Authors: Diego A. Silva, Kamilya Smagulova, Ahmed Elsheikh, Mohammed E. Fouda, Ahmed M. Eltawil
Abstract: Object detection is crucial in various cutting-edge applications, such as autonomous vehicles and advanced robotics systems, primarily relying on data from conventional frame-based RGB sensors. However, these sensors often struggle with issues like motion blur and poor performance in challenging lighting conditions. In response to these challenges, event-based cameras have emerged as an innovative paradigm. These cameras, mimicking the human eye, demonstrate superior performance in environments with fast motion and extreme lighting conditions while consuming less power. This study introduces ReYOLOv8, an advanced object detection framework that enhances a leading frame-based detection system with spatiotemporal modeling capabilities. We implemented a low-latency, memory-efficient method for encoding event data to boost the system's performance. We also developed a novel data augmentation technique tailored to leverage the unique attributes of event data, thus improving detection accuracy. Our models outperformed all comparable approaches in the GEN1 dataset, focusing on automotive applications, achieving mean Average Precision (mAP) improvements of 5%, 2.8%, and 2.5% across nano, small, and medium scales, respectively.These enhancements were achieved while reducing the number of trainable parameters by an average of 4.43% and maintaining real-time processing speeds between 9.2ms and 15.5ms. On the PEDRo dataset, which targets robotics applications, our models showed mAP improvements ranging from 9% to 18%, with 14.5x and 3.8x smaller models and an average speed enhancement of 1.67x.
Authors: Sihyeon Kim, Boryeong Cho, Sangmin Bae, Sumyeong Ahn, Se-Young Yun
Abstract: Despite the astonishing performance of recent Large Vision-Language Models (LVLMs), these models often generate inaccurate responses. To address this issue, previous studies have focused on mitigating hallucinations by employing contrastive decoding (CD) with augmented images, which amplifies the contrast with the original image. However, these methods have limitations, including reliance on a single augmentation, which is restrictive for certain tasks, as well as the high cost of using external knowledge. In this study, we address these limitations by exploring how to utilize multiple image augmentations. Through extensive experiments, we observed that different augmentations produce varying levels of contrast depending on the task. Based on this observation, we introduce a novel method called VACoDe, Visual Augmented Contrastive Decoding. This method adaptively selects the augmentation with the highest contrast for each task using the proposed softmax distance metric. Our empirical tests show that \alg outperforms previous methods and improves output quality in various vision-language tasks. Additionally, VACoDe can be universally applied across different model types and sizes without additional training or the use of external models and data.
Authors: Yinsong Wang, Siyi Du, Shaoming Zheng, Xinzhe Luo, Chen Qin
Abstract: Multi-contrast image registration is a challenging task due to the complex intensity relationships between different imaging contrasts. Conventional image registration methods are typically based on iterative optimizations for each input image pair, which is time-consuming and sensitive to contrast variations. While learning-based approaches are much faster during the inference stage, due to generalizability issues, they typically can only be applied to the fixed contrasts observed during the training stage. In this work, we propose a novel contrast-agnostic deformable image registration framework that can be generalized to arbitrary contrast images, without observing them during training. Particularly, we propose a random convolution-based contrast augmentation scheme, which simulates arbitrary contrasts of images over a single image contrast while preserving their inherent structural information. To ensure that the network can learn contrast-invariant representations for facilitating contrast-agnostic registration, we further introduce contrast-invariant latent regularization (CLR) that regularizes representation in latent space through a contrast invariance loss. Experiments show that CAR outperforms the baseline approaches regarding registration accuracy and also possesses better generalization ability to unseen imaging contrasts. Code is available at \url{https://github.com/Yinsong0510/CAR}.
Authors: Landon Dyken, Saugat Adhikari, Pravin Poudel, Steve Petruzza, Da Yan, Will Usher, Sidharth Kumar
Abstract: In order to assess damage and properly allocate relief efforts, mapping the extent of flood events is a necessary and important aspect of disaster management. In recent years, deep learning methods have evolved as an effective tool to quickly label high-resolution imagery and provide necessary flood extent mappings. These methods, though, require large amounts of annotated training data to create models that are accurate and robust to new flooded imagery. In this work, we provide FloodTrace, an application that enables effective crowdsourcing for flooded region annotation for machine learning training data, removing the requirement for annotation to be done solely by researchers. We accomplish this through two orthogonal methods within our application, informed by requirements from domain experts. First, we utilize elevation-guided annotation tools and 3D rendering to inform user annotation decisions with digital elevation model data, improving annotation accuracy. For this purpose, we provide a unique annotation method that uses topological data analysis to outperform the state-of-the-art elevation-guided annotation tool in efficiency. Second, we provide a framework for researchers to review aggregated crowdsourced annotations and correct inaccuracies using methods inspired by uncertainty visualization. We conducted a user study to confirm the application effectiveness in which 266 graduate students annotated high-resolution aerial imagery from Hurricane Matthew in North Carolina. Experimental results show the accuracy and efficiency benefits of our application apply even for untrained users. In addition, using our aggregation and correction framework, flood detection models trained on crowdsourced annotations were able to achieve performance equal to models trained on expert-labeled annotations, while requiring a fraction of the time on the part of the researcher.
Authors: Chao Wu, Yifan Gong, Liangkai Liu, Mengquan Li, Yushu Wu, Xuan Shen, Zhimin Li, Geng Yuan, Weisong Shi, Yanzhi Wang
Abstract: Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the deployment dilemma of simultaneously achieving high accuracy, excellent power efficiency, and meeting strict real-time requirements. To tackle this dilemma, we propose AyE-Edge, the first-of-this-kind development tool that explores automated algorithm-device deployment space search to realize Accurate yet power-Efficient real-time object detection on the Edge. Through a collaborative exploration of keyframe selection, CPU-GPU configuration, and DNN pruning strategy, AyE-Edge excels in extensive real-world experiments conducted on a mobile device. The results consistently demonstrate AyE-Edge's effectiveness, realizing outstanding real-time performance, detection accuracy, and notably, a remarkable 96.7% reduction in power consumption, compared to state-of-the-art (SOTA) competitors.
Authors: Heeseung Yun, Ruohan Gao, Ishwarya Ananthabhotla, Anurag Kumar, Jacob Donley, Chao Li, Gunhee Kim, Vamsi Krishna Ithapu, Calvin Murdock
Abstract: Egocentric videos provide comprehensive contexts for user and scene understanding, spanning multisensory perception to behavioral interaction. We propose Spherical World-Locking (SWL) as a general framework for egocentric scene representation, which implicitly transforms multisensory streams with respect to measurements of head orientation. Compared to conventional head-locked egocentric representations with a 2D planar field-of-view, SWL effectively offsets challenges posed by self-motion, allowing for improved spatial synchronization between input modalities. Using a set of multisensory embeddings on a worldlocked sphere, we design a unified encoder-decoder transformer architecture that preserves the spherical structure of the scene representation, without requiring expensive projections between image and world coordinate systems. We evaluate the effectiveness of the proposed framework on multiple benchmark tasks for egocentric video understanding, including audio-visual active speaker localization, auditory spherical source localization, and behavior anticipation in everyday activities.
Authors: Sarah Barrington, Matyas Bohacek, Hany Farid
Abstract: We describe a large-scale dataset--{\em 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 $9$ hours of footage from $220$ diverse individuals. Constituting more than 25 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: Bin Hu, Xinggang Wang, Wenyu Liu
Abstract: Person Re-Identification (ReID) aims to retrieve relevant individuals in non-overlapping camera images and has a wide range of applications in the field of public safety. In recent years, with the development of Vision Transformer (ViT) and self-supervised learning techniques, the performance of person ReID based on self-supervised pre-training has been greatly improved. Person ReID requires extracting highly discriminative local fine-grained features of the human body, while traditional ViT is good at extracting context-related global features, making it difficult to focus on local human body features. To this end, this article introduces the recently emerged Masked Image Modeling (MIM) self-supervised learning method into person ReID, and effectively extracts high-quality global and local features through large-scale unsupervised pre-training by combining masked image modeling and discriminative contrastive learning, and then conducts supervised fine-tuning training in the person ReID task. This person feature extraction method based on ViT with masked image modeling (PersonViT) has the good characteristics of unsupervised, scalable, and strong generalization capabilities, overcoming the problem of difficult annotation in supervised person ReID, and achieves state-of-the-art results on publicly available benchmark datasets, including MSMT17, Market1501, DukeMTMC-reID, and Occluded-Duke. The code and pre-trained models of the PersonViT method are released at https://github.com/hustvl/PersonViT to promote further research in the person ReID fie
Authors: Fan Zhang, Ziyue Ji, Weiguang Kang, Weiqing Li, Zhiyong Su
Abstract: With the support of Virtual Reality (VR) and Augmented Reality (AR) technologies, the 3D virtual eyeglasses try-on application is well on its way to becoming a new trending solution that offers a "try on" option to select the perfect pair of eyeglasses at the comfort of your own home. Reconstructing eyeglasses frames from a single image with traditional depth and image-based methods is extremely difficult due to their unique characteristics such as lack of sufficient texture features, thin elements, and severe self-occlusions. In this paper, we propose the first mesh deformation-based reconstruction framework for recovering high-precision 3D full-frame eyeglasses models from a single RGB image, leveraging prior and domain-specific knowledge. Specifically, based on the construction of a synthetic eyeglasses frame dataset, we first define a class-specific eyeglasses frame template with pre-defined keypoints. Then, given an input eyeglasses frame image with thin structure and few texture features, we design a keypoint detector and refiner to detect predefined keypoints in a coarse-to-fine manner to estimate the camera pose accurately. After that, using differentiable rendering, we propose a novel optimization approach for producing correct geometry by progressively performing free-form deformation (FFD) on the template mesh. We define a series of loss functions to enforce consistency between the rendered result and the corresponding RGB input, utilizing constraints from inherent structure, silhouettes, keypoints, per-pixel shading information, and so on. Experimental results on both the synthetic dataset and real images demonstrate the effectiveness of the proposed algorithm.
Authors: Yongcong Zhang, Bangyan Liao, Yifei Xue, Chen Lu, Peidong Liu, Yizhen Lao
Abstract: The line is a prevalent element in man-made environments, inherently encoding spatial structural information, thus making it a more robust choice for feature representation in practical applications. Despite its apparent advantages, previous rolling shutter bundle adjustment (RSBA) methods have only supported sparse feature points, which lack robustness, particularly in degenerate environments. In this paper, we introduce the first rolling shutter line-based bundle adjustment solution, RSL-BA. Specifically, we initially establish the rolling shutter camera line projection theory utilizing Pl\"ucker line parameterization. Subsequently, we derive a series of reprojection error formulations which are stable and efficient. Finally, we theoretically and experimentally demonstrate that our method can prevent three common degeneracies, one of which is first discovered in this paper. Extensive synthetic and real data experiments demonstrate that our method achieves efficiency and accuracy comparable to existing point-based rolling shutter bundle adjustment solutions.
Authors: Yuxin Zhu, Huiyu Duan, Kaiwei Zhang, Yucheng Zhu, Xilei Zhu, Long Teng, Xiongkuo Min, Guangtao Zhai
Abstract: Understanding and predicting viewer attention in omnidirectional videos (ODVs) is crucial for enhancing user engagement in virtual and augmented reality applications. Although both audio and visual modalities are essential for saliency prediction in ODVs, the joint exploitation of these two modalities has been limited, primarily due to the absence of large-scale audio-visual saliency databases and comprehensive analyses. This paper comprehensively investigates audio-visual attention in ODVs from both subjective and objective perspectives. Specifically, we first introduce a new audio-visual saliency database for omnidirectional videos, termed AVS-ODV database, containing 162 ODVs and corresponding eye movement data collected from 60 subjects under three audio modes including mute, mono, and ambisonics. Based on the constructed AVS-ODV database, we perform an in-depth analysis of how audio influences visual attention in ODVs. To advance the research on audio-visual saliency prediction for ODVs, we further establish a new benchmark based on the AVS-ODV database by testing numerous state-of-the-art saliency models, including visual-only models and audio-visual models. In addition, given the limitations of current models, we propose an innovative omnidirectional audio-visual saliency prediction network (OmniAVS), which is built based on the U-Net architecture, and hierarchically fuses audio and visual features from the multimodal aligned embedding space. Extensive experimental results demonstrate that the proposed OmniAVS model outperforms other state-of-the-art models on both ODV AVS prediction and traditional AVS predcition tasks. The AVS-ODV database and OmniAVS model will be released to facilitate future research.
Authors: Weizhi Zhong, Jichang Li, Yinqi Cai, Liang Lin, Guanbin Li
Abstract: Audio-driven lip sync has recently drawn significant attention due to its widespread application in the multimedia domain. Individuals exhibit distinct lip shapes when speaking the same utterance, attributed to the unique speaking styles of individuals, posing a notable challenge for audio-driven lip sync. Earlier methods for such task often bypassed the modeling of personalized speaking styles, resulting in sub-optimal lip sync conforming to the general styles. Recent lip sync techniques attempt to guide the lip sync for arbitrary audio by aggregating information from a style reference video, yet they can not preserve the speaking styles well due to their inaccuracy in style aggregation. This work proposes an innovative audio-aware style reference scheme that effectively leverages the relationships between input audio and reference audio from style reference video to address the style-preserving audio-driven lip sync. Specifically, we first develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video. Afterwards, to better render the lip motion into realistic talking face video, we devise a conditional latent diffusion model, integrating lip motion through modulated convolutional layers and fusing reference facial images via spatial cross-attention layers. Extensive experiments validate the efficacy of the proposed approach in achieving precise lip sync, preserving speaking styles, and generating high-fidelity, realistic talking face videos.
Authors: Weizhi Zhong, Junfan Lin, Peixin Chen, Liang Lin, Guanbin Li
Abstract: Audio-driven talking face video generation has attracted increasing attention due to its huge industrial potential. Some previous methods focus on learning a direct mapping from audio to visual content. Despite progress, they often struggle with the ambiguity of the mapping process, leading to flawed results. An alternative strategy involves facial structural representations (e.g., facial landmarks) as intermediaries. This multi-stage approach better preserves the appearance details but suffers from error accumulation due to the independent optimization of different stages. Moreover, most previous methods rely on generative adversarial networks, prone to training instability and mode collapse. To address these challenges, our study proposes a novel landmark-based diffusion model for talking face generation, which leverages facial landmarks as intermediate representations while enabling end-to-end optimization. Specifically, we first establish the less ambiguous mapping from audio to landmark motion of lip and jaw. Then, we introduce an innovative conditioning module called TalkFormer to align the synthesized motion with the motion represented by landmarks via differentiable cross-attention, which enables end-to-end optimization for improved lip synchronization. Besides, TalkFormer employs implicit feature warping to align the reference image features with the target motion for preserving more appearance details. Extensive experiments demonstrate that our approach can synthesize high-fidelity and lip-synced talking face videos, preserving more subject appearance details from the reference image.
Authors: Ahmed Abdelkawy, Asem Ali, Aly Farag
Abstract: Existing multimodal-based human action recognition approaches are either computationally expensive, which limits their applicability in real-time scenarios, or fail to exploit the spatial temporal information of multiple data modalities. In this work, we present an efficient pose-driven attention-guided multimodal network (EPAM-Net) for action recognition in videos. Specifically, we adapted X3D networks for both RGB and pose streams to capture spatio-temporal features from RGB videos and their skeleton sequences. Then skeleton features are utilized to help the visual network stream focusing on key frames and their salient spatial regions using a spatial temporal attention block. Finally, the scores of the two streams of the proposed network are fused for final classification. The experimental results show that our method achieves competitive performance on NTU-D 60 and NTU RGB-D 120 benchmark datasets. Moreover, our model provides a 6.2--9.9x reduction in FLOPs (floating-point operation, in number of multiply-adds) and a 9--9.6x reduction in the number of network parameters. The code will be available at https://github.com/ahmed-nady/Multimodal-Action-Recognition.
URLs: https://github.com/ahmed-nady/Multimodal-Action-Recognition.
Authors: Jia Wei, Yun Li, Meiyu Qiu, Hongyu Chen, Xiaomao Fan, Wenbin Lei
Abstract: Laryngo-pharyngeal cancer (LPC) is a highly fatal malignant disease affecting the head and neck region. Previous studies on endoscopic tumor detection, particularly those leveraging dual-branch network architectures, have shown significant advancements in tumor detection. These studies highlight the potential of dual-branch networks in improving diagnostic accuracy by effectively integrating global and local (lesion) feature extraction. However, they are still limited in their capabilities to accurately locate the lesion region and capture the discriminative feature information between the global and local branches. To address these issues, we propose a novel SAM-guided fusion network (SAM-FNet), a dual-branch network for laryngo-pharyngeal tumor detection. By leveraging the powerful object segmentation capabilities of the Segment Anything Model (SAM), we introduce the SAM into the SAM-FNet to accurately segment the lesion region. Furthermore, we propose a GAN-like feature optimization (GFO) module to capture the discriminative features between the global and local branches, enhancing the fusion feature complementarity. Additionally, we collect two LPC datasets from the First Affiliated Hospital (FAHSYSU) and the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University. The FAHSYSU dataset is used as the internal dataset for training the model, while the SAHSYSU dataset is used as the external dataset for evaluating the model's performance. Extensive experiments on both datasets of FAHSYSU and SAHSYSU demonstrate that the SAM-FNet can achieve competitive results, outperforming the state-of-the-art counterparts. The source code of SAM-FNet is available at the URL of https://github.com/VVJia/SAM-FNet.
Authors: Jungpil Shin, Abu Saleh Musa Miah, Md. Humaun Kabir, Md. Abdur Rahim, Abdullah Al Shiam
Abstract: Researchers have been developing Hand Gesture Recognition (HGR) systems to enhance natural, efficient, and authentic human-computer interaction, especially benefiting those who rely solely on hand gestures for communication. Despite significant progress, the automatic and precise identification of hand gestures remains a considerable challenge in computer vision. Recent studies have focused on specific modalities like RGB images, skeleton data, and spatiotemporal interest points. This paper provides a comprehensive review of HGR techniques and data modalities from 2014 to 2024, exploring advancements in sensor technology and computer vision. We highlight accomplishments using various modalities, including RGB, Skeleton, Depth, Audio, EMG, EEG, and Multimodal approaches and identify areas needing further research. We reviewed over 200 articles from prominent databases, focusing on data collection, data settings, and gesture representation. Our review assesses the efficacy of HGR systems through their recognition accuracy and identifies a gap in research on continuous gesture recognition, indicating the need for improved vision-based gesture systems. The field has experienced steady research progress, including advancements in hand-crafted features and deep learning (DL) techniques. Additionally, we report on the promising developments in HGR methods and the area of multimodal approaches. We hope this survey will serve as a potential guideline for diverse data modality-based HGR research.
Authors: Jiang Yuan, Ji Ma, Bo Wang, Weiming Hu
Abstract: Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more discriminative degradation representations and fully adapt them to specific image features is the key to this task. In this paper, we propose a new Content-decoupled Contrastive Learning-based blind image super-resolution (CdCL) framework following the typical blind SR pipeline. This framework introduces negative-free contrastive learning technique for the first time to model the implicit degradation representation, in which a new cyclic shift sampling strategy is designed to ensure decoupling between content features and degradation features from the data perspective, thereby improving the purity and discriminability of the learned implicit degradation space. In addition, to improve the efficiency and effectiveness of implicit degradation-based blind super-resolving, we design a detail-aware implicit degradation adaption module with lower complexity, which adapts degradation information to the specific LR image from both channel and spatial perspectives. Extensive experiments on synthetic and real data prove that the proposed CdCL comprehensively improves the quantitative and qualitative results of contrastive learning-based implicit blind SR paradigm, and achieves SOTA PSNR in this field. Even if the number of parameters is halved, our method still achieves very competitive results.
Authors: Stanislav Fort, Balaji Lakshminarayanan
Abstract: Adversarial examples pose a significant challenge to the robustness, reliability and alignment of deep neural networks. We propose a novel, easy-to-use approach to achieving high-quality representations that lead to adversarial robustness through the use of multi-resolution input representations and dynamic self-ensembling of intermediate layer predictions. We demonstrate that intermediate layer predictions exhibit inherent robustness to adversarial attacks crafted to fool the full classifier, and propose a robust aggregation mechanism based on Vickrey auction that we call \textit{CrossMax} to dynamically ensemble them. By combining multi-resolution inputs and robust ensembling, we achieve significant adversarial robustness on CIFAR-10 and CIFAR-100 datasets without any adversarial training or extra data, reaching an adversarial accuracy of $\approx$72% (CIFAR-10) and $\approx$48% (CIFAR-100) on the RobustBench AutoAttack suite ($L_\infty=8/255)$ with a finetuned ImageNet-pretrained ResNet152. This represents a result comparable with the top three models on CIFAR-10 and a +5 % gain compared to the best current dedicated approach on CIFAR-100. Adding simple adversarial training on top, we get $\approx$78% on CIFAR-10 and $\approx$51% on CIFAR-100, improving SOTA by 5 % and 9 % respectively and seeing greater gains on the harder dataset. We validate our approach through extensive experiments and provide insights into the interplay between adversarial robustness, and the hierarchical nature of deep representations. We show that simple gradient-based attacks against our model lead to human-interpretable images of the target classes as well as interpretable image changes. As a byproduct, using our multi-resolution prior, we turn pre-trained classifiers and CLIP models into controllable image generators and develop successful transferable attacks on large vision language models.
Authors: Junjie Jiang, Hao Zhuang, Xinjie Huang, Delei Kong, Zheng Fang
Abstract: Event cameras have the potential to revolutionize the field of robot vision, particularly in areas like stereo disparity estimation, owing to their high temporal resolution and high dynamic range. Many studies use deep learning for event camera stereo disparity estimation. However, these methods fail to fully exploit the temporal information in the event stream to acquire clear event representations. Additionally, there is room for further reduction in pixel shifts in the feature maps before constructing the cost volume. In this paper, we propose EV-MGDispNet, a novel event-based stereo disparity estimation method. Firstly, we propose an edge-aware aggregation (EAA) module, which fuses event frames and motion confidence maps to generate a novel clear event representation. Then, we propose a motion-guided attention (MGA) module, where motion confidence maps utilize deformable transformer encoders to enhance the feature map with more accurate edges. Finally, we also add a census left-right consistency loss function to enhance the left-right consistency of stereo event representation. Through conducting experiments within challenging real-world driving scenarios, we validate that our method outperforms currently known state-of-the-art methods in terms of mean absolute error (MAE) and root mean square error (RMSE) metrics.
Authors: Weiqi Fu, Lianming Xu, Xin Wu, Haoyang Wei, Li Wang
Abstract: In emergencies, the ability to quickly and accurately gather environmental data and command information, and to make timely decisions, is particularly critical. Traditional semantic communication frameworks, primarily based on a single modality, are susceptible to complex environments and lighting conditions, thereby limiting decision accuracy. To this end, this paper introduces a multimodal generative semantic communication framework named mm-GESCO. The framework ingests streams of visible and infrared modal image data, generates fused semantic segmentation maps, and transmits them using a combination of one-hot encoding and zlib compression techniques to enhance data transmission efficiency. At the receiving end, the framework can reconstruct the original multimodal images based on the semantic maps. Additionally, a latent diffusion model based on contrastive learning is designed to align different modal data within the latent space, allowing mm-GESCO to reconstruct latent features of any modality presented at the input. Experimental results demonstrate that mm-GESCO achieves a compression ratio of up to 200 times, surpassing the performance of existing semantic communication frameworks and exhibiting excellent performance in downstream tasks such as object classification and detection.
Authors: Junyan Ye, Zhutao Lv, Weijia Li, Jinhua Yu, Haote Yang, Huaping Zhong, Conghui He
Abstract: Cross-view geolocalization identifies the geographic location of street view images by matching them with a georeferenced satellite database. Significant challenges arise due to the drastic appearance and geometry differences between views. In this paper, we propose a new approach for cross-view image geo-localization, i.e., the Panorama-BEV Co-Retrieval Network. Specifically, by utilizing the ground plane assumption and geometric relations, we convert street view panorama images into the BEV view, reducing the gap between street panoramas and satellite imagery. In the existing retrieval of street view panorama images and satellite images, we introduce BEV and satellite image retrieval branches for collaborative retrieval. By retaining the original street view retrieval branch, we overcome the limited perception range issue of BEV representation. Our network enables comprehensive perception of both the global layout and local details around the street view capture locations. Additionally, we introduce CVGlobal, a global cross-view dataset that is closer to real-world scenarios. This dataset adopts a more realistic setup, with street view directions not aligned with satellite images. CVGlobal also includes cross-regional, cross-temporal, and street view to map retrieval tests, enabling a comprehensive evaluation of algorithm performance. Our method excels in multiple tests on common cross-view datasets such as CVUSA, CVACT, VIGOR, and our newly introduced CVGlobal, surpassing the current state-of-the-art approaches. The code and datasets can be found at \url{https://github.com/yejy53/EP-BEV}.
Authors: Yiying Yang, Fukun Yin, Jiayuan Fan, Xin Chen, Wanzhang Li, Gang Yu
Abstract: As Artificial Intelligence Generated Content (AIGC) advances, a variety of methods have been developed to generate text, images, videos, and 3D objects from single or multimodal inputs, contributing efforts to emulate human-like cognitive content creation. However, generating realistic large-scale scenes from a single input presents a challenge due to the complexities involved in ensuring consistency across extrapolated views generated by models. Benefiting from recent video generation models and implicit neural representations, we propose Scene123, a 3D scene generation model, that not only ensures realism and diversity through the video generation framework but also uses implicit neural fields combined with Masked Autoencoders (MAE) to effectively ensures the consistency of unseen areas across views. Specifically, we initially warp the input image (or an image generated from text) to simulate adjacent views, filling the invisible areas with the MAE model. However, these filled images usually fail to maintain view consistency, thus we utilize the produced views to optimize a neural radiance field, enhancing geometric consistency. Moreover, to further enhance the details and texture fidelity of generated views, we employ a GAN-based Loss against images derived from the input image through the video generation model. Extensive experiments demonstrate that our method can generate realistic and consistent scenes from a single prompt. Both qualitative and quantitative results indicate that our approach surpasses existing state-of-the-art methods. We show encourage video examples at https://yiyingyang12.github.io/Scene123.github.io/.
Authors: Ziyi Gao, Kai Chen, Zhipeng Wei, Tingshu Mou, Jingjing Chen, Zhiyu Tan, Hao Li, Yu-Gang Jiang
Abstract: Recent diffusion-based unrestricted attacks generate imperceptible adversarial examples with high transferability compared to previous unrestricted attacks and restricted attacks. However, existing works on diffusion-based unrestricted attacks are mostly focused on images yet are seldom explored in videos. In this paper, we propose the Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack (ReToMe-VA), which is the first framework to generate imperceptible adversarial video clips with higher transferability. Specifically, to achieve spatial imperceptibility, ReToMe-VA adopts a Timestep-wise Adversarial Latent Optimization (TALO) strategy that optimizes perturbations in diffusion models' latent space at each denoising step. TALO offers iterative and accurate updates to generate more powerful adversarial frames. TALO can further reduce memory consumption in gradient computation. Moreover, to achieve temporal imperceptibility, ReToMe-VA introduces a Recursive Token Merging (ReToMe) mechanism by matching and merging tokens across video frames in the self-attention module, resulting in temporally consistent adversarial videos. ReToMe concurrently facilitates inter-frame interactions into the attack process, inducing more diverse and robust gradients, thus leading to better adversarial transferability. Extensive experiments demonstrate the efficacy of ReToMe-VA, particularly in surpassing state-of-the-art attacks in adversarial transferability by more than 14.16% on average.
Authors: Jin Liu, Huaibo Huang, Jie Cao, Ran He
Abstract: Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples or the employment of DDIM Inversion to revert images to noise space, both of which substantially decelerate the image generation process. To overcome these limitations, this paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We observed that Latent Consistency Models employing consistency distillation can effectively extract representative Consistency Features from noisy images. To blend the Consistency Features extracted from both content and style images, we introduce a Style Enhancement Attention Control technique that meticulously merges content and style features within the attention space of the target image. Moreover, we propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control. Extensive experiments have validated the effectiveness of our proposed framework in enhancing stylization efficiency and fidelity. The code is available at \url{https://github.com/liujin112/ZePo}.
Authors: Shaonan Liu, Wenting Chen, Jie Liu, Xiaoling Luo, Linlin Shen
Abstract: Gaze estimation is pivotal in human scene comprehension tasks, particularly in medical diagnostic analysis. Eye-tracking technology facilitates the recording of physicians' ocular movements during image interpretation, thereby elucidating their visual attention patterns and information-processing strategies. In this paper, we initially define the context-aware gaze estimation problem in medical radiology report settings. To understand the attention allocation and cognitive behavior of radiologists during the medical image interpretation process, we propose a context-aware Gaze EstiMation (GEM) network that utilizes eye gaze data collected from radiologists to simulate their visual search behavior patterns throughout the image interpretation process. It consists of a context-awareness module, visual behavior graph construction, and visual behavior matching. Within the context-awareness module, we achieve intricate multimodal registration by establishing connections between medical reports and images. Subsequently, for a more accurate simulation of genuine visual search behavior patterns, we introduce a visual behavior graph structure, capturing such behavior through high-order relationships (edges) between gaze points (nodes). To maintain the authenticity of visual behavior, we devise a visual behavior-matching approach, adjusting the high-order relationships between them by matching the graph constructed from real and estimated gaze points. Extensive experiments on four publicly available datasets demonstrate the superiority of GEM over existing methods and its strong generalizability, which also provides a new direction for the effective utilization of diverse modalities in medical image interpretation and enhances the interpretability of models in the field of medical imaging. https://github.com/Tiger-SN/GEM
Authors: Zhuohang Dang, Minnan Luo, Jihong Wang, Chengyou Jia, Haochen Han, Herun Wan, Guang Dai, Xiaojun Chang, Jingdong Wang
Abstract: Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses.
Authors: Qiang Zheng, Chao Zhang, Jian Sun
Abstract: In recent years, point cloud analysis methods based on the Transformer architecture have made significant progress, particularly in the context of multimedia applications such as 3D modeling, virtual reality, and autonomous systems. However, the high computational resource demands of the Transformer architecture hinder its scalability, real-time processing capabilities, and deployment on mobile devices and other platforms with limited computational resources. This limitation remains a significant obstacle to its practical application in scenarios requiring on-device intelligence and multimedia processing. To address this challenge, we propose an efficient point cloud analysis architecture, \textbf{Point} \textbf{M}LP-\textbf{T}ransformer (PointMT). This study tackles the quadratic complexity of the self-attention mechanism by introducing a linear complexity local attention mechanism for effective feature aggregation. Additionally, to counter the Transformer's focus on token differences while neglecting channel differences, we introduce a parameter-free channel temperature adaptation mechanism that adaptively adjusts the attention weight distribution in each channel, enhancing the precision of feature aggregation. To improve the Transformer's slow convergence speed due to the limited scale of point cloud datasets, we propose an MLP-Transformer hybrid module, which significantly enhances the model's convergence speed. Furthermore, to boost the feature representation capability of point tokens, we refine the classification head, enabling point tokens to directly participate in prediction. Experimental results on multiple evaluation benchmarks demonstrate that PointMT achieves performance comparable to state-of-the-art methods while maintaining an optimal balance between performance and accuracy.
Authors: Zhengang Lu, Hongsheng Qin, Jing Li, Ming Sun, Jiubin Tan
Abstract: Metallic mesh is a transparent electromagnetic shielding film with a fine metal line structure. However, it can develop defects that affect the optoelectronic performance whether in the production preparation or in actual use. The development of in-situ non-destructive testing (NDT) devices for metallic mesh requires long working distances, reflective optical path design, and miniaturization. To address the limitations of existing smartphone microscopes, which feature short working distances and inadequate transmission imaging for industrial in-situ inspection, we propose a novel long-working distance reflective smartphone microscopy system (LD-RSM). LD-RSM builds a 4f optical imaging system with external optical components and a smartphone, utilizing a beam splitter to achieve reflective imaging with the illumination system and imaging system on the same side of the sample. It achieves an optical resolution of 4.92$\mu$m and a working distance of up to 22.23 mm. Additionally, we introduce a dual prior weighted Robust Principal Component Analysis (DW-RPCA) for defect detection. This approach leverages spectral filter fusion and Hough transform to model different defect types, enhancing the accuracy and efficiency of defect identification. Coupled with an optimized threshold segmentation algorithm, DW-RPCA method achieves a pixel-level accuracy of 84.8%. Our work showcases strong potential for growth in the field of in-situ on-line inspection of industrial products.
Authors: Minkyu Jeon, Rishwanth Raghu, Miro Astore, Geoffrey Woollard, Ryan Feathers, Alkin Kaz, Sonya M. Hanson, Pilar Cossio, Ellen D. Zhong
Abstract: Cryo-electron microscopy (cryo-EM) is a powerful technique for determining high-resolution 3D biomolecular structures from imaging data. As this technique can capture dynamic biomolecular complexes, 3D reconstruction methods are increasingly being developed to resolve this intrinsic structural heterogeneity. However, the absence of standardized benchmarks with ground truth structures and validation metrics limits the advancement of the field. Here, we propose CryoBench, a suite of datasets, metrics, and performance benchmarks for heterogeneous reconstruction in cryo-EM. We propose five datasets representing different sources of heterogeneity and degrees of difficulty. These include conformational heterogeneity generated from simple motions and random configurations of antibody complexes and from tens of thousands of structures sampled from a molecular dynamics simulation. We also design datasets containing compositional heterogeneity from mixtures of ribosome assembly states and 100 common complexes present in cells. We then perform a comprehensive analysis of state-of-the-art heterogeneous reconstruction tools including neural and non-neural methods and their sensitivity to noise, and propose new metrics for quantitative comparison of methods. We hope that this benchmark will be a foundational resource for analyzing existing methods and new algorithmic development in both the cryo-EM and machine learning communities.
