Authors: Muhammad Zaeem Shahzad, Muhammad Abdullah Hanif, Muhammad Shafique
Abstract: In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge. Conventional ML models trained on clear weather data falter when faced with scenarios like extreme fog or heavy rain, potentially leading to accidents and safety hazards. This paper addresses this issue by proposing a novel approach: employing a Denoising Deep Neural Network as a preprocessing step to transform adverse weather images into clear weather images, thereby enhancing the robustness of ML-ADAS systems. The proposed method eliminates the need for retraining all subsequent Depp Neural Networks (DNN) in the ML-ADAS pipeline, thus saving computational resources and time. Moreover, it improves driver visualization, which is critical for safe navigation in adverse weather conditions. By leveraging the UNet architecture trained on an augmented KITTI dataset with synthetic adverse weather images, we develop the Weather UNet (WUNet) DNN to remove weather artifacts. Our study demonstrates substantial performance improvements in object detection with WUNet preprocessing under adverse weather conditions. Notably, in scenarios involving extreme fog, our proposed solution improves the mean Average Precision (mAP) score of the YOLOv8n from 4% to 70%.
Authors: Abir Sen, Tapas Kumar Mishra, Ratnakar Dash
Abstract: Hand gesture recognition (HGR) is a vital component in enhancing the human-computer interaction experience, particularly in multimedia applications, such as virtual reality, gaming, smart home automation systems, etc. Users can control and navigate through these applications seamlessly by accurately detecting and recognizing gestures. However, in a real-time scenario, the performance of the gesture recognition system is sometimes affected due to the presence of complex background, low-light illumination, occlusion problems, etc. Another issue is building a fast and robust gesture-controlled human-computer interface (HCI) in the real-time scenario. The overall objective of this paper is to develop an efficient hand gesture detection and classification model using a channel-pruned YOLOv5-small model and utilize the model to build a gesture-controlled HCI with a quick response time (in ms) and higher detection speed (in fps). First, the YOLOv5s model is chosen for the gesture detection task. Next, the model is simplified by using a channel-pruned algorithm. After that, the pruned model is further fine-tuned to ensure detection efficiency. We have compared our suggested scheme with other state-of-the-art works, and it is observed that our model has shown superior results in terms of mAP (mean average precision), precision (\%), recall (\%), and F1-score (\%), fast inference time (in ms), and detection speed (in fps). Our proposed method paves the way for deploying a pruned YOLOv5s model for a real-time gesture-command-based HCI to control some applications, such as the VLC media player, Spotify player, etc., using correctly classified gesture commands in real-time scenarios. The average detection speed of our proposed system has reached more than 60 frames per second (fps) in real-time, which meets the perfect requirement in real-time application control.
Authors: Xiaochuan Lin, Xiangyong Chen
Abstract: Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotionally resonant visual stories remains challenging due to the complexity of aligning visual and textual information. This paper presents a novel approach leveraging large language models (LLMs) and large vision-language models (LVLMs) combined with instruction tuning to address these challenges. We introduce a new dataset comprising diverse visual stories, annotated with detailed captions and multimodal elements. Our method employs a combination of supervised and reinforcement learning to fine-tune the model, enhancing its narrative generation capabilities. Quantitative evaluations using GPT-4 and qualitative human assessments demonstrate that our approach significantly outperforms existing models, achieving higher scores in narrative coherence, relevance, emotional depth, and overall quality. The results underscore the effectiveness of instruction tuning and the potential of LLMs/LVLMs in advancing visual storytelling.
Authors: Mustafa Khan, Hamidreza Fazlali, Dhruv Sharma, Tongtong Cao, Dongfeng Bai, Yuan Ren, Bingbing Liu
Abstract: Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in real-time rendering and static scene reconstructions but struggles with modeling driving scenarios due to complex backgrounds, dynamic objects, and sparse views. We propose AutoSplat, a framework employing Gaussian splatting to achieve highly realistic reconstructions of autonomous driving scenes. By imposing geometric constraints on Gaussians representing the road and sky regions, our method enables multi-view consistent simulation of challenging scenarios including lane changes. Leveraging 3D templates, we introduce a reflected Gaussian consistency constraint to supervise both the visible and unseen side of foreground objects. Moreover, to model the dynamic appearance of foreground objects, we estimate residual spherical harmonics for each foreground Gaussian. Extensive experiments on Pandaset and KITTI demonstrate that AutoSplat outperforms state-of-the-art methods in scene reconstruction and novel view synthesis across diverse driving scenarios. Visit our $\href{https://autosplat.github.io/}{\text{project page}}$.
Authors: Raphael Bensadoun, Tom Monnier, Yanir Kleiman, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya, Omri Harosh, Roman Shapovalov, Benjamin Graham, Emilien Garreau, Animesh Karnewar, Ang Cao, Idan Azuri, Iurii Makarov, Eric-Tuan Le, Antoine Toisoul, David Novotny, Oran Gafni, Natalia Neverova, Andrea Vedaldi
Abstract: We introduce Meta 3D Gen (3DGen), a new state-of-the-art, fast pipeline for text-to-3D asset generation. 3DGen offers 3D asset creation with high prompt fidelity and high-quality 3D shapes and textures in under a minute. It supports physically-based rendering (PBR), necessary for 3D asset relighting in real-world applications. Additionally, 3DGen supports generative retexturing of previously generated (or artist-created) 3D shapes using additional textual inputs provided by the user. 3DGen integrates key technical components, Meta 3D AssetGen and Meta 3D TextureGen, that we developed for text-to-3D and text-to-texture generation, respectively. By combining their strengths, 3DGen represents 3D objects simultaneously in three ways: in view space, in volumetric space, and in UV (or texture) space. The integration of these two techniques achieves a win rate of 68% with respect to the single-stage model. We compare 3DGen to numerous industry baselines, and show that it outperforms them in terms of prompt fidelity and visual quality for complex textual prompts, while being significantly faster.
Authors: Zhiming Hu, Zheming Yin, Daniel Haeufle, Syn Schmitt, Andreas Bulling
Abstract: We present HOIMotion - a novel approach for human motion forecasting during human-object interactions that integrates information about past body poses and egocentric 3D object bounding boxes. Human motion forecasting is important in many augmented reality applications but most existing methods have only used past body poses to predict future motion. HOIMotion first uses an encoder-residual graph convolutional network (GCN) and multi-layer perceptrons to extract features from body poses and egocentric 3D object bounding boxes, respectively. Our method then fuses pose and object features into a novel pose-object graph and uses a residual-decoder GCN to forecast future body motion. We extensively evaluate our method on the Aria digital twin (ADT) and MoGaze datasets and show that HOIMotion consistently outperforms state-of-the-art methods by a large margin of up to 8.7% on ADT and 7.2% on MoGaze in terms of mean per joint position error. Complementing these evaluations, we report a human study (N=20) that shows that the improvements achieved by our method result in forecasted poses being perceived as both more precise and more realistic than those of existing methods. Taken together, these results reveal the significant information content available in egocentric 3D object bounding boxes for human motion forecasting and the effectiveness of our method in exploiting this information.
Authors: Tinghuai Wang, Guangming Wang, Kuan Eeik Tan
Abstract: Convolutional neural networks (CNN) have made significant advances in detecting roads from satellite images. However, existing CNN approaches are generally repurposed semantic segmentation architectures and suffer from the poor delineation of long and curved regions. Lack of overall road topology and structure information further deteriorates their performance on challenging remote sensing images. This paper presents a novel multi-task graph neural network (GNN) which simultaneously detects both road regions and road borders; the inter-play between these two tasks unlocks superior performance from two perspectives: (1) the hierarchically detected road borders enable the network to capture and encode holistic road structure to enhance road connectivity (2) identifying the intrinsic correlation of semantic landcover regions mitigates the difficulty in recognizing roads cluttered by regions with similar appearance. Experiments on challenging dataset demonstrate that the proposed architecture can improve the road border delineation and road extraction accuracy compared with the existing methods.
Authors: Huiling Wang
Abstract: Convolutional neural networks (CNNs) have achieved remarkable performance in hyperspectral image (HSI) classification over the last few years. Despite the progress that has been made, rich and informative spectral information of HSI has been largely underutilized by existing methods which employ convolutional kernels with limited size of receptive field in the spectral domain. To address this issue, we propose a spectral graph reasoning network (SGR) learning framework comprising two crucial modules: 1) a spectral decoupling module which unpacks and casts multiple spectral embeddings into a unified graph whose node corresponds to an individual spectral feature channel in the embedding space; the graph performs interpretable reasoning to aggregate and align spectral information to guide learning spectral-specific graph embeddings at multiple contextual levels 2) a spectral ensembling module explores the interactions and interdependencies across graph embedding hierarchy via a novel recurrent graph propagation mechanism. Experiments on two HSI datasets demonstrate that the proposed architecture can significantly improve the classification accuracy compared with the existing methods with a sizable margin.
Authors: Anay Majee, Ryan Sharp, Rishabh Iyer
Abstract: Confusion and forgetting of object classes have been challenges of prime interest in Few-Shot Object Detection (FSOD). To overcome these pitfalls in metric learning based FSOD techniques, we introduce a novel Submodular Mutual Information Learning (SMILe) framework which adopts combinatorial mutual information functions to enforce the creation of tighter and discriminative feature clusters in FSOD. Our proposed approach generalizes to several existing approaches in FSOD, agnostic of the backbone architecture demonstrating elevated performance gains. A paradigm shift from instance based objective functions to combinatorial objectives in SMILe naturally preserves the diversity within an object class resulting in reduced forgetting when subjected to few training examples. Furthermore, the application of mutual information between the already learnt (base) and newly added (novel) objects ensures sufficient separation between base and novel classes, minimizing the effect of class confusion. Experiments on popular FSOD benchmarks, PASCAL-VOC and MS-COCO show that our approach generalizes to State-of-the-Art (SoTA) approaches improving their novel class performance by up to 5.7% (3.3 mAP points) and 5.4% (2.6 mAP points) on the 10-shot setting of VOC (split 3) and 30-shot setting of COCO datasets respectively. Our experiments also demonstrate better retention of base class performance and up to 2x faster convergence over existing approaches agnostic of the underlying architecture.
Authors: Ahmad AlMughrabi, Ricardo Marques, Petia Radeva
Abstract: We propose MomentsNeRF, a novel framework for one- and few-shot neural rendering that predicts a neural representation of a 3D scene using Orthogonal Moments. Our architecture offers a new transfer learning method to train on multi-scenes and incorporate a per-scene optimization using one or a few images at test time. Our approach is the first to successfully harness features extracted from Gabor and Zernike moments, seamlessly integrating them into the NeRF architecture. We show that MomentsNeRF performs better in synthesizing images with complex textures and shapes, achieving a significant noise reduction, artifact elimination, and completing the missing parts compared to the recent one- and few-shot neural rendering frameworks. Extensive experiments on the DTU and Shapenet datasets show that MomentsNeRF improves the state-of-the-art by {3.39\;dB\;PSNR}, 11.1% SSIM, 17.9% LPIPS, and 8.3% DISTS metrics. Moreover, it outperforms state-of-the-art performance for both novel view synthesis and single-image 3D view reconstruction. The source code is accessible at: https://amughrabi.github.io/momentsnerf/.
Authors: Davide Alessandro Coccomini, Roberto Caldelli, Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro
Abstract: Deepfake technology is rapidly advancing, posing significant challenges to the detection of manipulated media content. Parallel to that, some adversarial attack techniques have been developed to fool the deepfake detectors and make deepfakes even more difficult to be detected. This paper explores the application of super resolution techniques as a possible adversarial attack in deepfake detection. Through our experiments, we demonstrate that minimal changes made by these methods in the visual appearance of images can have a profound impact on the performance of deepfake detection systems. We propose a novel attack using super resolution as a quick, black-box and effective method to camouflage fake images and/or generate false alarms on pristine images. Our results indicate that the usage of super resolution can significantly impair the accuracy of deepfake detectors, thereby highlighting the vulnerability of such systems to adversarial attacks. The code to reproduce our experiments is available at: https://github.com/davide-coccomini/Adversarial-Magnification-to-Deceive-Deepfake-Detection-through-Super-Resolution
Authors: Varun Sundar, Matthew Dutson, Andrei Ardelean, Claudio Bruschini, Edoardo Charbon, Mohit Gupta
Abstract: Event cameras capture the world at high time resolution and with minimal bandwidth requirements. However, event streams, which only encode changes in brightness, do not contain sufficient scene information to support a wide variety of downstream tasks. In this work, we design generalized event cameras that inherently preserve scene intensity in a bandwidth-efficient manner. We generalize event cameras in terms of when an event is generated and what information is transmitted. To implement our designs, we turn to single-photon sensors that provide digital access to individual photon detections; this modality gives us the flexibility to realize a rich space of generalized event cameras. Our single-photon event cameras are capable of high-speed, high-fidelity imaging at low readout rates. Consequently, these event cameras can support plug-and-play downstream inference, without capturing new event datasets or designing specialized event-vision models. As a practical implication, our designs, which involve lightweight and near-sensor-compatible computations, provide a way to use single-photon sensors without exorbitant bandwidth costs.
Authors: Junwei Zheng, Ruiping Liu, Yufan Chen, Kunyu Peng, Chengzhi Wu, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
Abstract: Panoramic images, capturing a 360{\deg} field of view (FoV), encompass omnidirectional spatial information crucial for scene understanding. However, it is not only costly to obtain training-sufficient dense-annotated panoramas but also application-restricted when training models in a close-vocabulary setting. To tackle this problem, in this work, we define a new task termed Open Panoramic Segmentation (OPS), where models are trained with FoV-restricted pinhole images in the source domain in an open-vocabulary setting while evaluated with FoV-open panoramic images in the target domain, enabling the zero-shot open panoramic semantic segmentation ability of models. Moreover, we propose a model named OOOPS with a Deformable Adapter Network (DAN), which significantly improves zero-shot panoramic semantic segmentation performance. To further enhance the distortion-aware modeling ability from the pinhole source domain, we propose a novel data augmentation method called Random Equirectangular Projection (RERP) which is specifically designed to address object deformations in advance. Surpassing other state-of-the-art open-vocabulary semantic segmentation approaches, a remarkable performance boost on three panoramic datasets, WildPASS, Stanford2D3D, and Matterport3D, proves the effectiveness of our proposed OOOPS model with RERP on the OPS task, especially +2.2% on outdoor WildPASS and +2.4% mIoU on indoor Stanford2D3D. The code will be available at https://junweizheng93.github.io/publications/OPS/OPS.html.
URLs: https://junweizheng93.github.io/publications/OPS/OPS.html.
Authors: Ruizhuo Song, Beiming Yuan
Abstract: Visual abstract reasoning problems hold immense importance in the field of image processing. Both Bongard-Logo and Raven's Progressive Matrices (RPM) belong to this domain, with Bongard-Logo categorized as image clustering reasoning and RPM involving image progression pattern reasoning. This paper introduces Valen, a novel baseline model under probabilistic highlighting models. Valen exhibits remarkable performance in solving both RPM and Bongard-Logo problems, offering a versatile solution. Our investigation delves into the underlying mechanisms of probability-highlighting solvers, realizing they approximate solutions to reasoning problem instances as distributions delineated by primary and auxiliary samples. We propose that the learning objective is not the distribution of correct solutions but one defined by both primary and auxiliary samples. To bridge discrepancies, we introduced the Tine method, an adversarial learning-based approach to assist Valen in estimating a solution distribution closer to the correct one, albeit with issues like unstable training. Reflecting on Tine, we propose modeling the sample distribution of reasoning problems as a mixture of Gaussian distributions, leading to the Funny method. This effectively enables Valen to capture the true form of the correct solution distribution. Furthermore, we designed the SBR method to model the distribution of progressive patterns representation similarly. Overall, the Funny, Tine, and SBR methods significantly improve Valen's performance, providing new ideas and methods for studying visual abstract reasoning problems.
Authors: Efstathia Soufleri, Deepak Ravikumar, Kaushik Roy
Abstract: Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each dedicated to processing one modality. Our observations indicate that the network processing intra-frames tend to converge to a flatter minimum than the network processing residuals, which in turn converges to a flatter minimum than the motion vector network. This hierarchy in convergence motivates our strategy for knowledge transfer among modalities to achieve flatter minima, which are generally associated with better generalization. With this insight, we propose Progressive Knowledge Distillation (PKD), a technique that incrementally transfers knowledge across the modalities. This method involves attaching early exits (Internal Classifiers - ICs) to the three networks. PKD distills knowledge starting from the motion vector network, followed by the residual, and finally, the intra-frame network, sequentially improving IC accuracy. Further, we propose the Weighted Inference with Scaled Ensemble (WISE), which combines outputs from the ICs using learned weights, boosting accuracy during inference. Our experiments demonstrate the effectiveness of training the ICs with PKD compared to standard cross-entropy-based training, showing IC accuracy improvements of up to 5.87% and 11.42% on the UCF-101 and HMDB-51 datasets, respectively. Additionally, WISE improves accuracy by up to 4.28% and 9.30% on UCF-101 and HMDB-51, respectively.
