GenAI across healthcare, education, finance, and artificial general intelligence domains. Through a unified perspective on both textual and visual generative models, this paper aims to provide insights into practical safety-related issues and further benefit the community in building responsible GenAI.
Authors: Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kiant\'e Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun
Abstract: While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g. value networks, clipping), and is notorious for its sensitivity to the precise implementation of these components. In response, we take a step back and ask what a minimalist RL algorithm for the era of generative models would look like. We propose REBEL, an algorithm that cleanly reduces the problem of policy optimization to regressing the relative reward between two completions to a prompt in terms of the policy, enabling strikingly lightweight implementation. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL, which allows us to match the strongest known theoretical guarantees in terms of convergence and sample complexity in the RL literature. REBEL can also cleanly incorporate offline data and be extended to handle the intransitive preferences we frequently see in practice. Empirically, we find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO, all while being simpler to implement and more computationally efficient than PPO. When fine-tuning Llama-3-8B-Instruct, REBEL achieves strong performance in AlpacaEval 2.0, MT-Bench, and Open LLM Leaderboard.
Authors: Jialiang Wei, Anne-Lise Courbis, Thomas Lambolais, Binbin Xu, Pierre Louis Bernard, G\'erard Dray, Walid Maalej
Abstract: App developers use the Graphical User Interface (GUI) of other apps as a source of inspiration for designing and improving their own apps. Recent research has thus suggested retrieving relevant GUI designs that match a certain text query from screenshot datasets acquired through crowdsourced or automated exploration of GUIs. However, such text-to-GUI retrieval approaches only leverage the textual information of the GUI elements, neglecting visual information such as icons or background images. In addition, retrieved screenshots are not steered by app developers and often lack important app features that require particular input data. To overcome these limitations, this paper proposes GUing, a GUI search engine based on a vision-language model called GUIClip, which we trained specifically for the problem of designing app GUIs. For this, we first collected from Google Play app introduction images which usually display the most representative screenshots and are often captioned (i.e.~labeled) by app vendors. Then, we developed an automated pipeline to classify, crop, and extract the captions from these images. This resulted in a large dataset which we share with this paper: including 303k app screenshots, out of which 135k have captions. We used this dataset to train a novel vision-language model, which is, to the best of our knowledge, the first of its kind in GUI retrieval. We evaluated our approach on various datasets from related work and in manual experiment. The results demonstrate that our model outperforms previous approaches in text-to-GUI retrieval achieving a Recall@10 of up to 0.69 and a HIT@10 of 0.91. We also explored the performance of GUIClip for other GUI tasks including GUI classification and sketch-to-GUI retrieval with encouraging results.
Authors: Yuchen Wang, Xingyu Zhu, Guanhui Ye, Shiyao Zhang, Xuetao Wei
Abstract: DNN-based watermarking methods are rapidly developing and delivering impressive performances. Recent advances achieve resolution-agnostic image watermarking by reducing the variant resolution watermarking problem to a fixed resolution watermarking problem. However, such a reduction process can potentially introduce artifacts and low robustness. To address this issue, we propose the first, to the best of our knowledge, Resolution-Agnostic Image WaterMarking (RAIMark) framework by watermarking the implicit neural representation (INR) of image. Unlike previous methods, our method does not rely on the previous reduction process by directly watermarking the continuous signal instead of image pixels, thus achieving resolution-agnostic watermarking. Precisely, given an arbitrary-resolution image, we fit an INR for the target image. As a continuous signal, such an INR can be sampled to obtain images with variant resolutions. Then, we quickly fine-tune the fitted INR to get a watermarked INR conditioned on a binary secret message. A pre-trained watermark decoder extracts the hidden message from any sampled images with arbitrary resolutions. By directly watermarking INR, we achieve resolution-agnostic watermarking with increased robustness. Extensive experiments show that our method outperforms previous methods with significant improvements: averagely improved bit accuracy by 7%$\sim$29%. Notably, we observe that previous methods are vulnerable to at least one watermarking attack (e.g. JPEG, crop, resize), while ours are robust against all watermarking attacks.