Authors: Liqi Yan, Qifan Wang, Junhan Zhao, Qiang Guan, Zheng Tang, Jianhui Zhang, Dongfang Liu
Abstract: First-Person-View (FPV) holds immense potential for revolutionizing the trajectory of Unmanned Aerial Vehicles (UAVs), offering an exhilarating avenue for navigating complex building structures. Yet, traditional Neural Radiance Field (NeRF) methods face challenges such as sampling single points per iteration and requiring an extensive array of views for supervision. UAV videos exacerbate these issues with limited viewpoints and significant spatial scale variations, resulting in inadequate detail rendering across diverse scales. In response, we introduce FPV-NeRF, addressing these challenges through three key facets: (1) Temporal consistency. Leveraging spatio-temporal continuity ensures seamless coherence between frames; (2) Global structure. Incorporating various global features during point sampling preserves space integrity; (3) Local granularity. Employing a comprehensive framework and multi-resolution supervision for multi-scale scene feature representation tackles the intricacies of UAV video spatial scales. Additionally, due to the scarcity of publicly available FPV videos, we introduce an innovative view synthesis method using NeRF to generate FPV perspectives from UAV footage, enhancing spatial perception for drones. Our novel dataset spans diverse trajectories, from outdoor to indoor environments, in the UAV domain, differing significantly from traditional NeRF scenarios. Through extensive experiments encompassing both interior and exterior building structures, FPV-NeRF demonstrates a superior understanding of the UAV flying space, outperforming state-of-the-art methods in our curated UAV dataset. Explore our project page for further insights: https://fpv-nerf.github.io/.
Authors: Delong Zhang, Yi-Xing Peng, Xiao-Ming Wu, Ancong Wu, Wei-Shi Zheng
Abstract: Online person re-identification services face privacy breaches from potential data leakage and recovery attacks, exposing cloud-stored images to malicious attackers and triggering public concern. The privacy protection of pedestrian images is crucial. Previous privacy-preserving person re-identification methods are unable to resist recovery attacks and compromise accuracy. In this paper, we propose an iterative method (PixelFade) to optimize pedestrian images into noise-like images to resist recovery attacks. We first give an in-depth study of protected images from previous privacy methods, which reveal that the chaos of protected images can disrupt the learning of recovery models. Accordingly, Specifically, we propose Noise-guided Objective Function with the feature constraints of a specific authorization model, optimizing pedestrian images to normal-distributed noise images while preserving their original identity information as per the authorization model. To solve the above non-convex optimization problem, we propose a heuristic optimization algorithm that alternately performs the Constraint Operation and the Partial Replacement Operation. This strategy not only safeguards that original pixels are replaced with noises to protect privacy, but also guides the images towards an improved optimization direction to effectively preserve discriminative features. Extensive experiments demonstrate that our PixelFade outperforms previous methods in resisting recovery attacks and Re-ID performance. The code is available at https://github.com/iSEE-Laboratory/PixelFade.
Authors: Yisheng Yang, Guodong Du, Chean Khim Toa, Ho-Kin Tang, Sim Kuan Goh
Abstract: Neural architecture search (NAS) automates neural network design by using optimization algorithms to navigate architecture spaces, reducing the burden of manual architecture design. While NAS has achieved success, applying it to emerging domains, such as analyzing unstructured 3D point clouds, remains underexplored due to the data lying in non-Euclidean spaces, unlike images. This paper presents Success-History-based Self-adaptive Differential Evolution with a Joint Point Interaction Dimension Search (SHSADE-PIDS), an evolutionary NAS framework that encodes discrete deep neural network architectures to continuous spaces and performs searches in the continuous spaces for efficient point cloud neural architectures. Comprehensive experiments on challenging 3D segmentation and classification benchmarks demonstrate SHSADE-PIDS's capabilities. It discovered highly efficient architectures with higher accuracy, significantly advancing prior NAS techniques. For segmentation on SemanticKITTI, SHSADE-PIDS attained 64.51% mean IoU using only 0.55M parameters and 4.5GMACs, reducing overhead by over 22-26X versus other top methods. For ModelNet40 classification, it achieved 93.4% accuracy with just 1.31M parameters, surpassing larger models. SHSADE-PIDS provided valuable insights into bridging evolutionary algorithms with neural architecture optimization, particularly for emerging frontiers like point cloud learning.
Authors: Hye-Geun Kim, Yong-Hyuk Moon, Yeong-Jun Cho
Abstract: Object re-identification (ReID) in large camera networks has many challenges. First, the similar appearances of objects degrade ReID performances. This challenge cannot be addressed by existing appearance-based ReID methods. Second, most ReID studies are performed in laboratory settings and do not consider ReID problems in real-world scenarios. To overcome these challenges, we introduce a novel ReID framework that leverages a spatial-temporal fusion network and causal identity matching (CIM). The framework estimates camera network topology using the proposed adaptive Parzen window and combines appearance features with spatial-temporal cue within the Fusion Network. It achieved outstanding performance across several datasets, including VeRi776, Vehicle-3I, and Market-1501, achieving up to 99.70% rank-1 accuracy and 95.5% mAP. Furthermore, the proposed CIM approach, which dynamically assigns gallery sets based on the camera network topology, further improved ReID accuracy and robustness in real-world settings, evidenced by a 94.95% mAP and 95.19% F1 score on the Vehicle-3I dataset. The experimental results support the effectiveness of incorporating spatial-temporal information and CIM for real-world ReID scenarios regardless of the data domain (e.g., vehicle, person).
Authors: Utkarsh Tiwari, Snehashis Majhi, Michal Balazia, Fran\c{c}ois Br\'emond
Abstract: Video anomaly detection (VAD) in autonomous driving scenario is an important task, however it involves several challenges due to the ego-centric views and moving camera. Due to this, it remains largely under-explored. While recent developments in weakly-supervised VAD methods have shown remarkable progress in detecting critical real-world anomalies in static camera scenario, the development and validation of such methods are yet to be explored for moving camera VAD. This is mainly due to existing datasets like DoTA not following training pre-conditions of weakly-supervised learning. In this paper, we aim to promote weakly-supervised method development for autonomous driving VAD. We reorganize the DoTA dataset and aim to validate recent powerful weakly-supervised VAD methods on moving camera scenarios. Further, we provide a detailed analysis of what modifications on state-of-the-art methods can significantly improve the detection performance. Towards this, we propose a "feature transformation block" and through experimentation we show that our propositions can empower existing weakly-supervised VAD methods significantly in improving the VAD in autonomous driving. Our codes/dataset/demo will be released at github.com/ut21/WSAD-Driving
Authors: Rukesh Prajapati, Amr S. El-Wakeel
Abstract: Road intersection monitoring and control research often utilize bird's eye view (BEV) simulators. In real traffic settings, achieving a BEV akin to that in a simulator necessitates the deployment of drones or specific sensor mounting, which is neither feasible nor practical. Consequently, traffic intersection management remains confined to simulation environments given these constraints. In this paper, we address the gap between simulated environments and real-world implementation by introducing a novel deep-learning model that converts a single camera's perspective of a road intersection into a BEV. We created a simulation environment that closely resembles a real-world traffic junction. The proposed model transforms the vehicles into BEV images, facilitating road intersection monitoring and control model processing. Inspired by image transformation techniques, we propose a Spatial-Transformer Double Decoder-UNet (SDD-UNet) model that aims to eliminate the transformed image distortions. In addition, the model accurately estimates the vehicle's positions and enables the direct application of simulation-trained models in real-world contexts. SDD-UNet model achieves an average dice similarity coefficient (DSC) above 95% which is 40% better than the original UNet model. The mean absolute error (MAE) is 0.102 and the centroid of the predicted mask is 0.14 meters displaced, on average, indicating high accuracy.
Authors: Jifei Miao, Junjun Pan, Michael K. Ng
Abstract: Reduced biquaternion (RB), as a four-dimensional algebra highly suitable for representing color pixels, has recently garnered significant attention from numerous scholars. In this paper, for color image processing problems, we introduce a concept of the non-negative RB matrix and then use the multiplication properties of RB to propose a non-negative RB matrix factorization (NRBMF) model. The NRBMF model is introduced to address the challenge of reasonably establishing a non-negative quaternion matrix factorization model, which is primarily hindered by the multiplication properties of traditional quaternions. Furthermore, this paper transforms the problem of solving the NRBMF model into an RB alternating non-negative least squares (RB-ANNLS) problem. Then, by introducing a method to compute the gradient of the real function with RB matrix variables, we solve the RB-ANNLS optimization problem using the RB projected gradient algorithm and conduct a convergence analysis of the algorithm. Finally, we validate the effectiveness and superiority of the proposed NRBMF model in color face recognition.
Authors: Kai Yu, Yang Zhou, Yang Bai, Zhi Da Soh, Xinxing Xu, Rick Siow Mong Goh, Ching-Yu Cheng, Yong Liu
Abstract: Retinal foundation models aim to learn generalizable representations from diverse retinal images, facilitating label-efficient model adaptation across various ophthalmic tasks. Despite their success, current retinal foundation models are generally restricted to a single imaging modality, such as Color Fundus Photography (CFP) or Optical Coherence Tomography (OCT), limiting their versatility. Moreover, these models may struggle to fully leverage expert annotations and overlook the valuable domain knowledge essential for domain-specific representation learning. To overcome these limitations, we introduce UrFound, a retinal foundation model designed to learn universal representations from both multimodal retinal images and domain knowledge. UrFound is equipped with a modality-agnostic image encoder and accepts either CFP or OCT images as inputs. To integrate domain knowledge into representation learning, we encode expert annotation in text supervision and propose a knowledge-guided masked modeling strategy for model pre-training. It involves reconstructing randomly masked patches of retinal images while predicting masked text tokens conditioned on the corresponding retinal image. This approach aligns multimodal images and textual expert annotations within a unified latent space, facilitating generalizable and domain-specific representation learning. Experimental results demonstrate that UrFound exhibits strong generalization ability and data efficiency when adapting to various tasks in retinal image analysis. By training on ~180k retinal images, UrFound significantly outperforms the state-of-the-art retinal foundation model trained on up to 1.6 million unlabelled images across 8 public retinal datasets. Our code and data are available at https://github.com/yukkai/UrFound.
Authors: Libo Zhang, Yuxuan Han, Wenbin Lin, Jingwang Ling, Feng Xu
Abstract: We present PRTGaussian, a realtime relightable novel-view synthesis method made possible by combining 3D Gaussians and Precomputed Radiance Transfer (PRT). By fitting relightable Gaussians to multi-view OLAT data, our method enables real-time, free-viewpoint relighting. By estimating the radiance transfer based on high-order spherical harmonics, we achieve a balance between capturing detailed relighting effects and maintaining computational efficiency. We utilize a two-stage process: in the first stage, we reconstruct a coarse geometry of the object from multi-view images. In the second stage, we initialize 3D Gaussians with the obtained point cloud, then simultaneously refine the coarse geometry and learn the light transport for each Gaussian. Extensive experiments on synthetic datasets show that our approach can achieve fast and high-quality relighting for general objects. Code and data are available at https://github.com/zhanglbthu/PRTGaussian.
Authors: Zhongche Qu, Zhi Zhang, Cong Liu, Jianhua Yin
Abstract: Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities since their data association usually relies on feature correspondences. Additionally, learning-based SLAM systems often fall short in terms of real-time performance and accuracy. Balancing real-time performance with dense 3D reconstruction capabilities is a challenging problem. In this paper, we propose a real-time RGB-D SLAM system that incorporates a novel view synthesis technique, 3D Gaussian Splatting, for 3D scene representation and pose estimation. This technique leverages the real-time rendering performance of 3D Gaussian Splatting with rasterization and allows for differentiable optimization in real time through CUDA implementation. We also enable mesh reconstruction from 3D Gaussians for explicit dense 3D reconstruction. To estimate accurate camera poses, we utilize a rotation-translation decoupled strategy with inverse optimization. This involves iteratively updating both in several iterations through gradient-based optimization. This process includes differentiably rendering RGB, depth, and silhouette maps and updating the camera parameters to minimize a combined loss of photometric loss, depth geometry loss, and visibility loss, given the existing 3D Gaussian map. However, 3D Gaussian Splatting (3DGS) struggles to accurately represent surfaces due to the multi-view inconsistency of 3D Gaussians, which can lead to reduced accuracy in both camera pose estimation and scene reconstruction. To address this, we utilize depth priors as additional regularization to enforce geometric constraints, thereby improving the accuracy of both pose estimation and 3D reconstruction. We also provide extensive experimental results on public benchmark datasets to demonstrate the effectiveness of our proposed methods in terms of pose accuracy, geometric accuracy, and rendering performance.
Authors: Blessing Agyei Kyem, Eugene Kofi Okrah Denteh, Joshua Kofi Asamoah, Kenneth Adomako Tutu, Armstrong Aboah
Abstract: Road infrastructure maintenance in developing countries faces unique challenges due to resource constraints and diverse environmental factors. This study addresses the critical need for efficient, accurate, and locally-relevant pavement distress detection methods in these regions. We present a novel deep learning approach combining YOLO (You Only Look Once) object detection models with a Convolutional Block Attention Module (CBAM) to simultaneously detect and classify multiple pavement distress types. The model demonstrates robust performance in detecting and classifying potholes, longitudinal cracks, alligator cracks, and raveling, with confidence scores ranging from 0.46 to 0.93. While some misclassifications occur in complex scenarios, these provide insights into unique challenges of pavement assessment in developing countries. Additionally, we developed a web-based application for real-time distress detection from images and videos. This research advances automated pavement distress detection and provides a tailored solution for developing countries, potentially improving road safety, optimizing maintenance strategies, and contributing to sustainable transportation infrastructure development.
Authors: Abdul-Razak Alhassan Gamani, Ibrahim Arhin, Adrena Kyeremateng Asamoah
Abstract: Accurate identification of strawberries during their maturing stages is crucial for optimizing yield management, and pest control, and making informed decisions related to harvest and post-harvest logistics. This study evaluates the performance of YOLOv8 model configurations for instance segmentation of strawberries into ripe and unripe stages in an open field environment. The YOLOv8n model demonstrated superior segmentation accuracy with a mean Average Precision (mAP) of 80.9\%, outperforming other YOLOv8 configurations. In terms of inference speed, YOLOv8n processed images at 12.9 milliseconds, while YOLOv8s, the least-performing model, processed at 22.2 milliseconds. Over 86 test images with 348 ground truth labels, YOLOv8n detected 235 ripe fruit classes and 51 unripe fruit classes out of 251 ground truth ripe fruits and 97 unripe ground truth labels, respectively. In comparison, YOLOv8s detected 204 ripe fruits and 37 unripe fruits. Overall, YOLOv8n achieved the fastest inference speed of 24.2 milliseconds, outperforming YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x, which processed images at 33.0 milliseconds, 44.3 milliseconds, 53.6 milliseconds, and 62.5 milliseconds, respectively. These results underscore the potential of advanced object segmentation algorithms to address complex visual recognition tasks in open-field agriculture effectively to address complex visual recognition tasks in open-field agriculture effectively.
Authors: Ziyin Zhou, Ke Sun, Zhongxi Chen, Huafeng Kuang, Xiaoshuai Sun, Rongrong Ji
Abstract: The rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial for understanding the vulnerabilities of existing detection methods and developing more robust techniques. However, current adversarial attacks often introduce visible noise, have poor transferability, and fail to address spectral differences between AI-generated and genuine images. To address this, we propose StealthDiffusion, a framework based on stable diffusion that modifies AI-generated images into high-quality, imperceptible adversarial examples capable of evading state-of-the-art forensic detectors. StealthDiffusion comprises two main components: Latent Adversarial Optimization, which generates adversarial perturbations in the latent space of stable diffusion, and Control-VAE, a module that reduces spectral differences between the generated adversarial images and genuine images without affecting the original diffusion model's generation process. Extensive experiments show that StealthDiffusion is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries with frequency spectra similar to genuine images. These forgeries are classified as genuine by advanced forensic classifiers and are difficult for humans to distinguish.
Authors: Yingjie Gao, Yanan Zhang, Ziyue Huang, Nanqing Liu, Di Huang
Abstract: In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated data. The fine-tuning based paradigm is currently dominating this field, where detectors are initially pre-trained on base classes with sufficient samples and then fine-tuned on novel ones with few samples, but the scarcity of labeled samples of novel classes greatly interferes precisely fitting their data distribution, thus hampering the performance. To address this issue, we propose a new framework for FSOD, namely Prototype-based Soft-labels and Test-Time Learning (PS-TTL). Specifically, we design a Test-Time Learning (TTL) module that employs a mean-teacher network for self-training to discover novel instances from test data, allowing detectors to learn better representations and classifiers for novel classes. Furthermore, we notice that even though relatively low-confidence pseudo-labels exhibit classification confusion, they still tend to recall foreground. We thus develop a Prototype-based Soft-labels (PS) strategy through assessing similarities between low-confidence pseudo-labels and category prototypes as soft-labels to unleash their potential, which substantially mitigates the constraints posed by few-shot samples. Extensive experiments on both the VOC and COCO benchmarks show that PS-TTL achieves the state-of-the-art, highlighting its effectiveness. The code and model are available at https://github.com/gaoyingjay/PS-TTL.
Authors: Pengyang Ling, Huaian Chen, Xiao Tan, Yimeng Shan, Yi Jin
Abstract: Images captured in hazy weather generally suffer from quality degradation, and many dehazing methods have been developed to solve this problem. However, single image dehazing problem is still challenging due to its ill-posed nature. In this paper, we propose a depth order guided single image dehazing method, which utilizes depth order in hazy images to guide the dehazing process to achieve a similar depth perception in corresponding dehazing results. The consistency of depth perception ensures that the regions that look farther or closer in hazy images also appear farther or closer in the corresponding dehazing results, and thus effectively avoid the undesired visual effects. To achieve this goal, a simple yet effective strategy is proposed to extract the depth order in hazy images, which offers a reference for depth perception in hazy weather. Additionally, a depth order embedded transformation model is devised, which performs transmission estimation under the guidance of depth order to realize an unchanged depth order in the dehazing results. The extracted depth order provides a powerful global constraint for the dehazing process, which contributes to the efficient utilization of global information, thereby bringing an overall improvement in restoration quality. Extensive experiments demonstrate that the proposed method can better recover potential structure and vivid color with higher computational efficiency than the state-of-the-art dehazing methods.
Authors: Koushik Biswas, Ridal Pal, Shaswat Patel, Debesh Jha, Meghana Karri, Amit Reza, Gorkem Durak, Alpay Medetalibeyoglu, Matthew Antalek, Yury Velichko, Daniela Ladner, Amir Borhani, Ulas Bagci
Abstract: Accurately segmenting different organs from medical images is a critical prerequisite for computer-assisted diagnosis and intervention planning. This study proposes a deep learning-based approach for segmenting various organs from CT and MRI scans and classifying diseases. Our study introduces a novel technique integrating momentum within residual blocks for enhanced training dynamics in medical image analysis. We applied our method in two distinct tasks: segmenting liver, lung, & colon data and classifying abdominal pelvic CT and MRI scans. The proposed approach has shown promising results, outperforming state-of-the-art methods on publicly available benchmarking datasets. For instance, in the lung segmentation dataset, our approach yielded significant enhancements over the TransNetR model, including a 5.72% increase in dice score, a 5.04% improvement in mean Intersection over Union (mIoU), an 8.02% improvement in recall, and a 4.42% improvement in precision. Hence, incorporating momentum led to state-of-the-art performance in both segmentation and classification tasks, representing a significant advancement in the field of medical imaging.
Authors: Guoan Xu, Wenfeng Huang, Tao Wu, Ligeng Chen, Wenjing Jia, Guangwei Gao, Xiatian Zhu, Stuart Perry
Abstract: Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segmentation methods often struggle with precise predictions in localized areas like object boundaries. To tackle this challenge, we introduce a new semantic segmentation architecture, ``MacFormer'', which features two key components. Firstly, using learnable agent tokens, a Mutual Agent Cross-Attention (MACA) mechanism effectively facilitates the bidirectional integration of features across encoder and decoder layers. This enables better preservation of low-level features, such as elementary edges, during decoding. Secondly, a Frequency Enhancement Module (FEM) in the decoder leverages high-frequency and low-frequency components to boost features in the frequency domain, benefiting object boundaries with minimal computational complexity increase. MacFormer is demonstrated to be compatible with various network architectures and outperforms existing methods in both accuracy and efficiency on benchmark datasets ADE20K and Cityscapes under different computational constraints.
Authors: Shuai Zhao, Yongkun Du, Zhineng Chen, Yu-Gang Jiang
Abstract: Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations that align well with images on real scenes, thereby limiting the performance of these methods. We note that vision-language models like CLIP, pre-trained on extensive real image-text pairs, effectively align images and text in a unified embedding space, suggesting the potential to derive the representations of real images from text alone. Building upon this premise, we introduce a novel method named Decoder Pre-training with only text for STR (DPTR). DPTR treats text embeddings produced by the CLIP text encoder as pseudo visual embeddings and uses them to pre-train the decoder. An Offline Randomized Perturbation (ORP) strategy is introduced. It enriches the diversity of text embeddings by incorporating natural image embeddings extracted from the CLIP image encoder, effectively directing the decoder to acquire the potential representations of real images. In addition, we introduce a Feature Merge Unit (FMU) that guides the extracted visual embeddings focusing on the character foreground within the text image, thereby enabling the pre-trained decoder to work more efficiently and accurately. Extensive experiments across various STR decoders and language recognition tasks underscore the broad applicability and remarkable performance of DPTR, providing a novel insight for STR pre-training. Code is available at https://github.com/Topdu/OpenOCR
Authors: Yifan Pu, Zhuofan Xia, Jiayi Guo, Dongchen Han, Qixiu Li, Duo Li, Yuhui Yuan, Ji Li, Yizeng Han, Shiji Song, Gao Huang, Xiu Li
Abstract: This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation, we present a novel diffusion transformer framework incorporating an additional set of mediator tokens to engage with queries and keys separately. By modulating the number of mediator tokens during the denoising generation phases, our model initiates the denoising process with a precise, non-ambiguous stage and gradually transitions to a phase enriched with detail. Concurrently, integrating mediator tokens simplifies the attention module's complexity to a linear scale, enhancing the efficiency of global attention processes. Additionally, we propose a time-step dynamic mediator token adjustment mechanism that further decreases the required computational FLOPs for generation, simultaneously facilitating the generation of high-quality images within the constraints of varied inference budgets. Extensive experiments demonstrate that the proposed method can improve the generated image quality while also reducing the inference cost of diffusion transformers. When integrated with the recent work SiT, our method achieves a state-of-the-art FID score of 2.01. The source code is available at https://github.com/LeapLabTHU/Attention-Mediators.
Authors: Rukai Wei, Heng Cui, Yu Liu, Yufeng Hou, Yanzhao Xie, Ke Zhou
Abstract: Implementing cross-modal hashing between 2D images and 3D point-cloud data is a growing concern in real-world retrieval systems. Simply applying existing cross-modal approaches to this new task fails to adequately capture latent multi-modal semantics and effectively bridge the modality gap between 2D and 3D. To address these issues without relying on hand-crafted labels, we propose contrastive masked autoencoders based self-supervised hashing (CMAH) for retrieval between images and point-cloud data. We start by contrasting 2D-3D pairs and explicitly constraining them into a joint Hamming space. This contrastive learning process ensures robust discriminability for the generated hash codes and effectively reduces the modality gap. Moreover, we utilize multi-modal auto-encoders to enhance the model's understanding of multi-modal semantics. By completing the masked image/point-cloud data modeling task, the model is encouraged to capture more localized clues. In addition, the proposed multi-modal fusion block facilitates fine-grained interactions among different modalities. Extensive experiments on three public datasets demonstrate that the proposed CMAH significantly outperforms all baseline methods.
Authors: Du Chen, Zhengqiang Zhang, Jie Liang, Lei Zhang
Abstract: Generative adversarial networks (GAN) and generative diffusion models (DM) have been widely used in real-world image super-resolution (Real-ISR) to enhance the image perceptual quality. However, these generative models are prone to generating visual artifacts and false image structures, resulting in unnatural Real-ISR results. Based on the fact that natural images exhibit high self-similarities, i.e., a local patch can have many similar patches to it in the whole image, in this work we propose a simple yet effective self-similarity loss (SSL) to improve the performance of generative Real-ISR models, enhancing the hallucination of structural and textural details while reducing the unpleasant visual artifacts. Specifically, we compute a self-similarity graph (SSG) of the ground-truth image, and enforce the SSG of Real-ISR output to be close to it. To reduce the training cost and focus on edge areas, we generate an edge mask from the ground-truth image, and compute the SSG only on the masked pixels. The proposed SSL serves as a general plug-and-play penalty, which could be easily applied to the off-the-shelf Real-ISR models. Our experiments demonstrate that, by coupling with SSL, the performance of many state-of-the-art Real-ISR models, including those GAN and DM based ones, can be largely improved, reproducing more perceptually realistic image details and eliminating many false reconstructions and visual artifacts. Codes and supplementary material can be found at https://github.com/ChrisDud0257/SSL
Authors: Hongchao Zhou, Shunbo Hu
Abstract: In this work, we propose a novel deformable convolutional pyramid network for unsupervised image registration. Specifically, the proposed network enhances the traditional pyramid network by adding an additional shared auxiliary decoder for image pairs. This decoder provides multi-scale high-level feature information from unblended image pairs for the registration task. During the registration process, we also design a multi-scale feature fusion block to extract the most beneficial features for the registration task from both global and local contexts. Validation results indicate that this method can capture complex deformations while achieving higher registration accuracy and maintaining smooth and plausible deformations.
Authors: Haoxuan Ding, Qi Wang, Junyu Gao, Qiang Li
Abstract: Traditional license plate detection and recognition models are often trained on closed datasets, limiting their ability to handle the diverse license plate formats across different regions. The emergence of large-scale pre-trained models has shown exceptional generalization capabilities, enabling few-shot and zero-shot learning. We propose OneShotLP, a training-free framework for video-based license plate detection and recognition, leveraging these advanced models. Starting with the license plate position in the first video frame, our method tracks this position across subsequent frames using a point tracking module, creating a trajectory of prompts. These prompts are input into a segmentation module that uses a promptable large segmentation model to generate local masks of the license plate regions. The segmented areas are then processed by multimodal large language models (MLLMs) for accurate license plate recognition. OneShotLP offers significant advantages, including the ability to function effectively without extensive training data and adaptability to various license plate styles. Experimental results on UFPR-ALPR and SSIG-SegPlate datasets demonstrate the superior accuracy of our approach compared to traditional methods. This highlights the potential of leveraging pre-trained models for diverse real-world applications in intelligent transportation systems. The code is available at https://github.com/Dinghaoxuan/OneShotLP.
Authors: Huafeng Qin, Yuming Fu, Jing Chen, Mounim A. El-Yacoubi, Xinbo Gao, Jun Wang
Abstract: Due to the advantages such as high security, high privacy, and liveness recognition, vein recognition has been received more and more attention in past years. Recently, deep learning models, e.g., Mamba has shown robust feature representation with linear computational complexity and successfully applied for visual tasks. However, vision Manba can capture long-distance feature dependencies but unfortunately deteriorate local feature details. Besides, manually designing a Mamba architecture based on human priori knowledge is very time-consuming and error-prone. In this paper, first, we propose a hybrid network structure named Global-local Vision Mamba (GLVM), to learn the local correlations in images explicitly and global dependencies among tokens for vein feature representation. Secondly, we design a Multi-head Mamba to learn the dependencies along different directions, so as to improve the feature representation ability of vision Mamba. Thirdly, to learn the complementary features, we propose a ConvMamba block consisting of three branches, named Multi-head Mamba branch (MHMamba), Feature Iteration Unit branch (FIU), and Convolutional Neural Network (CNN) branch, where the Feature Iteration Unit branch aims to fuse convolutional local features with Mamba-based global representations. Finally, a Globallocal Alternate Neural Architecture Search (GLNAS) method is proposed to search the optimal architecture of GLVM alternately with the evolutionary algorithm, thereby improving the recognition performance for vein recognition tasks. We conduct rigorous experiments on three public palm-vein databases to estimate the performance. The experimental results demonstrate that the proposed method outperforms the representative approaches and achieves state-of-the-art recognition accuracy.
Authors: Haijing Guo, Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Lingyi Hong, Pinxue Guo, Jinglun Li, Wenqiang Zhang
Abstract: Deep neural networks (DNNs) are known to be susceptible to adversarial examples, leading to significant performance degradation. In black-box attack scenarios, a considerable attack performance gap between the surrogate model and the target model persists. This work focuses on enhancing the transferability of adversarial examples to narrow this performance gap. We observe that the gradient information around the clean image, i.e. Neighbourhood Gradient Information, can offer high transferability. Leveraging this, we propose the NGI-Attack, which incorporates Example Backtracking and Multiplex Mask strategies, to use this gradient information and enhance transferability fully. Specifically, we first adopt Example Backtracking to accumulate Neighbourhood Gradient Information as the initial momentum term. Multiplex Mask, which forms a multi-way attack strategy, aims to force the network to focus on non-discriminative regions, which can obtain richer gradient information during only a few iterations. Extensive experiments demonstrate that our approach significantly enhances adversarial transferability. Especially, when attacking numerous defense models, we achieve an average attack success rate of 95.8%. Notably, our method can plugin with any off-the-shelf algorithm to improve their attack performance without additional time cost.
Authors: Sungyeon Kim, Boseung Jeong, Donghyun Kim, Suha Kwak
Abstract: Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces generalization to out-of-distribution (OOD) data and demands extensive computational resources. We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks while simultaneously addressing both these issues. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Furthermore, we propose MPM-NCE loss designed for fine-tuning on vision-language downstream tasks. It ensures precise alignment of multiple image-text pairs and discriminative feature learning. By extending the benchmark for robust fine-tuning beyond classification to include diverse tasks such as cross-modal retrieval and open vocabulary segmentation, we demonstrate the broad applicability of R-Adapter. Our extensive experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
Authors: Zhigang Tu, Zitao Gao, Zhengbo Zhang, Chunluan Zhou, Junsong Yuan, Bo Du
Abstract: Falling objects from buildings can cause severe injuries to pedestrians due to the great impact force they exert. Although surveillance cameras are installed around some buildings, it is challenging for humans to capture such events in surveillance videos due to the small size and fast motion of falling objects, as well as the complex background. Therefore, it is necessary to develop methods to automatically detect falling objects around buildings in surveillance videos. To facilitate the investigation of falling object detection, we propose a large, diverse video dataset called FADE (FAlling Object DEtection around Buildings) for the first time. FADE contains 1,881 videos from 18 scenes, featuring 8 falling object categories, 4 weather conditions, and 4 video resolutions. Additionally, we develop a new object detection method called FADE-Net, which effectively leverages motion information and produces small-sized but high-quality proposals for detecting falling objects around buildings. Importantly, our method is extensively evaluated and analyzed by comparing it with the previous approaches used for generic object detection, video object detection, and moving object detection on the FADE dataset. Experimental results show that the proposed FADE-Net significantly outperforms other methods, providing an effective baseline for future research. The dataset and code are publicly available at https://fadedataset.github.io/FADE.github.io/.
Authors: Nanyang Du, Chen Tang, Yuan Meng, Zhi Wang
Abstract: Performing unsupervised domain adaptation on resource-constrained edge devices is a significant task. Although existing research allows edge devices to use subnets with different computational budgets for inference, they often require expensive pre-training and do not consider the issues of parameter precision redundancy in the model, which is not conducive to the deployment of the model on edge devices. In this paper, we introduce a ReTraining-Free Quantized (RTF-Q) network based on unsupervised domain adaptation, featuring quantized subnets of varying computational costs that can operate on devices with dynamically changing computation budgets. Our network has three switchable dimensions: width (number of channels), input resolution, and quantization bit-width. Specifically, we choose subnet dimensions that have minimal impact on network performance and then directly load the official weight files without requiring expensive and time-consuming pre-training on Imagenet-1K. To further reduce the network's computational load and memory usage, we use quantization-aware training, reducing the BitOPs of full-precision networks by at least 1/16. We propose a training method called SandwichQ for multiple quantization bit widths, which can efficiently train multiple quantization subnets. By training in multiple quantization bit-width spaces simultaneously and using the proposed SandwichQ rule, we achieve better network performance compared to using a single quantization bit-width alone. Experimental results show that our method achieves classification accuracy comparable to SOTA methods on various UDA tasks, significantly reducing network size and computational overhead. Code will be available at https://github.com/dunanyang/RTF-Q.