Authors: Xu Han, Linghao Jin, Xuezhe Ma, Xiaofeng Liu
Abstract: Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially containing noise that can adversely affect downstream performance. Moreover, the growing reliance on multi-modal generation exacerbates this issue because of its susceptibility to adversarial attacks. To investigate how VLMs trained on adversarial noisy data perform on downstream medical tasks, we first craft noisy upstream datasets using multi-modal adversarial attacks. Through our comprehensive analysis, we unveil that moderate noise enhances model robustness and transferability, but increasing noise levels negatively impact downstream task performance. To mitigate this issue, we propose rectify adversarial noise (RAN) framework, a recipe designed to effectively defend adversarial attacks and rectify the influence of upstream noise during fine-tuning.
Authors: Zishan Gu, Changchang Yin, Fenglin Liu, Ping Zhang
Abstract: Large Vision Language Models (LVLMs) have recently achieved superior performance in various tasks on natural image and text data, which inspires a large amount of studies for LVLMs fine-tuning and training. Despite their advancements, there has been scant research on the robustness of these models against hallucination when fine-tuned on smaller datasets. In this study, we introduce a new benchmark dataset, the Medical Visual Hallucination Test (MedVH), to evaluate the hallucination of domain-specific LVLMs. MedVH comprises five tasks to evaluate hallucinations in LVLMs within the medical context, which includes tasks for comprehensive understanding of textual and visual input, as well as long textual response generation. Our extensive experiments with both general and medical LVLMs reveal that, although medical LVLMs demonstrate promising performance on standard medical tasks, they are particularly susceptible to hallucinations, often more so than the general models, raising significant concerns about the reliability of these domain-specific models. For medical LVLMs to be truly valuable in real-world applications, they must not only accurately integrate medical knowledge but also maintain robust reasoning abilities to prevent hallucination. Our work paves the way for future evaluations of these studies.
Authors: Satoshi Kondo
Abstract: Surgical skill assessment is paramount for ensuring patient safety and enhancing surgical outcomes. This study addresses the need for efficient and objective evaluation methods by introducing ZEAL (surgical skill assessment with Zero-shot surgical tool segmentation with a unifiEd foundAtion modeL). ZEAL uses segmentation masks of surgical instruments obtained through a unified foundation model for proficiency assessment. Through zero-shot inference with text prompts, ZEAL predicts segmentation masks, capturing essential features of both instruments and surroundings. Utilizing sparse convolutional neural networks and segmentation masks, ZEAL extracts feature vectors for foreground (instruments) and background. Long Short-Term Memory (LSTM) networks encode temporal dynamics, modeling sequential data and dependencies in surgical videos. Combining LSTM-encoded vectors, ZEAL produces a surgical skill score, offering an objective measure of proficiency. Comparative analysis with conventional methods using open datasets demonstrates ZEAL's superiority, affirming its potential in advancing surgical training and evaluation. This innovative approach to surgical skill assessment addresses challenges in traditional supervised learning techniques, paving the way for enhanced surgical care quality and patient outcomes.
Authors: Yanfeng Jiang, Ning Sun, Xueshuo Xie, Fei Yang, Tao Li
Abstract: Vision Transformers (ViTs) have exhibited exceptional performance across diverse computer vision tasks, while their substantial parameter size incurs significantly increased memory and computational demands, impeding effective inference on resource-constrained devices. Quantization has emerged as a promising solution to mitigate these challenges, yet existing methods still suffer from significant accuracy loss at low-bit. We attribute this issue to the distinctive distributions of post-LayerNorm and post-GELU activations within ViTs, rendering conventional hardware-friendly quantizers ineffective, particularly in low-bit scenarios. To address this issue, we propose a novel framework called Activation-Distribution-Friendly post-training Quantization for Vision Transformers, ADFQ-ViT. Concretely, we introduce the Per-Patch Outlier-aware Quantizer to tackle irregular outliers in post-LayerNorm activations. This quantizer refines the granularity of the uniform quantizer to a per-patch level while retaining a minimal subset of values exceeding a threshold at full-precision. To handle the non-uniform distributions of post-GELU activations between positive and negative regions, we design the Shift-Log2 Quantizer, which shifts all elements to the positive region and then applies log2 quantization. Moreover, we present the Attention-score enhanced Module-wise Optimization which adjusts the parameters of each quantizer by reconstructing errors to further mitigate quantization error. Extensive experiments demonstrate ADFQ-ViT provides significant improvements over various baselines in image classification, object detection, and instance segmentation tasks at 4-bit. Specifically, when quantizing the ViT-B model to 4-bit, we achieve a 10.23% improvement in Top-1 accuracy on the ImageNet dataset.
Authors: Tao Chen, XiRuo Jiang, Gensheng Pei, Zeren Sun, Yucheng Wang, Yazhou Yao
Abstract: Though adversarial erasing has prevailed in weakly supervised semantic segmentation to help activate integral object regions, existing approaches still suffer from the dilemma of under-activation and over-expansion due to the difficulty in determining when to stop erasing. In this paper, we propose a \textbf{K}nowledge \textbf{T}ransfer with \textbf{S}imulated Inter-Image \textbf{E}rasing (KTSE) approach for weakly supervised semantic segmentation to alleviate the above problem. In contrast to existing erasing-based methods that remove the discriminative part for more object discovery, we propose a simulated inter-image erasing scenario to weaken the original activation by introducing extra object information. Then, object knowledge is transferred from the anchor image to the consequent less activated localization map to strengthen network localization ability. Considering the adopted bidirectional alignment will also weaken the anchor image activation if appropriate constraints are missing, we propose a self-supervised regularization module to maintain the reliable activation in discriminative regions and improve the inter-class object boundary recognition for complex images with multiple categories of objects. In addition, we resort to intra-image erasing and propose a multi-granularity alignment module to gently enlarge the object activation to boost the object knowledge transfer. Extensive experiments and ablation studies on PASCAL VOC 2012 and COCO datasets demonstrate the superiority of our proposed approach. Source codes and models are available at https://github.com/NUST-Machine-Intelligence-Laboratory/KTSE.
URLs: https://github.com/NUST-Machine-Intelligence-Laboratory/KTSE.
Authors: Yiqun Wang, Zhao Zhou, Xiangcheng Du, Xingjiao Wu, Yingbin Zheng, Cheng Jin
Abstract: When dealing with the task of fine-grained scene image classification, most previous works lay much emphasis on global visual features when doing multi-modal feature fusion. In other words, models are deliberately designed based on prior intuitions about the importance of different modalities. In this paper, we present a new multi-modal feature fusion approach named MAA (Modality-Agnostic Adapter), trying to make the model learn the importance of different modalities in different cases adaptively, without giving a prior setting in the model architecture. More specifically, we eliminate the modal differences in distribution and then use a modality-agnostic Transformer encoder for a semantic-level feature fusion. Our experiments demonstrate that MAA achieves state-of-the-art results on benchmarks by applying the same modalities with previous methods. Besides, it is worth mentioning that new modalities can be easily added when using MAA and further boost the performance. Code is available at https://github.com/quniLcs/MAA.
Authors: Mengmeng Sheng, Zeren Sun, Tao Chen, Shuchao Pang, Yucheng Wang, Yazhou Yao
Abstract: Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection paradigm and usually rely on dataset-dependent prior knowledge (\eg, a pre-defined threshold) to cope with label noise, inevitably degrading the adaptivity. Moreover, existing methods tend to neglect the class balance in selecting samples, leading to biased model performance. To this end, we propose a simple yet effective approach named \textbf{SED} to deal with label noise in a \textbf{S}elf-adaptiv\textbf{E} and class-balance\textbf{D} manner. Specifically, we first design a novel sample selection strategy to empower self-adaptivity and class balance when identifying clean and noisy data. A mean-teacher model is then employed to correct labels of noisy samples. Subsequently, we propose a self-adaptive and class-balanced sample re-weighting mechanism to assign different weights to detected noisy samples. Finally, we additionally employ consistency regularization on selected clean samples to improve model generalization performance. Extensive experimental results on synthetic and real-world datasets demonstrate the effectiveness and superiority of our proposed method. The source code has been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/SED.
URLs: https://github.com/NUST-Machine-Intelligence-Laboratory/SED.
Authors: Roy Y. He, Hao Liu
Abstract: We propose a novel model for decomposing grayscale images into three distinct components: the structural part, representing sharp boundaries and regions with strong light-to-dark transitions; the smooth part, capturing soft shadows and shades; and the oscillatory part, characterizing textures and noise. To capture the homogeneous structures, we introduce a combination of $L^0$-gradient and curvature regularization on level lines. This new regularization term enforces strong sparsity on the image gradient while reducing the undesirable staircase effects as well as preserving the geometry of contours. For the smoothly varying component, we utilize the $L^2$-norm of the Laplacian that favors isotropic smoothness. To capture the oscillation, we use the inverse Sobolev seminorm. To solve the associated minimization problem, we design an efficient operator-splitting algorithm. Our algorithm effectively addresses the challenging non-convex non-smooth problem by separating it into sub-problems. Each sub-problem can be solved either directly using closed-form solutions or efficiently using the Fast Fourier Transform (FFT). We provide systematic experiments, including ablation and comparison studies, to analyze our model's behaviors and demonstrate its effectiveness as well as efficiency.
Authors: Gen Li, Zhihao Shu, Jie Ji, Minghai Qin, Fatemeh Afghah, Wei Niu, Xiaolong Ma
Abstract: Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take advantage of DNN's overfitting properties to perform video resolution upscaling. By splitting videos into chunks and applying a super-resolution (SR) model to overfit each chunk, this scheme of SR models plus video chunks is able to replace traditional video transmission to enhance video quality and transmission efficiency. However, many models and chunks are needed to guarantee high performance, which leads to tremendous overhead on model switching and memory footprints at the user end. To resolve such problems, we propose a Dynamic Deep neural network assisted by a Content-Aware data processing pipeline to reduce the model number down to one (Dy-DCA), which helps promote performance while conserving computational resources. Additionally, to achieve real acceleration on the user end, we designed a framework that optimizes dynamic features (e.g., dynamic shapes, sizes, and control flow) in Dy-DCA to enable a series of compilation optimizations, including fused code generation, static execution planning, etc. By employing such techniques, our method achieves better PSNR and real-time performance (33 FPS) on an off-the-shelf mobile phone. Meanwhile, assisted by our compilation optimization, we achieve a 1.7$\times$ speedup while saving up to 1.61$\times$ memory consumption. Code available in https://github.com/coulsonlee/Dy-DCA-ECCV2024.
Authors: Li Fang, Tianyu Li, Yanghong Lin, Shudong Zhou, Wei Yao
Abstract: Point clouds are vital in computer vision tasks such as 3D reconstruction, autonomous driving, and robotics. However, TLS-acquired point clouds often contain virtual points from reflective surfaces, causing disruptions. This study presents a reflection noise elimination algorithm for TLS point clouds. Our innovative reflection plane detection algorithm, based on geometry-optical models and physical properties, identifies and categorizes reflection points per optical reflection theory. We've adapted the LSFH feature descriptor to retain reflection features, mitigating interference from symmetrical architectural structures. By incorporating the Hausdorff feature distance, the algorithm enhances resilience to ghosting and deformation, improving virtual point detection accuracy. Extensive experiments on the 3DRN benchmark dataset, featuring diverse urban environments with virtual TLS reflection noise, show our algorithm improves precision and recall rates for 3D points in reflective regions by 57.03\% and 31.80\%, respectively. Our method achieves a 9.17\% better outlier detection rate and 5.65\% higher accuracy than leading methods. Access the 3DRN dataset at (https://github.com/Tsuiky/3DRN).
Authors: Jie Shao, LingHao Jiang
Abstract: The task of UAV-view geo-localization is to estimate the localization of a query satellite/drone image by matching it against a reference dataset consisting of drone/satellite images. Though tremendous strides have been made in feature alignment between satellite and drone views, vast differences in both inter and intra-class due to changes in viewpoint, altitude, and lighting remain a huge challenge. In this paper, a style alignment based dynamic observation method for UAV-view geo-localization is proposed to meet the above challenges from two perspectives: visual style transformation and surrounding noise control. Specifically, we introduce a style alignment strategy to transfrom the diverse visual style of drone-view images into a unified satellite images visual style. Then a dynamic observation module is designed to evaluate the spatial distribution of images by mimicking human observation habits. It is featured by the hierarchical attention block (HAB) with a dual-square-ring stream structure, to reduce surrounding noise and geographical deformation. In addition, we propose a deconstruction loss to push away features of different geo-tags and squeeze knowledge from unmatched images by correlation calculation. The experimental results demonstrate the state-of-the-art performance of our model on benchmarked datasets. In particular, when compared to the prior art on University-1652, our results surpass the best of them (FSRA), while only requiring 2x fewer parameters. Code will be released at https://github.com/Xcco1/SA\_DOM
Authors: Jie Shao, Jiacheng Wu, Wenzhong Shen, Cheng Yang
Abstract: Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD methods usually perform feature alignments from the target to the source. Unidirectional domain transfer would omit information about the target samples and result in suboptimal adaptation when there are large domain shifts. Therefore, we propose a pairwise attentive adversarial network with a Domain Mixup (DomMix) module to mitigate the aforementioned challenges. Specifically, a deep-level mixup is employed to construct an intermediate domain that allows features from both domains to share their differences. Then a pairwise attentive adversarial network is applied with attentive encoding on both image-level and instance-level features at different scales and optimizes domain alignment by adversarial learning. This allows the network to focus on regions with disparate contextual information and learn their similarities between different domains. Extensive experiments are conducted on several benchmark datasets, demonstrating the superiority of our proposed method.
Authors: Lei Chen, Feng Yan, Yujie Zhong, Shaoxiang Chen, Zequn Jie, Lin Ma
Abstract: Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex interactions between elements in structured documents such as mind maps and flowcharts. To address this issue, we introduce the new benchmark named MindBench, which not only includes meticulously constructed bilingual authentic or synthetic images, detailed annotations, evaluation metrics and baseline models, but also specifically designs five types of structured understanding and parsing tasks. These tasks include full parsing, partial parsing, position-related parsing, structured Visual Question Answering (VQA), and position-related VQA, covering key areas such as text recognition, spatial awareness, relationship discernment, and structured parsing. Extensive experimental results demonstrate the substantial potential and significant room for improvement in current models' ability to handle structured document information. We anticipate that the launch of MindBench will significantly advance research and application development in structured document analysis technology. MindBench is available at: https://miasanlei.github.io/MindBench.github.io/.
Authors: Penglei Sun, Yaoxian Song, Xinglin Pan, Peijie Dong, Xiaofei Yang, Qiang Wang, Zhixu Li, Tiefeng Li, Xiaowen Chu
Abstract: The existing works on object-level language grounding with 3D objects mostly focus on improving performance by utilizing the off-the-shelf pre-trained models to capture features, such as viewpoint selection or geometric priors. However, they have failed to consider exploring the cross-modal representation of language-vision alignment in the cross-domain field. To answer this problem, we propose a novel method called Domain Adaptation for Language Grounding (DA4LG) with 3D objects. Specifically, the proposed DA4LG consists of a visual adapter module with multi-task learning to realize vision-language alignment by comprehensive multimodal feature representation. Experimental results demonstrate that DA4LG competitively performs across visual and non-visual language descriptions, independent of the completeness of observation. DA4LG achieves state-of-the-art performance in the single-view setting and multi-view setting with the accuracy of 83.8% and 86.8% respectively in the language grounding benchmark SNARE. The simulation experiments show the well-practical and generalized performance of DA4LG compared to the existing methods. Our project is available at https://sites.google.com/view/da4lg.
Authors: Marc Josep Montagut Marques, Liu Mingxin, Kuri Thomas Shiojiri, Tomika Hagiwara, Kayo Hirose, Kaori Shiojiri, Shinjiro Umezu
Abstract: Artificial intelligence has significantly advanced the automation of diagnostic processes, benefiting various fields including agriculture. This study introduces an AI-based system for the automatic diagnosis of urban street plants using video footage obtained with accessible camera devices. The system aims to monitor plant health on a day-to-day basis, aiding in the control of disease spreading in urban areas. By combining two machine vision algorithms, YOLOv8 and DeepSORT, the system efficiently identifies and tracks individual leaves, extracting the optimal images for health analysis. YOLOv8, chosen for its speed and computational efficiency, locates leaves, while DeepSORT ensures robust tracking in complex environments. For detailed health assessment, DeepLabV3Plus, a convolutional neural network, is employed to segment and quantify leaf damage caused by bacteria, pests, and fungi. The hybrid system, named Plant Doctor, has been trained and validated using a diverse dataset including footage from Tokyo urban plants. The results demonstrate the robustness and accuracy of the system in diagnosing leaf damage, with potential applications in large scale urban flora illness monitoring. This approach provides a non-invasive, efficient, and scalable solution for urban tree health management, supporting sustainable urban ecosystems.