Authors: Jiaming Zhao, Wenbo Qiao, Peng Zhang, Hui Gao
Abstract: Implicit neural representations have emerged as a powerful paradigm to represent signals such as images and sounds. This approach aims to utilize neural networks to parameterize the implicit function of the signal. However, when representing implicit functions, traditional neural networks such as ReLU-based multilayer perceptrons face challenges in accurately modeling high-frequency components of signals. Recent research has begun to explore the use of Fourier Neural Networks (FNNs) to overcome this limitation. In this paper, we propose Quantum Implicit Representation Network (QIREN), a novel quantum generalization of FNNs. Furthermore, through theoretical analysis, we demonstrate that QIREN possesses a quantum advantage over classical FNNs. Lastly, we conducted experiments in signal representation, image superresolution, and image generation tasks to show the superior performance of QIREN compared to state-of-the-art (SOTA) models. Our work not only incorporates quantum advantages into implicit neural representations but also uncovers a promising application direction for Quantum Neural Networks.
Authors: Hashmat Shadab Malik, Numan Saeed, Asif Hanif, Muzammal Naseer, Mohammad Yaqub, Salman Khan, Fahad Shahbaz Khan
Abstract: Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raising serious concerns regarding the real-world deployment of tools employing such models in the healthcare sector. This underscores the importance of investigating the robustness of existing models. In this context, our work aims to empirically examine the adversarial robustness across current volumetric segmentation architectures, encompassing Convolutional, Transformer, and Mamba-based models. We extend this investigation across four volumetric segmentation datasets, evaluating robustness under both white box and black box adversarial attacks. Overall, we observe that while both pixel and frequency-based attacks perform reasonably well under \emph{white box} setting, the latter performs significantly better under transfer-based black box attacks. Across our experiments, we observe transformer-based models show higher robustness than convolution-based models with Mamba-based models being the most vulnerable. Additionally, we show that large-scale training of volumetric segmentation models improves the model's robustness against adversarial attacks. The code and robust models are available at https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models.
URLs: https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models.
Authors: Song Wang, Zhong Zhang, Huan Yan, Ming Xu, Guanghui Wang
Abstract: H&E-to-IHC stain translation techniques offer a promising solution for precise cancer diagnosis, especially in low-resource regions where there is a shortage of health professionals and limited access to expensive equipment. Considering the pixel-level misalignment of H&E-IHC image pairs, current research explores the pathological consistency between patches from the same positions of the image pair. However, most of them overemphasize the correspondence between domains or patches, overlooking the side information provided by the non-corresponding objects. In this paper, we propose a Mix-Domain Contrastive Learning (MDCL) method to leverage the supervision information in unpaired H&E-to-IHC stain translation. Specifically, the proposed MDCL method aggregates the inter-domain and intra-domain pathology information by estimating the correlation between the anchor patch and all the patches from the matching images, encouraging the network to learn additional contrastive knowledge from mixed domains. With the mix-domain pathology information aggregation, MDCL enhances the pathological consistency between the corresponding patches and the component discrepancy of the patches from the different positions of the generated IHC image. Extensive experiments on two H&E-to-IHC stain translation datasets, namely MIST and BCI, demonstrate that the proposed method achieves state-of-the-art performance across multiple metrics.
Authors: P. N. Karthikayan, Yoga Sri Varshan V, Hitesh Gupta Kattamuri, Umarani Jayaraman
Abstract: This paper presents dilated Residual Network (ResNet) models for disease classification from retinal fundus images. Dilated convolution filters are used to replace normal convolution filters in the higher layers of the ResNet model (dilated ResNet) in order to improve the receptive field compared to the normal ResNet model for disease classification. This study introduces computer-assisted diagnostic tools that employ deep learning, enhanced with explainable AI techniques. These techniques aim to make the tool's decision-making process transparent, thereby enabling medical professionals to understand and trust the AI's diagnostic decision. They are particularly relevant in today's healthcare landscape, where there is a growing demand for transparency in AI applications to ensure their reliability and ethical use. The dilated ResNet is used as a replacement for the normal ResNet to enhance the classification accuracy of retinal eye diseases and reduce the required computing time. The dataset used in this work is the Ocular Disease Intelligent Recognition (ODIR) dataset which is a structured ophthalmic database with eight classes covering most of the common retinal eye diseases. The evaluation metrics used in this work include precision, recall, accuracy, and F1 score. In this work, a comparative study has been made between normal ResNet models and dilated ResNet models on five variants namely ResNet-18, ResNet-34, ResNet-50, ResNet-101, and ResNet-152. The dilated ResNet model shows promising results as compared to normal ResNet with an average F1 score of 0.71, 0.70, 0.69, 0.67, and 0.70 respectively for the above respective variants in ODIR multiclass disease classification.