Authors: Vaibhav Ganatra, Drishti Goel
Abstract: Deep learning models used for medical image classification tasks are often constrained by the limited amount of training data along with severe class imbalance. Despite these problems, models should be explainable to enable human trust in the models' decisions to ensure wider adoption in high-risk situations. In this paper, we propose PRECISe, an explainable-by-design model meticulously constructed to concurrently address all three challenges. Evaluation on 2 imbalanced medical image datasets reveals that PRECISe outperforms the current state-of-the-art methods on data efficient generalization to minority classes, achieving an accuracy of ~87% in detecting pneumonia in chest x-rays upon training on <60 images only. Additionally, a case study is presented to highlight the model's ability to produce easily interpretable predictions, reinforcing its practical utility and reliability for medical imaging tasks.
Authors: Chaoyi Ai
Abstract: Human-Object Interaction (HOI) aims to identify the pairs of humans and objects in images and to recognize their relationships, ultimately forming $\langle human, object, verb \rangle$ triplets. Under default settings, HOI performance is nearly saturated, with many studies focusing on long-tail distribution and zero-shot/few-shot scenarios. Let us consider an intriguing problem:``What if there is only test dataset without training dataset, using multimodal visual foundation model in a training-free manner? '' This study uses two experimental settings: grounding truth and random arbitrary combinations. We get some interesting conclusion and find that the open vocabulary capabilities of the multimodal visual foundation model are not yet fully realized. Additionally, replacing the feature extraction with grounding DINO further confirms these findings.
Authors: Yuhan Zhu, Guozhen Zhang, Chen Xu, Haocheng Shen, Xiaoxin Chen, Gangshan Wu, Limin Wang
Abstract: Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically require per-image prompt adaptation during inference, which incurs high computational budgets and limits scalability and practical deployment. To overcome this issue, we introduce Self-TPT, a novel framework leveraging Self-supervised learning for efficient Test-time Prompt Tuning. The key aspect of Self-TPT is that it turns to efficient predefined class adaptation via self-supervised learning, thus avoiding computation-heavy per-image adaptation at inference. Self-TPT begins by co-training the self-supervised and the classification task using source data, then applies the self-supervised task exclusively for test-time new class adaptation. Specifically, we propose Contrastive Prompt Learning (CPT) as the key task for self-supervision. CPT is designed to minimize the intra-class distances while enhancing inter-class distinguishability via contrastive learning. Furthermore, empirical evidence suggests that CPT could closely mimic back-propagated gradients of the classification task, offering a plausible explanation for its effectiveness. Motivated by this finding, we further introduce a gradient matching loss to explicitly enhance the gradient similarity. We evaluated Self-TPT across three challenging zero-shot benchmarks. The results consistently demonstrate that Self-TPT not only significantly reduces inference costs but also achieves state-of-the-art performance, effectively balancing the efficiency-efficacy trade-off.
Authors: Hannuo Zhang, Huihui Li, Jiarui Lin, Yujie Zhang, Jianghua Fan, Hang Liu
Abstract: Optical remote sensing and Synthetic Aperture Radar(SAR) remote sensing are crucial for earth observation, offering complementary capabilities. While optical sensors provide high-quality images, they are limited by weather and lighting conditions. In contrast, SAR sensors can operate effectively under adverse conditions. This letter proposes a GAN-based SAR-to-optical image translation method named Seg-CycleGAN, designed to enhance the accuracy of ship target translation by leveraging semantic information from a pre-trained semantic segmentation model. Our method utilizes the downstream task of ship target semantic segmentation to guide the training of image translation network, improving the quality of output Optical-styled images. The potential of foundation-model-annotated datasets in SAR-to-optical translation tasks is revealed. This work suggests broader research and applications for downstream-task-guided frameworks. The code will be available at https://github.com/NPULHH/
Authors: Zhuoyan Liu, Bo Wang, Ye Li
Abstract: Underwater object detection has higher requirements of running speed and deployment efficiency for the detector due to its specific environmental challenges. NMS of two- or one-stage object detectors and transformer architecture of query-based end-to-end object detectors are not conducive to deployment on underwater embedded devices with limited processing power. As for the detrimental effect of underwater color cast noise, recent underwater object detectors make network architecture or training complex, which also hinders their application and deployment on underwater vehicle platforms. In this paper, we propose the Underwater DECO with improved deNoising training (U-DECN), the query-based end-to-end object detector (with ConvNet encoder-decoder architecture) for underwater color cast noise that addresses the above problems. We integrate advanced technologies from DETR variants into DECO and design optimization methods specifically for the ConvNet architecture, including Separate Contrastive DeNoising Forward and Deformable Convolution in SIM. To address the underwater color cast noise issue, we propose an underwater color denoising query to improve the generalization of the model for the biased object feature information by different color cast noise. Our U-DECN, with ResNet-50 backbone, achieves 61.4 AP (50 epochs), 63.3 AP (72 epochs), 64.0 AP (100 epochs) on DUO, and 21 FPS (5 times faster than Deformable DETR and DINO 4 FPS) on NVIDIA AGX Orin by TensorRT FP16, outperforming the other state-of-the-art query-based end-to-end object detectors. The code is available at https://github.com/LEFTeyex/U-DECN.
Authors: Zhirui Fang, Ming Yang, Weishuai Zeng, Boyu Li, Junpeng Yue, Ziluo Ding, Xiu Li, Zongqing Lu
Abstract: We explore leveraging large multi-modal models (LMMs) and text2image models to build a more general embodied agent. LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world, often failing to accurately identify object positions in images. A bridge is needed to connect LMMs to the physical world. The paper proposes a novel approach, egocentric vision language planning (EgoPlan), to handle long-horizon tasks from an egocentric perspective in varying household scenarios. This model leverages a diffusion model to simulate the fundamental dynamics between states and actions, integrating techniques like style transfer and optical flow to enhance generalization across different environmental dynamics. The LMM serves as a planner, breaking down instructions into sub-goals and selecting actions based on their alignment with these sub-goals, thus enabling more generalized and effective decision-making. Experiments show that EgoPlan improves long-horizon task success rates from the egocentric view compared to baselines across household scenarios.
Authors: Fenghe Tang, Ronghao Xu, Qingsong Yao, Xueming Fu, Quan Quan, Heqin Zhu, Zaiyi Liu, S. Kevin Zhou
Abstract: The generative self-supervised learning strategy exhibits remarkable learning representational capabilities. However, there is limited attention to end-to-end pre-training methods based on a hybrid architecture of CNN and Transformer, which can learn strong local and global representations simultaneously. To address this issue, we propose a generative pre-training strategy called Hybrid Sparse masKing (HySparK) based on masked image modeling and apply it to large-scale pre-training on medical images. First, we perform a bottom-up 3D hybrid masking strategy on the encoder to keep consistency masking. Then we utilize sparse convolution for the top CNNs and encode unmasked patches for the bottom vision Transformers. Second, we employ a simple hierarchical decoder with skip-connections to achieve dense multi-scale feature reconstruction. Third, we implement our pre-training method on a collection of multiple large-scale 3D medical imaging datasets. Extensive experiments indicate that our proposed pre-training strategy demonstrates robust transfer-ability in supervised downstream tasks and sheds light on HySparK's promising prospects. The code is available at https://github.com/FengheTan9/HySparK
Authors: Yuxin Qiao, Keqin Li, Junhong Lin, Rong Wei, Chufeng Jiang, Yang Luo, Haoyu Yang
Abstract: In multi-label classification, machine learning encounters the challenge of domain generalization when handling tasks with distributions differing from the training data. Existing approaches primarily focus on vision object recognition and neglect the integration of natural language. Recent advancements in vision-language pre-training leverage supervision from extensive visual-language pairs, enabling learning across diverse domains and enhancing recognition in multi-modal scenarios. However, these approaches face limitations in loss function utilization, generality across backbones, and class-aware visual fusion. This paper proposes solutions to these limitations by inferring the actual loss, broadening evaluations to larger vision-language backbones, and introducing Mixup-CLIPood, which incorporates a novel mix-up loss for enhanced class-aware visual fusion. Our method demonstrates superior performance in domain generalization across multiple datasets.
Authors: Varun Shiva Krishna Rupani, Velpooru Venkata Sai Thushar, Kondadi Tejith
Abstract: Drowsiness detection is essential for improving safety in areas such as transportation and workplace health. This study presents a real-time system designed to detect drowsiness using the Eye Aspect Ratio (EAR) and facial landmark detection techniques. The system leverages Dlibs pre-trained shape predictor model to accurately detect and monitor 68 facial landmarks, which are used to compute the EAR. By establishing a threshold for the EAR, the system identifies when eyes are closed, indicating potential drowsiness. The process involves capturing a live video stream, detecting faces in each frame, extracting eye landmarks, and calculating the EAR to assess alertness. Our experiments show that the system reliably detects drowsiness with high accuracy while maintaining low computational demands. This study offers a strong solution for real-time drowsiness detection, with promising applications in driver monitoring and workplace safety. Future research will investigate incorporating additional physiological and contextual data to further enhance detection accuracy and reliability.
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: Ahmad Rezaei, Mohammad Akbari, Saeed Ranjbar Alvar, Arezou Fatemi, Yong Zhang
Abstract: With generative models producing high quality images that are indistinguishable from real ones, there is growing concern regarding the malicious usage of AI-generated images. Imperceptible image watermarking is one viable solution towards such concerns. Prior watermarking methods map the image to a latent space for adding the watermark. Moreover, Latent Diffusion Models (LDM) generate the image in the latent space of a pre-trained autoencoder. We argue that this latent space can be used to integrate watermarking into the generation process. To this end, we present LaWa, an in-generation image watermarking method designed for LDMs. By using coarse-to-fine watermark embedding modules, LaWa modifies the latent space of pre-trained autoencoders and achieves high robustness against a wide range of image transformations while preserving perceptual quality of the image. We show that LaWa can also be used as a general image watermarking method. Through extensive experiments, we demonstrate that LaWa outperforms previous works in perceptual quality, robustness against attacks, and computational complexity, while having very low false positive rate. Code is available here.
Authors: Xinrong Hu, Dewen Zeng, Yawen Wu, Xueyang Li, Yiyu Shi
Abstract: In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset can further boost the performance for the downstream semantic segmentation remains unexplored.Applications of previous representation learning methods are hindered by the limited number of 3D volumes and high computational cost. In addition, most of pretext tasks designed specifically for Transformer are not applicable to hierarchical structure of Swin Transformer. Thus, this work proposes a token-level representation learning loss that maximizes agreement between token embeddings from different augmented views individually instead of volume-level global features. Moreover, we identify a potential representation collapse exclusively caused by this new loss. To prevent collapse, we invent a simple "rotate-and-restore" mechanism, which rotates and flips one augmented view of input volume, and later restores the order of tokens in the feature maps. We also modify the contrastive loss to address the discrimination between tokens at the same position but from different volumes. We test our pre-training scheme on two public medical segmentation datasets, and the results on the downstream segmentation task show more improvement of our methods than other state-of-the-art pre-trainig methods.
Authors: Yecheng Zhang, Huimin Zhao, Ying Long
Abstract: Rapidly acquiring three-dimensional (3D) building data, including geometric attributes like rooftop, height, and structure, as well as indicative attributes like function, quality, and age, is essential for accurate urban analysis, simulations, and policy updates. Existing large-scale building datasets lack accuracy, extensibility and indicative attributes. This paper presents a geospatial artificial intelligence (GeoAI) framework for large-scale building modeling, introducing the first Multi-Attribute Building dataset (CMAB) in China at a national scale. The dataset covers 3,667 natural cities with a total rooftop area of 21.3 billion square meters with an F1-Score of 89.93% in rooftop extraction through the OCRNet. We trained bootstrap aggregated XGBoost models with city administrative classifications, incorporating building features such as morphology, location, and function. Using multi-source data, including billions of high-resolution Google Earth imagery and 60 million street view images (SVI), 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. The results support urban planning and sustainable development.
Authors: Zixuan Wu, Yoolim Kim, Carolyn Jane Anderson
Abstract: Vision-Language Models (VLMs) building upon the foundation of powerful large language models have made rapid progress in reasoning across visual and textual data. While VLMs perform well on vision tasks that they are trained on, our results highlight key challenges in abstract pattern recognition. We present GlyphPattern, a 954 item dataset that pairs 318 human-written descriptions of visual patterns from 40 writing systems with three visual presentation styles. GlyphPattern evaluates abstract pattern recognition in VLMs, requiring models to understand and judge natural language descriptions of visual patterns. GlyphPattern patterns are drawn from a large-scale cognitive science investigation of human writing systems; as a result, they are rich in spatial reference and compositionality. Our experiments show that GlyphPattern is challenging for state-of-the-art VLMs (GPT-4o achieves only 55% accuracy), with marginal gains from few-shot prompting. Our detailed error analysis reveals challenges at multiple levels, including visual processing, natural language understanding, and pattern generalization.
Authors: Mingkun Zhang, Jianing Li, Wei Chen, Jiafeng Guo, Xueqi Cheng
Abstract: Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods.
Authors: Zhemin Zhang, Xun Gong
Abstract: Foundation models, such as CNNs and ViTs, have powered the development of image modeling. However, general guidance to model architecture design is still missing. The design of many modern model architectures, such as residual structures, multiplicative gating signal, and feed-forward networks, can be interpreted in terms of the heat conduction equation. This finding inspired us to model images by the heat conduction equation, where the essential idea is to conceptualize image features as temperatures and model their information interaction as the diffusion of thermal energy. We can take advantage of the rich knowledge in the heat conduction equation to guide us in designing new and more interpretable models. As an example, we propose Heat Conduction Layer and Refine Approximation Layer inspired by solving the heat conduction equation using Finite Difference Method and Fourier series, respectively. This paper does not aim to present a state-of-the-art model; instead, it seeks to integrate the overall architectural design of the model into the heat conduction theory framework. Nevertheless, our Heat Conduction Network (HcNet) still shows competitive performance. Code available at \url{https://github.com/ZheminZhang1/HcNet}.
Authors: Peng Wu, Xuerong Zhou, Guansong Pang, Zhiwei Yang, Qingsen Yan, Peng Wang, Yanning Zhang
Abstract: Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs). Our proposed method employs a two-stream network structure, with one stream focusing on the temporal dimension and the other primarily on the spatial dimension. By leveraging the learned knowledge from pre-trained VLMs and incorporating natural motion priors from raw videos, our model learns prompt embeddings that are aligned with spatio-temporal regions of videos (e.g., patches of individual frames) for identify specific local regions of anomalies, enabling accurate video anomaly detection while mitigating the influence of background information. Without relying on detailed spatio-temporal annotations or auxiliary object detection/tracking, our method achieves state-of-the-art performance on three public benchmarks for the WSVADL task.
Authors: Suncheng Xiang, Jincheng Li, Zhengjie Zhang, Shilun Cai, Jiale Guan, Dahong Qian
Abstract: Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras and plays an important role in the prevention and treatment of colorectal cancer in computer-aided diagnosis. However, traditional methods for object ReID directly adopting CNN models trained on the ImageNet dataset usually produce unsatisfactory retrieval performance on colonoscopic datasets due to the large domain gap. Worsely, these solutions typically learn unimodal modal representations on the basis of visual samples, which fails to explore complementary information from different modalities. To address this challenge, we propose a novel Deep Multimodal Collaborative Learning framework named DMCL for polyp re-identification, which can effectively encourage modality collaboration and reinforce generalization capability in medical scenarios. On the basis of it, a dynamic multimodal feature fusion strategy is introduced to leverage the optimized multimodal representations for multimodal fusion via end-to-end training. Experiments on the standard benchmarks show the benefits of the multimodal setting over state-of-the-art unimodal ReID models, especially when combined with the specialized multimodal fusion strategy.
Authors: Hyeono Jung, Jangwon Lee, Jiwon Yoo, Dami Ko, Gyeonghwan Kim
Abstract: Within the domain of person re-identification (ReID), partial ReID methods are considered mainstream, aiming to measure feature distances through comparisons of body parts between samples. However, in practice, previous methods often lack sufficient awareness of anatomical aspect of body parts, resulting in the failure to capture features of the same body parts across different samples. To address this issue, we introduce \textbf{Part Aware Transformer (PAFormer)}, a pose estimation based ReID model which can perform precise part-to-part comparison. In order to inject part awareness to pose tokens, we introduce learnable parameters called `pose token' which estimate the correlation between each body part and partial regions of the image. Notably, at inference phase, PAFormer operates without additional modules related to body part localization, which is commonly used in previous ReID methodologies leveraging pose estimation models. Additionally, leveraging the enhanced awareness of body parts, PAFormer suggests the use of a learning-based visibility predictor to estimate the degree of occlusion for each body part. Also, we introduce a teacher forcing technique using ground truth visibility scores which enables PAFormer to be trained only with visible parts. A set of extensive experiments show that our method outperforms existing approaches on well-known ReID benchmark datasets.
Authors: Taehong Moon, Moonseok Choi, EungGu Yun, Jongmin Yoon, Gayoung Lee, Jaewoong Cho, Juho Lee
Abstract: Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of score estimation networks during the inference. In this work, we propose a novel framework capable of adaptively allocating compute required for the score estimation, thereby reducing the overall sampling time of diffusion models. We observe that the amount of computation required for the score estimation may vary along the time step for which the score is estimated. Based on this observation, we propose an early-exiting scheme, where we skip the subset of parameters in the score estimation network during the inference, based on a time-dependent exit schedule. Using the diffusion models for image synthesis, we show that our method could significantly improve the sampling throughput of the diffusion models without compromising image quality. Furthermore, we also demonstrate that our method seamlessly integrates with various types of solvers for faster sampling, capitalizing on their compatibility to enhance overall efficiency. The source code and our experiments are available at \url{https://github.com/taehong-moon/ee-diffusion}
Authors: Ke Zhou, Zhongwei Qiu, Dongmei Fu
Abstract: Foundational vision models, such as the Segment Anything Model (SAM), have achieved significant breakthroughs through extensive pre-training on large-scale visual datasets. Despite their general success, these models may fall short in specialized tasks with limited data, and fine-tuning such large-scale models is often not feasible. Current strategies involve incorporating adaptors into the pre-trained SAM to facilitate downstream task performance with minimal model adjustment. However, these strategies can be hampered by suboptimal learning approaches for the adaptors. In this paper, we introduce a novel Multi-scale Contrastive Adaptor learning method named MCA-SAM, which enhances adaptor performance through a meticulously designed contrastive learning framework at both token and sample levels. Our Token-level Contrastive adaptor (TC-adaptor) focuses on refining local representations by improving the discriminability of patch tokens, while the Sample-level Contrastive adaptor (SC-adaptor) amplifies global understanding across different samples. Together, these adaptors synergistically enhance feature comparison within and across samples, bolstering the model's representational strength and its ability to adapt to new tasks. Empirical results demonstrate that MCA-SAM sets new benchmarks, outperforming existing methods in three challenging domains: camouflage object detection, shadow segmentation, and polyp segmentation. Specifically, MCA-SAM exhibits substantial relative performance enhancements, achieving a 20.0% improvement in MAE on the COD10K dataset, a 6.0% improvement in MAE on the CAMO dataset, a 15.4% improvement in BER on the ISTD dataset, and a 7.9% improvement in mDice on the Kvasir-SEG dataset.
Authors: Utkarsh Nath, Rajeev Goel, Eun Som Jeon, Changhoon Kim, Kyle Min, Yezhou Yang, Yingzhen Yang, Pavan Turaga
Abstract: To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion models used in these techniques are prone to viewpoint bias and thus lead to geometric inconsistencies such as the Janus problem. To counter this, we introduce MT3D, a text-to-3D generative model that leverages a high-fidelity 3D object to overcome viewpoint bias and explicitly infuse geometric understanding into the generation pipeline. Firstly, we employ depth maps derived from a high-quality 3D model as control signals to guarantee that the generated 2D images preserve the fundamental shape and structure, thereby reducing the inherent viewpoint bias. Next, we utilize deep geometric moments to ensure geometric consistency in the 3D representation explicitly. By incorporating geometric details from a 3D asset, MT3D enables the creation of diverse and geometrically consistent objects, thereby improving the quality and usability of our 3D representations.
Authors: Junjie He, Yifeng Geng, Liefeng Bo
Abstract: This paper presents UniPortrait, an innovative human image personalization framework that unifies single- and multi-ID customization with high face fidelity, extensive facial editability, free-form input description, and diverse layout generation. UniPortrait consists of only two plug-and-play modules: an ID embedding module and an ID routing module. The ID embedding module extracts versatile editable facial features with a decoupling strategy for each ID and embeds them into the context space of diffusion models. The ID routing module then combines and distributes these embeddings adaptively to their respective regions within the synthesized image, achieving the customization of single and multiple IDs. With a carefully designed two-stage training scheme, UniPortrait achieves superior performance in both single- and multi-ID customization. Quantitative and qualitative experiments demonstrate the advantages of our method over existing approaches as well as its good scalability, e.g., the universal compatibility with existing generative control tools. The project page is at https://aigcdesigngroup.github.io/UniPortrait-Page/ .
Authors: Eunsoo Im, Changhyun Jee, Jung Kwon Lee
Abstract: Person detection and tracking (PDT) has seen significant advancements with 2D camera-based systems in the autonomous vehicle field, leading to widespread adoption of these algorithms. However, growing privacy concerns have recently emerged as a major issue, prompting a shift towards LiDAR-based PDT as a viable alternative. Within this domain, "Tracking-by-Detection" (TBD) has become a prominent methodology. Despite its effectiveness, LiDAR-based PDT has not yet achieved the same level of performance as camera-based PDT. This paper examines key components of the LiDAR-based PDT framework, including detection post-processing, data association, motion modeling, and lifecycle management. Building upon these insights, we introduce SpbTrack, a robust person tracker designed for diverse environments. Our method achieves superior performance on noisy datasets and state-of-the-art results on KITTI Dataset benchmarks and custom office indoor dataset among LiDAR-based trackers. Project page at anonymous.
Authors: Zitian Wang, Zehao Huang, Yulu Gao, Naiyan Wang, Si Liu
Abstract: The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generator, MV2DFusion effectively combines modality-specific object semantics without biasing toward one single modality. Then the sparse fusion process can be accomplished based on the valuable object semantics, ensuring efficient and accurate object detection across various scenarios. Our framework's flexibility allows it to integrate with any image and point cloud-based detectors, showcasing its adaptability and potential for future advancements. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that MV2DFusion achieves state-of-the-art performance, particularly excelling in long-range detection scenarios.
Authors: Gousia Habib, Damandeep Singh, Ishfaq Ahmad Malik, Brejesh Lall
Abstract: The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the self-attention mechanism. This success has inspired researchers to explore the use of transformers in computer vision tasks to attain enhanced long-term semantic awareness. Vision transformers (ViTs) have excelled in various computer vision tasks due to their superior ability to capture long-distance dependencies using the self-attention mechanism. Contemporary ViTs like Data Efficient Transformers (DeiT) can effectively learn both global semantic information and local texture information from images, achieving performance comparable to traditional CNNs. However, their impressive performance comes with a high computational cost due to very large number of parameters, hindering their deployment on devices with limited resources like smartphones, cameras, drones etc. Additionally, ViTs require a large amount of data for training to achieve performance comparable to benchmark CNN models. Therefore, we identified two key challenges in deploying ViTs on smaller form factor devices: the high computational requirements of large models and the need for extensive training data. As a solution to these challenges, we propose compressing large ViT models using Knowledge Distillation (KD), which is implemented data-free to circumvent limitations related to data availability. Additionally, we conducted experiments on object detection within the same environment in addition to classification tasks. Based on our analysis, we found that datafree knowledge distillation is an effective method to overcome both issues, enabling the deployment of ViTs on less resourceconstrained devices.
Authors: Qian Qiao, Yu Xie, Shaoyao Huang, Fanzhang Li
Abstract: Few-shot image classification aims to classify novel classes with few labeled samples. Recent research indicates that deep local descriptors have better representational capabilities. These studies recognize the impact of background noise on classification performance. They typically filter query descriptors using all local descriptors in the support classes or engage in bidirectional selection between local descriptors in support and query sets. However, they ignore the fact that background features may be useful for the classification performance of specific tasks. This paper proposes a novel task-aware contrastive local descriptor selection network (TCDSNet). First, we calculate the contrastive discriminative score for each local descriptor in the support class, and select discriminative local descriptors to form a support descriptor subset. Finally, we leverage support descriptor subsets to adaptively select discriminative query descriptors for specific tasks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on both general and fine-grained datasets.
Authors: Geuntaek Lim, Hyunwoo Kim, Joonsoo Kim, Yukyung Choi
Abstract: Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they encounter the task discrepancy problem (i.e., localization-by-classification). To tackle this issue, recent studies have attempted to utilize action category names as auxiliary semantic knowledge through vision-language pre-training (VLP). However, there are still areas where existing research falls short. Previous approaches primarily focused on leveraging textual information from language models but overlooked the alignment of dynamic human action and VLP knowledge in a joint space. Furthermore, the deterministic representation employed in previous studies struggles to capture fine-grained human motions. To address these problems, we propose a novel framework that aligns human action knowledge and VLP knowledge in a probabilistic embedding space. Moreover, we propose intra- and inter-distribution contrastive learning to enhance the probabilistic embedding space based on statistical similarities. Extensive experiments and ablation studies reveal that our method significantly outperforms all previous state-of-the-art methods. Code is available at https://github.com/sejong-rcv/PVLR.
Authors: Tianhang Pan, Zhuoran Zheng, Xiuyi Jia
Abstract: Currently, most crowd counting methods have outstanding performance under normal weather conditions. However, they often struggle to maintain their performance in extreme and adverse weather conditions due to significant differences in the domain and a lack of adverse weather images for training. To address this issue and enhance the model's robustness in adverse weather, we propose a two-stage crowd counting method. Specifically, in the first stage, we introduce a multi-queue MoCo contrastive learning strategy to tackle the problem of weather class imbalance. This strategy facilitates the learning of weather-aware representations by the model. In the second stage, we propose to refine the representations under the guidance of contrastive learning, enabling the conversion of the weather-aware representations to the normal weather domain. While significantly improving the robustness, our method only marginally increases the weight of the model. In addition, we also create a new synthetic adverse weather dataset. Extensive experimental results show that our method achieves competitive performance.
Authors: Hao Liu, Xue Qin
Abstract: In high-risk railway construction, personal protective equipment monitoring is critical but challenging due to small and frequently obstructed targets. We propose YOLO-EA, an innovative model that enhances safety measure detection by integrating ECA into its backbone's convolutional layers, improving discernment of minuscule objects like hardhats. YOLO-EA further refines target recognition under occlusion by replacing GIoU with EIoU loss. YOLO-EA's effectiveness was empirically substantiated using a dataset derived from real-world railway construction site surveillance footage. It outperforms YOLOv5, achieving 98.9% precision and 94.7% recall, up 2.5% and 0.5% respectively, while maintaining real-time performance at 70.774 fps. This highly efficient and precise YOLO-EA holds great promise for practical application in intricate construction scenarios, enforcing stringent safety compliance during complex railway construction projects.
Authors: Zhichao Liao, Di Huang, Heming Fang, Yue Ma, Fengyuan Piao, Xinghui Li, Long Zeng, Pingfa Feng
Abstract: Drawing freehand sketches of mechanical components on multimedia devices for AI-based engineering modeling has become a new trend. However, its development is being impeded because existing works cannot produce suitable sketches for data-driven research. These works either generate sketches lacking a freehand style or utilize generative models not originally designed for this task resulting in poor effectiveness. To address this issue, we design a two-stage generative framework mimicking the human sketching behavior pattern, called MSFormer, which is the first time to produce humanoid freehand sketches tailored for mechanical components. The first stage employs Open CASCADE technology to obtain multi-view contour sketches from mechanical components, filtering perturbing signals for the ensuing generation process. Meanwhile, we design a view selector to simulate viewpoint selection tasks during human sketching for picking out information-rich sketches. The second stage translates contour sketches into freehand sketches by a transformer-based generator. To retain essential modeling features as much as possible and rationalize stroke distribution, we introduce a novel edge-constraint stroke initialization. Furthermore, we utilize a CLIP vision encoder and a new loss function incorporating the Hausdorff distance to enhance the generalizability and robustness of the model. Extensive experiments demonstrate that our approach achieves state-of-the-art performance for generating freehand sketches in the mechanical domain. Project page: https://mcfreeskegen.github.io .
Authors: Yixin Guo, Yu Liu, Jianghao Li, Weimin Wang, Qi Jia
Abstract: Zero-shot human-object interaction (HOI) detector is capable of generalizing to HOI categories even not encountered during training. Inspired by the impressive zero-shot capabilities offered by CLIP, latest methods strive to leverage CLIP embeddings for improving zero-shot HOI detection. However, these embedding-based methods train the classifier on seen classes only, inevitably resulting in seen-unseen confusion for the model during inference. Besides, we find that using prompt-tuning and adapters further increases the gap between seen and unseen accuracy. To tackle this challenge, we present the first generation-based model using CLIP for zero-shot HOI detection, coined HOIGen. It allows to unlock the potential of CLIP for feature generation instead of feature extraction only. To achieve it, we develop a CLIP-injected feature generator in accordance with the generation of human, object and union features. Then, we extract realistic features of seen samples and mix them with synthetic features together, allowing the model to train seen and unseen classes jointly. To enrich the HOI scores, we construct a generative prototype bank in a pairwise HOI recognition branch, and a multi-knowledge prototype bank in an image-wise HOI recognition branch, respectively. Extensive experiments on HICO-DET benchmark demonstrate our HOIGen achieves superior performance for both seen and unseen classes under various zero-shot settings, compared with other top-performing methods. Code is available at: https://github.com/soberguo/HOIGen
Authors: Haifan Gong, Yitao Wang, Yihan Wang, Jiashun Xiao, Xiang Wan, Haofeng Li
Abstract: The scarcity and complexity of voxel-level annotations in 3D medical imaging present significant challenges, particularly due to the domain gap between labeled datasets from well-resourced centers and unlabeled datasets from less-resourced centers. This disparity affects the fairness of artificial intelligence algorithms in healthcare. We introduce Diffuse-UDA, a novel method leveraging diffusion models to tackle Unsupervised Domain Adaptation (UDA) in medical image segmentation. Diffuse-UDA generates high-quality image-mask pairs with target domain characteristics and various structures, thereby enhancing UDA tasks. Initially, pseudo labels for target domain samples are generated. Subsequently, a specially tailored diffusion model, incorporating deformable augmentations, is trained on image-label or image-pseudo-label pairs from both domains. Finally, source domain labels guide the diffusion model to generate image-label pairs for the target domain. Comprehensive evaluations on several benchmarks demonstrate that Diffuse-UDA outperforms leading UDA and semi-supervised strategies, achieving performance close to or even surpassing the theoretical upper bound of models trained directly on target domain data. Diffuse-UDA offers a pathway to advance the development and deployment of AI systems in medical imaging, addressing disparities between healthcare environments. This approach enables the exploration of innovative AI-driven diagnostic tools, improves outcomes, saves time, and reduces human error.
Authors: Xiaoming Yu, Jie Tian, Zhenhua Hu
Abstract: With the development of generative technologies in deep learning, a large number of image-to-image translation and style transfer models have emerged at an explosive rate in recent years. These two technologies have made significant progress and can generate realistic images. However, many communities tend to confuse the two, because both generate the desired image based on the input image and both cover the two definitions of content and style. In fact, there are indeed significant differences between the two, and there is currently a lack of clear explanations to distinguish the two technologies, which is not conducive to the advancement of technology. We hope to serve the entire community by introducing the differences and connections between image-to-image translation and style transfer. The entire discussion process involves the concepts, forms, training modes, evaluation processes, and visualization results of the two technologies. Finally, we conclude that image-to-image translation divides images by domain, and the types of images in the domain are limited, and the scope involved is small, but the conversion ability is strong and can achieve strong semantic changes. Style transfer divides image types by single image, and the scope involved is large, but the transfer ability is limited, and it transfers more texture and color of the image.
Authors: Jisoo Kim, Jungbin Cho, Joonho Park, Soonmin Hwang, Da Eun Kim, Geon Kim, Youngjae Yu
Abstract: Speech-driven 3D facial animation has garnered lots of attention thanks to its broad range of applications. Despite recent advancements in achieving realistic lip motion, current methods fail to capture the nuanced emotional undertones conveyed through speech and produce monotonous facial motion. These limitations result in blunt and repetitive facial animations, reducing user engagement and hindering their applicability. To address these challenges, we introduce DEEPTalk, a novel approach that generates diverse and emotionally rich 3D facial expressions directly from speech inputs. To achieve this, we first train DEE (Dynamic Emotion Embedding), which employs probabilistic contrastive learning to forge a joint emotion embedding space for both speech and facial motion. This probabilistic framework captures the uncertainty in interpreting emotions from speech and facial motion, enabling the derivation of emotion vectors from its multifaceted space. Moreover, to generate dynamic facial motion, we design TH-VQVAE (Temporally Hierarchical VQ-VAE) as an expressive and robust motion prior overcoming limitations of VAEs and VQ-VAEs. Utilizing these strong priors, we develop DEEPTalk, A talking head generator that non-autoregressively predicts codebook indices to create dynamic facial motion, incorporating a novel emotion consistency loss. Extensive experiments on various datasets demonstrate the effectiveness of our approach in creating diverse, emotionally expressive talking faces that maintain accurate lip-sync. Source code will be made publicly available soon.