Authors: Hang Xu, Chen Long, Wenxiao Zhang, Yuan Liu, Zhen Cao, Zhen Dong, Bisheng Yang
Abstract: Corresponding author}In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a partial one with a single view image. In comparison with previous methods that relied on the global semantics of input images, EGIInet efficiently combines the information from two modalities by leveraging the geometric nature of the completion task. Specifically, we propose an explicitly guided information interaction strategy supported by modal alignment for point cloud completion. First, in contrast to previous methods which simply use 2D and 3D backbones to encode features respectively, we unified the encoding process to promote modal alignment. Second, we propose a novel explicitly guided information interaction strategy that could help the network identify critical information within images, thus achieving better guidance for completion. Extensive experiments demonstrate the effectiveness of our framework, and we achieved a new state-of-the-art (+16\% CD over XMFnet) in benchmark datasets despite using fewer parameters than the previous methods. The pre-trained model and code and are available at https://github.com/WHU-USI3DV/EGIInet.
Authors: Zihao Luo, Xiangde Luo, Zijun Gao, Guotai Wang
Abstract: Deep learning models have exhibited remarkable efficacy in accurately delineating the prostate for diagnosis and treatment of prostate diseases, but challenges persist in achieving robust generalization across different medical centers. Source-free Domain Adaptation (SFDA) is a promising technique to adapt deep segmentation models to address privacy and security concerns while reducing domain shifts between source and target domains. However, recent literature indicates that the performance of SFDA remains far from satisfactory due to unpredictable domain gaps. Annotating a few target domain samples is acceptable, as it can lead to significant performance improvement with a low annotation cost. Nevertheless, due to extremely limited annotation budgets, careful consideration is needed in selecting samples for annotation. Inspired by this, our goal is to develop Active Source-free Domain Adaptation (ASFDA) for medical image segmentation. Specifically, we propose a novel Uncertainty-guided Tiered Self-training (UGTST) framework, consisting of efficient active sample selection via entropy-based primary local peak filtering to aggregate global uncertainty and diversity-aware redundancy filter, coupled with a tiered self-learning strategy, achieves stable domain adaptation. Experimental results on cross-center prostate MRI segmentation datasets revealed that our method yielded marked advancements, with a mere 5% annotation, exhibiting an average Dice score enhancement of 9.78% and 7.58% in two target domains compared with state-of-the-art methods, on par with fully supervised learning. Code is available at:https://github.com/HiLab-git/UGTST
Authors: Zhanglei Yang, Haipeng Li, Mingbo Hong, Bing Zeng, Shuaicheng Liu
Abstract: We present RS-Diffusion, the first Diffusion Models-based method for single-frame Rolling Shutter (RS) correction. RS artifacts compromise visual quality of frames due to the row wise exposure of CMOS sensors. Most previous methods have focused on multi-frame approaches, using temporal information from consecutive frames for the motion rectification. However, few approaches address the more challenging but important single frame RS correction. In this work, we present an ``image-to-motion'' framework via diffusion techniques, with a designed patch-attention module. In addition, we present the RS-Real dataset, comprised of captured RS frames alongside their corresponding Global Shutter (GS) ground-truth pairs. The GS frames are corrected from the RS ones, guided by the corresponding Inertial Measurement Unit (IMU) gyroscope data acquired during capture. Experiments show that our RS-Diffusion surpasses previous single RS correction methods. Our method and proposed RS-Real dataset lay a solid foundation for advancing the field of RS correction.
Authors: Jonas B\"uhler, Jonas Fehrenbach, Lucas Steinmann, Christian Nauck, Marios Koulakis
Abstract: One persistent obstacle in industrial quality inspection is the detection of anomalies. In real-world use cases, two problems must be addressed: anomalous data is sparse and the same types of anomalies need to be detected on previously unseen objects. Current anomaly detection approaches can be trained with sparse nominal data, whereas domain generalization approaches enable detecting objects in previously unseen domains. Utilizing those two observations, we introduce the hybrid task of domain generalization on sparse classes. To introduce an accompanying dataset for this task, we present a modification of the well-established MVTec AD dataset by generating three new datasets. In addition to applying existing methods for benchmark, we design two embedding-based approaches, Spatial Embedding MLP (SEMLP) and Labeled PatchCore. Overall, SEMLP achieves the best performance with an average image-level AUROC of 87.2 % vs. 80.4 % by MIRO. The new and openly available datasets allow for further research to improve industrial anomaly detection.
Authors: Jiaxin Guo, Jiangliu Wang, Di Kang, Wenzhen Dong, Wenting Wang, Yun-hui Liu
Abstract: Real-time 3D reconstruction of surgical scenes plays a vital role in computer-assisted surgery, holding a promise to enhance surgeons' visibility. Recent advancements in 3D Gaussian Splatting (3DGS) have shown great potential for real-time novel view synthesis of general scenes, which relies on accurate poses and point clouds generated by Structure-from-Motion (SfM) for initialization. However, 3DGS with SfM fails to recover accurate camera poses and geometry in surgical scenes due to the challenges of minimal textures and photometric inconsistencies. To tackle this problem, in this paper, we propose the first SfM-free 3DGS-based method for surgical scene reconstruction by jointly optimizing the camera poses and scene representation. Based on the video continuity, the key of our method is to exploit the immediate optical flow priors to guide the projection flow derived from 3D Gaussians. Unlike most previous methods relying on photometric loss only, we formulate the pose estimation problem as minimizing the flow loss between the projection flow and optical flow. A consistency check is further introduced to filter the flow outliers by detecting the rigid and reliable points that satisfy the epipolar geometry. During 3D Gaussian optimization, we randomly sample frames to optimize the scene representations to grow the 3D Gaussian progressively. Experiments on the SCARED dataset demonstrate our superior performance over existing methods in novel view synthesis and pose estimation with high efficiency. Code is available at https://github.com/wrld/Free-SurGS.
Authors: Ramy Battrawy, Ren\'e Schuster, Didier Stricker
Abstract: Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable to clustering robustness. In this paper, we propose our EgoFlowNet - a point-level scene flow estimation network trained in a weakly-supervised manner and without object-based abstraction. Our approach predicts a binary segmentation mask that implicitly drives two parallel branches for ego-motion and scene flow. Unlike previous methods, we provide both branches with all input points and carefully integrate the binary mask into the feature extraction and losses. We also use a shared cost volume with local refinement that is updated at multiple scales without explicit clustering or rigidity assumptions. On realistic KITTI scenes, we show that our EgoFlowNet performs better than state-of-the-art methods in the presence of ground surface points.
Authors: Yanbin Hao, Diansong Zhou, Zhicai Wang, Chong-Wah Ngo, Meng Wang
Abstract: In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP's positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, PoSGU, and PoSTGU, respectively. These gating units can be feasibly combined into three types of spatio-temporal factorized positional MLP blocks, which not only decrease model complexity but also maintain good performance. Additionally, we enrich relative positional relationships by using channel grouping. Experimental results on three video-related tasks demonstrate that PosMLP-Video achieves competitive speed-accuracy trade-offs compared to the previous state-of-the-art models. In particular, PosMLP-Video pre-trained on ImageNet1K achieves 59.0%/70.3% top-1 accuracy on Something-Something V1/V2 and 82.1% top-1 accuracy on Kinetics-400 while requiring much fewer parameters and FLOPs than other models. The code is released at https://github.com/zhouds1918/PosMLP_Video.
Authors: Sungwon Hwang, Min-Jung Kim, Taewoong Kang, Jayeon Kang, Jaegul Choo
Abstract: Neural rendering-based urban scene reconstruction methods commonly rely on images collected from driving vehicles with cameras facing and moving forward. Although these methods can successfully synthesize from views similar to training camera trajectory, directing the novel view outside the training camera distribution does not guarantee on-par performance. In this paper, we tackle the Extrapolated View Synthesis (EVS) problem by evaluating the reconstructions on views such as looking left, right or downwards with respect to training camera distributions. To improve rendering quality for EVS, we initialize our model by constructing dense LiDAR map, and propose to leverage prior scene knowledge such as surface normal estimator and large-scale diffusion model. Qualitative and quantitative comparisons demonstrate the effectiveness of our methods on EVS. To the best of our knowledge, we are the first to address the EVS problem in urban scene reconstruction. Link to our project page: https://vegs3d.github.io/.
Authors: Eric Stumpe, Gernot Bodner, Francesco Flagiello, Matthias Zeppelzauer
Abstract: The use of multiple camera technologies in a combined multimodal monitoring system for plant phenotyping offers promising benefits. Compared to configurations that only utilize a single camera technology, cross-modal patterns can be recorded that allow a more comprehensive assessment of plant phenotypes. However, the effective utilization of cross-modal patterns is dependent on precise image registration to achieve pixel-accurate alignment, a challenge often complicated by parallax and occlusion effects inherent in plant canopy imaging. In this study, we propose a novel multimodal 3D image registration method that addresses these challenges by integrating depth information from a time-of-flight camera into the registration process. By leveraging depth data, our method mitigates parallax effects and thus facilitates more accurate pixel alignment across camera modalities. Additionally, we introduce an automated mechanism to identify and differentiate different types of occlusions, thereby minimizing the introduction of registration errors. To evaluate the efficacy of our approach, we conduct experiments on a diverse image dataset comprising six distinct plant species with varying leaf geometries. Our results demonstrate the robustness of the proposed registration algorithm, showcasing its ability to achieve accurate alignment across different plant types and camera compositions. Compared to previous methods it is not reliant on detecting plant specific image features and can thereby be utilized for a wide variety of applications in plant sciences. The registration approach principally scales to arbitrary numbers of cameras with different resolutions and wavelengths. Overall, our study contributes to advancing the field of plant phenotyping by offering a robust and reliable solution for multimodal image registration.
Authors: Sushovan Jena, Arya Pulkit, Kajal Singh, Anoushka Banerjee, Sharad Joshi, Ananth Ganesh, Dinesh Singh, Arnav Bhavsar
Abstract: With the rapid advances in deep learning and smart manufacturing in Industry 4.0, there is an imperative for high-throughput, high-performance, and fully integrated visual inspection systems. Most anomaly detection approaches using defect detection datasets, such as MVTec AD, employ one-class models that require fitting separate models for each class. On the contrary, unified models eliminate the need for fitting separate models for each class and significantly reduce cost and memory requirements. Thus, in this work, we experiment with considering a unified multi-class setup. Our experimental study shows that multi-class models perform at par with one-class models for the standard MVTec AD dataset. Hence, this indicates that there may not be a need to learn separate object/class-wise models when the object classes are significantly different from each other, as is the case of the dataset considered. Furthermore, we have deployed three different unified lightweight architectures on the CPU and an edge device (NVIDIA Jetson Xavier NX). We analyze the quantized multi-class anomaly detection models in terms of latency and memory requirements for deployment on the edge device while comparing quantization-aware training (QAT) and post-training quantization (PTQ) for performance at different precision widths. In addition, we explored two different methods of calibration required in post-training scenarios and show that one of them performs notably better, highlighting its importance for unsupervised tasks. Due to quantization, the performance drop in PTQ is further compensated by QAT, which yields at par performance with the original 32-bit Floating point in two of the models considered.
Authors: Muhammad Hussain
Abstract: This paper presents a comprehensive review of the evolution of the YOLO (You Only Look Once) object detection algorithm, focusing on YOLOv5, YOLOv8, and YOLOv10. We analyze the architectural advancements, performance improvements, and suitability for edge deployment across these versions. YOLOv5 introduced significant innovations such as the CSPDarknet backbone and Mosaic Augmentation, balancing speed and accuracy. YOLOv8 built upon this foundation with enhanced feature extraction and anchor-free detection, improving versatility and performance. YOLOv10 represents a leap forward with NMS-free training, spatial-channel decoupled downsampling, and large-kernel convolutions, achieving state-of-the-art performance with reduced computational overhead. Our findings highlight the progressive enhancements in accuracy, efficiency, and real-time performance, particularly emphasizing their applicability in resource-constrained environments. This review provides insights into the trade-offs between model complexity and detection accuracy, offering guidance for selecting the most appropriate YOLO version for specific edge computing applications.
Authors: Mengmeng Cui, Kunbo Zhang, Zhenan Sun
Abstract: In recent years, 2D-to-3D pose uplifting in monocular 3D Human Pose Estimation (HPE) has attracted widespread research interest. GNN-based methods and Transformer-based methods have become mainstream architectures due to their advanced spatial and temporal feature learning capacities. However, existing approaches typically construct joint-wise and frame-wise attention alignments in spatial and temporal domains, resulting in dense connections that introduce considerable local redundancy and computational overhead. In this paper, we take a global approach to exploit spatio-temporal information and realise efficient 3D HPE with a concise Graph and Skipped Transformer architecture. Specifically, in Spatial Encoding stage, coarse-grained body parts are deployed to construct Spatial Graph Network with a fully data-driven adaptive topology, ensuring model flexibility and generalizability across various poses. In Temporal Encoding and Decoding stages, a simple yet effective Skipped Transformer is proposed to capture long-range temporal dependencies and implement hierarchical feature aggregation. A straightforward Data Rolling strategy is also developed to introduce dynamic information into 2D pose sequence. Extensive experiments are conducted on Human3.6M, MPI-INF-3DHP and Human-Eva benchmarks. G-SFormer series methods achieve superior performances compared with previous state-of-the-arts with only around ten percent of parameters and significantly reduced computational complexity. Additionally, G-SFormer also exhibits outstanding robustness to inaccuracies in detected 2D poses.
Authors: Xiang Gao, Zhengbo Xu, Junhan Zhao, Jiaying Liu
Abstract: Recently, large-scale text-to-image (T2I) diffusion models have emerged as a powerful tool for image-to-image translation (I2I), allowing open-domain image translation via user-provided text prompts. This paper proposes frequency-controlled diffusion model (FCDiffusion), an end-to-end diffusion-based framework that contributes a novel solution to text-guided I2I from a frequency-domain perspective. At the heart of our framework is a feature-space frequency-domain filtering module based on Discrete Cosine Transform, which filters the latent features of the source image in the DCT domain, yielding filtered image features bearing different DCT spectral bands as different control signals to the pre-trained Latent Diffusion Model. We reveal that control signals of different DCT spectral bands bridge the source image and the T2I generated image in different correlations (e.g., style, structure, layout, contour, etc.), and thus enable versatile I2I applications emphasizing different I2I correlations, including style-guided content creation, image semantic manipulation, image scene translation, and image style translation. Different from related approaches, FCDiffusion establishes a unified text-guided I2I framework suitable for diverse image translation tasks simply by switching among different frequency control branches at inference time. The effectiveness and superiority of our method for text-guided I2I are demonstrated with extensive experiments both qualitatively and quantitatively. The code is publicly available at: https://github.com/XiangGao1102/FCDiffusion.
Authors: Zhaohe Liao, Jiangtong Li, Li Niu, Liqing Zhang
Abstract: Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes and perform consistent compositional reasoning. To address these challenges, we propose a \textit{model-agnostic} Video Alignment and Answer Aggregation (VA$^{3}$) framework, which is capable of enhancing both compositional consistency and accuracy of existing VidQA methods by integrating video aligner and answer aggregator modules. The video aligner hierarchically selects the relevant video clips based on the question, while the answer aggregator deduces the answer to the question based on its sub-questions, with compositional consistency ensured by the information flow along question decomposition graph and the contrastive learning strategy. We evaluate our framework on three settings of the AGQA-Decomp dataset with three baseline methods, and propose new metrics to measure the compositional consistency of VidQA methods more comprehensively. Moreover, we propose a large language model (LLM) based automatic question decomposition pipeline to apply our framework to any VidQA dataset. We extend MSVD and NExT-QA datasets with it to evaluate our VA$^3$ framework on broader scenarios. Extensive experiments show that our framework improves both compositional consistency and accuracy of existing methods, leading to more interpretable real-world VidQA models.
Authors: Xiaoyan Yu, Jannik Franzen, Wojciech Samek, Marina M. -C. H\"ohne, Dagmar Kainmueller
Abstract: Heatmaps generated on inputs of image classification networks via explainable AI methods like Grad-CAM and LRP have been observed to resemble segmentations of input images in many cases. Consequently, heatmaps have also been leveraged for achieving weakly supervised segmentation with image-level supervision. On the other hand, losses can be imposed on differentiable heatmaps, which has been shown to serve for (1)~improving heatmaps to be more human-interpretable, (2)~regularization of networks towards better generalization, (3)~training diverse ensembles of networks, and (4)~for explicitly ignoring confounding input features. Due to the latter use case, the paradigm of imposing losses on heatmaps is often referred to as "Right for the right reasons". We unify these two lines of research by investigating semi-supervised segmentation as a novel use case for the Right for the Right Reasons paradigm. First, we show formal parallels between differentiable heatmap architectures and standard encoder-decoder architectures for image segmentation. Second, we show that such differentiable heatmap architectures yield competitive results when trained with standard segmentation losses. Third, we show that such architectures allow for training with weak supervision in the form of image-level labels and small numbers of pixel-level labels, outperforming comparable encoder-decoder models. Code is available at \url{https://github.com/Kainmueller-Lab/TW-autoencoder}.