Authors: Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz, Ricardo Bedin Grando, Ayano Yorozu, Akihisa Ohya
Abstract: In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the contrastive loss from the CURL algorithm and a reconstruction loss from autoencoder, Curled-Dreamer achieves significant improvements in various DeepMind Control Suite tasks. Our extensive experiments demonstrate that Curled-Dreamer consistently outperforms state-of-the-art algorithms, achieving higher mean and median scores across a diverse set of tasks. The results indicate that the proposed approach not only accelerates learning but also enhances the robustness of the learned policies. This work highlights the potential of combining different learning paradigms to achieve superior performance in reinforcement learning applications.
Authors: Xinqi Jin, Zhui Zhu, Xikai Sun, Fan Dang, Jiangchuan Liu, Jingao Xu, Kebin Liu, Xinlei Chen, Yunhao Liu
Abstract: Neural enhancement through super-resolution (SR) deep neural networks (DNNs) opens up new possibilities for ultra-high-definition (UHD) live streaming over existing encoding and networking infrastructure. Yet, the heavy SR DNN inference overhead leads to severe deployment challenges. To reduce the overhead, existing systems propose to apply DNN-based SR only on carefully selected anchor frames while upscaling non-anchor frames via the lightweight reusing-based SR approach. However, frame-level scheduling is coarse-grained and fails to deliver optimal efficiency. In this work, we propose Palantir, the first neural-enhanced UHD live streaming system with fine-grained patch-level scheduling. Two novel techniques are incorporated into Palantir to select the most beneficial anchor patches and support latency-sensitive UHD live streaming applications. Firstly, under the guidance of our pioneering and theoretical analysis, Palantir constructs a directed acyclic graph (DAG) for lightweight yet accurate SR quality estimation under any possible anchor patch set. Secondly, to further optimize the scheduling latency, Palantir improves parallelizability by refactoring the computation subprocedure of the estimation process into a sparse matrix-matrix multiplication operation. The evaluation results suggest that Palantir incurs a negligible scheduling latency accounting for less than 5.7% of the end-to-end latency requirement. When compared to the naive method of applying DNN-based SR on all the frames, Palantir can reduce the SR DNN inference overhead by 20 times (or 60 times) while preserving 54.0-82.6% (or 32.8-64.0%) of the quality gain. When compared to the state-of-the-art real-time frame-level scheduling strategy, Palantir can reduce the SR DNN inference overhead by 80.1% at most (and 38.4% on average) without sacrificing the video quality.
Authors: Bhavna Gopal, Huanrui Yang, Jingyang Zhang, Mark Horton, Yiran Chen
Abstract: Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by introducing parameter efficiency into the adversarial training process, improving both clean accuracy and adversarial robustness. Instead of tuning the entire model, CLAT identifies and fine-tunes robustness-critical layers - those predominantly learning non-robust features - while freezing the remaining model to enhance robustness. It employs dynamic critical layer selection to adapt to changes in layer criticality throughout the fine-tuning process. Empirically, CLAT can be applied on top of existing adversarial training methods, significantly reduces the number of trainable parameters by approximately 95%, and achieves more than a 2% improvement in adversarial robustness compared to baseline methods.
Authors: Yuan Zhao, Zhenqi Jia, Rui Liu, De Hu, Feilong Bao, Guanglai Gao
Abstract: Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \textbf{MCDubber}, to convert the modeling object from a single sentence to a longer sequence with context information to ensure the consistency of the global context prosody. MCDubber comprises three main components: (1) A context duration aligner aims to learn the context-aware alignment between the text and lip frames; (2) A context prosody predictor seeks to read the global context visual sequence and predict the context-aware global energy and pitch; (3) A context acoustic decoder ultimately predicts the global context mel-spectrogram with the assistance of adjacent ground-truth mel-spectrograms of the target sentence. Through this process, MCDubber fully considers the influence of multimodal context on the prosody expressiveness of the current sentence when dubbing. The extracted mel-spectrogram belonging to the target sentence from the output context mel-spectrograms is the final required dubbing audio. Extensive experiments on the Chem benchmark dataset demonstrate that our MCDubber significantly improves dubbing expressiveness compared to all advanced baselines. The code and demos are available at https://github.com/XiaoYuanJun-zy/MCDubber.