Authors: Xiaozheng Zheng, Chao Wen, Zhaohu Li, Weiyi Zhang, Zhuo Su, Xu Chang, Yang Zhao, Zheng Lv, Xiaoyuan Zhang, Yongjie Zhang, Guidong Wang, Lan Xu
Abstract: In this paper, we present a novel 3D head avatar creation approach capable of generalizing from few-shot in-the-wild data with high-fidelity and animatable robustness. Given the underconstrained nature of this problem, incorporating prior knowledge is essential. Therefore, we propose a framework comprising prior learning and avatar creation phases. The prior learning phase leverages 3D head priors derived from a large-scale multi-view dynamic dataset, and the avatar creation phase applies these priors for few-shot personalization. Our approach effectively captures these priors by utilizing a Gaussian Splatting-based auto-decoder network with part-based dynamic modeling. Our method employs identity-shared encoding with personalized latent codes for individual identities to learn the attributes of Gaussian primitives. During the avatar creation phase, we achieve fast head avatar personalization by leveraging inversion and fine-tuning strategies. Extensive experiments demonstrate that our model effectively exploits head priors and successfully generalizes them to few-shot personalization, achieving photo-realistic rendering quality, multi-view consistency, and stable animation.
Authors: Long Xu, Shanghong Li, Yongquan Chen, Junkang Chen, Rui Huang, Feng Wu
Abstract: Interactive segmentation algorithms based on click points have garnered significant attention from researchers in recent years.However, existing studies typically use sparse click maps as model inputs to segment specific target objects, which primarily affect local regions and have limited abilities to focus on the whole target object, leading to increased times of clicks.In addition, most existing algorithms can not balance well between high performance and efficiency.To address this issue, we propose a click attention algorithm that expands the influence range of positive clicks based on the similarity between positively-clicked regions and the whole input.We also propose a discriminative affinity loss to reduce the attention coupling between positive and negative click regions to avoid an accuracy decrease caused by mutual interference between positive and negative clicks.Extensive experiments demonstrate that our approach is superior to existing methods and achieves cutting-edge performance in fewer parameters.An interactive demo and all reproducible codes will be released at https://github.com/hahamyt/ClickAttention.
Authors: Vasiliy Alekseev, Ilya Lukashevich, Ilia Zharikov, Ilya Vasiliev
Abstract: Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on different devices. Reduction in the number of network parameters helps to reduce the size of the model, but at the same time, thoughtlessly applied, can lead to a deterioration in the quality of the network. One way to reduce the number of model parameters is matrix decomposition, where a matrix is represented as a product of smaller matrices. In this paper, we propose a new way of applying the matrix decomposition with respect to the weights of convolutional layers. The essence of the method is to train not all convolutions, but only the subset of convolutions (basis convolutions), and represent the rest as linear combinations of the basis ones. Experiments on models from the ResNet family and the CIFAR-10 dataset demonstrate that basis convolutions can not only reduce the size of the model but also accelerate the forward and backward passes of the network. Another contribution of this work is that we propose a fast method for selecting a subset of network layers in which the use of matrix decomposition does not degrade the quality of the final model.
Authors: Aristi Papastavrou, Maria Lymperaiou, Giorgos Stamou
Abstract: In the rapidly evolving fields of natural language processing and computer vision, Visual Word Sense Disambiguation (VWSD) stands as a critical, yet challenging task. The quest for models that can seamlessly integrate and interpret multimodal data is more pressing than ever. Imagine a system that can understand language with the depth and nuance of human cognition, while simultaneously interpreting the rich visual context of the world around it. We present ARPA, an architecture that fuses the unparalleled contextual understanding of large language models with the advanced feature extraction capabilities of transformers, which then pass through a custom Graph Neural Network (GNN) layer to learn intricate relationships and subtle nuances within the data. This innovative architecture not only sets a new benchmark in visual word disambiguation but also introduces a versatile framework poised to transform how linguistic and visual data interact by harnessing the synergistic strengths of its components, ensuring robust performance even in the most complex disambiguation scenarios. Through a series of experiments and comparative analysis, we reveal the substantial advantages of our model, underscoring its potential to redefine standards in the field. Beyond its architectural prowess, our architecture excels through experimental enrichments, including sophisticated data augmentation and multi-modal training techniques. ARPA's introduction marks a significant milestone in visual word disambiguation, offering a compelling solution that bridges the gap between linguistic and visual modalities. We invite researchers and practitioners to explore the capabilities of our model, envisioning a future where such hybrid models drive unprecedented advancements in artificial intelligence.
Authors: Xuanpu Zhang, Dan Song, Pengxin Zhan, Qingguo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Anan Liu
Abstract: Image-based virtual try-on is an increasingly popular and important task to generate realistic try-on images of specific person. Existing methods always employ an accurate mask to remove the original garment in the source image, thus achieving realistic synthesized images in simple and conventional try-on scenarios based on powerful diffusion model. Therefore, acquiring suitable mask is vital to the try-on performance of these methods. However, obtaining precise inpainting masks, especially for complex wild try-on data containing diverse foreground occlusions and person poses, is not easy as Figure 1-Top shows. This difficulty often results in poor performance in more practical and challenging real-life scenarios, such as the selfie scene shown in Figure 1-Bottom. To this end, we propose a novel training paradigm combined with an efficient data augmentation method to acquire large-scale unpaired training data from wild scenarios, thereby significantly facilitating the try-on performance of our model without the need for additional inpainting masks. Besides, a try-on localization loss is designed to localize a more accurate try-on area to obtain more reasonable try-on results. It is noted that our method only needs the reference cloth image, source pose image and source person image as input, which is more cost-effective and user-friendly compared to existing methods. Extensive qualitative and quantitative experiments have demonstrated superior performance in wild scenarios with such a low-demand input.
Authors: Bohao Peng, Jian Wang, Yuechen Zhang, Wenbo Li, Ming-Chang Yang, Jiaya Jia
Abstract: Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.
Authors: Felix Assion, Florens Gressner, Nitin Augustine, Jona Klemenc, Ahmed Hammam, Alexandre Krattinger, Holger Trittenbach, Sascha Riemer
Abstract: High-autonomy vehicle functions rely on machine learning (ML) algorithms to understand the environment. Despite displaying remarkable performance in fair weather scenarios, perception algorithms are heavily affected by adverse weather and lighting conditions. To overcome these difficulties, ML engineers mainly rely on comprehensive real-world datasets. However, the difficulties in real-world data collection for critical areas of the operational design domain (ODD) often means synthetic data is required for perception training and safety validation. Thus, we present A-BDD, a large set of over 60,000 synthetically augmented images based on BDD100K that are equipped with semantic segmentation and bounding box annotations (inherited from the BDD100K dataset). The dataset contains augmented data for rain, fog, overcast and sunglare/shadow with varying intensity levels. We further introduce novel strategies utilizing feature-based image quality metrics like FID and CMMD, which help identify useful augmented and real-world data for ML training and testing. By conducting experiments on A-BDD, we provide evidence that data augmentations can play a pivotal role in closing performance gaps in adverse weather and lighting conditions.
Authors: Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang
Abstract: We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motions. In addition, we develop an effective text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weights of both the 3D Causal VAE and CogVideoX are publicly available at https://github.com/THUDM/CogVideo.
Authors: Kejia Zhang, Juanjuan Weng, Zhiming Luo, Shaozi Li
Abstract: Despite the significant advances that deep neural networks (DNNs) have achieved in various visual tasks, they still exhibit vulnerability to adversarial examples, leading to serious security concerns. Recent adversarial training techniques have utilized inverse adversarial attacks to generate high-confidence examples, aiming to align the distributions of adversarial examples with the high-confidence regions of their corresponding classes. However, in this paper, our investigation reveals that high-confidence outputs under inverse adversarial attacks are correlated with biased feature activation. Specifically, training with inverse adversarial examples causes the model's attention to shift towards background features, introducing a spurious correlation bias. To address this bias, we propose Debiased High-Confidence Adversarial Training (DHAT), a novel approach that not only aligns the logits of adversarial examples with debiased high-confidence logits obtained from inverse adversarial examples, but also restores the model's attention to its normal state by enhancing foreground logit orthogonality. Extensive experiments demonstrate that DHAT achieves state-of-the-art performance and exhibits robust generalization capabilities across various vision datasets. Additionally, DHAT can seamlessly integrate with existing advanced adversarial training techniques for improving the performance.
Authors: Junrui Zhang, Jiaqi Li, Yachuan Huang, Yiran Wang, Jinghong Zheng, Liao Shen, Zhiguo Cao
Abstract: In the field of monocular depth estimation (MDE), many models with excellent zero-shot performance in general scenes emerge recently. However, these methods often fail in predicting non-Lambertian surfaces, such as transparent or mirror (ToM) surfaces, due to the unique reflective properties of these regions. Previous methods utilize externally provided ToM masks and aim to obtain correct depth maps through direct in-painting of RGB images. These methods highly depend on the accuracy of additional input masks, and the use of random colors during in-painting makes them insufficiently robust. We are committed to incrementally enabling the baseline model to directly learn the uniqueness of non-Lambertian surface regions for depth estimation through a well-designed training framework. Therefore, we propose non-Lambertian surface regional guidance, which constrains the predictions of MDE model from the gradient domain to enhance its robustness. Noting the significant impact of lighting on this task, we employ the random tone-mapping augmentation during training to ensure the network can predict correct results for varying lighting inputs. Additionally, we propose an optional novel lighting fusion module, which uses Variational Autoencoders to fuse multiple images and obtain the most advantageous input RGB image for depth estimation when multi-exposure images are available. Our method achieves accuracy improvements of 33.39% and 5.21% in zero-shot testing on the Booster and Mirror3D dataset for non-Lambertian surfaces, respectively, compared to the Depth Anything V2. The state-of-the-art performance of 90.75 in delta1.05 within the ToM regions on the TRICKY2024 competition test set demonstrates the effectiveness of our approach.
Authors: Zhiyuan Zhang, Licheng Yang, Zhiyu Xiang
Abstract: Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several recent studies achieve rotation invariance at the cost of lower accuracies. In this work, we close this gap by proposing a novel yet effective rotation invariant architecture for 3D point cloud classification and segmentation. Instead of traditional pointwise operations, we construct local triangle surfaces to capture more detailed surface structure, based on which we can extract highly expressive rotation invariant surface properties which are then integrated into an attention-augmented convolution operator named RISurConv to generate refined attention features via self-attention layers. Based on RISurConv we build an effective neural network for 3D point cloud analysis that is invariant to arbitrary rotations while maintaining high accuracy. We verify the performance on various benchmarks with supreme results obtained surpassing the previous state-of-the-art by a large margin. We achieve an overall accuracy of 96.0% (+4.7%) on ModelNet40, 93.1% (+12.8%) on ScanObjectNN, and class accuracies of 91.5% (+3.6%), 82.7% (+5.1%), and 78.5% (+9.2%) on the three categories of the FG3D dataset for the fine-grained classification task. Additionally, we achieve 81.5% (+1.0%) mIoU on ShapeNet for the segmentation task. Code is available here: https://github.com/cszyzhang/RISurConv
Authors: Junjie Guo, Chenqiang Gao, Fangcen Liu, Deyu Meng
Abstract: Infrared-visible object detection aims to achieve robust object detection by leveraging the complementary information of infrared and visible image pairs. However, the commonly existing modality misalignment problem presents two challenges: fusing misalignment complementary features is difficult, and current methods cannot accurately locate objects in both modalities under misalignment conditions. In this paper, we propose a Decoupled Position Detection Transformer (DPDETR) to address these problems. Specifically, we explicitly formulate the object category, visible modality position, and infrared modality position to enable the network to learn the intrinsic relationships and output accurate positions of objects in both modalities. To fuse misaligned object features accurately, we propose a Decoupled Position Multispectral Cross-attention module that adaptively samples and aggregates multispectral complementary features with the constraint of infrared and visible reference positions. Additionally, we design a query-decoupled Multispectral Decoder structure to address the optimization gap among the three kinds of object information in our task and propose a Decoupled Position Contrastive DeNosing Training strategy to enhance the DPDETR's ability to learn decoupled positions. Experiments on DroneVehicle and KAIST datasets demonstrate significant improvements compared to other state-of-the-art methods. The code will be released at https://github.com/gjj45/DPDETR.
Authors: Sven Teufel, J\"org Gamerdinger, Georg Volk, Oliver Bringmann
Abstract: The safe operation of automated vehicles depends on their ability to perceive the environment comprehensively. However, occlusion, sensor range, and environmental factors limit their perception capabilities. To overcome these limitations, collective perception enables vehicles to exchange information. However, fusing this exchanged information is a challenging task. Early fusion approaches require large amounts of bandwidth, while intermediate fusion approaches face interchangeability issues. Late fusion of shared detections is currently the only feasible approach. However, it often results in inferior performance due to information loss. To address this issue, we propose MR3D-Net, a dynamic multi-resolution 3D sparse voxel grid fusion backbone architecture for LiDAR-based collective perception. We show that sparse voxel grids at varying resolutions provide a meaningful and compact environment representation that can adapt to the communication bandwidth. MR3D-Net achieves state-of-the-art performance on the OPV2V 3D object detection benchmark while reducing the required bandwidth by up to 94% compared to early fusion. Code is available at https://github.com/ekut-es/MR3D-Net
Authors: Ioannis Romanelis, Vlassios Fotis, Athanasios Kalogeras, Christos Alexakos, Konstantinos Moustakas, Adrian Munteanu
Abstract: We propose a novel point cloud U-Net diffusion architecture for 3D generative modeling capable of generating high-quality and diverse 3D shapes while maintaining fast generation times. Our network employs a dual-branch architecture, combining the high-resolution representations of points with the computational efficiency of sparse voxels. Our fastest variant outperforms all non-diffusion generative approaches on unconditional shape generation, the most popular benchmark for evaluating point cloud generative models, while our largest model achieves state-of-the-art results among diffusion methods, with a runtime approximately 70% of the previously state-of-the-art PVD. Beyond unconditional generation, we perform extensive evaluations, including conditional generation on all categories of ShapeNet, demonstrating the scalability of our model to larger datasets, and implicit generation which allows our network to produce high quality point clouds on fewer timesteps, further decreasing the generation time. Finally, we evaluate the architecture's performance in point cloud completion and super-resolution. Our model excels in all tasks, establishing it as a state-of-the-art diffusion U-Net for point cloud generative modeling. The code is publicly available at https://github.com/JohnRomanelis/SPVD.git.
Authors: Taewon Kang, Divya Kothandaraman, Dinesh Manocha, Ming C. Lin
Abstract: Recent 3D novel view synthesis (NVS) methods are limited to single-object-centric scenes generated from new viewpoints and struggle with complex environments. They often require extensive 3D data for training, lacking generalization beyond training distribution. Conversely, 3D-free methods can generate text-controlled views of complex, in-the-wild scenes using a pretrained stable diffusion model without tedious fine-tuning, but lack camera control. In this paper, we introduce HawkI++, a method capable of generating camera-controlled viewpoints from a single input image. HawkI++ excels in handling complex and diverse scenes without additional 3D data or extensive training. It leverages widely available pretrained NVS models for weak guidance, integrating this knowledge into a 3D-free view synthesis approach to achieve the desired results efficiently. Our experimental results demonstrate that HawkI++ outperforms existing models in both qualitative and quantitative evaluations, providing high-fidelity and consistent novel view synthesis at desired camera angles across a wide variety of scenes.
Authors: Mushui Liu, Bozheng Li, Yunlong Yu
Abstract: Recent Vision-Language Models (VLMs) \textit{e.g.} CLIP have made great progress in video recognition. Despite the improvement brought by the strong visual backbone in extracting spatial features, CLIP still falls short in capturing and integrating spatial-temporal features which is essential for video recognition. In this paper, we propose OmniCLIP, a framework that adapts CLIP for video recognition by focusing on learning comprehensive features encompassing spatial, temporal, and dynamic spatial-temporal scales, which we refer to as omni-scale features. This is achieved through the design of spatial-temporal blocks that include parallel temporal adapters (PTA), enabling efficient temporal modeling. Additionally, we introduce a self-prompt generator (SPG) module to capture dynamic object spatial features. The synergy between PTA and SPG allows OmniCLIP to discern varying spatial information across frames and assess object scales over time. We have conducted extensive experiments in supervised video recognition, few-shot video recognition, and zero-shot recognition tasks. The results demonstrate the effectiveness of our method, especially with OmniCLIP achieving a top-1 accuracy of 74.30\% on HMDB51 in a 16-shot setting, surpassing the recent MotionPrompt approach even with full training data. The code is available at \url{https://github.com/XiaoBuL/OmniCLIP}.
Authors: Hyunmin Choi, Jiwon Kim, Chiyoung Song, Simon S. Woo, Hyoungshick Kim
Abstract: We present Blind-Match, a novel biometric identification system that leverages homomorphic encryption (HE) for efficient and privacy-preserving 1:N matching. Blind-Match introduces a HE-optimized cosine similarity computation method, where the key idea is to divide the feature vector into smaller parts for processing rather than computing the entire vector at once. By optimizing the number of these parts, Blind-Match minimizes execution time while ensuring data privacy through HE. Blind-Match achieves superior performance compared to state-of-the-art methods across various biometric datasets. On the LFW face dataset, Blind-Match attains a 99.63% Rank-1 accuracy with a 128-dimensional feature vector, demonstrating its robustness in face recognition tasks. For fingerprint identification, Blind-Match achieves a remarkable 99.55% Rank-1 accuracy on the PolyU dataset, even with a compact 16-dimensional feature vector, significantly outperforming the state-of-the-art method, Blind-Touch, which achieves only 59.17%. Furthermore, Blind-Match showcases practical efficiency in large-scale biometric identification scenarios, such as Naver Cloud's FaceSign, by processing 6,144 biometric samples in 0.74 seconds using a 128-dimensional feature vector.
Authors: Lukas Meyer, Andreas Gilson, Ute Schmidt, Marc Stamminger
Abstract: We introduce FruitNeRF, a unified novel fruit counting framework that leverages state-of-the-art view synthesis methods to count any fruit type directly in 3D. Our framework takes an unordered set of posed images captured by a monocular camera and segments fruit in each image. To make our system independent of the fruit type, we employ a foundation model that generates binary segmentation masks for any fruit. Utilizing both modalities, RGB and semantic, we train a semantic neural radiance field. Through uniform volume sampling of the implicit Fruit Field, we obtain fruit-only point clouds. By applying cascaded clustering on the extracted point cloud, our approach achieves precise fruit count.The use of neural radiance fields provides significant advantages over conventional methods such as object tracking or optical flow, as the counting itself is lifted into 3D. Our method prevents double counting fruit and avoids counting irrelevant fruit.We evaluate our methodology using both real-world and synthetic datasets. The real-world dataset consists of three apple trees with manually counted ground truths, a benchmark apple dataset with one row and ground truth fruit location, while the synthetic dataset comprises various fruit types including apple, plum, lemon, pear, peach, and mango.Additionally, we assess the performance of fruit counting using the foundation model compared to a U-Net.
Authors: Siladittya Manna, Saumik Bhattacharya, Umapada Pal
Abstract: Medical image segmentation is one of the domains where sufficient annotated data is not available. This necessitates the application of low-data frameworks like few-shot learning. Contemporary prototype-based frameworks often do not account for the variation in features within the support and query images, giving rise to a large variance in prototype alignment. In this work, we adopt a prototype-based self-supervised one-way one-shot learning framework using pseudo-labels generated from superpixels to learn the semantic segmentation task itself. We use a correlation-based probability score to generate a dynamic prototype for each query pixel from the bag of prototypes obtained from the support feature map. This weighting scheme helps to give a higher weightage to contextually related prototypes. We also propose a quadrant masking strategy in the downstream segmentation task by utilizing prior domain information to discard unwanted false positives. We present extensive experimentations and evaluations on abdominal CT and MR datasets to show that the proposed simple but potent framework performs at par with the state-of-the-art methods.
Authors: Jaydeep Rade, Ethan Herron, Soumik Sarkar, Anwesha Sarkar, Adarsh Krishnamurthy
Abstract: Recent advancements in deep learning for predicting 3D protein structures have shown promise, particularly when leveraging inputs like protein sequences and Cryo-Electron microscopy (Cryo-EM) images. However, these techniques often fall short when predicting the structures of protein complexes (PCs), which involve multiple proteins. In our study, we investigate using atomic force microscopy (AFM) combined with deep learning to predict the 3D structures of PCs. AFM generates height maps that depict the PCs in various random orientations, providing a rich information for training a neural network to predict the 3D structures. We then employ the pre-trained UpFusion model (which utilizes a conditional diffusion model for synthesizing novel views) to train an instance-specific NeRF model for 3D reconstruction. The performance of UpFusion is evaluated through zero-shot predictions of 3D protein structures using AFM images. The challenge, however, lies in the time-intensive and impractical nature of collecting actual AFM images. To address this, we use a virtual AFM imaging process that transforms a `PDB' protein file into multi-view 2D virtual AFM images via volume rendering techniques. We extensively validate the UpFusion architecture using both virtual and actual multi-view AFM images. Our results include a comparison of structures predicted with varying numbers of views and different sets of views. This novel approach holds significant potential for enhancing the accuracy of protein complex structure predictions with further fine-tuning of the UpFusion network.
Authors: Zhihao Zheng, Mooi Choo Chuah
Abstract: Many learning-based low-light image enhancement (LLIE) algorithms are based on the Retinex theory. However, the Retinex-based decomposition techniques in such models introduce corruptions which limit their enhancement performance. In this paper, we propose a Latent Disentangle-based Enhancement Network (LDE-Net) for low light vision tasks. The latent disentanglement module disentangles the input image in latent space such that no corruption remains in the disentangled Content and Illumination components. For LLIE task, we design a Content-Aware Embedding (CAE) module that utilizes Content features to direct the enhancement of the Illumination component. For downstream tasks (e.g. nighttime UAV tracking and low-light object detection), we develop an effective light-weight enhancer based on the latent disentanglement framework. Comprehensive quantitative and qualitative experiments demonstrate that our LDE-Net significantly outperforms state-of-the-art methods on various LLIE benchmarks. In addition, the great results obtained by applying our framework on the downstream tasks also demonstrate the usefulness of our latent disentanglement design.
Authors: Jiameng Li, Yue Shi, Jiezhang Cao, Bingbing Ni, Wenjun Zhang, Kai Zhang, Luc Van Gool
Abstract: 3D Gaussian Splatting (3DGS) has attracted great attention in novel view synthesis because of its superior rendering efficiency and high fidelity. However, the trained Gaussians suffer from severe zooming degradation due to non-adjustable representation derived from single-scale training. Though some methods attempt to tackle this problem via post-processing techniques such as selective rendering or filtering techniques towards primitives, the scale-specific information is not involved in Gaussians. In this paper, we propose a unified optimization method to make Gaussians adaptive for arbitrary scales by self-adjusting the primitive properties (e.g., color, shape and size) and distribution (e.g., position). Inspired by the mipmap technique, we design pseudo ground-truth for the target scale and propose a scale-consistency guidance loss to inject scale information into 3D Gaussians. Our method is a plug-in module, applicable for any 3DGS models to solve the zoom-in and zoom-out aliasing. Extensive experiments demonstrate the effectiveness of our method. Notably, our method outperforms 3DGS in PSNR by an average of 9.25 dB for zoom-in and 10.40 dB for zoom-out on the NeRF Synthetic dataset.
Authors: Athulya Sundaresan Geetha, Muhammad Hussain
Abstract: The Segment Anything Model (SAM), introduced to the computer vision community by Meta in April 2023, is a groundbreaking tool that allows automated segmentation of objects in images based on prompts such as text, clicks, or bounding boxes. SAM excels in zero-shot performance, segmenting unseen objects without additional training, stimulated by a large dataset of over one billion image masks. SAM 2 expands this functionality to video, leveraging memory from preceding and subsequent frames to generate accurate segmentation across entire videos, enabling near real-time performance. This comparison shows how SAM has evolved to meet the growing need for precise and efficient segmentation in various applications. The study suggests that future advancements in models like SAM will be crucial for improving computer vision technology.
Authors: Hyungtae Lim, Seoyeon Jang, Benedikt Mersch, Jens Behley, Hyun Myung, Cyrill Stachniss
Abstract: Moving object segmentation (MOS) using a 3D light detection and ranging (LiDAR) sensor is crucial for scene understanding and identification of moving objects. Despite the availability of various types of 3D LiDAR sensors in the market, MOS research still predominantly focuses on 3D point clouds from mechanically spinning omnidirectional LiDAR sensors. Thus, we are, for example, lacking a dataset with MOS labels for point clouds from solid-state LiDAR sensors which have irregular scanning patterns. In this paper, we present a labeled dataset, called \textit{HeLiMOS}, that enables to test MOS approaches on four heterogeneous LiDAR sensors, including two solid-state LiDAR sensors. Furthermore, we introduce a novel automatic labeling method to substantially reduce the labeling effort required from human annotators. To this end, our framework exploits an instance-aware static map building approach and tracking-based false label filtering. Finally, we provide experimental results regarding the performance of commonly used state-of-the-art MOS approaches on HeLiMOS that suggest a new direction for a sensor-agnostic MOS, which generally works regardless of the type of LiDAR sensors used to capture 3D point clouds. Our dataset is available at https://sites.google.com/view/helimos.
Authors: Navid Ghassemi, Ali Goldani, Ian Q. Whishaw, Majid H. Mohajerani
Abstract: The cattle industry has been a major contributor to the economy of many countries, including the US and Canada. The integration of Artificial Intelligence (AI) has revolutionized this sector, mirroring its transformative impact across all industries by enabling scalable and automated monitoring and intervention practices. AI has also introduced tools and methods that automate many tasks previously performed by human labor with the help of computer vision, including health inspections. Among these methods, pose estimation has a special place; pose estimation is the process of finding the position of joints in an image of animals. Analyzing the pose of animal subjects enables precise identification and tracking of the animal's movement and the movements of its body parts. By summarizing the video and imagery data into movement and joint location using pose estimation and then analyzing this information, we can address the scalability challenge in cattle management, focusing on health monitoring, behavioural phenotyping and welfare concerns. Our study reviews recent advancements in pose estimation methodologies, their applicability in improving the cattle industry, existing challenges, and gaps in this field. Furthermore, we propose an initiative to enhance open science frameworks within this field of study by launching a platform designed to connect industry and academia.
Authors: Bj\"orn L\"utjens, Raffaele Ferrari, Duncan Watson-Parris, Noelle Selin
Abstract: Full-complexity Earth system models (ESMs) are computationally very expensive, limiting their use in exploring the climate outcomes of multiple emission pathways. More efficient emulators that approximate ESMs can directly map emissions onto climate outcomes, and benchmarks are being used to evaluate their accuracy on standardized tasks and datasets. We investigate a popular benchmark in data-driven climate emulation, ClimateBench, on which deep learning-based emulators are currently achieving the best performance. We implement a linear regression-based emulator, akin to pattern scaling, and find that it outperforms the incumbent 100M-parameter deep learning foundation model, ClimaX, on 3 out of 4 regionally-resolved surface-level climate variables. While emulating surface temperature is expected to be predominantly linear, this result is surprising for emulating precipitation. We identify that this outcome is a result of high levels of internal variability in the benchmark targets. To address internal variability, we update the benchmark targets with ensemble averages from the MPI-ESM1.2-LR model that contain 50 instead of 3 climate simulations per emission pathway. Using the new targets, we show that linear pattern scaling continues to be more accurate on temperature, but can be outperformed by a deep learning-based model for emulating precipitation. We publish our code, data, and an interactive tutorial at github.com/blutjens/climate-emulator.
Authors: Jian Lu, Shikhar Srivastava, Junyu Chen, Robik Shrestha, Manoj Acharya, Kushal Kafle, Christopher Kanan
Abstract: With the advent of multi-modal large language models (MLLMs), datasets used for visual question answering (VQA) and referring expression comprehension have seen a resurgence. However, the most popular datasets used to evaluate MLLMs are some of the earliest ones created, and they have many known problems, including extreme bias, spurious correlations, and an inability to permit fine-grained analysis. In this paper, we pioneer evaluating recent MLLMs (LLaVA 1.5, LLaVA-NeXT, BLIP2, InstructBLIP, GPT-4V, and GPT-4o) on datasets designed to address weaknesses in earlier ones. We assess three VQA datasets: 1) TDIUC, which permits fine-grained analysis on 12 question types; 2) TallyQA, which has simple and complex counting questions; and 3) DVQA, which requires optical character recognition for chart understanding. We also study VQDv1, a dataset that requires identifying all image regions that satisfy a given query. Our experiments reveal the weaknesses of many MLLMs that have not previously been reported. Our code is integrated into the widely used LAVIS framework for MLLM evaluation, enabling the rapid assessment of future MLLMs. Project webpage: https://kevinlujian.github.io/MLLM_Evaluations/
Authors: Lilin Xu, Keyi Wang, Chaojie Gu, Xiuzhen Guo, Shibo He, Jiming Chen
Abstract: The millimeter-wave (mmWave) radar has been exploited for gesture recognition. However, existing mmWave-based gesture recognition methods cannot identify different users, which is important for ubiquitous gesture interaction in many applications. In this paper, we propose GesturePrint, which is the first to achieve gesture recognition and gesture-based user identification using a commodity mmWave radar sensor. GesturePrint features an effective pipeline that enables the gesture recognition system to identify users at a minor additional cost. By introducing an efficient signal preprocessing stage and a network architecture GesIDNet, which employs an attention-based multilevel feature fusion mechanism, GesturePrint effectively extracts unique gesture features for gesture recognition and personalized motion pattern features for user identification. We implement GesturePrint and collect data from 17 participants performing 15 gestures in a meeting room and an office, respectively. GesturePrint achieves a gesture recognition accuracy (GRA) of 98.87% with a user identification accuracy (UIA) of 99.78% in the meeting room, and 98.22% GRA with 99.26% UIA in the office. Extensive experiments on three public datasets and a new gesture dataset show GesturePrint's superior performance in enabling effective user identification for gesture recognition systems.
Authors: Hao Li, Baris Oguz, Gabriel Arenas, Xing Yao, Jiacheng Wang, Alison Pouch, Brett Byram, Nadav Schwartz, Ipek Oguz
Abstract: Placenta volume measured from 3D ultrasound (3DUS) images is an important tool for tracking the growth trajectory and is associated with pregnancy outcomes. Manual segmentation is the gold standard, but it is time-consuming and subjective. Although fully automated deep learning algorithms perform well, they do not always yield high-quality results for each case. Interactive segmentation models could address this issue. However, there is limited work on interactive segmentation models for the placenta. Despite their segmentation accuracy, these methods may not be feasible for clinical use as they require relatively large computational power which may be especially prohibitive in low-resource environments, or on mobile devices. In this paper, we propose a lightweight interactive segmentation model aiming for clinical use to interactively segment the placenta from 3DUS images in real-time. The proposed model adopts the segmentation from our fully automated model for initialization and is designed in a human-in-the-loop manner to achieve iterative improvements. The Dice score and normalized surface Dice are used as evaluation metrics. The results show that our model can achieve superior performance in segmentation compared to state-of-the-art models while using significantly fewer parameters. Additionally, the proposed model is much faster for inference and robust to poor initial masks. The code is available at https://github.com/MedICL-VU/PRISM-placenta.
Authors: Guangdong Ma, Che-Yung Shen, Jingxi Li, Luzhe Huang, Cagatay Isil, Fazil Onuralp Ardic, Xilin Yang, Yuhang Li, Yuntian Wang, Md Sadman Sakib Rahman, Aydogan Ozcan
Abstract: Unidirectional imagers form images of input objects only in one direction, e.g., from field-of-view (FOV) A to FOV B, while blocking the image formation in the reverse direction, from FOV B to FOV A. Here, we report unidirectional imaging under spatially partially coherent light and demonstrate high-quality imaging only in the forward direction (A->B) with high power efficiency while distorting the image formation in the backward direction (B->A) along with low power efficiency. Our reciprocal design features a set of spatially engineered linear diffractive layers that are statistically optimized for partially coherent illumination with a given phase correlation length. Our analyses reveal that when illuminated by a partially coherent beam with a correlation length of ~1.5 w or larger, where w is the wavelength of light, diffractive unidirectional imagers achieve robust performance, exhibiting asymmetric imaging performance between the forward and backward directions - as desired. A partially coherent unidirectional imager designed with a smaller correlation length of less than 1.5 w still supports unidirectional image transmission, but with a reduced figure of merit. These partially coherent diffractive unidirectional imagers are compact (axially spanning less than 75 w), polarization-independent, and compatible with various types of illumination sources, making them well-suited for applications in asymmetric visual information processing and communication.
Authors: Cheng Wei, Yang Wang, Kuofeng Gao, Shuo Shao, Yiming Li, Zhibo Wang, Zhan Qin
Abstract: Recently, point clouds have been widely used in computer vision, whereas their collection is time-consuming and expensive. As such, point cloud datasets are the valuable intellectual property of their owners and deserve protection. To detect and prevent unauthorized use of these datasets, especially for commercial or open-sourced ones that cannot be sold again or used commercially without permission, we intend to identify whether a suspicious third-party model is trained on our protected dataset under the black-box setting. We achieve this goal by designing a scalable clean-label backdoor-based dataset watermark for point clouds that ensures both effectiveness and stealthiness. Unlike existing clean-label watermark schemes, which are susceptible to the number of categories, our method could watermark samples from all classes instead of only from the target one. Accordingly, it can still preserve high effectiveness even on large-scale datasets with many classes. Specifically, we perturb selected point clouds with non-target categories in both shape-wise and point-wise manners before inserting trigger patterns without changing their labels. The features of perturbed samples are similar to those of benign samples from the target class. As such, models trained on the watermarked dataset will have a distinctive yet stealthy backdoor behavior, i.e., misclassifying samples from the target class whenever triggers appear, since the trained DNNs will treat the inserted trigger pattern as a signal to deny predicting the target label. We also design a hypothesis-test-guided dataset ownership verification based on the proposed watermark. Extensive experiments on benchmark datasets are conducted, verifying the effectiveness of our method and its resistance to potential removal methods.