Authors: Seunghun Lee, Jiwan Seo, Kiljoon Han, Minwoo Choi, Sunghoon Im
Abstract: In this paper, we introduce the Context-Aware Video Instance Segmentation (CAVIS), a novel framework designed to enhance instance association by integrating contextual information adjacent to each object. To efficiently extract and leverage this information, we propose the Context-Aware Instance Tracker (CAIT), which merges contextual data surrounding the instances with the core instance features to improve tracking accuracy. Additionally, we introduce the Prototypical Cross-frame Contrastive (PCC) loss, which ensures consistency in object-level features across frames, thereby significantly enhancing instance matching accuracy. CAVIS demonstrates superior performance over state-of-the-art methods on all benchmark datasets in video instance segmentation (VIS) and video panoptic segmentation (VPS). Notably, our method excels on the OVIS dataset, which is known for its particularly challenging videos.
Authors: Marawan Elbatel, Konstantinos Kamnitsas, Xiaomeng Li
Abstract: Generative modeling seeks to approximate the statistical properties of real data, enabling synthesis of new data that closely resembles the original distribution. Generative Adversarial Networks (GANs) and Denoising Diffusion Probabilistic Models (DDPMs) represent significant advancements in generative modeling, drawing inspiration from game theory and thermodynamics, respectively. Nevertheless, the exploration of generative modeling through the lens of biological evolution remains largely untapped. In this paper, we introduce a novel family of models termed Generative Cellular Automata (GeCA), inspired by the evolution of an organism from a single cell. GeCAs are evaluated as an effective augmentation tool for retinal disease classification across two imaging modalities: Fundus and Optical Coherence Tomography (OCT). In the context of OCT imaging, where data is scarce and the distribution of classes is inherently skewed, GeCA significantly boosts the performance of 11 different ophthalmological conditions, achieving a 12% increase in the average F1 score compared to conventional baselines. GeCAs outperform both diffusion methods that incorporate UNet or state-of-the art variants with transformer-based denoising models, under similar parameter constraints. Code is available at: https://github.com/xmed-lab/GeCA.
Authors: Chang Li, Pengfei Zhang, Yu Wang
Abstract: Currently the semantic segmentation task of multispectral remotely sensed imagery (MSRSI) faces the following problems: 1) Usually, only single domain feature (i.e., space domain or frequency domain) is considered; 2) downsampling operation in encoder generally leads to the accuracy loss of edge extraction; 3) multichannel features of MSRSI are not fully considered; and 4) prior knowledge of remote sensing is not fully utilized. To solve the aforementioned issues, an index-space-wave state superposition Transformer (ISWSST) is the first to be proposed for MSRSI semantic segmentation by the inspiration from quantum mechanics, whose superiority is as follows: 1) index, space and wave states are superposed or fused to simulate quantum superposition by adaptively voting decision (i.e., ensemble learning idea) for being a stronger classifier and improving the segmentation accuracy; 2) a lossless wavelet pyramid encoder-decoder module is designed to losslessly reconstruct image and simulate quantum entanglement based on wavelet transform and inverse wavelet transform for avoiding the edge extraction loss; 3) combining multispectral features (i.e. remote sensing index and channel attention mechanism) is proposed to accurately extract ground objects from original resolution images; and 4) quantum mechanics are introduced to interpret the underlying superiority of ISWSST. Experiments show that ISWSST is validated and superior to the state-of-the-art architectures for the MSRSI segmentation task, which improves the segmentation and edge extraction accuracy effectively. Codes will be available publicly after our paper is accepted.
Authors: Bac Nguyen, Stefan Uhlich, Fabien Cardinaux, Lukas Mauch, Marzieh Edraki, Aaron Courville
Abstract: Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated remarkable zero-shot performance, further adaptation of the model to downstream tasks leads to undesirable degradation for OOD data. In this work, we introduce Sparse Adaptation for Fine-Tuning (SAFT), a method that prevents fine-tuning from forgetting the general knowledge in the pre-trained model. SAFT only updates a small subset of important parameters whose gradient magnitude is large, while keeping the other parameters frozen. SAFT is straightforward to implement and conceptually simple. Extensive experiments show that with only 0.1% of the model parameters, SAFT can significantly improve the performance of CLIP. It consistently outperforms baseline methods across several benchmarks. On the few-shot learning benchmark of ImageNet and its variants, SAFT gives a gain of 5.15% on average over the conventional fine-tuning method in OOD settings.
Authors: Zhizhou Zhong, Yuxi Mi, Yuge Huang, Jianqing Xu, Guodong Mu, Shouhong Ding, Jingyun Zhang, Rizen Guo, Yunsheng Wu, Shuigeng Zhou
Abstract: Contemporary face recognition systems use feature templates extracted from face images to identify persons. To enhance privacy, face template protection techniques are widely employed to conceal sensitive identity and appearance information stored in the template. This paper identifies an emerging privacy attack form utilizing diffusion models that could nullify prior protection, referred to as inversion attacks. The attack can synthesize high-quality, identity-preserving face images from templates, revealing persons' appearance. Based on studies of the diffusion model's generative capability, this paper proposes a defense to deteriorate the attack, by rotating templates to a noise-like distribution. This is achieved efficiently by spherically and linearly interpolating templates, or slerp, on their located hypersphere. This paper further proposes to group-wisely divide and drop out templates' feature dimensions, to enhance the irreversibility of rotated templates. The division of groups and dropouts within each group are learned in a recognition-favored way. The proposed techniques are concretized as a novel face template protection technique, SlerpFace. Extensive experiments show that SlerpFace provides satisfactory recognition accuracy and comprehensive privacy protection against inversion and other attack forms, superior to prior arts.
Authors: Marco Mistretta, Alberto Baldrati, Marco Bertini, Andrew D. Bagdanov
Abstract: Vision-Language Models (VLMs) demonstrate remarkable zero-shot generalization to unseen tasks, but fall short of the performance of supervised methods in generalizing to downstream tasks with limited data. Prompt learning is emerging as a parameter-efficient method for adapting VLMs, but state-of-the-art approaches require annotated samples. In this paper we propose a novel approach to prompt learning based on unsupervised knowledge distillation from more powerful models. Our approach, which we call Knowledge Distillation Prompt Learning (KDPL), can be integrated into existing prompt learning techniques and eliminates the need for labeled examples during adaptation. Our experiments on more than ten standard benchmark datasets demonstrate that KDPL is very effective at improving generalization of learned prompts for zero-shot domain generalization, zero-shot cross-dataset generalization, and zero-shot base-to-novel class generalization problems. KDPL requires no ground-truth labels for adaptation, and moreover we show that even in the absence of any knowledge of training class names it can be used to effectively transfer knowledge. The code is publicly available at https://github.com/miccunifi/KDPL.
Authors: Hao Liang, Jiapeng Li, Tianyi Bai, Chong Chen, Conghui He, Bin Cui, 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: Xiruo Jiang, Yazhou Yao, Xili Dai, Fumin Shen, Xian-Sheng Hua, Heng-Tao Shen
Abstract: Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval. Prior literature predominantly focuses on pair-based and proxy-based methods to maximize inter-class discrepancy and minimize intra-class diversity. However, these methods tend to suffer from the collapse of the embedding space due to their over-reliance on label information. This leads to sub-optimal feature representation and inferior model performance. To maintain the structure of embedding space and avoid feature collapse, we propose a novel loss function called Anti-Collapse Loss. Specifically, our proposed loss primarily draws inspiration from the principle of Maximal Coding Rate Reduction. It promotes the sparseness of feature clusters in the embedding space to prevent collapse by maximizing the average coding rate of sample features or class proxies. Moreover, we integrate our proposed loss with pair-based and proxy-based methods, resulting in notable performance improvement. Comprehensive experiments on benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art methods. Extensive ablation studies verify the effectiveness of our method in preventing embedding space collapse and promoting generalization performance.
Authors: Chao Zhou, Yuan-Gen Wang, Zi-jia Wang, Xiangui Kang
Abstract: Adversarial examples have shown a powerful ability to make a well-trained model misclassified. Current mainstream adversarial attack methods only consider one of the distortions among $L_0$-norm, $L_2$-norm, and $L_\infty$-norm. $L_0$-norm based methods cause large modification on a single pixel, resulting in naked-eye visible detection, while $L_2$-norm and $L_\infty$-norm based methods suffer from weak robustness against adversarial defense since they always diffuse tiny perturbations to all pixels. A more realistic adversarial perturbation should be sparse and imperceptible. In this paper, we propose a novel $L_p$-norm distortion-efficient adversarial attack, which not only owns the least $L_2$-norm loss but also significantly reduces the $L_0$-norm distortion. To this aim, we design a new optimization scheme, which first optimizes an initial adversarial perturbation under $L_2$-norm constraint, and then constructs a dimension unimportance matrix for the initial perturbation. Such a dimension unimportance matrix can indicate the adversarial unimportance of each dimension of the initial perturbation. Furthermore, we introduce a new concept of adversarial threshold for the dimension unimportance matrix. The dimensions of the initial perturbation whose unimportance is higher than the threshold will be all set to zero, greatly decreasing the $L_0$-norm distortion. Experimental results on three benchmark datasets show that under the same query budget, the adversarial examples generated by our method have lower $L_0$-norm and $L_2$-norm distortion than the state-of-the-art. Especially for the MNIST dataset, our attack reduces 8.1$\%$ $L_2$-norm distortion meanwhile remaining 47$\%$ pixels unattacked. This demonstrates the superiority of the proposed method over its competitors in terms of adversarial robustness and visual imperceptibility.
Authors: Hanxi Li, Jingqi Wu, Lin Yuanbo, Hao Chen, Deyin Liu, Chunhua Shen
Abstract: In the realm of practical Anomaly Detection (AD) tasks, manual labeling of anomalous pixels proves to be a costly endeavor. Consequently, many AD methods are crafted as one-class classifiers, tailored for training sets completely devoid of anomalies, ensuring a more cost-effective approach. While some pioneering work has demonstrated heightened AD accuracy by incorporating real anomaly samples in training, this enhancement comes at the price of labor-intensive labeling processes. This paper strikes the balance between AD accuracy and labeling expenses by introducing ADClick, a novel Interactive Image Segmentation (IIS) algorithm. ADClick efficiently generates "ground-truth" anomaly masks for real defective images, leveraging innovative residual features and meticulously crafted language prompts. Notably, ADClick showcases a significantly elevated generalization capacity compared to existing state-of-the-art IIS approaches. Functioning as an anomaly labeling tool, ADClick generates high-quality anomaly labels (AP $= 94.1\%$ on MVTec AD) based on only $3$ to $5$ manual click annotations per training image. Furthermore, we extend the capabilities of ADClick into ADClick-Seg, an enhanced model designed for anomaly detection and localization. By fine-tuning the ADClick-Seg model using the weak labels inferred by ADClick, we establish the state-of-the-art performances in supervised AD tasks (AP $= 86.4\%$ on MVTec AD and AP $= 78.4\%$, PRO $= 98.6\%$ on KSDD2).
Authors: Elizabeth Hou, Ross Greenwood, Piyush Kumar
Abstract: Statistical tracking filters depend on accurate target measurements and uncertainty estimates for good tracking performance. In this work, we propose novel machine learning models for target detection and uncertainty estimation in range-Doppler map (RDM) images for Ground Moving Target Indicator (GMTI) radars. We show that by using the outputs of these models, we can significantly improve the performance of a multiple hypothesis tracker for complex multi-target air-to-ground tracking scenarios.
Authors: Son Nguyen, Thinh Nguyen, Khoa Doan, Kok-Seng Wong
Abstract: Federated Learning (FL) is a distributed machine learning approach that maintains data privacy by training on decentralized data sources. Similar to centralized machine learning, FL is also susceptible to backdoor attacks. Most backdoor attacks in FL assume a predefined target class and require control over a large number of clients or knowledge of benign clients' information. Furthermore, they are not imperceptible and are easily detected by human inspection due to clear artifacts left on the poison data. To overcome these challenges, we propose Venomancer, an effective backdoor attack that is imperceptible and allows target-on-demand. Specifically, imperceptibility is achieved by using a visual loss function to make the poison data visually indistinguishable from the original data. Target-on-demand property allows the attacker to choose arbitrary target classes via conditional adversarial training. Additionally, experiments showed that the method is robust against state-of-the-art defenses such as Norm Clipping, Weak DP, Krum, and Multi-Krum. The source code is available at https://anonymous.4open.science/r/Venomancer-3426.
Authors: Ce Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte, Yao Yao, Luc Van Gool
Abstract: We introduce Stereo Risk, a new deep-learning approach to solve the classical stereo-matching problem in computer vision. As it is well-known that stereo matching boils down to a per-pixel disparity estimation problem, the popular state-of-the-art stereo-matching approaches widely rely on regressing the scene disparity values, yet via discretization of scene disparity values. Such discretization often fails to capture the nuanced, continuous nature of scene depth. Stereo Risk departs from the conventional discretization approach by formulating the scene disparity as an optimal solution to a continuous risk minimization problem, hence the name "stereo risk". We demonstrate that $L^1$ minimization of the proposed continuous risk function enhances stereo-matching performance for deep networks, particularly for disparities with multi-modal probability distributions. Furthermore, to enable the end-to-end network training of the non-differentiable $L^1$ risk optimization, we exploited the implicit function theorem, ensuring a fully differentiable network. A comprehensive analysis demonstrates our method's theoretical soundness and superior performance over the state-of-the-art methods across various benchmark datasets, including KITTI 2012, KITTI 2015, ETH3D, SceneFlow, and Middlebury 2014.
Authors: Rui-Yang Ju, Chun-Tse Chien, Chia-Min Lin, Jen-Shiun Chiang
Abstract: Children often suffer wrist injuries in daily life, while fracture injuring radiologists usually need to analyze and interpret X-ray images before surgical treatment by surgeons. The development of deep learning has enabled neural network models to work as computer-assisted diagnosis (CAD) tools to help doctors and experts in diagnosis. Since the YOLOv8 models have obtained the satisfactory success in object detection tasks, it has been applied to fracture detection. The Global Context (GC) block effectively models the global context in a lightweight way, and incorporating it into YOLOv8 can greatly improve the model performance. This paper proposes the YOLOv8+GC model for fracture detection, which is an improved version of the YOLOv8 model with the GC block. Experimental results demonstrate that compared to the original YOLOv8 model, the proposed YOLOv8-GC model increases the mean average precision calculated at intersection over union threshold of 0.5 (mAP 50) from 63.58% to 66.32% on the GRAZPEDWRI-DX dataset, achieving the state-of-the-art (SOTA) level. The implementation code for this work is available on GitHub at https://github.com/RuiyangJu/YOLOv8_Global_Context_Fracture_Detection.
URLs: https://github.com/RuiyangJu/YOLOv8_Global_Context_Fracture_Detection.
Authors: Weizhou Liu, Xingce Wang, Haichuan Zhao, Xingfei Xue, Zhongke Wu, Xuequan Lu, Ying He
Abstract: This paper introduces a new approach for generating globally consistent normals for point clouds sampled from manifold surfaces. Given that the generalized winding number (GWN) field generated by a point cloud with globally consistent normals is a solution to a PDE with jump boundary conditions and possesses harmonic properties, and the Dirichlet energy of the GWN field can be defined as an integral over the boundary surface, we formulate a boundary energy derived from the Dirichlet energy of the GWN. Taking as input a point cloud with randomly oriented normals, we optimize this energy to restore the global harmonicity of the GWN field, thereby recovering the globally consistent normals. Experiments show that our method outperforms state-of-the-art approaches, exhibiting enhanced robustness to noise, outliers, complex topologies, and thin structures. Our code can be found at \url{https://github.com/liuweizhou319/BIM}.
Authors: Jianzhu Guo, Dingyun Zhang, Xiaoqiang Liu, Zhizhou Zhong, Yuan Zhang, Pengfei Wan, Di Zhang
Abstract: Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficiency for practical usage. To enhance the generation quality and generalization ability, we scale up the training data to about 69 million high-quality frames, adopt a mixed image-video training strategy, upgrade the network architecture, and design better motion transformation and optimization objectives. Additionally, we discover that compact implicit keypoints can effectively represent a kind of blendshapes and meticulously propose a stitching and two retargeting modules, which utilize a small MLP with negligible computational overhead, to enhance the controllability. Experimental results demonstrate the efficacy of our framework even compared to diffusion-based methods. The generation speed remarkably reaches 12.8ms on an RTX 4090 GPU with PyTorch. The inference code and models are available at https://github.com/KwaiVGI/LivePortrait
Authors: Shyam Gupta, Dhanisha Sharma, Songling Huang
Abstract: For the past three years, Kaggle has been hosting the Image Matching Challenge, which focuses on solving a 3D image reconstruction problem using a collection of 2D images. Each year, this competition fosters the development of innovative and effective methodologies by its participants. In this paper, we introduce an advanced ensemble technique that we developed, achieving a score of 0.153449 on the private leaderboard and securing the 160th position out of over 1,000 participants. Additionally, we conduct a comprehensive review of existing methods and techniques employed by top-performing teams in the competition. Our solution, alongside the insights gathered from other leading approaches, contributes to the ongoing advancement in the field of 3D image reconstruction. This research provides valuable knowledge for future participants and researchers aiming to excel in similar image matching and reconstruction challenges.