Authors: Eyal Hanania, Ilya Volovik, Daphna Link-Sourani, Israel Cohen, Moti Freiman
Abstract: T1 mapping is a valuable quantitative MRI technique for diagnosing diffuse myocardial diseases. Traditional methods, relying on breath-hold sequences and echo triggering, face challenges with patient compliance and arrhythmias, limiting their effectiveness. Image registration can enable motion-robust T1 mapping, but inherent intensity differences between time points pose a challenge. We introduce MBSS-T1, a self-supervised model for motion correction in cardiac T1 mapping, constrained by physical and anatomical principles. The physical constraints ensure expected signal decay behavior, while the anatomical constraints maintain realistic deformations. The unique combination of these constraints ensures accurate T1 mapping along the longitudinal relaxation axis. MBSS-T1 outperformed baseline deep-learning-based image registration approaches in a 5-fold experiment on a public dataset of 210 patients (STONE sequence) and an internal dataset of 19 patients (MOLLI sequence). MBSS-T1 excelled in model fitting quality ($R^2$: 0.975 vs. 0.941, 0.946), anatomical alignment (Dice score: 0.89 vs. 0.84, 0.88), and expert visual quality assessment for the presence of visible motion artifacts (4.33 vs. 3.38, 3.66). MBSS-T1 has the potential to enable motion-robust T1 mapping for a broader range of patients, overcoming challenges such as arrhythmias and suboptimal compliance, and allowing for free-breathing T1 mapping without requiring large training datasets. Our code will be publicly available upon acceptance.
Authors: Shuaiyu Yuan, Tristan Whitmarsh, Dimitri A Kessler, Otso Arponen, Mary A McLean, Gabrielle Baxter, Frank Riemer, Aneurin J Kennerley, William J Brackenbury, Fiona J Gilbert, Joshua D Kaggie
Abstract: New multinuclear MRI techniques, such as sodium MRI, generally suffer from low image quality due to an inherently low signal. Postprocessing methods, such as image denoising, have been developed for image enhancement. However, the assessment of these enhanced images is challenging especially considering when there is a lack of high resolution and high signal images as reference, such as in sodium MRI. No-reference Image Quality Assessment (NR-IQA) metrics are approaches to solve this problem. Existing learning-based NR-IQA metrics rely on labels derived from subjective human opinions or metrics like Signal-to-Noise Ratio (SNR), which are either time-consuming or lack accurate ground truths, resulting in unreliable assessment. We note that deep learning (DL) models have a unique characteristic in that they are specialized to a characteristic training set, meaning that deviations between the input testing data from the training data will reduce prediction accuracy. Therefore, we propose a novel DL-based NR-IQA metric, the Model Specialization Metric (MSM), which does not depend on ground-truth images or labels. MSM measures the difference between the input image and the model's prediction for evaluating the quality of the input image. Experiments conducted on both simulated distorted proton T1-weighted MR images and denoised sodium MR images demonstrate that MSM exhibits a superior evaluation performance on various simulated noises and distortions. MSM also has a substantial agreement with the expert evaluations, achieving an averaged Cohen's Kappa coefficient of 0.6528, outperforming the existing NR-IQA metrics.
Authors: Jutika Borah, Kumaresh Sarmah, Hidam Kumarjit Singh
Abstract: Imaging techniques such as Chest X-rays, whole slide images, and optical coherence tomography serve as the initial screening and detection for a wide variety of medical pulmonary and ophthalmic conditions respectively. This paper investigates the intricacies of using pretrained deep convolutional neural networks with transfer learning across diverse medical imaging datasets with varying modalities for binary and multiclass classification. We conducted a comprehensive performance analysis with ten network architectures and model families each with pretraining and random initialization. Our finding showed that the use of pretrained models as fixed feature extractors yields poor performance irrespective of the datasets. Contrary, histopathology microscopy whole slide images have better performance. It is also found that deeper and more complex architectures did not necessarily result in the best performance. This observation implies that the improvements in ImageNet are not parallel to the medical imaging tasks. Within a medical domain, the performance of the network architectures varies within model families with shifts in datasets. This indicates that the performance of models within a specific modality may not be conclusive for another modality within the same domain. This study provides a deeper understanding of the applications of deep learning techniques in medical imaging and highlights the impact of pretrained networks across different medical imaging datasets under five different experimental settings.