Authors: Federico Figari Tomenotti, Nicoletta Noceti
Abstract: The ability to anticipate others' goals and intentions is at the basis of human-human social interaction. Such ability, largely based on non-verbal communication, is also a key to having natural and pleasant interactions with artificial agents, like robots. In this work, we discuss a preliminary experiment on the use of head pose as a visual cue to understand and anticipate action goals, particularly reaching and transporting movements. By reasoning on the spatio-temporal connections between the head, hands and objects in the scene, we will show that short-range anticipation is possible, laying the foundations for future applications to human-robot interaction.
Authors: Roberto Daza, Luis F. Gomez, Julian Fierrez, Aythami Morales, Ruben Tolosana, Javier Ortega-Garcia
Abstract: This work introduces an innovative method for estimating attention levels (cognitive load) using an ensemble of facial analysis techniques applied to webcam videos. Our method is particularly useful, among others, in e-learning applications, so we trained, evaluated, and compared our approach on the mEBAL2 database, a public multi-modal database acquired in an e-learning environment. mEBAL2 comprises data from 60 users who performed 8 different tasks. These tasks varied in difficulty, leading to changes in their cognitive loads. Our approach adapts state-of-the-art facial analysis technologies to quantify the users' cognitive load in the form of high or low attention. Several behavioral signals and physiological processes related to the cognitive load are used, such as eyeblink, heart rate, facial action units, and head pose, among others. Furthermore, we conduct a study to understand which individual features obtain better results, the most efficient combinations, explore local and global features, and how temporary time intervals affect attention level estimation, among other aspects. We find that global facial features are more appropriate for multimodal systems using score-level fusion, particularly as the temporal window increases. On the other hand, local features are more suitable for fusion through neural network training with score-level fusion approaches. Our method outperforms existing state-of-the-art accuracies using the public mEBAL2 benchmark.
Authors: Guodong Du, Runhua Jiang, Senqiao Yang, Haoyang Li, Wei Chen, Keren Li, Sim Kuan Goh, Ho-Kin Tang
Abstract: Darwinian evolution of the biological brain is documented through multiple lines of evidence, although the modes of evolutionary changes remain unclear. Drawing inspiration from the evolved neural systems (e.g., visual cortex), deep learning models have demonstrated superior performance in visual tasks, among others. While the success of training deep neural networks has been relying on back-propagation (BP) and its variants to learn representations from data, BP does not incorporate the evolutionary processes that govern biological neural systems. This work proposes a neural network optimization framework based on evolutionary theory. Specifically, BP-trained deep neural networks for visual recognition tasks obtained from the ending epochs are considered the primordial ancestors (initial population). Subsequently, the population evolved with differential evolution. Extensive experiments are carried out to examine the relationships between Darwinian evolution and neural network optimization, including the correspondence between datasets, environment, models, and living species. The empirical results show that the proposed framework has positive impacts on the network, with reduced over-fitting and an order of magnitude lower time complexity compared to BP. Moreover, the experiments show that the proposed framework performs well on deep neural networks and big datasets.
Authors: Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer
Abstract: This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between those factors by explicitly accounting for the causal relationship between the static/dynamic variables and that improves the model expressivity through additional Normalizing Flows. A formal definition of the factors is proposed. This formalism leads to the derivation of sufficient conditions for the ground truth factors to be identifiable, and to the introduction of a novel theoretically grounded disentanglement constraint that can be directly and efficiently incorporated into our new framework. The experiments show that the proposed approach outperforms previous complex state-of-the-art techniques in scenarios where the dynamics of a scene are influenced by its content.
Authors: Hanqiu Chen, Xuebin Yao, Pradeep Subedi, Cong Hao
Abstract: Edge computing is a distributed computing paradigm that collects and processes data at or near the source of data generation. The on-device learning at edge relies on device-to-device wireless communication to facilitate real-time data sharing and collaborative decision-making among multiple devices. This significantly improves the adaptability of the edge computing system to the changing environments. However, as the scale of the edge computing system is getting larger, communication among devices is becoming the bottleneck because of the limited bandwidth of wireless communication leads to large data transfer latency. To reduce the amount of device-to-device data transmission and accelerate on-device learning, in this paper, we propose Residual-INR, a fog computing-based communication-efficient on-device learning framework by utilizing implicit neural representation (INR) to compress images/videos into neural network weights. Residual-INR enhances data transfer efficiency by collecting JPEG images from edge devices, compressing them into INR format at the fog node, and redistributing them for on-device learning. By using a smaller INR for full image encoding and a separate object INR for high-quality object region reconstruction through residual encoding, our technique can reduce the encoding redundancy while maintaining the object quality. Residual-INR is a promising solution for edge on-device learning because it reduces data transmission by up to 5.16 x across a network of 10 edge devices. It also facilitates CPU-free accelerated on-device learning, achieving up to 2.9 x speedup without sacrificing accuracy. Our code is available at: https://github.com/sharclab/Residual-INR.
Authors: Kaiwen Geng, Zhiyi Shi, Xiaoyan Zhao, Alaa Ali, Jing Wang, Joseph Leader, Jiantao Pu
Abstract: Abstract Background: Pulmonary function tests (PFTs) and computed tomography (CT) imaging are vital in diagnosing, managing, and monitoring lung diseases. A common issue in practice is the lack of access to recorded pulmonary functions despite available chest CT scans. Purpose: To develop and validate a deep learning algorithm for predicting pulmonary function directly from chest CT scans. Methods: The development cohort came from the Pittsburgh Lung Screening Study (PLuSS) (n=3619). The validation cohort came from the Specialized Centers of Clinically Oriented Research (SCCOR) in COPD (n=662). A deep learning model called BeyondCT, combining a three-dimensional (3D) convolutional neural network (CNN) and Vision Transformer (ViT) architecture, was used to predict forced vital capacity (FVC) and forced expiratory volume in one second (FEV1) from non-contrasted inspiratory chest CT scans. A 3D CNN model without ViT was used for comparison. Subject demographics (age, gender, smoking status) were also incorporated into the model. Performance was compared to actual PFTs using mean absolute error (MAE, L), percentage error, and R square. Results: The 3D-CNN model achieved MAEs of 0.395 L and 0.383 L, percentage errors of 13.84% and 18.85%, and R square of 0.665 and 0.679 for FVC and FEV1, respectively. The BeyondCT model without demographics had MAEs of 0.362 L and 0.371 L, percentage errors of 10.89% and 14.96%, and R square of 0.719 and 0.727, respectively. Including demographics improved performance (p<0.05), with MAEs of 0.356 L and 0.353 L, percentage errors of 10.79% and 14.82%, and R square of 0.77 and 0.739 for FVC and FEV1 in the test set. Conclusion: The BeyondCT model showed robust performance in predicting lung function from non-contrast inspiratory chest CT scans.
Authors: Ghazal Kaviani, Reza Marzban, Ghassan AlRegib
Abstract: This paper investigates image denoising, comparing traditional non-learning-based techniques, represented by Block-Matching 3D (BM3D), with modern learning-based methods, exemplified by NBNet. We assess these approaches across diverse datasets, including CURE-OR, CURE-TSR, SSID+, Set-12, and Chest-Xray, each presenting unique noise challenges. Our analysis employs seven Image Quality Assessment (IQA) metrics and examines the impact on object detection performance. We find that while BM3D excels in scenarios like blur challenges, NBNet is more effective in complex noise environments such as under-exposure and over-exposure. The study reveals the strengths and limitations of each method, providing insights into the effectiveness of different denoising strategies in varied real-world applications.
Authors: Ruiquan Ge, Xiao Yu, Yifei Chen, Fan Jia, Shenghao Zhu, Guanyu Zhou, Yiyu Huang, Chenyan Zhang, Dong Zeng, Changmiao Wang, Qiegen Liu, Shanzhou Niu
Abstract: Magnetic Resonance Imaging (MRI) has become essential in clinical diagnosis due to its high resolution and multiple contrast mechanisms. However, the relatively long acquisition time limits its broader application. To address this issue, this study presents an innovative conditional guided diffusion model, named as TC-KANRecon, which incorporates the Multi-Free U-KAN (MF-UKAN) module and a dynamic clipping strategy. TC-KANRecon model aims to accelerate the MRI reconstruction process through deep learning methods while maintaining the quality of the reconstructed images. The MF-UKAN module can effectively balance the tradeoff between image denoising and structure preservation. Specifically, it presents the multi-head attention mechanisms and scalar modulation factors, which significantly enhances the model's robustness and structure preservation capabilities in complex noise environments. Moreover, the dynamic clipping strategy in TC-KANRecon adjusts the cropping interval according to the sampling steps, thereby mitigating image detail loss typically caused by traditional cropping methods and enriching the visual features of the images. Furthermore, the MC-Model module incorporates full-sampling k-space information, realizing efficient fusion of conditional information, enhancing the model's ability to process complex data, and improving the realism and detail richness of reconstructed images. Experimental results demonstrate that the proposed method outperforms other MRI reconstruction methods in both qualitative and quantitative evaluations. Notably, TC-KANRecon method exhibits excellent reconstruction results when processing high-noise, low-sampling-rate MRI data. Our source code is available at https://github.com/lcbkmm/TC-KANRecon.
Authors: Wenqi Tao, Huaming Ling, Zuoqiang Shi, Bao Wang
Abstract: Protecting data privacy in deep learning (DL) is of crucial importance. Several celebrated privacy notions have been established and used for privacy-preserving DL. However, many existing mechanisms achieve privacy at the cost of significant utility degradation and computational overhead. In this paper, we propose a stochastic differential equation-based residual perturbation for privacy-preserving DL, which injects Gaussian noise into each residual mapping of ResNets. Theoretically, we prove that residual perturbation guarantees differential privacy (DP) and reduces the generalization gap of DL. Empirically, we show that residual perturbation is computationally efficient and outperforms the state-of-the-art differentially private stochastic gradient descent (DPSGD) in utility maintenance without sacrificing membership privacy.
Authors: Enqiang Xu, Xinhui Li, Zhigong Zhou, Jiahao Ji, Jinyuan Zhao, Dadong Miao, Songlin Wang, Lin Liu, Sulong Xu
Abstract: In the rapidly evolving field of e-commerce, the effectiveness of search re-ranking models is crucial for enhancing user experience and driving conversion rates. Despite significant advancements in feature representation and model architecture, the integration of multimodal information remains underexplored. This study addresses this gap by investigating the computation and fusion of textual and visual information in the context of re-ranking. We propose \textbf{A}dvancing \textbf{R}e-Ranking with \textbf{M}ulti\textbf{m}odal Fusion and \textbf{T}arget-Oriented Auxiliary Tasks (ARMMT), which integrates an attention-based multimodal fusion technique and an auxiliary ranking-aligned task to enhance item representation and improve targeting capabilities. This method not only enriches the understanding of product attributes but also enables more precise and personalized recommendations. Experimental evaluations on JD.com's search platform demonstrate that ARMMT achieves state-of-the-art performance in multimodal information integration, evidenced by a 0.22\% increase in the Conversion Rate (CVR), significantly contributing to Gross Merchandise Volume (GMV). This pioneering approach has the potential to revolutionize e-commerce re-ranking, leading to elevated user satisfaction and business growth.
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: Lei Zhou, Yuzhong Zhang, Jiadong Zhang, Xuejun Qian, Chen Gong, Kun Sun, Zhongxiang Ding, Xing Wang, Zhenhui Li, Zaiyi Liu, Dinggang Shen
Abstract: Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However, accurate segmentation of breast tumor is a challenging task, often necessitating the development of complex networks. To strike an optimal trade-off between computational costs and segmentation performance, we propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. Specifically, the hybrid network consists of a encoder-decoder architecture by stacking convolution and decovolution layers. Effective 3D transformer layers are then implemented after the encoder subnetworks, to capture global dependencies between the bottleneck features. To improve the efficiency of hybrid network, two parallel encoder subnetworks are designed for the decoder and the transformer layers, respectively. To further enhance the discriminative capability of hybrid network, a prototype learning guided prediction module is proposed, where the category-specified prototypical features are calculated through on-line clustering. All learned prototypical features are finally combined with the features from decoder for tumor mask prediction. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network achieves superior performance than the state-of-the-art (SOTA) methods, while maintaining balance between segmentation accuracy and computation cost. Moreover, we demonstrate that automatically generated tumor masks can be effectively applied to identify HER2-positive subtype from HER2-negative subtype with the similar accuracy to the analysis based on manual tumor segmentation. The source code is available at https://github.com/ZhouL-lab/PLHN.
Authors: Viet Anh Nguyen, Minh Lenhat, Khoa Nguyen, Duong Duc Hieu, Dao Huu Hung, Truong Son Hy
Abstract: The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. To apply transformers across different data modalities, practitioners have to make specific clever data-modality-dependent constructions. In this paper, we propose Sampling Foundational Transformer (SFT) that can work on multiple data modalities (e.g., point cloud, graph, and sequence) and constraints (e.g., rotational-invariant). The existence of such model is important as contemporary foundational modeling requires operability on multiple data sources. For efficiency on large number of tokens, our model relies on our context aware sampling-without-replacement mechanism for both linear asymptotic computational complexity and real inference time gain. For efficiency, we rely on our newly discovered pseudoconvex formulation of transformer layer to increase model's convergence rate. As a model working on multiple data modalities, SFT has achieved competitive results on many benchmarks, while being faster in inference, compared to other very specialized models.
Authors: Rohit Jena, Deeksha Sethi, Pratik Chaudhari, James C. Gee
Abstract: Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. Finally, we propose a general recipe to choose the best paradigm for a given registration problem, based on these observations.
Authors: Mobina Mansoori, Sajjad Shahabodini, Jamshid Abouei, Konstantinos N. Plataniotis, Arash Mohammadi
Abstract: Polyp segmentation plays a crucial role in the early detection and diagnosis of colorectal cancer. However, obtaining accurate segmentations often requires labor-intensive annotations and specialized models. Recently, Meta AI Research released a general Segment Anything Model 2 (SAM 2), which has demonstrated promising performance in several segmentation tasks. In this work, we evaluate the performance of SAM 2 in segmenting polyps under various prompted settings. We hope this report will provide insights to advance the field of polyp segmentation and promote more interesting work in the future. This project is publicly available at https://github.com/ sajjad-sh33/Polyp-SAM-2.
URLs: https://github.com/
Authors: Zhaoming Kong, Fangxi Deng, Xiaowei Yang
Abstract: Image denoising is an appealing and challenging task, in that noise statistics of real-world observations may vary with local image contents and different image channels. Specifically, the green channel usually has twice the sampling rate in raw data. To handle noise variances and leverage such channel-wise prior information, we propose a simple and effective green channel prior-based image denoising (GCP-ID) method, which integrates GCP into the classic patch-based denoising framework. Briefly, we exploit the green channel to guide the search for similar patches, which aims to improve the patch grouping quality and encourage sparsity in the transform domain. The grouped image patches are then reformulated into RGGB arrays to explicitly characterize the density of green samples. Furthermore, to enhance the adaptivity of GCP-ID to various image contents, we cast the noise estimation problem into a classification task and train an effective estimator based on convolutional neural networks (CNNs). Experiments on real-world datasets demonstrate the competitive performance of the proposed GCP-ID method for image and video denoising applications in both raw and sRGB spaces. Our code is available at https://github.com/ZhaomingKong/GCP-ID.
Authors: Uditangshu Aurangabadkar, Darren Ramsook, Anil Kokaram
Abstract: The success of modern Deep Neural Network (DNN) approaches can be attributed to the use of complex optimization criteria beyond standard losses such as mean absolute error (MAE) or mean squared error (MSE). In this work, we propose a novel method of utilising a no-reference sharpness metric Q introduced by Zhu and Milanfar for removing out-of-focus blur from images. We also introduce a novel dataset of real-world out-of-focus images for assessing restoration models. Our fine-tuned method produces images with a 7.5 % increase in perceptual quality (LPIPS) as compared to a standard model trained only on MAE. Furthermore, we observe a 6.7 % increase in Q (reflecting sharper restorations) and 7.25 % increase in PSNR over most state-of-the-art (SOTA) methods.
Authors: Shanu Saklani, Chitwan Goel, Shrey Bansal, Zhe Wang, Soumya Dutta, Tushar M. Athawale, David Pugmire, Christopher R. Johnson
Abstract: The increasing adoption of Deep Neural Networks (DNNs) has led to their application in many challenging scientific visualization tasks. While advanced DNNs offer impressive generalization capabilities, understanding factors such as model prediction quality, robustness, and uncertainty is crucial. These insights can enable domain scientists to make informed decisions about their data. However, DNNs inherently lack ability to estimate prediction uncertainty, necessitating new research to construct robust uncertainty-aware visualization techniques tailored for various visualization tasks. In this work, we propose uncertainty-aware implicit neural representations to model scalar field data sets effectively and comprehensively study the efficacy and benefits of estimated uncertainty information for volume visualization tasks. We evaluate the effectiveness of two principled deep uncertainty estimation techniques: (1) Deep Ensemble and (2) Monte Carlo Dropout (MCDropout). These techniques enable uncertainty-informed volume visualization in scalar field data sets. Our extensive exploration across multiple data sets demonstrates that uncertainty-aware models produce informative volume visualization results. Moreover, integrating prediction uncertainty enhances the trustworthiness of our DNN model, making it suitable for robustly analyzing and visualizing real-world scientific volumetric data sets.
Authors: Du Nguyen, Stefan Sommer
Abstract: We express parallel transport for several common matrix Lie groups with a family of pseudo-Riemannian metrics in terms of matrix exponential and exponential actions. The expression for parallel transport is preserved by taking the quotient under certain scenarios. In particular, for a Stiefel manifold of orthogonal matrices of size $n\times d$, we give an expression for parallel transport along a geodesic from time zero to $t$, that could be computed with time complexity of $O(nd^2)$ for small $t$, and of $O(td^3)$ for large t, contributing a step in a long-standing open problem in matrix manifolds. A similar result holds for flag manifolds with the canonical metric. We also show the parallel transport formulas for the generalized linear group, and the special orthogonal group under these metrics.
Authors: Melanie Dohmen, Tuan Truong, Ivo M. Baltruschat, Matthias Lenga
Abstract: Reference metrics have been developed to objectively and quantitatively compare two images. Especially for evaluating the quality of reconstructed or compressed images, these metrics have shown very useful. Extensive tests of such metrics on benchmarks of artificially distorted natural images have revealed which metric best correlate with human perception of quality. Direct transfer of these metrics to the evaluation of generative models in medical imaging, however, can easily lead to pitfalls, because assumptions about image content, image data format and image interpretation are often very different. Also, the correlation of reference metrics and human perception of quality can vary strongly for different kinds of distortions and commonly used metrics, such as SSIM, PSNR and MAE are not the best choice for all situations. We selected five pitfalls that showcase unexpected and probably undesired reference metric scores and discuss strategies to avoid them.
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 deep neural networks opens up new possibilities for ultra-high-definition 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 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. In the presented solutions, two novel techniques are incorporated to make good scheduling decisions for inference overhead optimization and reduce the scheduling latency. Firstly, under the guidance of our pioneering and theoretical analysis, Palantir constructs a directed acyclic graph (DAG) for lightweight yet accurate 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 state-of-the-art real-time frame-level scheduling strategy, Palantir reduces the energy overhead of SR-integrated mobile clients by 38.1% at most (and 22.4% on average) and the monetary costs of cloud-based SR by 80.1% at most (and 38.4% on average).
Authors: Qiaoxin Li, Dong Liang, Yinsheng Li
Abstract: Dual-energy computed tomography (DECT) has been widely used to obtain quantitative elemental composition of imaged subjects for personalized and precise medical diagnosis. Compared with existing high-end DECT leveraging advanced X-ray source and/or detector technologies, the use of the sequentially-scanning data acquisition scheme to implement DECT may make broader impact on clinical practice because this scheme requires no specialized hardware designs. However, since the concentration of iodinated contrast agent in the imaged subject varies over time, sequentially-scanned data sets acquired at two tube potentials are temporally inconsistent. As existing material decomposition approaches for DECT assume that the data sets acquired at two tube potentials are temporally consistent, the violation of this assumption results in inaccurate quantification accuracy of iodine concentration. In this work, we developed a technique to achieve sequentially-scanning DECT imaging using high temporal resolution image reconstruction and temporal extrapolation, ACCELERATION in short, to address the technical challenge induced by temporal inconsistency of sequentially-scanned data sets and improve iodine quantification accuracy in sequentially-scanning DECT. ACCELERATION has been validated and evaluated using numerical simulation data sets generated from clinical human subject exams. Results demonstrated the improvement of iodine quantification accuracy using ACCELERATION.
Authors: Yosuke Yamagishi, Shouhei Hanaoka, Tomohiro Kikuchi, Takahiro Nakao, Yuta Nakamura, Yukihiro Nomura, Soichiro Miki, Takeharu Yoshikawa, Osamu Abe
Abstract: Purpose: This study aimed to evaluate the zero-shot performance of Segment Anything Model 2 (SAM 2) in 3D segmentation of abdominal organs in CT scans, leveraging its video tracking capabilities for volumetric medical imaging. Materials and Methods: Using a subset of the TotalSegmentator CT dataset (n=123) from 8 different institutions, we assessed SAM 2's ability to segment 8 abdominal organs. Segmentation was initiated from three different Z-coordinate levels (caudal, mid, and cranial levels) of each organ. Performance was measured using the Dice similarity coefficient (DSC). We also analyzed organ volumes to contextualize the results. Results: As a zero-shot approach, larger organs with clear boundaries demonstrated high segmentation performance, with mean(median) DSCs as follows: liver 0.821(0.898), left kidney 0.870(0.921), right kidney 0.862(0.935), and spleen 0.891(0.932). Smaller or less defined structures showed lower performance: gallbladder 0.531(0.590), pancreas 0.361(0.359), and adrenal glands 0.203-0.308(0.109-0.231). Significant differences in DSC were observed depending on the starting initial slice of segmentation for different organs. A moderate positive correlation was observed between volume size and DSCs (Spearman's rs = 0.731, P <.001 at caudal-level). DSCs exhibited high variability within organs, ranging from near 0 to almost 1.0, indicating substantial inconsistency in segmentation performance between scans. Conclusion: SAM 2 demonstrated promising zero-shot performance in segmenting certain abdominal organs in CT scans, particularly larger organs with clear boundaries. The model's ability to segment previously unseen targets without additional training highlights its potential for cross-domain generalization in medical imaging. However, improvements are needed for smaller and less defined structures.
Authors: Andrew Freeman
Abstract: Traditionally, video is structured as a sequence of discrete image frames. Recently, however, a novel video sensing paradigm has emerged which eschews video frames entirely. These "event" sensors aim to mimic the human vision system with asynchronous sensing, where each pixel has an independent, sparse data stream. While these cameras enable high-speed and high-dynamic-range sensing, researchers often revert to a framed representation of the event data for existing applications, or build bespoke applications for a particular camera's event data type. At the same time, classical video systems have significant computational redundancy at the application layer, since pixel samples are repeated across frames in the uncompressed domain. To address the shortcomings of existing systems, I introduce Address, Decimation, {\Delta}t Event Representation (AD{\Delta}ER, pronounced "adder"), a novel intermediate video representation and system framework. The framework transcodes a variety of framed and event camera sources into a single event-based representation, which supports source-modeled lossy compression and backward compatibility with traditional frame-based applications. I demonstrate that AD{\Delta}ER achieves state-of-the-art application speed and compression performance for scenes with high temporal redundancy. Crucially, I describe how AD{\Delta}ER unlocks an entirely new control mechanism for computer vision: application speed can correlate with both the scene content and the level of lossy compression. Finally, I discuss the implications for event-based video on large-scale video surveillance and resource-constrained sensing.
Authors: Yingjin Song, Denis Paperno, Albert Gatt
Abstract: Visual storytelling systems generate multi-sentence stories from image sequences. In this task, capturing contextual information and bridging visual variation bring additional challenges. We propose a simple yet effective framework that leverages the generalization capabilities of pretrained foundation models, only training a lightweight vision-language mapping network to connect modalities, while incorporating context to enhance coherence. We introduce a multimodal contrastive objective that also improves visual relevance and story informativeness. Extensive experimental results, across both automatic metrics and human evaluations, demonstrate that the stories generated by our framework are diverse, coherent, informative, and interesting.
Authors: In\^es Gomes, Lu\'is F. Teixeira, Jan N. van Rijn, Carlos Soares, Andr\'e Restivo, Lu\'is Cunha, Mois\'es Santos
Abstract: The increasing use of deep learning across various domains highlights the importance of understanding the decision-making processes of these black-box models. Recent research focusing on the decision boundaries of deep classifiers, relies on generated synthetic instances in areas of low confidence, uncovering samples that challenge both models and humans. We propose a novel approach to enhance the interpretability of deep binary classifiers by selecting representative samples from the decision boundary - prototypes - and applying post-model explanation algorithms. We evaluate the effectiveness of our approach through 2D visualizations and GradientSHAP analysis. Our experiments demonstrate the potential of the proposed method, revealing distinct and compact clusters and diverse prototypes that capture essential features that lead to low-confidence decisions. By offering a more aggregated view of deep classifiers' decision boundaries, our work contributes to the responsible development and deployment of reliable machine learning systems.
Authors: Mina Huh, Fangyuan Xu, Yi-Hao Peng, Chongyan Chen, Hansika Murugu, Danna Gurari, Eunsol Choi, Amy Pavel
Abstract: Vision language models can now generate long-form answers to questions about images - long-form visual question answers (LFVQA). We contribute VizWiz-LF, a dataset of long-form answers to visual questions posed by blind and low vision (BLV) users. VizWiz-LF contains 4.2k long-form answers to 600 visual questions, collected from human expert describers and six VQA models. We develop and annotate functional roles of sentences of LFVQA and demonstrate that long-form answers contain information beyond the question answer such as explanations and suggestions. We further conduct automatic and human evaluations with BLV and sighted people to evaluate long-form answers. BLV people perceive both human-written and generated long-form answers to be plausible, but generated answers often hallucinate incorrect visual details, especially for unanswerable visual questions (e.g., blurry or irrelevant images). To reduce hallucinations, we evaluate the ability of VQA models to abstain from answering unanswerable questions across multiple prompting strategies.
Authors: Royina Karegoudra Jayanth, Yinshuang Xu, Ziyun Wang, Evangelos Chatzipantazis, Daniel Gehrig, Kostas Daniilidis
Abstract: Presently, neural networks are widely employed to accurately estimate 2D displacements and associated uncertainties from Inertial Measurement Unit (IMU) data that can be integrated into stochastic filter networks like the Extended Kalman Filter (EKF) as measurements and uncertainties for the update step in the filter. However, such neural approaches overlook symmetry which is a crucial inductive bias for model generalization. This oversight is notable because (i) physical laws adhere to symmetry principles when considering the gravity axis, meaning there exists the same transformation for both the physical entity and the resulting trajectory, and (ii) displacements should remain equivariant to frame transformations when the inertial frame changes. To address this, we propose a subequivariant framework by: (i) deriving fundamental layers such as linear and nonlinear layers for a subequivariant network, designed to handle sequences of vectors and scalars, (ii) employing the subequivariant network to predict an equivariant frame for the sequence of inertial measurements. This predicted frame can then be utilized for extracting invariant features through projection, which are integrated with arbitrary network architectures, (iii) transforming the invariant output by frame transformation to obtain equivariant displacements and covariances. We demonstrate the effectiveness and generalization of our Equivariant Framework on a filter-based approach with TLIO architecture for TLIO and Aria datasets, and an end-to-end deep learning approach with RONIN architecture for RONIN, RIDI and OxIOD datasets.
Authors: Xiao Liu, Tianjie Zhang, Yu Gu, Iat Long Iong, Yifan Xu, Xixuan Song, Shudan Zhang, Hanyu Lai, Xinyi Liu, Hanlin Zhao, Jiadai Sun, Xinyue Yang, Yu Yang, Zehan Qi, Shuntian Yao, Xueqiao Sun, Siyi Cheng, Qinkai Zheng, Hao Yu, Hanchen Zhang, Wenyi Hong, Ming Ding, Lihang Pan, Xiaotao Gu, Aohan Zeng, Zhengxiao Du, Chan Hee Song, Yu Su, Yuxiao Dong, Jie Tang
Abstract: Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual foundation agents across diverse scenarios, including Embodied, Graphical User Interface, and Visual Design, with tasks formulated to probe the depth of LMMs' understanding and interaction capabilities. Through rigorous testing across nine proprietary LMM APIs and eight open models, we demonstrate the considerable yet still developing agent capabilities of these models. Additionally, VAB constructs a trajectory training set constructed through hybrid methods including Program-based Solvers, LMM Agent Bootstrapping, and Human Demonstrations, promoting substantial performance improvements in LMMs through behavior cloning. Our work not only aims to benchmark existing models but also provides a solid foundation for future development into visual foundation agents. Code, train \& test data, and part of fine-tuned open LMMs are available at \url{https://github.com/THUDM/VisualAgentBench}.
Authors: Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong Liu, Dacheng Tao
Abstract: Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) and derives that both have consistent mathematical formulation. Then inspired by effective EA variants, we propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block, which consists of three residual parts, i.e., Multi-scale region aggregation, global and local interaction, and feed-forward network modules, to model multi-scale, interactive, and individual information separately. Moreover, we design a task-related head docked with transformer backbone to complete final information fusion more flexibly and improve a modulated deformable MSA to dynamically model irregular locations. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach over state-of-the-art methods. E.g., our Mobile (1.8 M), Tiny (6.1 M), Small (24.3 M), and Base (49.0 M) models achieve 69.4, 78.4, 83.1, and 83.9 Top-1 only trained on ImageNet-1K with naive training recipe; EATFormer-Tiny/Small/Base armed Mask-R-CNN obtain 45.4/47.4/49.0 box AP and 41.4/42.9/44.2 mask AP on COCO detection, surpassing contemporary MPViT-T, Swin-T, and Swin-S by 0.6/1.4/0.5 box AP and 0.4/1.3/0.9 mask AP separately with less FLOPs; Our EATFormer-Small/Base achieve 47.3/49.3 mIoU on ADE20K by Upernet that exceeds Swin-T/S by 2.8/1.7. Code is available at https://github.com/zhangzjn/EATFormer.
Authors: Shoaib Ahmed Siddiqui, David Krueger, Yann LeCun, St\'ephane Deny
Abstract: Current state-of-the-art deep networks are all powered by backpropagation. In this paper, we explore alternatives to full backpropagation in the form of blockwise learning rules, leveraging the latest developments in self-supervised learning. We show that a blockwise pretraining procedure consisting of training independently the 4 main blocks of layers of a ResNet-50 with Barlow Twins' loss function at each block performs almost as well as end-to-end backpropagation on ImageNet: a linear probe trained on top of our blockwise pretrained model obtains a top-1 classification accuracy of 70.48%, only 1.1% below the accuracy of an end-to-end pretrained network (71.57% accuracy). We perform extensive experiments to understand the impact of different components within our method and explore a variety of adaptations of self-supervised learning to the blockwise paradigm, building an exhaustive understanding of the critical avenues for scaling local learning rules to large networks, with implications ranging from hardware design to neuroscience.
Authors: Yifeng Ma, Suzhen Wang, Yu Ding, Bowen Ma, Tangjie Lv, Changjie Fan, Zhipeng Hu, Zhidong Deng, Xin Yu
Abstract: Audio-driven talking head generation has drawn growing attention. To produce talking head videos with desired facial expressions, previous methods rely on extra reference videos to provide expression information, which may be difficult to find and hence limits their usage. In this work, we propose TalkCLIP, a framework that can generate talking heads where the expressions are specified by natural language, hence allowing for specifying expressions more conveniently. To model the mapping from text to expressions, we first construct a text-video paired talking head dataset where each video has diverse text descriptions that depict both coarse-grained emotions and fine-grained facial movements. Leveraging the proposed dataset, we introduce a CLIP-based style encoder that projects natural language-based descriptions to the representations of expressions. TalkCLIP can even infer expressions for descriptions unseen during training. TalkCLIP can also use text to modulate expression intensity and edit expressions. Extensive experiments demonstrate that TalkCLIP achieves the advanced capability of generating photo-realistic talking heads with vivid facial expressions guided by text descriptions.