Authors: Qixiang Chen, Lei Wang, Piotr Koniusz, Tom Gedeon
Abstract: Videos contain rich spatio-temporal information. Traditional methods for extracting motion, used in tasks such as action recognition, often rely on visual contents rather than precise motion features. This phenomenon is referred to as 'blind motion extraction' behavior, which proves inefficient in capturing motions of interest due to a lack of motion-guided cues. Recently, attention mechanisms have enhanced many computer vision tasks by effectively highlighting salient visual areas. Inspired by this, we propose using a modified Sigmoid function with learnable slope and shift parameters as an attention mechanism to activate and modulate motion signals derived from frame differencing maps. This approach generates a sequence of attention maps that enhance the processing of motion-related video content. To ensure temporally continuity and smoothness of the attention maps, we apply pair-wise temporal attention variation regularization to remove unwanted motions (e.g., noise) while preserving important ones. We then perform Hadamard product between each pair of attention maps and the original video frames to highlight the evolving motions of interest over time. These highlighted motions, termed video motion prompts, are subsequently used as inputs to the model instead of the original video frames. We formalize this process as a motion prompt layer and incorporate the regularization term into the loss function to learn better motion prompts. This layer serves as an adapter between the model and the video data, bridging the gap between traditional 'blind motion extraction' and the extraction of relevant motions of interest.
Authors: Le Yang, Ziwei Zheng, Yizeng Han, Hao Cheng, Shiji Song, Gao Huang, Fan Li
Abstract: Recent proposed neural network-based Temporal Action Detection (TAD) models are inherently limited to extracting the discriminative representations and modeling action instances with various lengths from complex scenes by shared-weights detection heads. Inspired by the successes in dynamic neural networks, in this paper, we build a novel dynamic feature aggregation (DFA) module that can simultaneously adapt kernel weights and receptive fields at different timestamps. Based on DFA, the proposed dynamic encoder layer aggregates the temporal features within the action time ranges and guarantees the discriminability of the extracted representations. Moreover, using DFA helps to develop a Dynamic TAD head (DyHead), which adaptively aggregates the multi-scale features with adjusted parameters and learned receptive fields better to detect the action instances with diverse ranges from videos. With the proposed encoder layer and DyHead, a new dynamic TAD model, DyFADet, achieves promising performance on a series of challenging TAD benchmarks, including HACS-Segment, THUMOS14, ActivityNet-1.3, Epic-Kitchen 100, Ego4D-Moment QueriesV1.0, and FineAction. Code is released to https://github.com/yangle15/DyFADet-pytorch.
Authors: Weitai Kang, Gaowen Liu, Mubarak Shah, Yan Yan
Abstract: Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision signals. Although previous works achieve impressive results, their passive utilization of annotation, i.e. the sole use of the box annotation as regression ground truth, results in a suboptimal performance. In this paper, we present SegVG, a novel method transfers the box-level annotation as Segmentation signals to provide an additional pixel-level supervision for Visual Grounding. Specifically, we propose the Multi-layer Multi-task Encoder-Decoder as the target grounding stage, where we learn a regression query and multiple segmentation queries to ground the target by regression and segmentation of the box in each decoding layer, respectively. This approach allows us to iteratively exploit the annotation as signals for both box-level regression and pixel-level segmentation. Moreover, as the backbones are typically initialized by pretrained parameters learned from unimodal tasks and the queries for both regression and segmentation are static learnable embeddings, a domain discrepancy remains among these three types of features, which impairs subsequent target grounding. To mitigate this discrepancy, we introduce the Triple Alignment module, where the query, text, and vision tokens are triangularly updated to share the same space by triple attention mechanism. Extensive experiments on five widely used datasets validate our state-of-the-art (SOTA) performance.
Authors: Hezhen Hu, Zhiwen Fan, Tianhao Wu, Yihan Xi, Seoyoung Lee, Georgios Pavlakos, Zhangyang Wang
Abstract: Nuanced expressiveness, particularly through fine-grained hand and facial expressions, is pivotal for enhancing the realism and vitality of digital human representations. In this work, we focus on investigating the expressiveness of human avatars when learned from monocular RGB video; a setting that introduces new challenges in capturing and animating fine-grained details. To this end, we introduce EVA, a drivable human model that meticulously sculpts fine details based on 3D Gaussians and SMPL-X, an expressive parametric human model. Focused on enhancing expressiveness, our work makes three key contributions. First, we highlight the critical importance of aligning the SMPL-X model with RGB frames for effective avatar learning. Recognizing the limitations of current SMPL-X prediction methods for in-the-wild videos, we introduce a plug-and-play module that significantly ameliorates misalignment issues. Second, we propose a context-aware adaptive density control strategy, which is adaptively adjusting the gradient thresholds to accommodate the varied granularity across body parts. Last but not least, we develop a feedback mechanism that predicts per-pixel confidence to better guide the learning of 3D Gaussians. Extensive experiments on two benchmarks demonstrate the superiority of our framework both quantitatively and qualitatively, especially on the fine-grained hand and facial details. See the project website at \url{https://evahuman.github.io}
Authors: Mingkui Feng, Hancheng Yu, Xiaoyu Dang, Ming Zhou
Abstract: Objects in aerial images are typically embedded in complex backgrounds and exhibit arbitrary orientations. When employing oriented bounding boxes (OBB) to represent arbitrary oriented objects, the periodicity of angles could lead to discontinuities in label regression values at the boundaries, inducing abrupt fluctuations in the loss function. To address this problem, an OBB representation based on the complex plane is introduced in the oriented detection framework, and a trigonometric loss function is proposed. Moreover, leveraging prior knowledge of complex background environments and significant differences in large objects in aerial images, a conformer RPN head is constructed to predict angle information. The proposed loss function and conformer RPN head jointly generate high-quality oriented proposals. A category-aware dynamic label assignment based on predicted category feedback is proposed to address the limitations of solely relying on IoU for proposal label assignment. This method makes negative sample selection more representative, ensuring consistency between classification and regression features. Experiments were conducted on four realistic oriented detection datasets, and the results demonstrate superior performance in oriented object detection with minimal parameter tuning and time costs. Specifically, mean average precision (mAP) scores of 82.02%, 71.99%, 69.87%, and 98.77% were achieved on the DOTA-v1.0, DOTA-v1.5, DIOR-R, and HRSC2016 datasets, respectively.
Authors: Sanket Gandhi, Atul, Samanyu Mahajan, Vishal Sharma, Rushil Gupta, Arnab Kumar Mondal, Parag Singla
Abstract: Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can learning disentangled representation further improve the accuracy of visual dynamics prediction in object-centric models?" While there has been some attempt to learn such disentangled representations for the case of static images \citep{nsb}, to the best of our knowledge, ours is the first work which tries to do this in a general setting for video, without making any specific assumptions about the kind of attributes that an object might have. The key building block of our architecture is the notion of a {\em block}, where several blocks together constitute an object. Each block is represented as a linear combination of a given number of learnable concept vectors, which is iteratively refined during the learning process. The blocks in our model are discovered in an unsupervised manner, by attending over object masks, in a style similar to discovery of slots \citep{slot_attention}, for learning a dense object-centric representation. We employ self-attention via transformers over the discovered blocks to predict the next state resulting in discovery of visual dynamics. We perform a series of experiments on several benchmark 2-D, and 3-D datasets demonstrating that our architecture (1) can discover semantically meaningful blocks (2) help improve accuracy of dynamics prediction compared to SOTA object-centric models (3) perform significantly better in OOD setting where the specific attribute combinations are not seen earlier during training. Our experiments highlight the importance discovery of disentangled representation for visual dynamics prediction.
Authors: Yueyang Li, Weiming Zeng, Wenhao Dong, Luhui Cai, Lei Wang, Hongyu Chen, Hongjie Yan, Lingbin Bian, Nizhuan Wang
Abstract: Background: Deep learning models have shown promise in diagnosing neurodevelopmental disorders (NDD) like ASD and ADHD. However, many models either use graph neural networks (GNN) to construct single-level brain functional networks (BFNs) or employ spatial convolution filtering for local information extraction from rs-fMRI data, often neglecting high-order features crucial for NDD classification. Methods: We introduce a Multi-view High-order Network (MHNet) to capture hierarchical and high-order features from multi-view BFNs derived from rs-fMRI data for NDD prediction. MHNet has two branches: the Euclidean Space Features Extraction (ESFE) module and the Non-Euclidean Space Features Extraction (Non-ESFE) module, followed by a Feature Fusion-based Classification (FFC) module for NDD identification. ESFE includes a Functional Connectivity Generation (FCG) module and a High-order Convolutional Neural Network (HCNN) module to extract local and high-order features from BFNs in Euclidean space. Non-ESFE comprises a Generic Internet-like Brain Hierarchical Network Generation (G-IBHN-G) module and a High-order Graph Neural Network (HGNN) module to capture topological and high-order features in non-Euclidean space. Results: Experiments on three public datasets show that MHNet outperforms state-of-the-art methods using both AAL1 and Brainnetome Atlas templates. Extensive ablation studies confirm the superiority of MHNet and the effectiveness of using multi-view fMRI information and high-order features. Our study also offers atlas options for constructing more sophisticated hierarchical networks and explains the association between key brain regions and NDD. Conclusion: MHNet leverages multi-view feature learning from both Euclidean and non-Euclidean spaces, incorporating high-order information from BFNs to enhance NDD classification performance.
Authors: Mingzhe Guo, Zhipeng Zhang, Liping Jing, Yuan He, Ke Wang, Heng Fan
Abstract: We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation.
Authors: Weitai Kang, Luowei Zhou, Junyi Wu, Changchang Sun, Yan Yan
Abstract: Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt transformer-based models to fuse features from both modalities, further introducing various modules that modulate visual features to align with the language expressions and eliminate the irrelevant redundant information. However, their loss function, still adopting common Object Detection losses, solely governs the bounding box regression output, failing to fully optimize for the above objectives. To tackle this problem, in this paper, we first analyze the attention mechanisms of transformer-based models. Building upon this, we further propose a novel framework named Attention-Driven Constraint Balancing (AttBalance) to optimize the behavior of visual features within language-relevant regions. Extensive experimental results show that our method brings impressive improvements. Specifically, we achieve constant improvements over five different models evaluated on four different benchmarks. Moreover, we attain a new state-of-the-art performance by integrating our method into QRNet.
Authors: Weitai Kang, Mengxue Qu, Yunchao Wei, Yan Yan
Abstract: Semi-Supervised Visual Grounding (SSVG) is a new challenge for its sparse labeled data with the need for multimodel understanding. A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student framework to provide pseudo confidence supervision and attention-based supervision. However, this approach is incompatible with current state-of-the-art visual grounding models, which follow the Transformer-based pipeline. These pipelines directly regress results without region proposals or foreground binary classification, rendering them unsuitable for fitting in RefTeacher due to the absence of confidence scores. Furthermore, the geometric difference in teacher and student inputs, stemming from different data augmentations, induces natural misalignment in attention-based constraints. To establish a compatible SSVG framework, our paper proposes the ACTive REtraining approach for Semi-Supervised Visual Grounding, abbreviated as ACTRESS. Initially, the model is enhanced by incorporating an additional quantized detection head to expose its detection confidence. Building upon this, ACTRESS consists of an active sampling strategy and a selective retraining strategy. The active sampling strategy iteratively selects high-quality pseudo labels by evaluating three crucial aspects: Faithfulness, Robustness, and Confidence, optimizing the utilization of unlabeled data. The selective retraining strategy retrains the model with periodic re-initialization of specific parameters, facilitating the model's escape from local minima. Extensive experiments demonstrates our superior performance on widely-used benchmark datasets.
Authors: Wei Xu, Chunsheng Shi, Sifan Tu, Xin Zhou, Dingkang Liang, Xiang Bai
Abstract: We propose UniSeg3D, a unified 3D segmentation framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary semantic segmentation tasks within a single model. Most previous 3D segmentation approaches are specialized for a specific task, thereby limiting their understanding of 3D scenes to a task-specific perspective. In contrast, the proposed method unifies six tasks into unified representations processed by the same Transformer. It facilitates inter-task knowledge sharing and, therefore, promotes comprehensive 3D scene understanding. To take advantage of multi-task unification, we enhance the performance by leveraging task connections. Specifically, we design a knowledge distillation method and a contrastive learning method to transfer task-specific knowledge across different tasks. Benefiting from extensive inter-task knowledge sharing, our UniSeg3D becomes more powerful. Experiments on three benchmarks, including the ScanNet20, ScanRefer, and ScanNet200, demonstrate that the UniSeg3D consistently outperforms current SOTA methods, even those specialized for individual tasks. We hope UniSeg3D can serve as a solid unified baseline and inspire future work. The code will be available at https://dk-liang.github.io/UniSeg3D/.
Authors: Lia Morra, Antonio Santangelo, Pietro Basci, Luca Piano, Fabio Garcea, Fabrizio Lamberti, Massimo Leone
Abstract: Social networks are creating a digital world in which the cognitive, emotional, and pragmatic value of the imagery of human faces and bodies is arguably changing. However, researchers in the digital humanities are often ill-equipped to study these phenomena at scale. This work presents FRESCO (Face Representation in E-Societies through Computational Observation), a framework designed to explore the socio-cultural implications of images on social media platforms at scale. FRESCO deconstructs images into numerical and categorical variables using state-of-the-art computer vision techniques, aligning with the principles of visual semiotics. The framework analyzes images across three levels: the plastic level, encompassing fundamental visual features like lines and colors; the figurative level, representing specific entities or concepts; and the enunciation level, which focuses particularly on constructing the point of view of the spectator and observer. These levels are analyzed to discern deeper narrative layers within the imagery. Experimental validation confirms the reliability and utility of FRESCO, and we assess its consistency and precision across two public datasets. Subsequently, we introduce the FRESCO score, a metric derived from the framework's output that serves as a reliable measure of similarity in image content.
Authors: Zhe Min, Zachary M. C. Baum, Shaheer U. Saeed, Mark Emberton, Dean C. Barratt, Zeike A. Taylor, Yipeng Hu
Abstract: This paper investigates both biomechanical-constrained non-rigid medical image registrations and accurate identifications of material properties for soft tissues, using physics-informed neural networks (PINNs). The complex nonlinear elasticity theory is leveraged to formally establish the partial differential equations (PDEs) representing physics laws of biomechanical constraints that need to be satisfied, with which registration and identification tasks are treated as forward (i.e., data-driven solutions of PDEs) and inverse (i.e., parameter estimation) problems under PINNs respectively. Two net configurations (i.e., Cfg1 and Cfg2) have also been compared for both linear and nonlinear physics model. Two sets of experiments have been conducted, using pairs of undeformed and deformed MR images from clinical cases of prostate cancer biopsy. Our contributions are summarised as follows. 1) We developed a learning-based biomechanical-constrained non-rigid registration algorithm using PINNs, where linear elasticity is generalised to the nonlinear version. 2) We demonstrated extensively that nonlinear elasticity shows no statistical significance against linear models in computing point-wise displacement vectors but their respective benefits may depend on specific patients, with finite-element (FE) computed ground-truth. 3) We formulated and solved the inverse parameter estimation problem, under the joint optimisation scheme of registration and parameter identification using PINNs, whose solutions can be accurately found by locating saddle points.
Authors: Tiankai Hang, Shuyang Gu
Abstract: Diffusion models have emerged as the de facto choice for generating visual signals. However, training a single model to predict noise across various levels poses significant challenges, necessitating numerous iterations and incurring significant computational costs. Various approaches, such as loss weighting strategy design and architectural refinements, have been introduced to expedite convergence. In this study, we propose a novel approach to design the noise schedule for enhancing the training of diffusion models. Our key insight is that the importance sampling of the logarithm of the Signal-to-Noise ratio (logSNR), theoretically equivalent to a modified noise schedule, is particularly beneficial for training efficiency when increasing the sample frequency around $\log \text{SNR}=0$. We empirically demonstrate the superiority of our noise schedule over the standard cosine schedule. Furthermore, we highlight the advantages of our noise schedule design on the ImageNet benchmark, showing that the designed schedule consistently benefits different prediction targets.
Authors: Shubham Kale, Shashank Sharma, Abhilash Khuntia
Abstract: This project focuses on creating a smart surveillance system for Indian cities that can identify and analyze people's attributes in real time. Using advanced technologies like artificial intelligence and machine learning, the system can recognize attributes such as upper body color, what the person is wearing, accessories they are wearing, headgear, etc., and analyze behavior through cameras installed around the city.