Authors: Keumgang Cha, Junghoon Seo, Taekyung Lee
Abstract: As the potential of foundation models in visual tasks has garnered significant attention, pretraining these models before downstream tasks has become a crucial step. The three key factors in pretraining foundation models are the pretraining method, the size of the pretraining dataset, and the number of model parameters. Recently, research in the remote sensing field has focused primarily on the pretraining method and the size of the dataset, with limited emphasis on the number of model parameters. This paper addresses this gap by examining the effect of increasing the number of model parameters on the performance of foundation models in downstream tasks such as rotated object detection and semantic segmentation. We pretrained foundation models with varying numbers of parameters, including 86M, 605.26M, 1.3B, and 2.4B, to determine whether performance in downstream tasks improved with an increase in parameters. To the best of our knowledge, this is the first billion-scale foundation model in the remote sensing field. Furthermore, we propose an effective method for scaling up and fine-tuning a vision transformer in the remote sensing field. To evaluate general performance in downstream tasks, we employed the DOTA v2.0 and DIOR-R benchmark datasets for rotated object detection, and the Potsdam and LoveDA datasets for semantic segmentation. Experimental results demonstrated that, across all benchmark datasets and downstream tasks, the performance of the foundation models and data efficiency improved as the number of parameters increased. Moreover, our models achieve the state-of-the-art performance on several datasets including DIOR-R, Postdam, and LoveDA.
Authors: Weifeng Chen, Yatai Ji, Jie Wu, Hefeng Wu, Pan Xie, Jiashi Li, Xin Xia, Xuefeng Xiao, Liang Lin
Abstract: Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video (T2V) methods often struggling to produce high-quality and motion-consistent videos. In this work, we introduce Control-A-Video, a controllable T2V diffusion model that can generate videos conditioned on text prompts and reference control maps like edge and depth maps. To tackle video quality and motion consistency issues, we propose novel strategies to incorporate content prior and motion prior into the diffusion-based generation process. Specifically, we employ a first-frame condition scheme to transfer video generation from the image domain. Additionally, we introduce residual-based and optical flow-based noise initialization to infuse motion priors from reference videos, promoting relevance among frame latents for reduced flickering. Furthermore, we present a Spatio-Temporal Reward Feedback Learning (ST-ReFL) algorithm that optimizes the video diffusion model using multiple reward models for video quality and motion consistency, leading to superior outputs. Comprehensive experiments demonstrate that our framework generates higher-quality, more consistent videos compared to existing state-of-the-art methods in controllable text-to-video generation
Authors: Yuhang Zang, Wei Li, Jun Han, Kaiyang Zhou, Chen Change Loy
Abstract: Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual object detection -- understanding visible objects within different human-AI interactive contexts. Three representative scenarios are investigated, including the language cloze test, visual captioning, and question answering. Moreover, we present ContextDET, a unified multimodal model that is capable of end-to-end differentiable modeling of visual-language contexts, so as to locate, identify, and associate visual objects with language inputs for human-AI interaction. Our ContextDET involves three key submodels: (i) a visual encoder for extracting visual representations, (ii) a pre-trained LLM for multimodal context decoding, and (iii) a visual decoder for predicting bounding boxes given contextual object words. The new generate-then-detect framework enables us to detect object words within human vocabulary. Extensive experiments show the advantages of ContextDET on our proposed CODE benchmark, open-vocabulary detection, and referring image segmentation. Github: https://github.com/yuhangzang/ContextDET.
Authors: Fusheng Yu, Jiang Li, Xiaoping Wang, Shaojin Wu, Junjie Zhang, Zhigang Zeng
Abstract: Detecting safety clothing and helmets is paramount for ensuring the safety of construction workers. However, the development of deep learning models in this domain has been impeded by the scarcity of high-quality datasets. In this study, we construct a large, complex, and realistic safety clothing and helmet detection (SFCHD) dataset. SFCHD is derived from two authentic chemical plants, comprising 12,373 images, 7 categories, and 50,552 annotations. We partition the SFCHD dataset into training and testing sets with a ratio of 4:1 and validate its utility by applying several classic object detection algorithms. Furthermore, drawing inspiration from spatial and channel attention mechanisms, we design a spatial and channel attention-based low-light enhancement (SCALE) module. SCALE is a plug-and-play component with a high degree of flexibility. Extensive evaluations of the SCALE module on both the ExDark and SFCHD datasets have empirically demonstrated its efficacy in enhancing the performance of detectors under low-light conditions. The dataset and code are publicly available at https://github.com/lijfrank-open/SFCHD-SCALE.
Authors: Ting Zhe, Jing Zhang, Yongqian Li, Yong Luo, Han Hu, Dacheng Tao
Abstract: Detecting hand actions in videos is crucial for understanding video content and has diverse real-world applications. Existing approaches often focus on whole-body actions or coarse-grained action categories, lacking fine-grained hand-action localization information. To fill this gap, we introduce the FHA-Kitchens (Fine-Grained Hand Actions in Kitchen Scenes) dataset, providing both coarse- and fine-grained hand action categories along with localization annotations. This dataset comprises 2,377 video clips and 30,047 frames, annotated with approximately 200k bounding boxes and 880 action categories. Evaluation of existing action detection methods on FHA-Kitchens reveals varying generalization capabilities across different granularities. To handle multi-granularity in hand actions, we propose MG-HAD, an End-to-End Multi-Granularity Hand Action Detection method. It incorporates two new designs: Multi-dimensional Action Queries and Coarse-Fine Contrastive Denoising. Extensive experiments demonstrate MG-HAD's effectiveness for multi-granularity hand action detection, highlighting the significance of FHA-Kitchens for future research and real-world applications. The dataset and source code are available at https://github.com/superZ678/MG-HAD.
Authors: Wenqi Shao, Meng Lei, Yutao Hu, Peng Gao, Kaipeng Zhang, Fanqing Meng, Peng Xu, Siyuan Huang, Hongsheng Li, Yu Qiao, Ping Luo
Abstract: Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress in tackling complex multimodal tasks. Among these cutting-edge developments, Google's Bard stands out for its remarkable multimodal capabilities, promoting comprehensive comprehension and reasoning across various domains. This work presents an early and holistic evaluation of LVLMs' multimodal abilities, with a particular focus on Bard, by proposing a lightweight variant of LVLM-eHub, named Tiny LVLM-eHub. In comparison to the vanilla version, Tiny LVLM-eHub possesses several appealing properties. Firstly, it provides a systematic assessment of six categories of multimodal capabilities, including visual perception, visual knowledge acquisition, visual reasoning, visual commonsense, object hallucination, and embodied intelligence, through quantitative evaluation of $42$ standard text-related visual benchmarks. Secondly, it conducts an in-depth analysis of LVLMs' predictions using the ChatGPT Ensemble Evaluation (CEE), which leads to a robust and accurate evaluation and exhibits improved alignment with human evaluation compared to the word matching approach. Thirdly, it comprises a mere $2.1$K image-text pairs, facilitating ease of use for practitioners to evaluate their own offline LVLMs. Through extensive experimental analysis, this study demonstrates that Bard outperforms previous LVLMs in most multimodal capabilities except object hallucination, to which Bard is still susceptible. Tiny LVLM-eHub serves as a baseline evaluation for various LVLMs and encourages innovative strategies aimed at advancing multimodal techniques. Our project is publicly available at \url{https://github.com/OpenGVLab/Multi-Modality-Arena}.
Authors: Zhenrong Zhang, Jianan Liu, Yuxuan Xia, Tao Huang, Qing-Long Han, Hongbin Liu
Abstract: Online multi-object tracking (MOT) plays a pivotal role in autonomous systems. The state-of-the-art approaches usually employ a tracking-by-detection method, and data association plays a critical role. This paper proposes a learning and graph-optimized (LEGO) modular tracker to improve data association performance in the existing literature. The proposed LEGO tracker integrates graph optimization and self-attention mechanisms, which efficiently formulate the association score map, facilitating the accurate and efficient matching of objects across time frames. To further enhance the state update process, the Kalman filter is added to ensure consistent tracking by incorporating temporal coherence in the object states. Our proposed method utilizing LiDAR alone has shown exceptional performance compared to other online tracking approaches, including LiDAR-based and LiDAR-camera fusion-based methods. LEGO ranked 1st at the time of submitting results to KITTI object tracking evaluation ranking board and remains 2nd at the time of submitting this paper, among all online trackers in the KITTI MOT benchmark for cars1
Authors: Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, Joan Lasenby
Abstract: In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding. The OpenIns3D framework employs a "Mask-Snap-Lookup" scheme. The "Mask" module learns class-agnostic mask proposals in 3D point clouds, the "Snap" module generates synthetic scene-level images at multiple scales and leverages 2D vision-language models to extract interesting objects, and the "Lookup" module searches through the outcomes of "Snap" to assign category names to the proposed masks. This approach, yet simple, achieves state-of-the-art performance across a wide range of 3D open-vocabulary tasks, including recognition, object detection, and instance segmentation, on both indoor and outdoor datasets. Moreover, OpenIns3D facilitates effortless switching between different 2D detectors without requiring retraining. When integrated with powerful 2D open-world models, it achieves excellent results in scene understanding tasks. Furthermore, when combined with LLM-powered 2D models, OpenIns3D exhibits an impressive capability to comprehend and process highly complex text queries that demand intricate reasoning and real-world knowledge. Project page: https://zheninghuang.github.io/OpenIns3D/
Authors: Shuhao Kang, Youqi Liao, Jianping Li, Fuxun Liang, Yuhao Li, Xianghong Zou, Fangning Li, Xieyuanli Chen, Zhen Dong, Bisheng Yang
Abstract: Image-to-point cloud (I2P) registration is a fundamental task for robots and autonomous vehicles to achieve cross-modality data fusion and localization. Current I2P registration methods primarily focus on estimating correspondences at the point or pixel level, often neglecting global alignment. As a result, I2P matching can easily converge to a local optimum if it lacks high-level guidance from global constraints. To improve the success rate and general robustness, this paper introduces CoFiI2P, a novel I2P registration network that extracts correspondences in a coarse-to-fine manner. First, the image and point cloud data are processed through a two-stream encoder-decoder network for hierarchical feature extraction. Second, a coarse-to-fine matching module is designed to leverage these features and establish robust feature correspondences. Specifically, In the coarse matching phase, a novel I2P transformer module is employed to capture both homogeneous and heterogeneous global information from the image and point cloud data. This enables the estimation of coarse super-point/super-pixel matching pairs with discriminative descriptors. In the fine matching module, point/pixel pairs are established with the guidance of super-point/super-pixel correspondences. Finally, based on matching pairs, the transform matrix is estimated with the EPnP-RANSAC algorithm. Experiments conducted on the KITTI Odometry dataset demonstrate that CoFiI2P achieves impressive results, with a relative rotation error (RRE) of 1.14 degrees and a relative translation error (RTE) of 0.29 meters, while maintaining real-time speed.Additional experiments on the Nuscenes datasets confirm our method's generalizability. The project page is available at \url{https://whu-usi3dv.github.io/CoFiI2P}.
Authors: Chaoyue Xing, Wei Mao, Miaomiao Liu
Abstract: In this paper, we tackle the problem of scene-aware 3D human motion forecasting. A key challenge of this task is to predict future human motions that are consistent with the scene by modeling the human-scene interactions. While recent works have demonstrated that explicit constraints on human-scene interactions can prevent the occurrence of ghost motion, they only provide constraints on partial human motion e.g., the global motion of the human or a few joints contacting the scene, leaving the rest of the motion unconstrained. To address this limitation, we propose to model the human-scene interaction with the mutual distance between the human body and the scene. Such mutual distances constrain both the local and global human motion, resulting in a whole-body motion constrained prediction. In particular, mutual distance constraints consist of two components, the signed distance of each vertex on the human mesh to the scene surface and the distance of basis scene points to the human mesh. We further introduce a global scene representation learned from a signed distance function (SDF) volume to ensure coherence between the global scene representation and the explicit constraint from the mutual distance. We develop a pipeline with two sequential steps: predicting the future mutual distances first, followed by forecasting future human motion. During training, we explicitly encourage consistency between predicted poses and mutual distances. Extensive evaluations on the existing synthetic and real datasets demonstrate that our approach consistently outperforms the state-of-the-art methods.
Authors: Yangyang Guo, Fangkai Jiao, Zhiqi Shen, Liqiang Nie, Mohan Kankanhalli
Abstract: Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA but somewhat ignored this particular attribute. This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. The dataset is specifically designed to address the challenge of questions that models do not know. To this end, we first augment the existing data via deliberate perturbations on either the image or question. In specific, we carefully ensure that the question-image semantics remain close to the original unperturbed distribution. By this means, the identification of unanswerable questions becomes challenging, setting our dataset apart from others that involve mere image replacement. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models and discover their significant limitations when applied to our dataset. Additionally, we also propose a straightforward method to tackle these unanswerable questions. This dataset, we believe, will serve as a valuable benchmark for enhancing the abstention capability of VQA models, thereby leading to increased trustworthiness of AI systems. We have made the dataset (https://github.com/guoyang9/UNK-VQA) available to facilitate further exploration in this area.
Authors: Simon Wiedemann, Reinhard Heckel
Abstract: Cryogenic electron tomography is a technique for imaging biological samples in 3D. A microscope collects a series of 2D projections of the sample, and the goal is to reconstruct the 3D density of the sample called the tomogram. Reconstruction is difficult as the 2D projections are noisy and can not be recorded from all directions, resulting in a missing wedge of information. Tomograms conventionally reconstructed with filtered back-projection suffer from noise and strong artifacts due to the missing wedge. Here, we propose a deep-learning approach for simultaneous denoising and missing wedge reconstruction called DeepDeWedge. The algorithm requires no ground truth data and is based on fitting a neural network to the 2D projections using a self-supervised loss. DeepDeWedge is simpler than current state-of-the-art approaches for denoising and missing wedge reconstruction, performs competitively and produces more denoised tomograms with higher overall contrast.
Authors: Yan Li, Weiwei Guo, Xue Yang, Ning Liao, Dunyun He, Jiaqi Zhou, Wenxian Yu
Abstract: An increasingly massive number of remote-sensing images spurs the development of extensible object detectors that can detect objects beyond training categories without costly collecting new labeled data. In this paper, we aim to develop open-vocabulary object detection (OVD) technique in aerial images that scales up object vocabulary size beyond training data. The performance of OVD greatly relies on the quality of class-agnostic region proposals and pseudo-labels for novel object categories. To simultaneously generate high-quality proposals and pseudo-labels, we propose CastDet, a CLIP-activated student-teacher open-vocabulary object Detection framework. Our end-to-end framework following the student-teacher self-learning mechanism employs the RemoteCLIP model as an extra omniscient teacher with rich knowledge. By doing so, our approach boosts not only novel object proposals but also classification. Furthermore, we devise a dynamic label queue strategy to maintain high-quality pseudo labels during batch training. We conduct extensive experiments on multiple existing aerial object detection datasets, which are set up for the OVD task. Experimental results demonstrate our CastDet achieving superior open-vocabulary detection performance, e.g., reaching 46.5% mAP on VisDroneZSD novel categories, which outperforms the state-of-the-art open-vocabulary detectors by 21.0% mAP. To our best knowledge, this is the first work to apply and develop the open-vocabulary object detection technique for aerial images. The code is available at https://github.com/lizzy8587/CastDet.
Authors: Yiyang Luo, Ke Lin, Chao Gu
Abstract: Indoor scene modification has emerged as a prominent area within computer vision, particularly for its applications in Augmented Reality (AR) and Virtual Reality (VR). Traditional methods often rely on pre-existing object databases and predetermined object positions, limiting their flexibility and adaptability to new scenarios. In response to this challenge, we present a novel end-to-end multi-modal deep neural network capable of generating point cloud objects seamlessly integrated with their surroundings, driven by textual instructions. Our model revolutionizes scene modification by enabling the creation of new environments with previously unseen object layouts, eliminating the need for pre-stored CAD models. Leveraging Point-E as our generative model, we introduce innovative techniques such as quantized position prediction and Top-K estimation to address the issue of false negatives resulting from ambiguous language descriptions. Furthermore, we conduct comprehensive evaluations to showcase the diversity of generated objects, the efficacy of textual instructions, and the quantitative metrics, affirming the realism and versatility of our model in generating indoor objects. To provide a holistic assessment, we incorporate visual grounding as an additional metric, ensuring the quality and coherence of the scenes produced by our model. Through these advancements, our approach not only advances the state-of-the-art in indoor scene modification but also lays the foundation for future innovations in immersive computing and digital environment creation.
Authors: Quang Nguyen, Truong Vu, Cuong Pham, Anh Tran, Khoi Nguyen
Abstract: In the ever-expanding digital landscape, safeguarding sensitive information remains paramount. This paper delves deep into digital protection, specifically focusing on steganography. While prior research predominantly fixated on individual bit decoding, we address this limitation by introducing ``message accuracy'', a novel metric evaluating the entirety of decoded messages for a more holistic evaluation. In addition, we propose an adaptive universal loss tailored to enhance message accuracy, named Log-Sum-Exponential (LSE) loss, thereby significantly improving the message accuracy of recent approaches. Furthermore, we also introduce a new latent-aware encoding technique in our framework named \Approach, harnessing pretrained Stable Diffusion for advanced steganographic image generation, giving rise to a better trade-off between image quality and message recovery. Throughout experimental results, we have demonstrated the superior performance of the new LSE loss and latent-aware encoding technique. This comprehensive approach marks a significant step in evolving evaluation metrics, refining loss functions, and innovating image concealment techniques, aiming for more robust and dependable information protection.
Authors: Yankun Wu, Yuta Nakashima, Noa Garcia
Abstract: Several studies have raised awareness about social biases in image generative models, demonstrating their predisposition towards stereotypes and imbalances. This paper contributes to this growing body of research by introducing an evaluation protocol that analyzes the impact of gender indicators at every step of the generation process on Stable Diffusion images. Leveraging insights from prior work, we explore how gender indicators not only affect gender presentation but also the representation of objects and layouts within the generated images. Our findings include the existence of differences in the depiction of objects, such as instruments tailored for specific genders, and shifts in overall layouts. We also reveal that neutral prompts tend to produce images more aligned with masculine prompts than their feminine counterparts. We further explore where bias originates through representational disparities and how it manifests in the images via prompt-image dependencies, and provide recommendations for developers and users to mitigate potential bias in image generation.
Authors: Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
Abstract: This paper introduces ViscoNet, a novel one-branch-adapter architecture for concurrent spatial and visual conditioning. Our lightweight model requires trainable parameters and dataset size multiple orders of magnitude smaller than the current state-of-the-art IP-Adapter. However, our method successfully preserves the generative power of the frozen text-to-image (T2I) backbone. Notably, it excels in addressing mode collapse, a pervasive issue previously overlooked. Our novel architecture demonstrates outstanding capabilities in achieving a harmonious visual-text balance, unlocking unparalleled versatility in various human image generation tasks, including pose re-targeting, virtual try-on, stylization, person re-identification, and textile transfer.Demo and code are available from project page https://soon-yau.github.io/visconet/ .
Authors: Denis Zavadski, Johann-Friedrich Feiden, Carsten Rother
Abstract: The field of image synthesis has made tremendous strides forward in the last years. Besides defining the desired output image with text-prompts, an intuitive approach is to additionally use spatial guidance in form of an image, such as a depth map. In state-of-the-art approaches, this guidance is realized by a separate controlling model that controls a pre-trained image generation network, such as a latent diffusion model. Understanding this process from a control system perspective shows that it forms a feedback-control system, where the control module receives a feedback signal from the generation process and sends a corrective signal back. When analysing existing systems, we observe that the feedback signals are timely sparse and have a small number of bits. As a consequence, there can be long delays between newly generated features and the respective corrective signals for these features. It is known that this delay is the most unwanted aspect of any control system. In this work, we take an existing controlling network (ControlNet) and change the communication between the controlling network and the generation process to be of high-frequency and with large-bandwidth. By doing so, we are able to considerably improve the quality of the generated images, as well as the fidelity of the control. Also, the controlling network needs noticeably fewer parameters and hence is about twice as fast during inference and training time. Another benefit of small-sized models is that they help to democratise our field and are likely easier to understand. We call our proposed network ControlNet-XS. When comparing with the state-of-the-art approaches, we outperform them for pixel-level guidance, such as depth, canny-edges, and semantic segmentation, and are on a par for loose keypoint-guidance of human poses. All code and pre-trained models will be made publicly available.
Authors: Yoonwoo Jeong, Jinwoo Lee, Chiheon Kim, Minsu Cho, Doyup Lee
Abstract: Transfer learning of large-scale Text-to-Image (T2I) models has recently shown impressive potential for Novel View Synthesis (NVS) of diverse objects from a single image. While previous methods typically train large models on multi-view datasets for NVS, fine-tuning the whole parameters of T2I models not only demands a high cost but also reduces the generalization capacity of T2I models in generating diverse images in a new domain. In this study, we propose an effective method, dubbed NVS-Adapter, which is a plug-and-play module for a T2I model, to synthesize novel multi-views of visual objects while fully exploiting the generalization capacity of T2I models. NVS-Adapter consists of two main components; view-consistency cross-attention learns the visual correspondences to align the local details of view features, and global semantic conditioning aligns the semantic structure of generated views with the reference view. Experimental results demonstrate that the NVS-Adapter can effectively synthesize geometrically consistent multi-views and also achieve high performance on benchmarks without full fine-tuning of T2I models. The code and data are publicly available in ~\href{https://postech-cvlab.github.io/nvsadapter/}{https://postech-cvlab.github.io/nvsadapter/}.
URLs: https://postech-cvlab.github.io/nvsadapter/, https://postech-cvlab.github.io/nvsadapter/
Authors: Zihao Zhao, Yuxiao Liu, Han Wu, Mei Wang, Yonghao Li, Sheng Wang, Lin Teng, Disheng Liu, Zhiming Cui, Qian Wang, Dinggang Shen
Abstract: Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks, attributable to its generalizability and interpretability. The use of CLIP has recently gained increasing interest in the medical imaging domain, serving both as a pre-training paradigm for aligning medical vision and language, and as a critical component in diverse clinical tasks. With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP paradigm within the domain of medical imaging, regarding both refined CLIP pre-training and CLIP-driven applications. In this study, We (1) start with a brief introduction to the fundamentals of CLIP methodology. (2) Then, we investigate the adaptation of CLIP pre-training in the medical domain, focusing on how to optimize CLIP given characteristics of medical images and reports. (3) Furthermore, we explore the practical utilization of CLIP pre-trained models in various tasks, including classification, dense prediction, and cross-modal tasks. (4) Finally, we discuss existing limitations of CLIP in the context of medical imaging and propose forward-looking directions to address the demands of medical imaging domain. We expect that this comprehensive survey will provide researchers in the field of medical image analysis with a holistic understanding of the CLIP paradigm and its potential implications. The project page can be found on https://github.com/zhaozh10/Awesome-CLIP-in-Medical-Imaging.
URLs: https://github.com/zhaozh10/Awesome-CLIP-in-Medical-Imaging.
Authors: Jiangning Zhang, Xuhai Chen, Yabiao Wang, Chengjie Wang, Yong Liu, Xiangtai Li, Ming-Hsuan Yang, Dacheng Tao
Abstract: This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultaneously testing both normal and anomaly images across multiple classes. Existing reconstruction-based methods typically adopt pyramidal networks as encoders and decoders to obtain multi-resolution features, often involving complex sub-modules with extensive handcraft engineering. In contrast, a plain Vision Transformer (ViT) showcasing a more straightforward architecture has proven effective in multiple domains, including detection and segmentation tasks. It is simpler, more effective, and elegant. Following this spirit, we explore the use of only plain ViT features for MUAD. We first abstract a Meta-AD concept by synthesizing current reconstruction-based methods. Subsequently, we instantiate a novel ViT-based ViTAD structure, designed incrementally from both global and local perspectives. This model provide a strong baseline to facilitate future research. Additionally, this paper uncovers several intriguing findings for further investigation. Finally, we comprehensively and fairly benchmark various approaches using eight metrics. Utilizing a basic training regimen with only an MSE loss, ViTAD achieves state-of-the-art results and efficiency on MVTec AD, VisA, and Uni-Medical datasets. \Eg, achieving 85.4 mAD that surpasses UniAD by +3.0 for the MVTec AD dataset, and it requires only 1.1 hours and 2.3G GPU memory to complete model training on a single V100 that can serve as a strong baseline to facilitate the development of future research. Full code is available at https://zhangzjn.github.io/projects/ViTAD/.
Authors: Yifeng Ma, Shiwei Zhang, Jiayu Wang, Xiang Wang, Yingya Zhang, Zhidong Deng
Abstract: Emotional talking head generation has attracted growing attention. Previous methods, which are mainly GAN-based, still struggle to consistently produce satisfactory results across diverse emotions and cannot conveniently specify personalized emotions. In this work, we leverage powerful diffusion models to address the issue and propose DreamTalk, a framework that employs meticulous design to unlock the potential of diffusion models in generating emotional talking heads. Specifically, DreamTalk consists of three crucial components: a denoising network, a style-aware lip expert, and a style predictor. The diffusion-based denoising network can consistently synthesize high-quality audio-driven face motions across diverse emotions. To enhance lip-motion accuracy and emotional fullness, we introduce a style-aware lip expert that can guide lip-sync while preserving emotion intensity. To more conveniently specify personalized emotions, a diffusion-based style predictor is utilized to predict the personalized emotion directly from the audio, eliminating the need for extra emotion reference. By this means, DreamTalk can consistently generate vivid talking faces across diverse emotions and conveniently specify personalized emotions. Extensive experiments validate DreamTalk's effectiveness and superiority. The code is available at https://github.com/ali-vilab/dreamtalk.
Authors: Minhyun Lee, Song Park, Byeongho Heo, Dongyoon Han, Hyunjung Shim
Abstract: Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting in significant storage requirements. This storage challenge is a critical bottleneck for scaling up models. A recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i.e., tokens) as network inputs for vision classification. This approach achieved 90% of the performance of a model trained on full-pixel images with only 1% of the storage. While SeiT needs labeled data, its potential in scenarios beyond fully supervised learning remains largely untapped. In this paper, we extend SeiT by integrating Masked Token Modeling (MTM) for self-supervised pre-training. Recognizing that self-supervised approaches often demand more data due to the lack of labels, we introduce TokenAdapt and ColorAdapt. These methods facilitate comprehensive token-friendly data augmentation, effectively addressing the increased data requirements of self-supervised learning. We evaluate our approach across various scenarios, including storage-efficient ImageNet-1k classification, fine-grained classification, ADE-20k semantic segmentation, and robustness benchmarks. Experimental results demonstrate consistent performance improvement in diverse experiments, validating the effectiveness of our method. Code is available at https://github.com/naver-ai/seit.
Authors: Partha Ghosh, Soubhik Sanyal, Cordelia Schmid, Bernhard Sch\"olkopf
Abstract: We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies, with attention to computational and dataset efficiency. To capture long spatio-temporal dependencies, our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks developed for three-dimensional object representation and employs a single latent code to model an entire video clip. Individual video frames are then synthesized from an intermediate tri-plane representation, which itself is derived from the primary latent code. This novel strategy more than halves the computational complexity measured in FLOPs compared to the most efficient state-of-the-art methods. Consequently, our approach facilitates the efficient and temporally coherent generation of videos. Moreover, our joint frame modeling approach, in contrast to autoregressive methods, mitigates the generation of visual artifacts. We further enhance the model's capabilities by integrating an optical flow-based module within our Generative Adversarial Network (GAN) based generator architecture, thereby compensating for the constraints imposed by a smaller generator size. As a result, our model synthesizes high-fidelity video clips at a resolution of $256\times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps. The efficacy and versatility of our approach are empirically validated through qualitative and quantitative assessments across three different datasets comprising both synthetic and real video clips. We will make our training and inference code public.
Authors: Shaoheng Fang, Rui Ye, Wenhao Wang, Zuhong Liu, Yuxiao Wang, Yafei Wang, Siheng Chen, Yanfeng Wang
Abstract: Roadside unit (RSU) can significantly improve the safety and robustness of autonomous vehicles through Vehicle-to-Everything (V2X) communication. Currently, the usage of a single RSU mainly focuses on real-time inference and V2X collaboration, while neglecting the potential value of the high-quality data collected by RSU sensors. Integrating the vast amounts of data from numerous RSUs can provide a rich source of data for model training. However, the absence of ground truth annotations and the difficulty of transmitting enormous volumes of data are two inevitable barriers to fully exploiting this hidden value. In this paper, we introduce FedRSU, an innovative federated learning framework for self-supervised scene flow estimation. In FedRSU, we present a recurrent self-supervision training paradigm, where for each RSU, the scene flow prediction of points at every timestamp can be supervised by its subsequent future multi-modality observation. Another key component of FedRSU is federated learning, where multiple devices collaboratively train an ML model while keeping the training data local and private. With the power of the recurrent self-supervised learning paradigm, FL is able to leverage innumerable underutilized data from RSU. To verify the FedRSU framework, we construct a large-scale multi-modality dataset RSU-SF. The dataset consists of 17 RSU clients, covering various scenarios, modalities, and sensor settings. Based on RSU-SF, we show that FedRSU can greatly improve model performance in ITS and provide a comprehensive benchmark under diverse FL scenarios. To the best of our knowledge, we provide the first real-world LiDAR-camera multi-modal dataset and benchmark for the FL community.
Authors: Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Mingli Zhu, Ruotong Wang, Li Liu, Chao Shen
Abstract: As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed successively or concurrently, in the status of a rapid arms race. However, mainly due to the diverse settings, and the difficulties of implementation and reproducibility of existing works, there is a lack of a unified and standardized benchmark of backdoor learning, causing unfair comparisons, and unreliable conclusions (e.g., misleading, biased or even false conclusions). Consequently, it is difficult to evaluate the current progress and design the future development roadmap of this literature. To alleviate this dilemma, we build a comprehensive benchmark of backdoor learning called BackdoorBench. Our benchmark makes three valuable contributions to the research community. 1) We provide an integrated implementation of state-of-the-art (SOTA) backdoor learning algorithms (currently including 16 attack and 27 defense algorithms), based on an extensible modular-based codebase. 2) We conduct comprehensive evaluations of 12 attacks against 16 defenses, with 5 poisoning ratios, based on 4 models and 4 datasets, thus 11,492 pairs of evaluations in total. 3) Based on above evaluations, we present abundant analysis from 8 perspectives via 18 useful analysis tools, and provide several inspiring insights about backdoor learning. We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning. Finally, we have created a user-friendly website at http://backdoorbench.com, which collects all important information of BackdoorBench, including codebase, docs, leaderboard, and model Zoo.
Authors: Richard Vogg, Timo L\"uddecke, Jonathan Henrich, Sharmita Dey, Matthias Nuske, Valentin Hassler, Derek Murphy, Julia Fischer, Julia Ostner, Oliver Sch\"ulke, Peter M. Kappeler, Claudia Fichtel, Alexander Gail, Stefan Treue, Hansj\"org Scherberger, Florentin W\"org\"otter, Alexander S. Ecker
Abstract: Advances in computer vision as well as increasingly widespread video-based behavioral monitoring have great potential for transforming how we study animal cognition and behavior. However, there is still a fairly large gap between the exciting prospects and what can actually be achieved in practice today, especially in videos from the wild. With this perspective paper, we want to contribute towards closing this gap, by guiding behavioral scientists in what can be expected from current methods and steering computer vision researchers towards problems that are relevant to advance research in animal behavior. We start with a survey of the state-of-the-art methods for computer vision problems that are directly relevant to the video-based study of animal behavior, including object detection, multi-individual tracking, individual identification, and (inter)action recognition. We then review methods for effort-efficient learning, which is one of the biggest challenges from a practical perspective. Finally, we close with an outlook into the future of the emerging field of computer vision for animal behavior, where we argue that the field should develop approaches to unify detection, tracking, identification and (inter)action recognition in a single, video-based framework.
Authors: Zicheng Zhang, Haoning Wu, Erli Zhang, Guangtao Zhai, Weisi Lin
Abstract: The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and understanding remains a yet-to-explore domain. To this end, we design benchmark settings to emulate human language responses related to low-level vision: the low-level visual perception (A1) via visual question answering related to low-level attributes (e.g. clarity, lighting); and the low-level visual description (A2), on evaluating MLLMs for low-level text descriptions. Furthermore, given that pairwise comparison can better avoid ambiguity of responses and has been adopted by many human experiments, we further extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. Specifically, for perception (A1), we carry out the LLVisionQA+ dataset, comprising 2,990 single images and 1,999 image pairs each accompanied by an open-ended question about its low-level features; for description (A2), we propose the LLDescribe+ dataset, evaluating MLLMs for low-level descriptions on 499 single images and 450 pairs. Additionally, we evaluate MLLMs on assessment (A3) ability, i.e. predicting score, by employing a softmax-based approach to enable all MLLMs to generate quantifiable quality ratings, tested against human opinions in 7 image quality assessment (IQA) datasets. With 24 MLLMs under evaluation, we demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than single image evaluations (like humans). We hope that our benchmark will motivate further research into uncovering and enhancing these nascent capabilities of MLLMs. Datasets will be available at https://github.com/Q-Future/Q-Bench.
Authors: Yunwei Bai, Ying Kiat Tan, Shiming Chen, Yao Shu, Tsuhan Chen
Abstract: Few-shot-learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labeled samples of the new classes (support set) as reference. So far, plenty of algorithms involve training data augmentation to improve the generalization capability of FSL models, but outlier queries or support images during inference can still pose great generalization challenges. In this work, to reduce the bias caused by the outlier samples, we generate additional test-class samples by combining original samples with suitable train-class samples via a generative image combiner. Then, we obtain averaged features via an augmentor, which leads to more typical representations through the averaging. We experimentally and theoretically demonstrate the effectiveness of our method, e.g., obtaining a test accuracy improvement proportion of around 10% (e.g., from 46.86% to 53.28%) for trained FSL models. Importantly, given pretrained image combiner, our method is training-free for off-the-shelf FSL models, whose performance can be improved without extra datasets nor further training of the models themselves.