Authors: Zhantao Yang, Ruili Feng, Keyu Yan, Huangji Wang, Zhicai Wang, Shangwen Zhu, Han Zhang, Jie Xiao, Pingyu Wu, Kai Zhu, Jixuan Chen, Chen-Wei Xie, Chaojie Mao, Yue Yang, Hongyang Zhang, Yu Liu, Fan Cheng
Abstract: This paper presents Bag-of-Concept Graph (BACON) to gift models with limited linguistic abilities to taste the privilege of Vision Language Models (VLMs) and boost downstream tasks such as detection, visual question answering (VQA), and image generation. Since the visual scenes in physical worlds are structured with complex relations between objects, BACON breaks down annotations into basic minimum elements and presents them in a graph structure. Element-wise style enables easy understanding, and structural composition liberates difficult locating. Careful prompt design births the BACON captions with the help of public-available VLMs and segmentation methods. In this way, we gather a dataset with 100K annotated images, which endow VLMs with remarkable capabilities, such as accurately generating BACON, transforming prompts into BACON format, envisioning scenarios in the style of BACONr, and dynamically modifying elements within BACON through interactive dialogue and more. Wide representative experiments, including detection, VQA, and image generation tasks, tell BACON as a lifeline to achieve previous out-of-reach tasks or excel in their current cutting-edge solutions.
Authors: Pan Zhang, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Rui Qian, Lin Chen, Qipeng Guo, Haodong Duan, Bin Wang, Linke Ouyang, Songyang Zhang, Wenwei Zhang, Yining Li, Yang Gao, Peng Sun, Xinyue Zhang, Wei Li, Jingwen Li, Wenhai Wang, Hang Yan, Conghui He, Xingcheng Zhang, Kai Chen, Jifeng Dai, Yu Qiao, Dahua Lin, Jiaqi Wang
Abstract: We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks. The InternLM-XComposer-2.5 is publicly available at https://github.com/InternLM/InternLM-XComposer.
Authors: Shengcheng Luo, Quanquan Peng, Jun Lv, Kaiwen Hong, Katherine Rose Driggs-Campbell, Cewu Lu, Yong-Lu Li
Abstract: Employing a teleoperation system for gathering demonstrations offers the potential for more efficient learning of robot manipulation. However, teleoperating a robot arm equipped with a dexterous hand or gripper, via a teleoperation system poses significant challenges due to its high dimensionality, complex motions, and differences in physiological structure. In this study, we introduce a novel system for joint learning between human operators and robots, that enables human operators to share control of a robot end-effector with a learned assistive agent, facilitating simultaneous human demonstration collection and robot manipulation teaching. In this setup, as data accumulates, the assistive agent gradually learns. Consequently, less human effort and attention are required, enhancing the efficiency of the data collection process. It also allows the human operator to adjust the control ratio to achieve a trade-off between manual and automated control. We conducted experiments in both simulated environments and physical real-world settings. Through user studies and quantitative evaluations, it is evident that the proposed system could enhance data collection efficiency and reduce the need for human adaptation while ensuring the collected data is of sufficient quality for downstream tasks. Videos are available at https://norweig1an.github.io/human-agent-joint-learning.github.io/.
URLs: https://norweig1an.github.io/human-agent-joint-learning.github.io/.
Authors: Xiaotian Zou, Yongkang Chen
Abstract: Large Visual Language Models (VLMs) such as GPT-4 have achieved remarkable success in generating comprehensive and nuanced responses, surpassing the capabilities of large language models. However, with the integration of visual inputs, new security concerns emerge, as malicious attackers can exploit multiple modalities to achieve their objectives. This has led to increasing attention on the vulnerabilities of VLMs to jailbreak. Most existing research focuses on generating adversarial images or nonsensical image collections to compromise these models. However, the challenge of leveraging meaningful images to produce targeted textual content using the VLMs' logical comprehension of images remains unexplored. In this paper, we explore the problem of logical jailbreak from meaningful images to text. To investigate this issue, we introduce a novel dataset designed to evaluate flowchart image jailbreak. Furthermore, we develop a framework for text-to-text jailbreak using VLMs. Finally, we conduct an extensive evaluation of the framework on GPT-4o and GPT-4-vision-preview, with jailbreak rates of 92.8% and 70.0%, respectively. Our research reveals significant vulnerabilities in current VLMs concerning image-to-text jailbreak. These findings underscore the need for a deeper examination of the security flaws in VLMs before their practical deployment.
Authors: Sherri Harms
Abstract: It is clear, from the major press coverage that Virtual Reality (VR) development is garnering, that there is a huge amount of development interest in VR across multiple industries, including video streaming, gaming and simulated learning. Even though PC, web, and mobile are still the top platforms for software development, it is important for university computer science (CS) programs to expose students to VR as a development platform. Additionally, it is important for CS students to learn how to learn about new technologies, since change is constant in the CS field. CS curriculum changes happen much slower than the pace of technology adoption. As new technologies are introduced, CS faculty and students often learn together, especially in smaller CS programs. This paper describes how student-led VR projects are used, across the CS curriculum, as basic CS concepts are covered. The student-led VR projects are engaging, and promote learning and creativity. Additionally, each student project inspires more students to try their hand at VR development as well.
Authors: Zach Eidex, Mojtaba Safari, Jacob Wynne, Richard L. J. Qiu, Tonghe Wang, David Viar Hernandez, Hui-Kuo Shu, Hui Mao, Xiaofeng Yang
Abstract: Purpose: Apparent diffusion coefficient (ADC) maps derived from diffusion weighted (DWI) MRI provides functional measurements about the water molecules in tissues. However, DWI is time consuming and very susceptible to image artifacts, leading to inaccurate ADC measurements. This study aims to develop a deep learning framework to synthesize ADC maps from multi-parametric MR images. Methods: We proposed the multiparametric residual vision transformer model (MPR-ViT) that leverages the long-range context of ViT layers along with the precision of convolutional operators. Residual blocks throughout the network significantly increasing the representational power of the model. The MPR-ViT model was applied to T1w and T2- fluid attenuated inversion recovery images of 501 glioma cases from a publicly available dataset including preprocessed ADC maps. Selected patients were divided into training (N=400), validation (N=50) and test (N=51) sets, respectively. Using the preprocessed ADC maps as ground truth, model performance was evaluated and compared against the Vision Convolutional Transformer (VCT) and residual vision transformer (ResViT) models. Results: The results are as follows using T1w + T2-FLAIR MRI as inputs: MPR-ViT - PSNR: 31.0 +/- 2.1, MSE: 0.009 +/- 0.0005, SSIM: 0.950 +/- 0.015. In addition, ablation studies showed the relative impact on performance of each input sequence. Both qualitative and quantitative results indicate that the proposed MR- ViT model performs favorably against the ground truth data. Conclusion: We show that high-quality ADC maps can be synthesized from structural MRI using a MPR- VCT model. Our predicted images show better conformality to the ground truth volume than ResViT and VCT predictions. These high-quality synthetic ADC maps would be particularly useful for disease diagnosis and intervention, especially when ADC maps have artifacts or are unavailable.
Authors: Joan Nwatu, Oana Ignat, Rada Mihalcea
Abstract: To address this issue, we formulate translated non-English, geographic, and socioeconomic integrated prompts and evaluate their impact on VL model performance for data from different countries and income groups. Our findings show that geographic and socioeconomic integrated prompts improve VL performance on lower-income data and favor the retrieval of topic appearances commonly found in data from low-income households. From our analyses, we identify and highlight contexts where these strategies yield the most improvements. Our model analysis code is publicly available at https://github.com/Anniejoan/Uplifting-Lower-income-data .
URLs: https://github.com/Anniejoan/Uplifting-Lower-income-data
Authors: Furqan Shaukat, Syed Muhammad Anwar, Abhijeet Parida, Van Khanh Lam, Marius George Linguraru, Mubarak Shah
Abstract: Lung cancer has been one of the major threats to human life for decades. Computer-aided diagnosis can help with early lung nodul detection and facilitate subsequent nodule characterization. Large Visual Language models (VLMs) have been found effective for multiple downstream medical tasks that rely on both imaging and text data. However, lesion level detection and subsequent diagnosis using VLMs have not been explored yet. We propose CADe, for segmenting lung nodules in a zero-shot manner using a variant of the Segment Anything Model called MedSAM. CADe trains on a prompt suite on input computed tomography (CT) scans by using the CLIP text encoder through prefix tuning. We also propose, CADx, a method for the nodule characterization as benign/malignant by making a gallery of radiomic features and aligning image-feature pairs through contrastive learning. Training and validation of CADe and CADx have been done using one of the largest publicly available datasets, called LIDC. To check the generalization ability of the model, it is also evaluated on a challenging dataset, LUNGx. Our experimental results show that the proposed methods achieve a sensitivity of 0.86 compared to 0.76 that of other fully supervised methods.The source code, datasets and pre-processed data can be accessed using the link:
Authors: Francis Xiatian Zhang, Shuang Chen, Xianghua Xie, Hubert P. H. Shum
Abstract: Video inpainting fills in corrupted video content with plausible replacements. While recent advances in endoscopic video inpainting have shown potential for enhancing the quality of endoscopic videos, they mainly repair 2D visual information without effectively preserving crucial 3D spatial details for clinical reference. Depth-aware inpainting methods attempt to preserve these details by incorporating depth information. Still, in endoscopic contexts, they face challenges including reliance on pre-acquired depth maps, less effective fusion designs, and ignorance of the fidelity of 3D spatial details. To address them, we introduce a novel Depth-aware Endoscopic Video Inpainting (DAEVI) framework. It features a Spatial-Temporal Guided Depth Estimation module for direct depth estimation from visual features, a Bi-Modal Paired Channel Fusion module for effective channel-by-channel fusion of visual and depth information, and a Depth Enhanced Discriminator to assess the fidelity of the RGB-D sequence comprised of the inpainted frames and estimated depth images. Experimental evaluations on established benchmarks demonstrate our framework's superiority, achieving a 2% improvement in PSNR and a 6% reduction in MSE compared to state-of-the-art methods. Qualitative analyses further validate its enhanced ability to inpaint fine details, highlighting the benefits of integrating depth information into endoscopic inpainting.
Authors: Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges, Romann M. Weber
Abstract: Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the training procedure by periodically inserting a null condition. There is also no clear extension of CFG to unconditional models. In this paper, we revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG), which provides the benefits of CFG without the need for any special training procedures. Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model. Additionally, by leveraging the time-step information encoded in all diffusion networks, we propose an extension of CFG, called time-step guidance (TSG), which can be applied to any diffusion model, including unconditional ones. Our guidance techniques are easy to implement and have the same sampling cost as CFG. Through extensive experiments, we demonstrate that ICG matches the performance of standard CFG across various conditional diffusion models. Moreover, we show that TSG improves generation quality in a manner similar to CFG, without relying on any conditional information.
Authors: Cuong Pham, Cuong C. Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do
Abstract: Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs.
Authors: Jiayue Chu, Chenhe Du, Xiyue Lin, Yuyao Zhang, Hongjiang Wei
Abstract: Reconstructing high-fidelity magnetic resonance (MR) images from under-sampled k-space is a commonly used strategy to reduce scan time. The posterior sampling of diffusion models based on the real measurement data holds significant promise of improved reconstruction accuracy. However, traditional posterior sampling methods often lack effective data consistency guidance, leading to inaccurate and unstable reconstructions. Implicit neural representation (INR) has emerged as a powerful paradigm for solving inverse problems by modeling a signal's attributes as a continuous function of spatial coordinates. In this study, we present a novel posterior sampler for diffusion models using INR, named DiffINR. The INR-based component incorporates both the diffusion prior distribution and the MRI physical model to ensure high data fidelity. DiffINR demonstrates superior performance on experimental datasets with remarkable accuracy, even under high acceleration factors (up to R=12 in single-channel reconstruction). Notably, our proposed framework can be a generalizable framework to solve inverse problems in other medical imaging tasks.
Authors: Haimin Zhang, Jiahao Xia, Min Xu
Abstract: Combining the message-passing paradigm with the global attention mechanism has emerged as an effective framework for learning over graphs. The message-passing paradigm and the global attention mechanism fundamentally generate node embeddings based on information aggregated from a node's local neighborhood or from the whole graph. The most basic and commonly used aggregation approach is to take the sum of information from a node's local neighbourhood or from the whole graph. However, it is unknown if the dominant information is from a node itself or from the node's neighbours (or the rest of the graph nodes). Therefore, there exists information lost at each layer of embedding generation, and this information lost could be accumulated and become more serious when more layers are used in the model. In this paper, we present a differential encoding method to address the issue of information lost. The idea of our method is to encode the differential representation between the information from a node's neighbours (or the rest of the graph nodes) and that from the node itself. The obtained differential encoding is then combined with the original aggregated local or global representation to generate the updated node embedding. By integrating differential encodings, the representational ability of generated node embeddings is improved. The differential encoding method is empirically evaluated on different graph tasks on seven benchmark datasets. The results show that it is a general method that improves the message-passing update and the global attention update, advancing the state-of-the-art performance for graph representation learning on these datasets.
Authors: Zhiqi Bu, Shiyun Xu
Abstract: We propose the generalized Newton's method (GeN) -- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the intensive tuning of the learning rate scheduler. In practice, out method is easily implementable, since it only requires additional forward passes with almost zero computational overhead (in terms of training time and memory cost), if the overhead is amortized over many iterations. We present extensive experiments on language and vision tasks (e.g. GPT and ResNet) to showcase that GeN optimizers match the state-of-the-art performance, which was achieved with carefully tuned learning rate schedulers. Code to be released at \url{https://github.com/ShiyunXu/AutoGeN}.
Authors: Fan Luo, Juan Zhang, Shenghui Xu
Abstract: Self-attention-based networks have achieved remarkable performance in sequential recommendation tasks. A crucial component of these models is positional encoding. In this study, we delve into the learned positional embedding, demonstrating that it often captures the distance between tokens. Building on this insight, we introduce novel attention models that directly learn positional relations. Extensive experiments reveal that our proposed models, \textbf{PARec} and \textbf{FPARec} outperform previous self-attention-based approaches.Our code is available at the link for anonymous review: https://anonymous.4open.science/ r/FPARec-2C55/
Authors: Yihan Hu, Siqi Chai, Zhening Yang, Jingyu Qian, Kun Li, Wenxin Shao, Haichao Zhang, Wei Xu, Qiang Liu
Abstract: As autonomous driving systems being deployed to millions of vehicles, there is a pressing need of improving the system's scalability, safety and reducing the engineering cost. A realistic, scalable, and practical simulator of the driving world is highly desired. In this paper, we present an efficient solution based on generative models which learns the dynamics of the driving scenes. With this model, we can not only simulate the diverse futures of a given driving scenario but also generate a variety of driving scenarios conditioned on various prompts. Our innovative design allows the model to operate in both full-Autoregressive and partial-Autoregressive modes, significantly improving inference and training speed without sacrificing generative capability. This efficiency makes it ideal for being used as an online reactive environment for reinforcement learning, an evaluator for planning policies, and a high-fidelity simulator for testing. We evaluated our model against two real-world datasets: the Waymo motion dataset and the nuPlan dataset. On the simulation realism and scene generation benchmark, our model achieves the state-of-the-art performance. And in the planning benchmarks, our planner outperforms the prior arts. We conclude that the proposed generative model may serve as a foundation for a variety of motion planning tasks, including data generation, simulation, planning, and online training. Source code is public at https://github.com/HorizonRobotics/GUMP/
Authors: Zhaotian Weng, Zijun Gao, Jerone Andrews, Jieyu Zhao
Abstract: Vision-language models (VLMs) pre-trained on extensive datasets can inadvertently learn biases by correlating gender information with specific objects or scenarios. Current methods, which focus on modifying inputs and monitoring changes in the model's output probability scores, often struggle to comprehensively understand bias from the perspective of model components. We propose a framework that incorporates causal mediation analysis to measure and map the pathways of bias generation and propagation within VLMs. This approach allows us to identify the direct effects of interventions on model bias and the indirect effects of interventions on bias mediated through different model components. Our results show that image features are the primary contributors to bias, with significantly higher impacts than text features, specifically accounting for 32.57% and 12.63% of the bias in the MSCOCO and PASCAL-SENTENCE datasets, respectively. Notably, the image encoder's contribution surpasses that of the text encoder and the deep fusion encoder. Further experimentation confirms that contributions from both language and vision modalities are aligned and non-conflicting. Consequently, focusing on blurring gender representations within the image encoder, which contributes most to the model bias, reduces bias efficiently by 22.03% and 9.04% in the MSCOCO and PASCAL-SENTENCE datasets, respectively, with minimal performance loss or increased computational demands.
Authors: Pandiyaraju V, Shravan Venkatraman, Pavan Kumar S, Santhosh Malarvannan, Kannan A
Abstract: Breast cancer poses a profound threat to lives globally, claiming numerous lives each year. Therefore, timely detection is crucial for early intervention and improved chances of survival. Accurately diagnosing and classifying breast tumors using ultrasound images is a persistent challenge in medicine, demanding cutting-edge solutions for improved treatment strategies. This research introduces multiattention-enhanced deep learning (DL) frameworks designed for the classification and segmentation of breast cancer tumors from ultrasound images. A spatial channel attention mechanism is proposed for segmenting tumors from ultrasound images, utilizing a novel LinkNet DL framework with an InceptionResNet backbone. Following this, the paper proposes a deep convolutional neural network with an integrated multi-attention framework (DCNNIMAF) to classify the segmented tumor as benign, malignant, or normal. From experimental results, it is observed that the segmentation model has recorded an accuracy of 98.1%, with a minimal loss of 0.6%. It has also achieved high Intersection over Union (IoU) and Dice Coefficient scores of 96.9% and 97.2%, respectively. Similarly, the classification model has attained an accuracy of 99.2%, with a low loss of 0.31%. Furthermore, the classification framework has achieved outstanding F1-Score, precision, and recall values of 99.1%, 99.3%, and 99.1%, respectively. By offering a robust framework for early detection and accurate classification of breast cancer, this proposed work significantly advances the field of medical image analysis, potentially improving diagnostic precision and patient outcomes.
Authors: Eui Jun Hwang, Sukmin Cho, Huije Lee, Youngwoo Yoon, Jong C. Park
Abstract: Sign language, essential for the deaf and hard-of-hearing, presents unique challenges in translation and production due to its multimodal nature and the inherent ambiguity in mapping sign language motion to spoken language words. Previous methods often rely on gloss annotations, requiring time-intensive labor and specialized expertise in sign language. Gloss-free methods have emerged to address these limitations, but they often depend on external sign language data or dictionaries, failing to completely eliminate the need for gloss annotations. There is a clear demand for a comprehensive approach that can supplant gloss annotations and be utilized for both Sign Language Translation (SLT) and Sign Language Production (SLP). We introduce Universal Gloss-level Representation (UniGloR), a unified and self-supervised solution for both SLT and SLP, trained on multiple datasets including PHOENIX14T, How2Sign, and NIASL2021. Our results demonstrate UniGloR's effectiveness in the translation and production tasks. We further report an encouraging result for the Sign Language Recognition (SLR) on previously unseen data. Our study suggests that self-supervised learning can be made in a unified manner, paving the way for innovative and practical applications in future research.
Authors: Nelson de Moura (ASTRA), Augustin Gervreau-Mercier (ASTRA), Fernando Garrido (ASTRA), Fawzi Nashashibi (ASTRA)
Abstract: The implementation of road user models that realistically reproduce a credible behavior in a multi-agentsimulation is still an open problem. A data-driven approach consists on to deduce behaviors that may exist in real situation to obtain different types of trajectories from a large set of observations. The data, and its classification, could then be used to train models capable to extrapolate such behavior. Cars and two different types of Vulnerable Road Users (VRU) will be considered by the trajectory clustering methods proposed: pedestrians and cyclists. The results reported here evaluate methods to extract well-defined trajectory classes from raw data without the use of map information while also separating ''eccentric'' or incomplete trajectories from the ones that are complete and representative in any scenario. Two environments will serve as test for the methods develop, three different intersections and one roundabout. The resulting clusters of trajectories can then be used for prediction or learning tasks or discarded if it is composed by outliers.
Authors: Tariq M Khan, Shahzaib Iqbal, Syed S. Naqvi, Imran Razzak, Erik Meijering
Abstract: Retinal diseases can cause irreversible vision loss in both eyes if not diagnosed and treated early. Since retinal diseases are so complicated, retinal imaging is likely to show two or more abnormalities. Current deep learning techniques for segmenting retinal images with many labels and attributes have poor detection accuracy and generalisability. This paper presents a multipath convolutional neural network for multifeature segmentation. The proposed network is lightweight and spatially sensitive to information. A patch-based implementation is used to extract local image features, and focal modulation attention blocks are incorporated between the encoder and the decoder for improved segmentation. Filter optimisation is used to prevent filter overlaps and speed up model convergence. A combination of convolution operations and group convolution operations is used to reduce computational costs. This is the first robust and generalisable network capable of segmenting multiple features of fundus images (including retinal vessels, microaneurysms, optic discs, haemorrhages, hard exudates, and soft exudates). The results of our experimental evaluation on more than ten publicly available datasets with multiple features show that the proposed network outperforms recent networks despite having a small number of learnable parameters.
Authors: Frederic Z. Zhang, Paul Albert, Cristian Rodriguez-Opazo, Anton van den Hengel, Ehsan Abbasnejad
Abstract: Pre-trained models produce strong generic representations that can be adapted via fine-tuning. The learned weight difference relative to the pre-trained model, known as a task vector, characterises the direction and stride of fine-tuning. The significance of task vectors is such that simple arithmetic operations on them can be used to combine diverse representations from different domains. This paper builds on these properties of task vectors and aims to answer (1) whether components of task vectors, particularly parameter blocks, exhibit similar characteristics, and (2) how such blocks can be used to enhance knowledge composition and transfer. To this end, we introduce aTLAS, an algorithm that linearly combines parameter blocks with different learned coefficients, resulting in anisotropic scaling at the task vector level. We show that such linear combinations explicitly exploit the low intrinsic dimensionality of pre-trained models, with only a few coefficients being the learnable parameters. Furthermore, composition of parameter blocks leverages the already learned representations, thereby reducing the dependency on large amounts of data. We demonstrate the effectiveness of our method in task arithmetic, few-shot recognition and test-time adaptation, with supervised or unsupervised objectives. In particular, we show that (1) learned anisotropic scaling allows task vectors to be more disentangled, causing less interference in composition; (2) task vector composition excels with scarce or no labeled data and is less prone to domain shift, thus leading to better generalisability; (3) mixing the most informative parameter blocks across different task vectors prior to training can reduce the memory footprint and improve the flexibility of knowledge transfer. Moreover, we show the potential of aTLAS as a PEFT method, particularly with less data, and demonstrate that its scalibility.
Authors: Yipin Guo, Zihao Li, Yilin Lang, Qinyuan Ren
Abstract: Operators devoid of multiplication, such as Shift and Add, have gained prominence for their compatibility with hardware. However, neural networks (NNs) employing these operators typically exhibit lower accuracy compared to conventional NNs with identical structures. ShiftAddAug uses costly multiplication to augment efficient but less powerful multiplication-free operators, improving performance without any inference overhead. It puts a ShiftAdd tiny NN into a large multiplicative model and encourages it to be trained as a sub-model to obtain additional supervision. In order to solve the weight discrepancy problem between hybrid operators, a new weight sharing method is proposed. Additionally, a novel two stage neural architecture search is used to obtain better augmentation effects for smaller but stronger multiplication-free tiny neural networks. The superiority of ShiftAddAug is validated through experiments in image classification and semantic segmentation, consistently delivering noteworthy enhancements. Remarkably, it secures up to a 4.95% increase in accuracy on the CIFAR100 compared to its directly trained counterparts, even surpassing the performance of multiplicative NNs.
Authors: Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
Abstract: Despite notable advancements, the integration of deep learning (DL) techniques into impactful clinical applications, particularly in the realm of digital histopathology, has been hindered by challenges associated with achieving robust generalization across diverse imaging domains and characteristics. Traditional mitigation strategies in this field such as data augmentation and stain color normalization have proven insufficient in addressing this limitation, necessitating the exploration of alternative methodologies. To this end, we propose a novel generative method for domain generalization in histopathology images. Our method employs a generative, self-supervised Vision Transformer to dynamically extract characteristics of image patches and seamlessly infuse them into the original images, thereby creating novel, synthetic images with diverse attributes. By enriching the dataset with such synthesized images, we aim to enhance its holistic nature, facilitating improved generalization of DL models to unseen domains. Extensive experiments conducted on two distinct histopathology datasets demonstrate the effectiveness of our proposed approach, outperforming the state of the art substantially, on the Camelyon17-wilds challenge dataset (+2%) and on a second epithelium-stroma dataset (+26%). Furthermore, we emphasize our method's ability to readily scale with increasingly available unlabeled data samples and more complex, higher parametric architectures. Source code is available at https://github.com/sdoerrich97/vits-are-generative-models .
URLs: https://github.com/sdoerrich97/vits-are-generative-models
Authors: Luyi Han, Tao Tan, Tianyu Zhang, Xin Wang, Yuan Gao, Chunyao Lu, Xinglong Liang, Haoran Dou, Yunzhi Huang, Ritse Mann
Abstract: Adversarial learning helps generative models translate MRI from source to target sequence when lacking paired samples. However, implementing MRI synthesis with adversarial learning in clinical settings is challenging due to training instability and mode collapse. To address this issue, we leverage intermediate sequences to estimate the common latent space among multi-sequence MRI, enabling the reconstruction of distinct sequences from the common latent space. We propose a generative model that compresses discrete representations of each sequence to estimate the Gaussian distribution of vector-quantized common (VQC) latent space between multiple sequences. Moreover, we improve the latent space consistency with contrastive learning and increase model stability by domain augmentation. Experiments using BraTS2021 dataset show that our non-adversarial model outperforms other GAN-based methods, and VQC latent space aids our model to achieve (1) anti-interference ability, which can eliminate the effects of noise, bias fields, and artifacts, and (2) solid semantic representation ability, with the potential of one-shot segmentation. Our code is publicly available.
Authors: Victor W{\aa}hlstrand Sk\"arstr\"om, Lisa Johansson, Jennifer Alv\'en, Mattias Lorentzon, Ida H\"aggstr\"om
Abstract: We present a novel method for explainable vertebral fracture assessment (XVFA) in low-dose radiographs using deep neural networks, incorporating vertebra detection and keypoint localization with uncertainty estimates. We incorporate Genant's semi-quantitative criteria as a differentiable rule-based means of classifying both vertebra fracture grade and morphology. Unlike previous work, XVFA provides explainable classifications relatable to current clinical methodology, as well as uncertainty estimations, while at the same time surpassing state-of-the art methods with a vertebra-level sensitivity of 93% and end-to-end AUC of 97% in a challenging setting. Moreover, we compare intra-reader agreement with model uncertainty estimates, with model reliability on par with human annotators.
Authors: Jamimamul Bakas, Praneta Rawat, Kalyan Kokkalla, Ruchira Naskar
Abstract: In this work, we deal with the problem of re compression based image forgery detection, where some regions of an image are modified illegitimately, hence giving rise to presence of dual compression characteristics within a single image. There have been some significant researches in this direction, in the last decade. However, almost all existing techniques fail to detect this form of forgery, when the first compression factor is greater than the second. We address this problem in re compression based forgery detection, here Recently, Machine Learning techniques have started gaining a lot of importance in the domain of digital image forensics. In this work, we propose a Convolution Neural Network based deep learning architecture, which is capable of detecting the presence of re compression based forgery in JPEG images. The proposed architecture works equally efficiently, even in cases where the first compression ratio is greater than the second. In this work, we also aim to localize the regions of image manipulation based on re compression features, using the trained neural network. Our experimental results prove that the proposed method outperforms the state of the art, with respect to forgery detection and localization accuracy.
Authors: Ziad Al-Haj Hemidi, Christian Weihsbach, Mattias P. Heinrich
Abstract: Motion artifacts in Magnetic Resonance Imaging (MRI) arise due to relatively long acquisition times and can compromise the clinical utility of acquired images. Traditional motion correction methods often fail to address severe motion, leading to distorted and unreliable results. Deep Learning (DL) alleviated such pitfalls through generalization with the cost of vanishing structures and hallucinations, making it challenging to apply in the medical field where hallucinated structures can tremendously impact the diagnostic outcome. In this work, we present an instance-wise motion correction pipeline that leverages motion-guided Implicit Neural Representations (INRs) to mitigate the impact of motion artifacts while retaining anatomical structure. Our method is evaluated using the NYU fastMRI dataset with different degrees of simulated motion severity. For the correction alone, we can improve over state-of-the-art image reconstruction methods by $+5\%$ SSIM, $+5\:db$ PSNR, and $+14\%$ HaarPSI. Clinical relevance is demonstrated by a subsequent experiment, where our method improves classification outcomes by at least $+1.5$ accuracy percentage points compared to motion-corrupted images.
Authors: Zhe Hu, Yixiao Ren, Jing Li, Yu Yin
Abstract: This paper introduces VIVA, a benchmark for VIsion-grounded decision-making driven by human VAlues. While most large vision-language models (VLMs) focus on physical-level skills, our work is the first to examine their multimodal capabilities in leveraging human values to make decisions under a vision-depicted situation. VIVA contains 1,062 images depicting diverse real-world situations and the manually annotated decisions grounded in them. Given an image there, the model should select the most appropriate action to address the situation and provide the relevant human values and reason underlying the decision. Extensive experiments based on VIVA show the limitation of VLMs in using human values to make multimodal decisions. Further analyses indicate the potential benefits of exploiting action consequences and predicted human values.
Authors: Stijn Oomes, Arnoud Visser
Abstract: To be able to play soccer, a robot needs a good estimate of its current position on the field. Ideally, multiple features are visible that have known locations. By applying trigonometry we can estimate the viewpoint from where this observation was actually made. Given that the Nao robots of the Standard Platform League have quite a limited field of view, a given camera frame typically only allows for one or two points to be recognized. In this paper we propose a method for determining the (x, y) coordinates on the field and the height h of the camera from the geometry of a simplified tetrahedron. This configuration is formed by two observed points on the ground plane plus the gravitational direction. When the distance between the two points is known, and the directions to the points plus the gravitational direction are measured, all dimensions of the tetrahedron can be determined. By performing these calculations with rational trigonometry instead of classical trigonometry, the computations turn out to be 28.7% faster, with equal numerical accuracy. The position of the head of the Nao can also be externally measured with the OptiTrack system. The difference between externally measured and internally predicted position from sensor data gives us mean absolute errors in the 3-6 centimeters range, when we estimated the gravitational direction from the vanishing point of the outer edges of the goal posts.
Authors: Yunpeng Jiang, Paul Weng, Yutong Ban
Abstract: Data augmentation is widely applied and has shown its benefits in different machine learning tasks. However, as recently observed in some downstream tasks, data augmentation may introduce an unfair impact on classifications. While it can improve the performance of some classes, it can actually be detrimental for other classes, which can be problematic in some application domains. In this paper, to counteract this phenomenon, we propose a FAir Classification approach with a Two-player game (FACT). We first formulate the training of a classifier with data augmentation as a fair optimization problem, which can be further written as an adversarial two-player game. Following this formulation, we propose a novel multiplicative weight optimization algorithm, for which we theoretically prove that it can converge to a solution that is fair over classes. Interestingly, our formulation also reveals that this fairness issue over classes is not due to data augmentation only, but is in fact a general phenomenon. Our empirical experiments demonstrate that the performance of our learned classifiers is indeed more fairly distributed over classes in five datasets, with only limited impact on the average accuracy.
Authors: Chris Lin, Mingyu Lu, Chanwoo Kim, Su-In Lee
Abstract: As diffusion models are deployed in real-world settings, data attribution is needed to ensure fair acknowledgment for contributors of high-quality training data and to identify sources of harmful content. Previous work focuses on identifying individual training samples important for the generation of a given image. However, instead of focusing on a given generated image, some use cases require understanding global properties of the distribution learned by a diffusion model (e.g., demographic diversity). Furthermore, training data for diffusion models are often contributed in groups rather than separately (e.g., multiple artworks from the same artist). Hence, here we tackle the problem of attributing global properties of diffusion models to groups of training data. Specifically, we develop a method to efficiently estimate Shapley values by leveraging model pruning and fine-tuning. We empirically demonstrate the utility of our method with three use cases: (i) global image quality for a DDPM trained on a CIFAR dataset, (ii) demographic diversity for an LDM trained on CelebA-HQ, and (iii) overall aesthetic quality for a Stable Diffusion model LoRA-finetuned on Post-Impressionist artworks.
Authors: Runyu Ding, Yuzhe Qin, Jiyue Zhu, Chengzhe Jia, Shiqi Yang, Ruihan Yang, Xiaojuan Qi, Xiaolong Wang
Abstract: Teleoperation is a crucial tool for collecting human demonstrations, but controlling robots with bimanual dexterous hands remains a challenge. Existing teleoperation systems struggle to handle the complexity of coordinating two hands for intricate manipulations. We introduce Bunny-VisionPro, a real-time bimanual dexterous teleoperation system that leverages a VR headset. Unlike previous vision-based teleoperation systems, we design novel low-cost devices to provide haptic feedback to the operator, enhancing immersion. Our system prioritizes safety by incorporating collision and singularity avoidance while maintaining real-time performance through innovative designs. Bunny-VisionPro outperforms prior systems on a standard task suite, achieving higher success rates and reduced task completion times. Moreover, the high-quality teleoperation demonstrations improve downstream imitation learning performance, leading to better generalizability. Notably, Bunny-VisionPro enables imitation learning with challenging multi-stage, long-horizon dexterous manipulation tasks, which have rarely been addressed in previous work. Our system's ability to handle bimanual manipulations while prioritizing safety and real-time performance makes it a powerful tool for advancing dexterous manipulation and imitation learning.
Authors: Yuhao Gao, Gensheng Pei, Mengmeng Sheng, Zeren Sun, Tao Chen, Yazhou Yao
Abstract: While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change learning. Additionally, transformer networks struggle with low-level details. RCTNet addresses these limitations by introducing \textbf{(1)} an early fusion backbone to exploit both spatial and temporal features early on, \textbf{(2)} a Cross-Stage Aggregation (CSA) module for enhanced temporal representation, \textbf{(3)} a Multi-Scale Feature Fusion (MSF) module for enriched feature extraction in the decoder, and \textbf{(4)} an Efficient Self-deciphering Attention (ESA) module utilizing transformers to capture global information and fine-grained details for accurate change detection. Extensive experiments demonstrate RCTNet's clear superiority over traditional RS image CD methods, showing significant improvement and an optimal balance between accuracy and computational cost.