Authors: Yushi Lan, Fangzhou Hong, Shuai Yang, Shangchen Zhou, Xuyi Meng, Bo Dai, Xingang Pan, Chen Change Loy
Abstract: The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled. This paper introduces a novel framework called LN3Diff to address this gap and enable fast, high-quality, and generic conditional 3D generation. Our approach harnesses a 3D-aware architecture and variational autoencoder (VAE) to encode the input image into a structured, compact, and 3D latent space. The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field. Through training a diffusion model on this 3D-aware latent space, our method achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation across various datasets. Moreover, it surpasses existing 3D diffusion methods in terms of inference speed, requiring no per-instance optimization. Our proposed LN3Diff presents a significant advancement in 3D generative modeling and holds promise for various applications in 3D vision and graphics tasks.
Authors: Kaile Du, Yifan Zhou, Fan Lyu, Yuyang Li, Chen Lu, Guangcan Liu
Abstract: The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unavailable. This issue leads to a proliferation of false-positive errors due to erroneously high confidence multi-label predictions, exacerbating catastrophic forgetting within the disjoint label space. In this paper, we aim to refine multi-label confidence calibration in MLCIL and propose a Confidence Self-Calibration (CSC) approach. Firstly, for label relationship calibration, we introduce a class-incremental graph convolutional network that bridges the isolated label spaces by constructing learnable, dynamically extended label relationship graph. Then, for confidence calibration, we present a max-entropy regularization for each multi-label increment, facilitating confidence self-calibration through the penalization of over-confident output distributions. Our approach attains new state-of-the-art results in MLCIL tasks on both MS-COCO and PASCAL VOC datasets, with the calibration of label confidences confirmed through our methodology.
Authors: Ting-Kang Yen, Igor Morawski, Shusil Dangi, Kai He, Chung-Yi Lin, Jia-Fong Yeh, Hung-Ting Su, Winston Hsu
Abstract: Event-based object detection has recently garnered attention in the computer vision community due to the exceptional properties of event cameras, such as high dynamic range and no motion blur. However, feature asynchronism and sparsity cause invisible objects due to no relative motion to the camera, posing a significant challenge in the task. Prior works have studied various implicit-learned memories to retain as many temporal cues as possible. However, implicit memories still struggle to preserve long-term features effectively. In this paper, we consider those invisible objects as pseudo-occluded objects and aim to detect them by tracking through occlusions. Firstly, we introduce the visibility attribute of objects and contribute an auto-labeling algorithm to not only clean the existing event camera dataset but also append additional visibility labels to it. Secondly, we exploit tracking strategies for pseudo-occluded objects to maintain their permanence and retain their bounding boxes, even when features have not been available for a very long time. These strategies can be treated as an explicit-learned memory guided by the tracking objective to record the displacements of objects across frames. Lastly, we propose a spatio-temporal feature aggregation module to enrich the latent features and a consistency loss to increase the robustness of the overall pipeline. We conduct comprehensive experiments to verify our method's effectiveness where still objects are retained, but real occluded objects are discarded. The results demonstrate that (1) the additional visibility labels can assist in supervised training, and (2) our method outperforms state-of-the-art approaches with a significant improvement of 7.9% absolute mAP.
Authors: Tiantian Geng, Teng Wang, Yanfu Zhang, Jinming Duan, Weili Guan, Feng Zheng, Ling shao
Abstract: Video localization tasks aim to temporally locate specific instances in videos, including temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods over-specialize on each task, overlooking the fact that these instances often occur in the same video to form the complete video content. In this work, we present UniAV, a Unified Audio-Visual perception network, to achieve joint learning of TAL, SED and AVEL tasks for the first time. UniAV can leverage diverse data available in task-specific datasets, allowing the model to learn and share mutually beneficial knowledge across tasks and modalities. To tackle the challenges posed by substantial variations in datasets (size/domain/duration) and distinct task characteristics, we propose to uniformly encode visual and audio modalities of all videos to derive generic representations, while also designing task-specific experts to capture unique knowledge for each task. Besides, we develop a unified language-aware classifier by utilizing a pre-trained text encoder, enabling the model to flexibly detect various types of instances and previously unseen ones by simply changing prompts during inference. UniAV outperforms its single-task counterparts by a large margin with fewer parameters, achieving on-par or superior performances compared to state-of-the-art task-specific methods across ActivityNet 1.3, DESED and UnAV-100 benchmarks.
Authors: Babak Poorebrahim Gilkalaye, Shubhabrata Mukherjee, Reza Derakhshani
Abstract: Generative AI has revolutionized modern machine learning by providing unprecedented realism, diversity, and efficiency in data generation. This technology holds immense potential for biometrics, including for securing sensitive and personally identifiable information. Given the irrevocability of biometric samples and mounting privacy concerns, biometric template security and secure matching are among the most sought-after features of modern biometric systems. This paper proposes a novel obfuscation method using Generative AI to enhance biometric template security. Our approach utilizes synthetic facial images generated by a Generative Adversarial Network (GAN) as "random chaff points" within a secure vault system. Our method creates n sub-templates from the original template, each obfuscated with m GAN chaff points. During verification, s closest vectors to the biometric query are retrieved from each vault and combined to generate hash values, which are then compared with the stored hash value. Thus, our method safeguards user identities during the training and deployment phases by employing the GAN-generated synthetic images. Our protocol was tested using the AT&T, GT, and LFW face datasets, achieving ROC areas under the curve of 0.99, 0.99, and 0.90, respectively. Our results demonstrate that the proposed method can maintain high accuracy and reasonable computational complexity comparable to those unprotected template methods while significantly enhancing security and privacy, underscoring the potential of Generative AI in developing proactive defensive strategies for biometric systems.
Authors: Shiwei Lian, Feitian Zhang
Abstract: The generalization of the end-to-end deep reinforcement learning (DRL) for object-goal visual navigation is a long-standing challenge since object classes and placements vary in new test environments. Learning domain-independent visual representation is critical for enabling the trained DRL agent with the ability to generalize to unseen scenes and objects. In this letter, a target-directed attention network (TDANet) is proposed to learn the end-to-end object-goal visual navigation policy with zero-shot ability. TDANet features a novel target attention (TA) module that learns both the spatial and semantic relationships among objects to help TDANet focus on the most relevant observed objects to the target. With the Siamese architecture (SA) design, TDANet distinguishes the difference between the current and target states and generates the domain-independent visual representation. To evaluate the navigation performance of TDANet, extensive experiments are conducted in the AI2-THOR embodied AI environment. The simulation results demonstrate a strong generalization ability of TDANet to unseen scenes and target objects, with higher navigation success rate (SR) and success weighted by length (SPL) than other state-of-the-art models. TDANet is finally deployed on a wheeled robot in real scenes, demonstrating satisfactory generalization of TDANet to the real world.
Authors: Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, Philip Torr
Abstract: Continual segmentation has not yet tackled the challenge of improving open-vocabulary segmentation models with training data for accurate segmentation across large, continually expanding vocabularies. We discover that traditional continual training results in severe catastrophic forgetting, failing to outperform a zero-shot segmentation baseline. We introduce a novel training-free strategy, kNN-CLIP, which augments the model with a database of instance embeddings for semantic and panoptic segmentation that achieves zero forgetting. We demonstrate that kNN-CLIP can adapt to continually growing vocabularies without the need for retraining or large memory costs. kNN-CLIP enables open-vocabulary segmentation methods to expand their vocabularies on any domain with a single pass through the data, while only storing compact embeddings. This approach minimizes both compute and memory costs. kNN-CLIP achieves state-of-the-art performance across large-vocabulary semantic and panoptic segmentation datasets. We hope kNN-CLIP represents a significant step forward in enabling more efficient and adaptable continual segmentation, paving the way for advances in real-world large-vocabulary continual segmentation methods.
Authors: Zou Zhen, Yu Hu, Zhao Feng
Abstract: Images corrupted by rain streaks often lose vital frequency information for perception, and image deraining aims to solve this issue which relies on global and local degradation modeling. Recent studies have witnessed the effectiveness and efficiency of Mamba for perceiving global and local information based on its exploiting local correlation among patches, however, rarely attempts have been explored to extend it with frequency analysis for image deraining, limiting its ability to perceive global degradation that is relevant to frequency modeling (e.g. Fourier transform). In this paper, we propose FreqMamba, an effective and efficient paradigm that leverages the complementary between Mamba and frequency analysis for image deraining. The core of our method lies in extending Mamba with frequency analysis from two perspectives: extending it with frequency-band for exploiting frequency correlation, and connecting it with Fourier transform for global degradation modeling. Specifically, FreqMamba introduces complementary triple interaction structures including spatial Mamba, frequency band Mamba, and Fourier global modeling. Frequency band Mamba decomposes the image into sub-bands of different frequencies to allow 2D scanning from the frequency dimension. Furthermore, leveraging Mamba's unique data-dependent properties, we use rainy images at different scales to provide degradation priors to the network, thereby facilitating efficient training. Extensive experiments show that our method outperforms state-of-the-art methods both visually and quantitatively.
Authors: Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Eric Granger
Abstract: Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-level labels. The absence of bounding box (bbox) supervision during training raises challenges in the literature for hyper-parameter tuning, model selection, and evaluation. WSOL methods rely on a validation set with bbox annotations for model selection, and a test set with bbox annotations for threshold estimation for producing bboxes from localization maps. This approach, however, is not aligned with the WSOL setting as these annotations are typically unavailable in real-world scenarios. Our initial empirical analysis shows a significant decline in LOC performance when model selection and threshold estimation rely solely on class labels and the image itself, respectively, compared to using manual bbox annotations. This highlights the importance of incorporating bbox labels for optimal model performance. In this paper, a new WSOL evaluation protocol is proposed that provides LOC information without the need for manual bbox annotations. In particular, we generated noisy pseudo-boxes from a pretrained off-the-shelf region proposal method such as Selective Search, CLIP, and RPN for model selection. These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations. Our experiments with several WSOL methods on ILSVRC and CUB datasets show that using the proposed pseudo-bboxes for validation facilitates the model selection and threshold estimation, with LOC performance comparable to those selected using GT bboxes on the validation set and threshold estimation on the test set. It also outperforms models selected using class-level labels, and then dynamically thresholded based solely on LOC maps.
Authors: Zhanjie Zhang, Quanwei Zhang, Huaizhong Lin, Wei Xing, Juncheng Mo, Shuaicheng Huang, Jinheng Xie, Guangyuan Li, Junsheng Luan, Lei Zhao, Dalong Zhang, Lixia Chen
Abstract: Artistic style transfer aims to transfer the learned artistic style onto an arbitrary content image, generating artistic stylized images. Existing generative adversarial network-based methods fail to generate highly realistic stylized images and always introduce obvious artifacts and disharmonious patterns. Recently, large-scale pre-trained diffusion models opened up a new way for generating highly realistic artistic stylized images. However, diffusion model-based methods generally fail to preserve the content structure of input content images well, introducing some undesired content structure and style patterns. To address the above problems, we propose a novel pre-trained diffusion-based artistic style transfer method, called LSAST, which can generate highly realistic artistic stylized images while preserving the content structure of input content images well, without bringing obvious artifacts and disharmonious style patterns. Specifically, we introduce a Step-aware and Layer-aware Prompt Space, a set of learnable prompts, which can learn the style information from the collection of artworks and dynamically adjusts the input images' content structure and style pattern. To train our prompt space, we propose a novel inversion method, called Step-ware and Layer-aware Prompt Inversion, which allows the prompt space to learn the style information of the artworks collection. In addition, we inject a pre-trained conditional branch of ControlNet into our LSAST, which further improved our framework's ability to maintain content structure. Extensive experiments demonstrate that our proposed method can generate more highly realistic artistic stylized images than the state-of-the-art artistic style transfer methods.
Authors: Yilong Chen, Zongyi Xu, xiaoshui Huang, Ruicheng Zhang, Xinqi Jiang, Xinbo Gao
Abstract: Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely unexplored. To tackle this gap, we implement LiDAR semantic segmentation using scatter image annotation, effectively integrating an efficient annotation strategy with network training. Specifically, we propose employing scatter images to annotate LiDAR point clouds, combining a pre-trained optical flow estimation network with a foundation image segmentation model to rapidly propagate manual annotations into dense labels for both images and point clouds. Moreover, we propose ScatterNet, a network that includes three pivotal strategies to reduce the performance gap caused by such annotations. Firstly, it utilizes dense semantic labels as supervision for the image branch, alleviating the modality imbalance between point clouds and images. Secondly, an intermediate fusion branch is proposed to obtain multimodal texture and structural features. Lastly, a perception consistency loss is introduced to determine which information needs to be fused and which needs to be discarded during the fusion process. Extensive experiments on the nuScenes and SemanticKITTI datasets have demonstrated that our method requires less than 0.02% of the labeled points to achieve over 95% of the performance of fully-supervised methods. Notably, our labeled points are only 5% of those used in the most advanced weakly supervised methods.
Authors: Xuanyu Zhang, Youmin Xu, Runyi Li, Jiwen Yu, Weiqi Li, Zhipei Xu, Jian Zhang
Abstract: AI-generated video has revolutionized short video production, filmmaking, and personalized media, making video local editing an essential tool. However, this progress also blurs the line between reality and fiction, posing challenges in multimedia forensics. To solve this urgent issue, V2A-Mark is proposed to address the limitations of current video tampering forensics, such as poor generalizability, singular function, and single modality focus. Combining the fragility of video-into-video steganography with deep robust watermarking, our method can embed invisible visual-audio localization watermarks and copyright watermarks into the original video frames and audio, enabling precise manipulation localization and copyright protection. We also design a temporal alignment and fusion module and degradation prompt learning to enhance the localization accuracy and decoding robustness. Meanwhile, we introduce a sample-level audio localization method and a cross-modal copyright extraction mechanism to couple the information of audio and video frames. The effectiveness of V2A-Mark has been verified on a visual-audio tampering dataset, emphasizing its superiority in localization precision and copyright accuracy, crucial for the sustainable development of video editing in the AIGC video era.
Authors: Zhihang Lin, Mingbao Lin, Luxi Lin, Rongrong Ji
Abstract: Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens Withdrawal (VTW), a plug-and-play module to boost MLLMs for rapid inference. Our approach is inspired by two intriguing phenomena we have observed: (1) the attention sink phenomenon that is prevalent in LLMs also persists in MLLMs, suggesting that initial tokens and nearest tokens receive the majority of attention, while middle vision tokens garner minimal attention in deep layers; (2) the presence of information migration, which implies that visual information is transferred to subsequent text tokens within the first few layers of MLLMs. As per our findings, we conclude that vision tokens are unnecessary in the deep layers of MLLMs. Thus, we strategically withdraw them at a certain layer, enabling only text tokens to engage in subsequent layers. To pinpoint the ideal layer for VTW, we initially analyze a limited set of tiny datasets and choose the first layer that meets the Kullback-Leibler divergence criterion. Our VTW approach can cut computational overhead by over 40\% across diverse multimodal tasks while maintaining performance. Our code is released at \url{https://github.com/lzhxmu/VTW}.
Authors: Liming Han, Zhaoxiang Liu, Shiguo Lian
Abstract: Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from the source image to 3D features with the help of a reference image and matches to the 2D features extracted from the destination image by the coarse-to-fine 3D matching. Our key discovery is that by introducing the reference image, the source image's fine points are screened and furtherly their feature descriptors are enriched from 2D to 3D, which improves the match performance with the destination image. Experimental results on multiple datasets show that the proposed method achieves the state-of-the-art on the tasks of homography estimation, pose estimation and visual localization especially in challenging scenes.
Authors: Fei Wang, Jun Cheng
Abstract: Most existing methods often rely on complex models to predict scene depth with high accuracy, resulting in slow inference that is not conducive to deployment. To better balance precision and speed, we first designed SmallDepth based on sparsity. Second, to enhance the feature representation ability of SmallDepth during training under the condition of equal complexity during inference, we propose an equivalent transformation module(ETM). Third, to improve the ability of each layer in the case of a fixed SmallDepth to perceive different context information and improve the robustness of SmallDepth to the left-right direction and illumination changes, we propose pyramid loss. Fourth, to further improve the accuracy of SmallDepth, we utilized the proposed function approximation loss (APX) to transfer knowledge in the pretrained HQDecv2, obtained by optimizing the previous HQDec to address grid artifacts in some regions, to SmallDepth. Extensive experiments demonstrate that each proposed component improves the precision of SmallDepth without changing the complexity of SmallDepth during inference, and the developed approach achieves state-of-the-art results on KITTI at an inference speed of more than 500 frames per second and with approximately 2 M parameters. The code and models will be publicly available at https://github.com/fwucas/FA-Depth.
Authors: Yibin Wang, Weizhong Zhang, Changhai Zhou, Cheng Jin
Abstract: Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-level guidance during training. Besides, their text encoders, pre-trained on a single font type, struggle to adapt to the diverse font styles encountered in practical applications. Consequently, these methods suffer from character distortion, repetition, and absence, particularly in polystylistic scenarios. To this end, this paper proposes DreamText for high-fidelity scene text synthesis. Our key idea is to reconstruct the diffusion training process, introducing more refined guidance tailored to this task, to expose and rectify the model's attention at the character level and strengthen its learning of text regions. This transformation poses a hybrid optimization challenge, involving both discrete and continuous variables. To effectively tackle this challenge, we employ a heuristic alternate optimization strategy. Meanwhile, we jointly train the text encoder and generator to comprehensively learn and utilize the diverse font present in the training dataset. This joint training is seamlessly integrated into the alternate optimization process, fostering a synergistic relationship between learning character embedding and re-estimating character attention. Specifically, in each step, we first encode potential character-generated position information from cross-attention maps into latent character masks. These masks are then utilized to update the representation of specific characters in the current step, which, in turn, enables the generator to correct the character's attention in the subsequent steps. Both qualitative and quantitative results demonstrate the superiority of our method to the state of the art.
Authors: Zeen Song, Siyu Zhao, Xingyu Zhang, Jiangmeng Li, Changwen Zheng, Wenwen Qiang
Abstract: Large-scale pre-trained vision-language models such as CLIP have been widely applied to a variety of downstream scenarios. In real-world applications, the CLIP model is often utilized in more diverse scenarios than those encountered during its training, a challenge known as the out-of-distribution (OOD) problem. However, our experiments reveal that CLIP performs unsatisfactorily in certain domains. Through a causal analysis, we find that CLIP's current prediction process cannot guarantee a low OOD risk. The lowest OOD risk can be achieved when the prediction process is based on invariant causal mechanisms, i.e., predicting solely based on invariant latent factors. However, theoretical analysis indicates that CLIP does not identify these invariant latent factors. Therefore, we propose the Invariant Causal Mechanism for CLIP (CLIP-ICM), a framework that first identifies invariant latent factors using interventional data and then performs invariant predictions across various domains. Our method is simple yet effective, without significant computational overhead. Experimental results demonstrate that CLIP-ICM significantly improves CLIP's performance in OOD scenarios.
Authors: Yuzhou Ji, He Zhu, Junshu Tang, Wuyi Liu, Zhizhong Zhang, Yuan Xie, Xin Tan
Abstract: The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications. However, it is a challenging task to achieve high quality, efficiency and zero-shot ability at the same time with semantics in radiance fields. In this work, we present FastLGS, an approach that supports real-time open-vocabulary query within 3D Gaussian Splatting (3DGS) under high resolution. We propose the semantic feature grid to save multi-view CLIP features which are extracted based on Segment Anything Model (SAM) masks, and map the grids to low dimensional features for semantic field training through 3DGS. Once trained, we can restore pixel-aligned CLIP embeddings through feature grids from rendered features for open-vocabulary queries. Comparisons with other state-of-the-art methods prove that FastLGS can achieve the first place performance concerning both speed and accuracy, where FastLGS is 98x faster than LERF and 4x faster than LangSplat. Meanwhile, experiments show that FastLGS is adaptive and compatible with many downstream tasks, such as 3D segmentation and 3D object inpainting, which can be easily applied to other 3D manipulation systems.
Authors: Hai-Long Sun, Da-Wei Zhou, Yang Li, Shiyin Lu, Chao Yi, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye
Abstract: The rapid development of Multimodal Large Language Models (MLLMs) like GPT-4V has marked a significant step towards artificial general intelligence. Existing methods mainly focus on aligning vision encoders with LLMs through supervised fine-tuning (SFT) to endow LLMs with multimodal abilities, making MLLMs' inherent ability to react to multiple languages progressively deteriorate as the training process evolves. We empirically find that the imbalanced SFT datasets, primarily composed of English-centric image-text pairs, lead to significantly reduced performance in non-English languages. This is due to the failure of aligning the vision encoder and LLM with multilingual tokens during the SFT process. In this paper, we introduce Parrot, a novel method that utilizes textual guidance to drive visual token alignment at the language level. Parrot makes the visual tokens condition on diverse language inputs and uses Mixture-of-Experts (MoE) to promote the alignment of multilingual tokens. Specifically, to enhance non-English visual tokens alignment, we compute the cross-attention using the initial visual features and textual embeddings, the result of which is then fed into the MoE router to select the most relevant experts. The selected experts subsequently convert the initial visual tokens into language-specific visual tokens. Moreover, considering the current lack of benchmarks for evaluating multilingual capabilities within the field, we collect and make available a Massive Multilingual Multimodal Benchmark which includes 6 languages, 15 categories, and 12,000 questions, named as MMMB. Our method not only demonstrates state-of-the-art performance on multilingual MMBench and MMMB, but also excels across a broad range of multimodal tasks. Both the source code and the training dataset of Parrot will be made publicly available. Code is available at: https://github.com/AIDC-AI/Parrot.
Authors: Yimian Dai, Minrui Zou, Yuxuan Li, Xiang Li, Kang Ni, Jian Yang
Abstract: Synthetic Aperture Radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive, ambiguous targets. While deep neural networks have advanced SAR target detection, their intrinsic low-frequency bias and static post-training weights falter with coherent noise and preserving subtle details across heterogeneous terrains. Motivated by traditional SAR image denoising, we propose DenoDet, a network aided by explicit frequency domain transform to calibrate convolutional biases and pay more attention to high-frequencies, forming a natural multi-scale subspace representation to detect targets from the perspective of multi-subspace denoising. We design TransDeno, a dynamic frequency domain attention module that performs as a transform domain soft thresholding operation, dynamically denoising across subspaces by preserving salient target signals and attenuating noise. To adaptively adjust the granularity of subspace processing, we also propose a deformable group fully-connected layer (DeGroFC) that dynamically varies the group conditioned on the input features. Without bells and whistles, our plug-and-play TransDeno sets state-of-the-art scores on multiple SAR target detection datasets. The code is available at https://github.com/GrokCV/GrokSAR.
Authors: Yuming Zhang, Shouxin Zhang, Peizhe Wang, Feiyu Zhu, Dongzhi Guan, Junhao Su, Jiabin Liu, Changpeng Cai
Abstract: Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent research has sought to address these issues, with one promising approach being local learning. This method involves partitioning the backbone network into gradient-isolated modules and manually designing auxiliary networks to train these local modules. Existing methods often neglect the interaction of information between local modules, leading to myopic issues and a performance gap compared to E2E training. To address these limitations, we propose the Multilaminar Leap Augmented Auxiliary Network (MLAAN). Specifically, MLAAN comprises Multilaminar Local Modules (MLM) and Leap Augmented Modules (LAM). MLM captures both local and global features through independent and cascaded auxiliary networks, alleviating performance issues caused by insufficient global features. However, overly simplistic auxiliary networks can impede MLM's ability to capture global information. To address this, we further design LAM, an enhanced auxiliary network that uses the Exponential Moving Average (EMA) method to facilitate information exchange between local modules, thereby mitigating the shortsightedness resulting from inadequate interaction. The synergy between MLM and LAM has demonstrated excellent performance. Our experiments on the CIFAR-10, STL-10, SVHN, and ImageNet datasets show that MLAAN can be seamlessly integrated into existing local learning frameworks, significantly enhancing their performance and even surpassing end-to-end (E2E) training methods, while also reducing GPU memory consumption.
Authors: Amir Masoud Rahmani, Parisa Khoshvaght, Hamid Alinejad-Rokny, Samira Sadeghi, Parvaneh Asghari, Zohre Arabi, Mehdi Hosseinzadeh
Abstract: Acute lymphoblastic leukemia (ALL) severity is determined by the presence and ratios of blast cells (abnormal white blood cells) in both bone marrow and peripheral blood. Manual diagnosis of this disease is a tedious and time-consuming operation, making it difficult for professionals to accurately examine blast cell characteristics. To address this difficulty, researchers use deep learning and machine learning. In this paper, a ResNet-based feature extractor is utilized to detect ALL, along with a variety of feature selectors and classifiers. To get the best results, a variety of transfer learning models, including the Resnet, VGG, EfficientNet, and DensNet families, are used as deep feature extractors. Following extraction, different feature selectors are used, including Genetic algorithm, PCA, ANOVA, Random Forest, Univariate, Mutual information, Lasso, XGB, Variance, and Binary ant colony. After feature qualification, a variety of classifiers are used, with MLP outperforming the others. The recommended technique is used to categorize ALL and HEM in the selected dataset which is C-NMC 2019. This technique got an impressive 90.71% accuracy and 95.76% sensitivity for the relevant classifications, and its metrics on this dataset outperformed others.
Authors: Hao Liang, Jiapeng Li, Tianyi Bai, Xijie Huang, Linzhuang Sun, Zhengren Wang, Conghui He, Bin Cui, Chong Chen, Wentao Zhang
Abstract: Recently, with the rise of web videos, managing and understanding large-scale video datasets has become increasingly important. Video Large Language Models (VideoLLMs) have emerged in recent years due to their strong video understanding capabilities. However, training and inference processes for VideoLLMs demand vast amounts of data, presenting significant challenges to data management, particularly regarding efficiency, robustness, and effectiveness. In this work, we present KeyVideoLLM, a text-video frame similarity-based keyframe selection method designed to manage VideoLLM data efficiently, robustly, and effectively. Specifically, KeyVideoLLM achieves a remarkable data compression rate of up to 60.9 times, substantially lowering disk space requirements, which proves its high efficiency. Additionally, it maintains a 100% selection success rate across all video formats and scales, enhances processing speed by up to 200 times compared to existing keyframe selection methods, and does not require hyperparameter tuning. Beyond its outstanding efficiency and robustness, KeyVideoLLM further improves model performance in video question-answering tasks during both training and inference stages. Notably, it consistently achieved the state-of-the-art (SoTA) experimental results on diverse datasets.
Authors: Benno Krojer, Dheeraj Vattikonda, Luis Lara, Varun Jampani, Eva Portelance, Christopher Pal, Siva Reddy
Abstract: An image editing model should be able to perform diverse edits, ranging from object replacement, changing attributes or style, to performing actions or movement, which require many forms of reasoning. Current general instruction-guided editing models have significant shortcomings with action and reasoning-centric edits. Object, attribute or stylistic changes can be learned from visually static datasets. On the other hand, high-quality data for action and reasoning-centric edits is scarce and has to come from entirely different sources that cover e.g. physical dynamics, temporality and spatial reasoning. To this end, we meticulously curate the AURORA Dataset (Action-Reasoning-Object-Attribute), a collection of high-quality training data, human-annotated and curated from videos and simulation engines. We focus on a key aspect of quality training data: triplets (source image, prompt, target image) contain a single meaningful visual change described by the prompt, i.e., truly minimal changes between source and target images. To demonstrate the value of our dataset, we evaluate an AURORA-finetuned model on a new expert-curated benchmark (AURORA-Bench) covering 8 diverse editing tasks. Our model significantly outperforms previous editing models as judged by human raters. For automatic evaluations, we find important flaws in previous metrics and caution their use for semantically hard editing tasks. Instead, we propose a new automatic metric that focuses on discriminative understanding. We hope that our efforts : (1) curating a quality training dataset and an evaluation benchmark, (2) developing critical evaluations, and (3) releasing a state-of-the-art model, will fuel further progress on general image editing.
Authors: Prarthana Bhattacharyya, Joshua Mitton, Ryan Page, Owen Morgan, Ben Menzies, Gabriel Homewood, Kemi Jacobs, Paolo Baesso, Dave Trickett, Chris Mair, Taru Muhonen, Rory Clark, Louis Berridge, Richard Vigars, Iain Wallace
Abstract: This paper introduces Helios, the first extremely low-power, real-time, event-based hand gesture recognition system designed for all-day on smart eyewear. As augmented reality (AR) evolves, current smart glasses like the Meta Ray-Bans prioritize visual and wearable comfort at the expense of functionality. Existing human-machine interfaces (HMIs) in these devices, such as capacitive touch and voice controls, present limitations in ergonomics, privacy and power consumption. Helios addresses these challenges by leveraging natural hand interactions for a more intuitive and comfortable user experience. Our system utilizes a extremely low-power and compact 3mmx4mm/20mW event camera to perform natural hand-based gesture recognition for always-on smart eyewear. The camera's output is processed by a convolutional neural network (CNN) running on a NXP Nano UltraLite compute platform, consuming less than 350mW. Helios can recognize seven classes of gestures, including subtle microgestures like swipes and pinches, with 91% accuracy. We also demonstrate real-time performance across 20 users at a remarkably low latency of 60ms. Our user testing results align with the positive feedback we received during our recent successful demo at AWE-USA-2024.
Authors: Junhao Su, Changpeng Cai, Feiyu Zhu, Chenghao He, Xiaojie Xu, Dongzhi Guan, Chenyang Si
Abstract: Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network parameter updates, leading to significant GPU memory use. Supervised local learning, which segments the network into multiple local blocks updated by independent auxiliary networks. However, these methods cannot replace end-to-end training due to lower accuracy, as gradients only propagate within their local block, creating a lack of information exchange between blocks. To address this issue and establish information transfer across blocks, we propose a Momentum Auxiliary Network (MAN) that establishes a dynamic interaction mechanism. The MAN leverages an exponential moving average (EMA) of the parameters from adjacent local blocks to enhance information flow. This auxiliary network, updated through EMA, helps bridge the informational gap between blocks. Nevertheless, we observe that directly applying EMA parameters has certain limitations due to feature discrepancies among local blocks. To overcome this, we introduce learnable biases, further boosting performance. We have validated our method on four image classification datasets (CIFAR-10, STL-10, SVHN, ImageNet), attaining superior performance and substantial memory savings. Notably, our method can reduce GPU memory usage by more than 45\% on the ImageNet dataset compared to end-to-end training, while achieving higher performance. The Momentum Auxiliary Network thus offers a new perspective for supervised local learning. Our code is available at: https://github.com/JunhaoSu0/MAN.
Authors: Cheng Gong, Yao Chen, Qiuyang Luo, Ye Lu, Tao Li, Yuzhi Zhang, Yufei Sun, Le Zhang
Abstract: Multi-exit network is a promising architecture for efficient model inference by sharing backbone networks and weights among multiple exits. However, the gradient conflict of the shared weights results in sub-optimal accuracy. This paper introduces Deep Feature Surgery (\methodname), which consists of feature partitioning and feature referencing approaches to resolve gradient conflict issues during the training of multi-exit networks. The feature partitioning separates shared features along the depth axis among all exits to alleviate gradient conflict while simultaneously promoting joint optimization for each exit. Subsequently, feature referencing enhances multi-scale features for distinct exits across varying depths to improve the model accuracy. Furthermore, \methodname~reduces the training operations with the reduced complexity of backpropagation. Experimental results on Cifar100 and ImageNet datasets exhibit that \methodname~provides up to a \textbf{50.00\%} reduction in training time and attains up to a \textbf{6.94\%} enhancement in accuracy when contrasted with baseline methods across diverse models and tasks. Budgeted batch classification evaluation on MSDNet demonstrates that DFS uses about $\mathbf{2}\boldsymbol{\times}$ fewer average FLOPs per image to achieve the same classification accuracy as baseline methods on Cifar100. The code is available at https://github.com/GongCheng1919/dfs.
Authors: Sukrut Rao, Sweta Mahajan, Moritz B\"ohle, Bernt Schiele
Abstract: Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for classification. Such models typically require first coming up with a set of concepts relevant to the task and then aligning the representations of a feature extractor to map to these concepts. However, even with powerful foundational feature extractors like CLIP, there are no guarantees that the specified concepts are detectable. In this work, we leverage recent advances in mechanistic interpretability and propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm: instead of pre-selecting concepts based on the downstream classification task, we use sparse autoencoders to first discover concepts learnt by the model, and then name them and train linear probes for classification. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model. We perform a comprehensive evaluation across multiple datasets and CLIP architectures and show that our method yields semantically meaningful concepts, assigns appropriate names to them that make them easy to interpret, and yields performant and interpretable CBMs. Code available at https://github.com/neuroexplicit-saar/discover-then-name.
URLs: https://github.com/neuroexplicit-saar/discover-then-name.
Authors: Wanggong Yang, Xiaona Wang, Yingrui Qiu, Yifei Zhao
Abstract: Generating landscape paintings expands the possibilities of artistic creativity and imagination. Traditional landscape painting methods involve using ink or colored ink on rice paper, which requires substantial time and effort. These methods are susceptible to errors and inconsistencies and lack precise control over lines and colors. This paper presents LPGen, a high-fidelity, controllable model for landscape painting generation, introducing a novel multi-modal framework that integrates image prompts into the diffusion model. We extract its edges and contours by computing canny edges from the target landscape image. These, along with natural language text prompts and drawing style references, are fed into the latent diffusion model as conditions. We implement a decoupled cross-attention strategy to ensure compatibility between image and text prompts, facilitating multi-modal image generation. A decoder generates the final image. Quantitative and qualitative analyses demonstrate that our method outperforms existing approaches in landscape painting generation and exceeds the current state-of-the-art. The LPGen network effectively controls the composition and color of landscape paintings, generates more accurate images, and supports further research in deep learning-based landscape painting generation.
Authors: Wei Wang, Qing Li
Abstract: Computer vision (CV) is one of the most crucial fields in artificial intelligence. In recent years, a variety of deep learning models based on convolutional neural networks (CNNs) and Transformers have been designed to tackle diverse problems in CV. These algorithms have found practical applications in areas such as robotics and facial recognition. Despite the increasing power of current CV models, several fundamental questions remain unresolved: Why do CNNs require deep layers? What ensures the generalization ability of CNNs? Why do residual-based networks outperform fully convolutional networks like VGG? What is the fundamental difference between residual-based CNNs and Transformer-based networks? Why can CNNs utilize LoRA and pruning techniques? The root cause of these questions lies in the lack of a robust theoretical foundation for deep learning models in CV. To address these critical issues and techniques, we employ the Universal Approximation Theorem (UAT) to provide a theoretical basis for convolution- and Transformer-based models in CV. By doing so, we aim to elucidate these questions from a theoretical perspective.
Authors: Florent Brondolo, Samuel Beaussant
Abstract: This study investigates the interpretability, classification, and segmentation of CT-scan images of rock samples, with a particular focus on the application of DINOv2 within Geosciences. We compared various segmentation techniques to evaluate their efficacy, efficiency, and adaptability in geological image analysis. The methods assessed include the Otsu thresholding method, clustering techniques (K-means and fuzzy C-means), a supervised machine learning approach (Random Forest), and deep learning methods (UNet and DINOv2). We tested these methods using ten binary sandstone datasets and three multi-class calcite datasets. To begin, we provide a thorough interpretability analysis of DINOv2's features in the geoscientific context, discussing its suitability and inherent ability to process CT-scanned rock data. In terms of classification, the out-of-the-box DINOv2 demonstrates an impressive capability to perfectly classify rock images, even when the CT scans are out of its original training set. Regarding segmentation, thresholding and unsupervised methods, while fast, perform poorly despite image preprocessing, whereas supervised methods show better results. We underscore the computational demands of deep learning but highlight its minimal intervention, superior generalization, and performance without additional image preprocessing. Additionally, we observe a lack of correlation between a network's depth or the number of parameters and its performance. Our results show that a LoRA fine-tuned DINOv2 excels in out-of-distribution segmentation and significantly outperforms other methods in multi-class segmentation. By systematically comparing these methods, we identify the most efficient strategy for meticulous and laborious segmentation tasks. DINOv2 proves advantageous, achieving segmentations that could be described as "better than ground-truth" against relatively small training sets.
Authors: Xingchen Zeng, Haichuan Lin, Yilin Ye, Wei Zeng
Abstract: Emerging multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA). Recent efforts primarily focus on scaling up training datasets (i.e., charts, data tables, and question-answer (QA) pairs) through data collection and synthesis. However, our empirical study on existing MLLMs and CQA datasets reveals notable gaps. First, current data collection and synthesis focus on data volume and lack consideration of fine-grained visual encodings and QA tasks, resulting in unbalanced data distribution divergent from practical CQA scenarios. Second, existing work follows the training recipe of the base MLLMs initially designed for natural images, under-exploring the adaptation to unique chart characteristics, such as rich text elements. To fill the gap, we propose a visualization-referenced instruction tuning approach to guide the training dataset enhancement and model development. Specifically, we propose a novel data engine to effectively filter diverse and high-quality data from existing datasets and subsequently refine and augment the data using LLM-based generation techniques to better align with practical QA tasks and visual encodings. Then, to facilitate the adaptation to chart characteristics, we utilize the enriched data to train an MLLM by unfreezing the vision encoder and incorporating a mixture-of-resolution adaptation strategy for enhanced fine-grained recognition. Experimental results validate the effectiveness of our approach. Even with fewer training examples, our model consistently outperforms state-of-the-art CQA models on established benchmarks. We also contribute a dataset split as a benchmark for future research. Source codes and datasets of this paper are available at https://github.com/zengxingchen/ChartQA-MLLM.
Authors: Zheng Liu, Hao Liang, Xijie Huang, Wentao Xiong, Qinhan Yu, Linzhuang Sun, Chong Chen, Conghui He, Bin Cui, Wentao Zhang
Abstract: Recently, with the rise of web images, managing and understanding large-scale image datasets has become increasingly important. Vision Large Language Models (VLLMs) have recently emerged due to their robust vision-understanding capabilities. However, training these models requires vast amounts of data, posing challenges to efficiency, effectiveness, data quality, and privacy. In this paper, we introduce SynthVLM, a novel data synthesis pipeline for VLLMs. Unlike existing methods that generate captions from images, SynthVLM employs advanced diffusion models and high-quality captions to automatically generate and select high-resolution images from captions, creating precisely aligned image-text pairs. Leveraging these pairs, we achieve state-of-the-art (SoTA) performance on various vision question answering tasks, maintaining high alignment quality and preserving advanced language abilities. Moreover, SynthVLM surpasses traditional GPT-4 Vision-based caption generation methods in performance while significantly reducing computational overhead. Crucially, our method's reliance on purely generated data ensures the preservation of privacy, achieving SoTA performance with just 100k data points (only 18% of the official dataset size).
Authors: Jiangyi Wang, Zhongyao Cheng, Na Zhao, Jun Cheng, Xulei Yang
Abstract: Point cloud analysis is challenging due to its unique characteristics of unorderness, sparsity and irregularity. Prior works attempt to capture local relationships by convolution operations or attention mechanisms, exploiting geometric information from coordinates implicitly. These methods, however, are insufficient to describe the explicit local geometry, e.g., curvature and orientation. In this paper, we propose On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module. This is inspired by Point Feature Histogram (PFH) from computer vision community. However, the utilization of vanilla PFH encounters great difficulties when applied to large datasets and dense point clouds, as it demands considerable time for feature generation. In contrast, we introduce the Local Reference Constructor module, which approximates the local coordinate systems based on triangle sets. Owing to this, our OPFR only requires extra 1.56ms for inference (65x faster than vanilla PFH) and 0.012M more parameters, and it can serve as a versatile plug-and-play module for various backbones, particularly MLP-based and Transformer-based backbones examined in this study. Additionally, we introduce the novel Hierarchical Sampling module aimed at enhancing the quality of triangle sets, thereby ensuring robustness of the obtained geometric features. Our proposed method improves overall accuracy (OA) on ModelNet40 from 90.7% to 94.5% (+3.8%) for classification, and OA on S3DIS Area-5 from 86.4% to 90.0% (+3.6%) for semantic segmentation, respectively, building upon PointNet++ backbone. When integrated with Point Transformer backbone, we achieve state-of-the-art results on both tasks: 94.8% OA on ModelNet40 and 91.7% OA on S3DIS Area-5.
Authors: Alexandra Kapp, Edith Hoffmann, Esther Weigmann, Helena Mihaljevi\'c
Abstract: Road unevenness significantly impacts the safety and comfort of various traffic participants, especially vulnerable road users such as cyclists and wheelchair users. This paper introduces StreetSurfaceVis, a novel dataset comprising 9,122 street-level images collected from a crowdsourcing platform and manually annotated by road surface type and quality. The dataset is intended to train models for comprehensive surface assessments of road networks. Existing open datasets are constrained by limited geospatial coverage and camera setups, typically excluding cycleways and footways. By crafting a heterogeneous dataset, we aim to fill this gap and enable robust models that maintain high accuracy across diverse image sources. However, the frequency distribution of road surface types and qualities is highly imbalanced. We address the challenge of ensuring sufficient images per class while reducing manual annotation by proposing a sampling strategy that incorporates various external label prediction resources. More precisely, we estimate the impact of (1) enriching the image data with OpenStreetMap tags, (2) iterative training and application of a custom surface type classification model, (3) amplifying underrepresented classes through prompt-based classification with GPT-4o or similarity search using image embeddings. We show that utilizing a combination of these strategies effectively reduces manual annotation workload while ensuring sufficient class representation.
Authors: Thiziri Nait Saada, Valentina Di Proietto, Benoit Schmauch, Katharina Von Loga, Lucas Fidon
Abstract: Multiple Instance Learning (MIL) models have proven effective for cancer prognosis from Whole Slide Images. However, the original MIL formulation incorrectly assumes the patches of the same image to be independent, leading to a loss of spatial context as information flows through the network. Incorporating contextual knowledge into predictions is particularly important given the inclination for cancerous cells to form clusters and the presence of spatial indicators for tumors. State-of-the-art methods often use attention mechanisms eventually combined with graphs to capture spatial knowledge. In this paper, we take a novel and transversal approach, addressing this issue through the lens of regularization. We propose Context-Aware Regularization for Multiple Instance Learning (CARMIL), a versatile regularization scheme designed to seamlessly integrate spatial knowledge into any MIL model. Additionally, we present a new and generic metric to quantify the Context-Awareness of any MIL model when applied to Whole Slide Images, resolving a previously unexplored gap in the field. The efficacy of our framework is evaluated for two survival analysis tasks on glioblastoma (TCGA GBM) and colon cancer data (TCGA COAD).
Authors: Xun Huang, Ziyu Xu, Hai Wu, Jinlong Wang, Qiming Xia, Yan Xia, Jonathan Li, Kyle Gao, Chenglu Wen, Cheng Wang
Abstract: LiDAR-based vision systems are integral for 3D object detection, which is crucial for autonomous navigation. However, they suffer from performance degradation in adverse weather conditions due to the quality deterioration of LiDAR point clouds. Fusing LiDAR with the weather-robust 4D radar sensor is expected to solve this problem. However, the fusion of LiDAR and 4D radar is challenging because they differ significantly in terms of data quality and the degree of degradation in adverse weather. To address these issues, we introduce L4DR, a weather-robust 3D object detection method that effectively achieves LiDAR and 4D Radar fusion. Our L4DR includes Multi-Modal Encoding (MME) and Foreground-Aware Denoising (FAD) technique to reconcile sensor gaps, which is the first exploration of the complementarity of early fusion between LiDAR and 4D radar. Additionally, we design an Inter-Modal and Intra-Modal ({IM}2 ) parallel feature extraction backbone coupled with a Multi-Scale Gated Fusion (MSGF) module to counteract the varying degrees of sensor degradation under adverse weather conditions. Experimental evaluation on a VoD dataset with simulated fog proves that L4DR is more adaptable to changing weather conditions. It delivers a significant performance increase under different fog levels, improving the 3D mAP by up to 20.0% over the traditional LiDAR-only approach. Moreover, the results on the K-Radar dataset validate the consistent performance improvement of L4DR in real-world adverse weather conditions.
Authors: Tianrun Chen, Ankang Lu, Lanyun Zhu, Chaotao Ding, Chunan Yu, Deyi Ji, Zejian Li, Lingyun Sun, Papa Mao, Ying Zang
Abstract: The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2), a successor with enhanced architecture and a larger training corpus, we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/
Authors: Shijie Ma, Fei Zhu, Zhen Cheng, Xu-Yao Zhang
Abstract: Efficiency and trustworthiness are two eternal pursuits when applying deep learning in real-world applications. With regard to efficiency, dataset distillation (DD) endeavors to reduce training costs by distilling the large dataset into a tiny synthetic dataset. However, existing methods merely concentrate on in-distribution (InD) classification in a closed-world setting, disregarding out-of-distribution (OOD) samples. On the other hand, OOD detection aims to enhance models' trustworthiness, which is always inefficiently achieved in full-data settings. For the first time, we simultaneously consider both issues and propose a novel paradigm called Trustworthy Dataset Distillation (TrustDD). By distilling both InD samples and outliers, the condensed datasets are capable of training models competent in both InD classification and OOD detection. To alleviate the requirement of real outlier data, we further propose to corrupt InD samples to generate pseudo-outliers, namely Pseudo-Outlier Exposure (POE). Comprehensive experiments on various settings demonstrate the effectiveness of TrustDD, and POE surpasses the state-of-the-art method Outlier Exposure (OE). Compared with the preceding DD, TrustDD is more trustworthy and applicable to open-world scenarios. Our code is available at https://github.com/mashijie1028/TrustDD
Authors: Zexin Li, Xiaoxi He, Yufei Li, Wei Yang, Lothar Thiele, Cong Liu
Abstract: Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that multi-input single-output (MISO) deep neural networks (DNN) outperform traditional single-input single-output (SISO) models, representing a significant step towards this goal. In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage. Leveraging existing SISO model compression techniques, MIMONet develops a new deep-compression method that is specifically tailored to MIMO models. This new method explores unique yet non-trivial properties of the MIMO model, resulting in boosted accuracy and on-device efficiency. Extensive experiments on three embedded platforms commonly used in robotic systems, as well as a case study using the TurtleBot3 robot, demonstrate that MIMONet achieves higher accuracy and superior on-device efficiency compared to state-of-the-art SISO and MISO models, as well as a baseline MIMO model we constructed. Our evaluation highlights the real-world applicability of MIMONet and its potential to significantly enhance the performance of intelligent robotic systems.
Authors: Amr Gomaa, Bilal Mahdy, Niko Kleer, Antonio Kr\"uger
Abstract: Robot-assisted surgical systems have demonstrated significant potential in enhancing surgical precision and minimizing human errors. However, existing systems cannot accommodate individual surgeons' unique preferences and requirements. Additionally, they primarily focus on general surgeries (e.g., laparoscopy) and are unsuitable for highly precise microsurgeries, such as ophthalmic procedures. Thus, we propose an image-guided approach for surgeon-centered autonomous agents that can adapt to the individual surgeon's skill level and preferred surgical techniques during ophthalmic cataract surgery. Our approach trains reinforcement and imitation learning agents simultaneously using curriculum learning approaches guided by image data to perform all tasks of the incision phase of cataract surgery. By integrating the surgeon's actions and preferences into the training process, our approach enables the robot to implicitly learn and adapt to the individual surgeon's unique techniques through surgeon-in-the-loop demonstrations. This results in a more intuitive and personalized surgical experience for the surgeon while ensuring consistent performance for the autonomous robotic apprentice. We define and evaluate the effectiveness of our approach in a simulated environment using our proposed metrics and highlight the trade-off between a generic agent and a surgeon-centered adapted agent. Finally, our approach has the potential to extend to other ophthalmic and microsurgical procedures, opening the door to a new generation of surgeon-in-the-loop autonomous surgical robots. We provide an open-source simulation framework for future development and reproducibility at https://github.com/amrgomaaelhady/CataractAdaptSurgRobot.
URLs: https://github.com/amrgomaaelhady/CataractAdaptSurgRobot.
Authors: Jing Xu
Abstract: Chest X-ray is one of the most common radiological examination types for the diagnosis of chest diseases. Nowadays, the automatic classification technology of radiological images has been widely used in clinical diagnosis and treatment plans. However, each disease has its own different response characteristic receptive field region, which is the main challenge for chest disease classification tasks. Besides, the imbalance of sample data categories further increases the difficulty of tasks. To solve these problems, we propose a new multi-label chest disease image classification scheme based on a multi-scale attention network. In this scheme, multi-scale information is iteratively fused to focus on regions with a high probability of disease, to effectively mine more meaningful information from data, and the classification performance can be improved only by image level annotation. We also designed a new loss function to improve the rationality of visual perception and the performance of multi-label image classification by forcing the consistency of attention regions before and after image transformation. A comprehensive experiment was carried out on the public Chest X-Ray14 and CheXpert datasets to achieve state of the art results, which verified the effectiveness of this method in chest X-ray image classification.
Authors: Sheng Li, Geng Yuan, Yawen Wu, Yue Dai, Tianyu Wang, Chao Wu, Alex K. Jones, Jingtong Hu, Yanzhi Wang, Xulong Tang
Abstract: Many emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and require the deployment of DNN models on edge devices. These applications naturally require i) handling streaming-in inference requests and ii) fine-tuning the deployed models to adapt to possible deployment scenario changes. Continual learning (CL) is widely adopted to satisfy these needs. CL is a popular deep learning paradigm that handles both continuous model fine-tuning and overtime inference requests. However, an inappropriate model fine-tuning scheme could involve significant redundancy and consume considerable time and energy, making it challenging to apply CL on edge devices. In this paper, we propose ETuner, an efficient edge continual learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, ETuner reduces overall fine-tuning execution time by 64%, energy consumption by 56%, and improves average inference accuracy by 1.75% over the immediate model fine-tuning approach.
Authors: Minheng Chen, Tonglong Li, Zhirun Zhang, Youyong Kong
Abstract: A robust and efficient optimization-based 2D/3D registration framework is crucial for the navigation system of orthopedic surgical robots. It can provide precise position information of surgical instruments and implants during surgery. While artificial intelligence technology has advanced rapidly in recent years, traditional optimization-based registration methods remain indispensable in the field of 2D/3D registration.he exceptional precision of this method enables it to be considered as a post-processing step of the learning-based methods, thereby offering a reliable assurance for registration. In this paper, we present a coarse-to-fine registration framework based on the CMA-ES algorithm. We conducted intensive testing of our method using data from different parts of the spine. The results shows the effectiveness of the proposed framework on real orthopedic spine surgery clinical data. This work can be viewed as an additional extension that complements the optimization-based methods employed in our previous studies.
Authors: Amel Imene Hadj Bouzid, Baudouin Denis de Senneville, Fabien Baldacci, Pascal Desbarats, Patrick Berger, Ilyes Benlala, Ga\"el Dournes
Abstract: This research embarked on a comparative exploration of the holistic segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized data from two CF reference centers, covering five major CF structural changes. Initially, it compared the 2D and 3D models, highlighting the 3D model's superior capability in capturing complex features like mucus plugs and consolidations. To improve the 2D model's performance, a loss adapted to fine structures segmentation was implemented and evaluated, significantly enhancing its accuracy, though not surpassing the 3D model's performance. The models underwent further validation through external evaluation against pulmonary function tests (PFTs), confirming the robustness of the findings. Moreover, this study went beyond comparing metrics; it also included comprehensive assessments of the models' interpretability and reliability, providing valuable insights for their clinical application.
Authors: Ashesh Ashesh, Florian Jug
Abstract: In this work, we present denoiSplit, a method to tackle a new analysis task, i.e. the challenge of joint semantic image splitting and unsupervised denoising. This dual approach has important applications in fluorescence microscopy, where semantic image splitting has important applications but noise does generally hinder the downstream analysis of image content. Image splitting involves dissecting an image into its distinguishable semantic structures. We show that the current state-of-the-art method for this task struggles in the presence of image noise, inadvertently also distributing the noise across the predicted outputs. The method we present here can deal with image noise by integrating an unsupervised denoising subtask. This integration results in improved semantic image unmixing, even in the presence of notable and realistic levels of imaging noise. A key innovation in denoiSplit is the use of specifically formulated noise models and the suitable adjustment of KL-divergence loss for the high-dimensional hierarchical latent space we are training. We showcase the performance of denoiSplit across multiple tasks on real-world microscopy images. Additionally, we perform qualitative and quantitative evaluations and compare the results to existing benchmarks, demonstrating the effectiveness of using denoiSplit: a single Variational Splitting Encoder-Decoder (VSE) Network using two suitable noise models to jointly perform semantic splitting and denoising.
Authors: Yihe Fan, Yuxin Cao, Ziyu Zhao, Ziyao Liu, Shaofeng Li
Abstract: Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities that increasingly influence various aspects of our daily lives, constantly defining the new boundary of Artificial General Intelligence (AGI). Image modalities, enriched with profound semantic information and a more continuous mathematical nature compared to other modalities, greatly enhance the functionalities of MLLMs when integrated. However, this integration serves as a double-edged sword, providing attackers with expansive vulnerabilities to exploit for highly covert and harmful attacks. The pursuit of reliable AI systems like powerful MLLMs has emerged as a pivotal area of contemporary research. In this paper, we endeavor to demostrate the multifaceted risks associated with the incorporation of image modalities into MLLMs. Initially, we delineate the foundational components and training processes of MLLMs. Subsequently, we construct a threat model, outlining the security vulnerabilities intrinsic to MLLMs. Moreover, we analyze and summarize existing scholarly discourses on MLLMs' attack and defense mechanisms, culminating in suggestions for the future research on MLLM security. Through this comprehensive analysis, we aim to deepen the academic understanding of MLLM security challenges and propel forward the development of trustworthy MLLM systems.
Authors: Yipeng Zhang, Laurent Charlin, Richard Zemel, Mengye Ren
Abstract: We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation. The framework reveals that many existing UCL approaches overlook cross-task consolidation and try to balance plasticity and stability in a shared embedding space. This results in worse performance due to a lack of within-task data diversity and reduced effectiveness in learning the current task. Our method, Osiris, which explicitly optimizes all three objectives on separate embedding spaces, achieves state-of-the-art performance on all benchmarks, including two novel benchmarks proposed in this paper featuring semantically structured task sequences. Compared to standard benchmarks, these two structured benchmarks more closely resemble visual signals received by humans and animals when navigating real-world environments. Finally, we show some preliminary evidence that continual models can benefit from such realistic learning scenarios.
Authors: Dionysia Danai Brilli, Evangelos Georgaras, Stefania Tsilivaki, Nikos Melanitis, Konstantina Nikita
Abstract: Assistive technologies for the visually impaired have evolved to facilitate interaction with a complex and dynamic world. In this paper, we introduce AIris, an AI-powered wearable device that provides environmental awareness and interaction capabilities to visually impaired users. AIris combines a sophisticated camera mounted on eyewear with a natural language processing interface, enabling users to receive real-time auditory descriptions of their surroundings. We have created a functional prototype system that operates effectively in real-world conditions. AIris demonstrates the ability to accurately identify objects and interpret scenes, providing users with a sense of spatial awareness previously unattainable with traditional assistive devices. The system is designed to be cost-effective and user-friendly, supporting general and specialized tasks: face recognition, scene description, text reading, object recognition, money counting, note-taking, and barcode scanning. AIris marks a transformative step, bringing AI enhancements to assistive technology, enabling rich interactions with a human-like feel.
Authors: Zhaohuan Zhan, Lisha Yu, Sijie Yu, Guang Tan
Abstract: In the Vision-and-Language Navigation (VLN) task, the agent is required to navigate to a destination following a natural language instruction. While learning-based approaches have been a major solution to the task, they suffer from high training costs and lack of interpretability. Recently, Large Language Models (LLMs) have emerged as a promising tool for VLN due to their strong generalization capabilities. However, existing LLM-based methods face limitations in memory construction and diversity of navigation strategies. To address these challenges, we propose a suite of techniques. Firstly, we introduce a method to maintain a topological map that stores navigation history, retaining information about viewpoints, objects, and their spatial relationships. This map also serves as a global action space. Additionally, we present a Navigation Chain of Thoughts module, leveraging human navigation examples to enrich navigation strategy diversity. Finally, we establish a pipeline that integrates navigational memory and strategies with perception and action prediction modules. Experimental results on the REVERIE and R2R datasets show that our method effectively enhances the navigation ability of the LLM and improves the interpretability of navigation reasoning.
Authors: Jorge Condor, Sebastien Speierer, Lukas Bode, Aljaz Bozic, Simon Green, Piotr Didyk, Adrian Jarabo
Abstract: Efficient scene representations are essential for many computer graphics applications. A general unified representation that can handle both surfaces and volumes simultaneously, remains a research challenge. Inspired by recent methods for scene reconstruction that leverage mixtures of 3D Gaussians to model radiance fields, we formalize and generalize the modeling of scattering and emissive media using mixtures of simple kernel-based volumetric primitives. We introduce closed-form solutions for transmittance and free-flight distance sampling for different kernels, and propose several optimizations to use our method efficiently within any off-the-shelf volumetric path tracer. We demonstrate our method as a compact and efficient alternative to other forms of volume modeling for forward and inverse rendering of scattering media. Furthermore, we adapt and showcase our method in radiance field optimization and rendering, providing additional flexibility compared to current state of the art given its ray-tracing formulation. We also introduce the Epanechnikov kernel and demonstrate its potential as an efficient alternative to the traditionally-used Gaussian kernel in scene reconstruction tasks. The versatility and physically-based nature of our approach allows us to go beyond radiance fields and bring to kernel-based modeling and rendering any path-tracing enabled functionality such as scattering, relighting and complex camera models.
Authors: Aditya Gunturu, Yi Wen, Nandi Zhang, Jarin Thundathil, Rubaiat Habib Kazi, Ryo Suzuki
Abstract: We introduce Augmented Physics, a machine learning-integrated authoring tool designed for creating embedded interactive physics simulations from static textbook diagrams. Leveraging recent advancements in computer vision, such as Segment Anything and Multi-modal LLMs, our web-based system enables users to semi-automatically extract diagrams from physics textbooks and generate interactive simulations based on the extracted content. These interactive diagrams are seamlessly integrated into scanned textbook pages, facilitating interactive and personalized learning experiences across various physics concepts, such as optics, circuits, and kinematics. Drawing from an elicitation study with seven physics instructors, we explore four key augmentation strategies: 1) augmented experiments, 2) animated diagrams, 3) bi-directional binding, and 4) parameter visualization. We evaluate our system through technical evaluation, a usability study (N=12), and expert interviews (N=12). Study findings suggest that our system can facilitate more engaging and personalized learning experiences in physics education.
Authors: Xiao Liu, Peng Gao, Tao Yu, Fei Wang, Ru-Yue Yuan
Abstract: Deep learning, especially convolutional neural networks (CNNs) and Transformer architectures, have become the focus of extensive research in medical image segmentation, achieving impressive results. However, CNNs come with inductive biases that limit their effectiveness in more complex, varied segmentation scenarios. Conversely, while Transformer-based methods excel at capturing global and long-range semantic details, they suffer from high computational demands. In this study, we propose CSWin-UNet, a novel U-shaped segmentation method that incorporates the CSWin self-attention mechanism into the UNet to facilitate horizontal and vertical stripes self-attention. This method significantly enhances both computational efficiency and receptive field interactions. Additionally, our innovative decoder utilizes a content-aware reassembly operator that strategically reassembles features, guided by predicted kernels, for precise image resolution restoration. Our extensive empirical evaluations on diverse datasets, including synapse multi-organ CT, cardiac MRI, and skin lesions, demonstrate that CSWin-UNet maintains low model complexity while delivering high segmentation accuracy.
Authors: Philipp Schoch, Fan Yang, Yuntao Ma, Stefan Leutenegger, Marco Hutter, Quentin Leboutet
Abstract: Current visual navigation systems often treat the environment as static, lacking the ability to adaptively interact with obstacles. This limitation leads to navigation failure when encountering unavoidable obstructions. In response, we introduce IN-Sight, a novel approach to self-supervised path planning, enabling more effective navigation strategies through interaction with obstacles. Utilizing RGB-D observations, IN-Sight calculates traversability scores and incorporates them into a semantic map, facilitating long-range path planning in complex, maze-like environments. To precisely navigate around obstacles, IN-Sight employs a local planner, trained imperatively on a differentiable costmap using representation learning techniques. The entire framework undergoes end-to-end training within the state-of-the-art photorealistic Intel SPEAR Simulator. We validate the effectiveness of IN-Sight through extensive benchmarking in a variety of simulated scenarios and ablation studies. Moreover, we demonstrate the system's real-world applicability with zero-shot sim-to-real transfer, deploying our planner on the legged robot platform ANYmal, showcasing its practical potential for interactive navigation in real environments.
Authors: Vishnu Sashank Dorbala, Vishnu Dutt Sharma, Pratap Tokekar, Dinesh Manocha
Abstract: In Zero-Shot ObjectNav, an embodied ground agent is expected to navigate to a target object specified by a natural language label without any environment-specific fine-tuning. This is challenging, given the limited view of a ground agent and its independent exploratory behavior. To address these issues, we consider an assistive overhead agent with a bounded global view alongside the ground agent and present two coordinated navigation schemes for judicious exploration. We establish the influence of the Generative Communication (GC) between the embodied agents equipped with Vision-Language Models (VLMs) in improving zero-shot ObjectNav, achieving a 10% improvement in the ground agent's ability to find the target object in comparison with an unassisted setup in simulation. We further analyze the GC for unique traits quantifying the presence of hallucination and cooperation. In particular, we identify a unique trait of "preemptive hallucination" specific to our embodied setting, where the overhead agent assumes that the ground agent has executed an action in the dialogue when it is yet to move. Finally, we conduct real-world inferences with GC and showcase qualitative examples where countering pre-emptive hallucination via prompt finetuning improves real-world ObjectNav performance.
Authors: Qiuyu Zhu, Liheng Hu, Sijin Wang
Abstract: In the face of complex natural images, existing deep clustering algorithms fall significantly short in terms of clustering accuracy when compared to supervised classification methods, making them less practical. This paper introduces an image clustering algorithm based on self-supervised pretrained models and latent feature distribution optimization, substantially enhancing clustering performance. It is found that: (1) For complex natural images, we effectively enhance the discriminative power of latent features by leveraging self-supervised pretrained models and their fine-tuning, resulting in improved clustering performance. (2) In the latent feature space, by searching for k-nearest neighbor images for each training sample and shortening the distance between the training sample and its nearest neighbor, the discriminative power of latent features can be further enhanced, and clustering performance can be improved. (3) In the latent feature space, reducing the distance between sample features and the nearest predefined cluster centroids can optimize the distribution of latent features, therefore further improving clustering performance. Through experiments on multiple datasets, our approach outperforms the latest clustering algorithms and achieves state-of-the-art clustering results. When the number of categories in the datasets is small, such as CIFAR-10 and STL-10, and there are significant differences between categories, our clustering algorithm has similar accuracy to supervised methods without using pretrained models, slightly lower than supervised methods using pre-trained models. The code linked algorithm is https://github.com/LihengHu/semi.
Authors: Andreas Knoblauch
Abstract: IVISIT is a generic interactive visual simulation tool that is based on Python/Numpy and can be used for system simulation, parameter optimization, parameter management, and visualization of system dynamics as required, for example,for developing neural network simulations, machine learning applications, or computer vision systems. It provides classes for rapid prototyping of applications and visualization and manipulation of system properties using interactive GUI elements like sliders, images, textboxes, option lists, checkboxes and buttons based on Tkinter and Matplotlib. Parameters and simulation configurations can be stored and managed based on SQLite database functions. This technical report describes the main architecture and functions of IVISIT, and provides easy examples how to rapidly implement interactive applications and manage parameter settings.
Authors: Han Wang, Tan Rui Yang, Usman Naseem, Roy Ka-Wei Lee
Abstract: Hate speech is a pressing issue in modern society, with significant effects both online and offline. Recent research in hate speech detection has primarily centered on text-based media, largely overlooking multimodal content such as videos. Existing studies on hateful video datasets have predominantly focused on English content within a Western context and have been limited to binary labels (hateful or non-hateful), lacking detailed contextual information. This study presents MultiHateClip1 , an novel multilingual dataset created through hate lexicons and human annotation. It aims to enhance the detection of hateful videos on platforms such as YouTube and Bilibili, including content in both English and Chinese languages. Comprising 2,000 videos annotated for hatefulness, offensiveness, and normalcy, this dataset provides a cross-cultural perspective on gender-based hate speech. Through a detailed examination of human annotation results, we discuss the differences between Chinese and English hateful videos and underscore the importance of different modalities in hateful and offensive video analysis. Evaluations of state-of-the-art video classification models, such as VLM, GPT-4V and Qwen-VL, on MultiHateClip highlight the existing challenges in accurately distinguishing between hateful and offensive content and the urgent need for models that are both multimodally and culturally nuanced. MultiHateClip represents a foundational advance in enhancing hateful video detection by underscoring the necessity of a multimodal and culturally sensitive approach in combating online hate speech.
Authors: Mohamed Hassan, Aleksandar Vakanski, Min Xian
Abstract: Effective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the generalization of deep learning models by regularizing the sharpness of the loss landscape. Among the optimization approaches that explicitly minimize sharpness, Sharpness-Aware Minimization (SAM) has shown potential in enhancing generalization performance on general domain image datasets. This success has led to the development of several advanced sharpness-based algorithms aimed at addressing the limitations of SAM, such as Adaptive SAM, surrogate-Gap SAM, Weighted SAM, and Curvature Regularized SAM. These sharpness-based optimizers have shown improvements in model generalization compared to conventional stochastic gradient descent optimizers and their variants on general domain image datasets, but they have not been thoroughly evaluated on medical images. This work provides a review of recent sharpness-based methods for improving the generalization of deep learning networks and evaluates the methods performance on medical breast ultrasound images. Our findings indicate that the initial SAM method successfully enhances the generalization of various deep learning models. While Adaptive SAM improves generalization of convolutional neural networks, it fails to do so for vision transformers. Other sharpness-based optimizers, however, do not demonstrate consistent results. The results reveal that, contrary to findings in the non-medical domain, SAM is the only recommended sharpness-based optimizer that consistently improves generalization in medical image analysis, and further research is necessary to refine the variants of SAM to enhance generalization performance in this field