Authors: Rui Li, Mikhail Kudryashev, Artur Yakimovich
Abstract: Optic deconvolution in light microscopy (LM) refers to recovering the object details from images, revealing the ground truth of samples. Traditional explicit methods in LM rely on the point spread function (PSF) during image acquisition. Yet, these approaches often fall short due to inaccurate PSF models and noise artifacts, hampering the overall restoration quality. In this paper, we approached the optic deconvolution as an inverse problem. Motivated by the nonstandard-form compression scheme introduced by Beylkin, Coifman, and Rokhlin (BCR), we proposed an innovative physics-informed neural network Multi-Stage Residual-BCR Net (m-rBCR) to approximate the optic deconvolution. We validated the m-rBCR model on four microscopy datasets - two simulated microscopy datasets from ImageNet and BioSR, real dSTORM microscopy images, and real widefield microscopy images. In contrast to the explicit deconvolution methods (e.g. Richardson-Lucy) and other state-of-the-art NN models (U-Net, DDPM, CARE, DnCNN, ESRGAN, RCAN, Noise2Noise, MPRNet, and MIMO-U-Net), the m-rBCR model demonstrates superior performance to other candidates by PSNR and SSIM in two real microscopy datasets and the simulated BioSR dataset. In the simulated ImageNet dataset, m-rBCR ranks the second-best place (right after MIMO-U-Net). With the backbone from the optical physics, m-rBCR exploits the trainable parameters with better performances (from ~30 times fewer than the benchmark MIMO-U-Net to ~210 times than ESRGAN). This enables m-rBCR to achieve a shorter runtime (from ~3 times faster than MIMO-U-Net to ~300 times faster than DDPM). To summarize, by leveraging physics constraints our model reduced potentially redundant parameters significantly in expertise-oriented NN candidates and achieved high efficiency with superior performance.
Authors: Yuan Sun, Navid Salami Pargoo, Taqiya Ehsan, Zhao Zhang Jorge Ortiz
Abstract: Complex human activity recognition (CHAR) remains a pivotal challenge within ubiquitous computing, especially in the context of smart environments. Existing studies typically require meticulous labeling of both atomic and complex activities, a task that is labor-intensive and prone to errors due to the scarcity and inaccuracies of available datasets. Most prior research has focused on datasets that either precisely label atomic activities or, at minimum, their sequence approaches that are often impractical in real world settings.In response, we introduce VCHAR (Variance-Driven Complex Human Activity Recognition), a novel framework that treats the outputs of atomic activities as a distribution over specified intervals. Leveraging generative methodologies, VCHAR elucidates the reasoning behind complex activity classifications through video-based explanations, accessible to users without prior machine learning expertise. Our evaluation across three publicly available datasets demonstrates that VCHAR enhances the accuracy of complex activity recognition without necessitating precise temporal or sequential labeling of atomic activities. Furthermore, user studies confirm that VCHAR's explanations are more intelligible compared to existing methods, facilitating a broader understanding of complex activity recognition among non-experts.
Authors: Yilun Xu, Gabriele Corso, Tommi Jaakkola, Arash Vahdat, Karsten Kreis
Abstract: Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single continuous Gaussian distribution arguably represents an unnecessarily challenging learning problem. We propose Discrete-Continuous Latent Variable Diffusion Models (DisCo-Diff) to simplify this task by introducing complementary discrete latent variables. We augment DMs with learnable discrete latents, inferred with an encoder, and train DM and encoder end-to-end. DisCo-Diff does not rely on pre-trained networks, making the framework universally applicable. The discrete latents significantly simplify learning the DM's complex noise-to-data mapping by reducing the curvature of the DM's generative ODE. An additional autoregressive transformer models the distribution of the discrete latents, a simple step because DisCo-Diff requires only few discrete variables with small codebooks. We validate DisCo-Diff on toy data, several image synthesis tasks as well as molecular docking, and find that introducing discrete latents consistently improves model performance. For example, DisCo-Diff achieves state-of-the-art FID scores on class-conditioned ImageNet-64/128 datasets with ODE sampler.
Authors: Yucheng Tang, Yufan He, Vishwesh Nath, Pengfeig Guo, Ruining Deng, Tianyuan Yao, Quan Liu, Can Cui, Mengmeng Yin, Ziyue Xu, Holger Roth, Daguang Xu, Haichun Yang, Yuankai Huo
Abstract: In digital pathology, the traditional method for deep learning-based image segmentation typically involves a two-stage process: initially segmenting high-resolution whole slide images (WSI) into smaller patches (e.g., 256x256, 512x512, 1024x1024) and subsequently reconstructing them to their original scale. This method often struggles to capture the complex details and vast scope of WSIs. In this paper, we propose the holistic histopathology (HoloHisto) segmentation method to achieve end-to-end segmentation on gigapixel WSIs, whose maximum resolution is above 80,000$\times$70,000 pixels. HoloHisto fundamentally shifts the paradigm of WSI segmentation to an end-to-end learning fashion with 1) a large (4K) resolution base patch for elevated visual information inclusion and efficient processing, and 2) a novel sequential tokenization mechanism to properly model the contextual relationships and efficiently model the rich information from the 4K input. To our best knowledge, HoloHisto presents the first holistic approach for gigapixel resolution WSI segmentation, supporting direct I/O of complete WSI and their corresponding gigapixel masks. Under the HoloHisto platform, we unveil a random 4K sampler that transcends ultra-high resolution, delivering 31 and 10 times more pixels than standard 2D and 3D patches, respectively, for advancing computational capabilities. To facilitate efficient 4K resolution dense prediction, we leverage sequential tokenization, utilizing a pre-trained image tokenizer to group image features into a discrete token grid. To assess the performance, our team curated a new kidney pathology image segmentation (KPIs) dataset with WSI-level glomeruli segmentation from whole mouse kidneys. From the results, HoloHisto-4K delivers remarkable performance gains over previous state-of-the-art models.
Authors: Tiankai Hang, Huan Yang, Bei Liu, Jianlong Fu, Xin Geng, Baining Guo
Abstract: Recent works on language-guided image manipulation have shown great power of language in providing rich semantics, especially for face images. However, the other natural information, motions, in language is less explored. In this paper, we leverage the motion information and study a novel task, language-guided face animation, that aims to animate a static face image with the help of languages. To better utilize both semantics and motions from languages, we propose a simple yet effective framework. Specifically, we propose a recurrent motion generator to extract a series of semantic and motion information from the language and feed it along with visual information to a pre-trained StyleGAN to generate high-quality frames. To optimize the proposed framework, three carefully designed loss functions are proposed including a regularization loss to keep the face identity, a path length regularization loss to ensure motion smoothness, and a contrastive loss to enable video synthesis with various language guidance in one single model. Extensive experiments with both qualitative and quantitative evaluations on diverse domains (\textit{e.g.,} human face, anime face, and dog face) demonstrate the superiority of our model in generating high-quality and realistic videos from one still image with the guidance of language. Code will be available at https://github.com/TiankaiHang/language-guided-animation.git.
URLs: https://github.com/TiankaiHang/language-guided-animation.git.
Authors: Jonathan Ventura, Camille Pawlak, Milo Honsberger, Cameron Gonsalves, Julian Rice, Natalie L. R. Love, Skyler Han, Viet Nguyen, Keilana Sugano, Jacqueline Doremus, G. Andrew Fricker, Jenn Yost, Matt Ritter
Abstract: We introduce a novel deep learning method for detection of individual trees in urban environments using high-resolution multispectral aerial imagery. We use a convolutional neural network to regress a confidence map indicating the locations of individual trees, which are localized using a peak finding algorithm. Our method provides complete spatial coverage by detecting trees in both public and private spaces, and can scale to very large areas. We performed a thorough evaluation of our method, supported by a new dataset of over 1,500 images and almost 100,000 tree annotations, covering eight cities, six climate zones, and three image capture years. We trained our model on data from Southern California, and achieved a precision of 73.6% and recall of 73.3% using test data from this region. We generally observed similar precision and slightly lower recall when extrapolating to other California climate zones and image capture dates. We used our method to produce a map of trees in the entire urban forest of California, and estimated the total number of urban trees in California to be about 43.5 million. Our study indicates the potential for deep learning methods to support future urban forestry studies at unprecedented scales.
Authors: Gustav Grund Pihlgren, Konstantina Nikolaidou, Prakash Chandra Chhipa, Nosheen Abid, Rajkumar Saini, Fredrik Sandin, Marcus Liwicki
Abstract: In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss function for images that computes the error between two images as the distance between deep features extracted from a neural network. Most applications of the loss use pretrained networks called loss networks for deep feature extraction. However, despite increasingly widespread use, the effects of loss network implementation on the trained models have not been studied. This work rectifies this through a systematic evaluation of the effect of different pretrained loss networks on four different application areas. Specifically, the work evaluates 14 different pretrained architectures with four different feature extraction layers. The evaluation reveals that VGG networks without batch normalization have the best performance and that the choice of feature extraction layer is at least as important as the choice of architecture. The analysis also reveals that deep perceptual loss does not adhere to the transfer learning conventions that better ImageNet accuracy implies better downstream performance and that feature extraction from the later layers provides better performance.
Authors: Mingxuan Liu, Subhankar Roy, Zhun Zhong, Nicu Sebe, Elisa Ricci
Abstract: Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners. In the literature such problems have been partially addressed under very restricted settings, where novel classes are learned by jointly accessing a related labelled set (e.g., NCD) or by leveraging only a supervisedly pre-trained model (e.g., class-iNCD). In this work we challenge the status quo in class-iNCD and propose a learning paradigm where class discovery occurs continuously and truly unsupervisedly, without needing any related labelled set. In detail, we propose to exploit the richer priors from strong self-supervised pre-trained models (PTM). To this end, we propose simple baselines, composed of a frozen PTM backbone and a learnable linear classifier, that are not only simple to implement but also resilient under longer learning scenarios. We conduct extensive empirical evaluation on a multitude of benchmarks and show the effectiveness of our proposed baselines when compared with sophisticated state-of-the-art methods. The code is open source.
Authors: Jinghong Li, Koichi Ota, Wen Gu, Shinobu Hasegawa
Abstract: With the widespread use of the internet, it has become increasingly crucial to extract specific information from vast amounts of academic articles efficiently. Data mining techniques are generally employed to solve this issue. However, data mining for academic articles is challenging since it requires automatically extracting specific patterns in complex and unstructured layout documents. Current data mining methods for academic articles employ rule-based(RB) or machine learning(ML) approaches. However, using rule-based methods incurs a high coding cost for complex typesetting articles. On the other hand, simply using machine learning methods requires annotation work for complex content types within the paper, which can be costly. Furthermore, only using machine learning can lead to cases where patterns easily recognized by rule-based methods are mistakenly extracted. To overcome these issues, from the perspective of analyzing the standard layout and typesetting used in the specified publication, we emphasize implementing specific methods for specific characteristics in academic articles. We have developed a novel Text Block Refinement Framework (TBRF), a machine learning and rule-based scheme hybrid. We used the well-known ACL proceeding articles as experimental data for the validation experiment. The experiment shows that our approach achieved over 95% classification accuracy and 90% detection accuracy for tables and figures.
Authors: Anita Rau, Sophia Bano, Yueming Jin, Pablo Azagra, Javier Morlana, Rawen Kader, Edward Sanderson, Bogdan J. Matuszewski, Jae Young Lee, Dong-Jae Lee, Erez Posner, Netanel Frank, Varshini Elangovan, Sista Raviteja, Zhengwen Li, Jiquan Liu, Seenivasan Lalithkumar, Mobarakol Islam, Hongliang Ren, Laurence B. Lovat, Jos\'e M. M. Montiel, Danail Stoyanov
Abstract: Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. Establishing a benchmark dataset, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction from synthetic colonoscopy images is robustly solvable, while pose estimation remains an open research question.
Authors: Moshe Kimhi, Shai Kimhi, Evgenii Zheltonozhskii, Or Litany, Chaim Baskin
Abstract: We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the spatial correlation of labels in segmentation maps by grouping neighboring pixels and considering their pseudo labels collectively. With this contextual information, our method, named S4MC, increases the amount of unlabeled data used during training while maintaining the quality of the pseudo labels, all with negligible computational overhead. Through extensive experiments on standard benchmarks, we demonstrate that S4MC outperforms existing state-of-the-art semi-supervised learning approaches, offering a promising solution for reducing the cost of acquiring dense annotations. For example, S4MC achieves a 1.39 mIoU improvement over the prior art on PASCAL VOC 12 with 366 annotated images. The code to reproduce our experiments is available at https://s4mcontext.github.io/
Authors: Ozan Unal, Christos Sakaridis, Suman Saha, Luc Van Gool
Abstract: 3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen in popularity. A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes. However, for real-life applications that require physical interactions, a bounding box insufficiently describes the geometry of an object. We therefore tackle the problem of dense 3D visual grounding, i.e. referral-based 3D instance segmentation. We propose a dense 3D grounding network ConcreteNet, featuring four novel stand-alone modules that aim to improve grounding performance for challenging repetitive instances, i.e. instances with distractors of the same semantic class. First, we introduce a bottom-up attentive fusion module that aims to disambiguate inter-instance relational cues, next, we construct a contrastive training scheme to induce separation in the latent space, we then resolve view-dependent utterances via a learned global camera token, and finally we employ multi-view ensembling to improve referred mask quality. ConcreteNet ranks 1st on the challenging ScanRefer online benchmark and has won the ICCV 3rd Workshop on Language for 3D Scenes "3D Object Localization" challenge.
Authors: Aman Bhatta, Domingo Mery, Haiyu Wu, Joyce Annan, Micheal C. King, Kevin W. Bowyer
Abstract: State-of-the-art deep CNN face matchers are typically created using extensive training sets of color face images. Our study reveals that such matchers attain virtually identical accuracy when trained on either grayscale or color versions of the training set, even when the evaluation is done using color test images. Furthermore, we demonstrate that shallower models, lacking the capacity to model complex representations, rely more heavily on low-level features such as those associated with color. As a result, they display diminished accuracy when trained with grayscale images. We then consider possible causes for deeper CNN face matchers "not seeing color". Popular web-scraped face datasets actually have 30 to 60% of their identities with one or more grayscale images. We analyze whether this grayscale element in the training set impacts the accuracy achieved, and conclude that it does not. We demonstrate that using only grayscale images for both training and testing achieves accuracy comparable to that achieved using only color images for deeper models. This holds true for both real and synthetic training datasets. HSV color space, which separates chroma and luma information, does not improve the network's learning about color any more than in the RGB color space. We then show that the skin region of an individual's images in a web-scraped training set exhibits significant variation in their mapping to color space. This suggests that color carries limited identity-specific information. We also show that when the first convolution layer is restricted to a single filter, models learn a grayscale conversion filter and pass a grayscale version of the input color image to the next layer. Finally, we demonstrate that leveraging the lower per-image storage for grayscale to increase the number of images in the training set can improve accuracy of the face recognition model.
Authors: Ke Zhang, Neman Abdoli, Patrik Gilley, Youkabed Sadri, Xuxin Chen, Theresa C. Thai, Lauren Dockery, Kathleen Moore, Robert S. Mannel, Yuchen Qiu
Abstract: Objective Neoadjuvant chemotherapy (NACT) is one kind of treatment for advanced stage ovarian cancer patients. However, due to the nature of tumor heterogeneity, the clinical outcomes to NACT vary significantly among different subgroups. Partial responses to NACT may lead to suboptimal debulking surgery, which will result in adverse prognosis. To address this clinical challenge, the purpose of this study is to develop a novel image marker to achieve high accuracy prognosis prediction of NACT at an early stage. Methods For this purpose, we first computed a total of 1373 radiomics features to quantify the tumor characteristics, which can be grouped into three categories: geometric, intensity, and texture features. Second, all these features were optimized by principal component analysis algorithm to generate a compact and informative feature cluster. This cluster was used as input for developing and optimizing support vector machine (SVM) based classifiers, which indicated the likelihood of receiving suboptimal cytoreduction after the NACT treatment. Two different kernels for SVM algorithm were explored and compared. A total of 42 ovarian cancer cases were retrospectively collected to validate the scheme. A nested leave-one-out cross-validation framework was adopted for model performance assessment. Results The results demonstrated that the model with a Gaussian radial basis function kernel SVM yielded an AUC (area under the ROC [receiver characteristic operation] curve) of 0.806. Meanwhile, this model achieved overall accuracy (ACC) of 83.3%, positive predictive value (PPV) of 81.8%, and negative predictive value (NPV) of 83.9%. Conclusion This study provides meaningful information for the development of radiomics based image markers in NACT treatment outcome prediction.
Authors: Klara Janouskova, Tamir Shor, Chaim Baskin, Jiri Matas
Abstract: Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled image with no other data available at test-time. In particular, this work focuses on adaptation by optimizing self-supervised losses at test-time. Multiple baselines based on different principles are evaluated under diverse conditions and a novel adversarial training is introduced for adaptation with mask refinement. Our additions to the baselines result in a 3.51 and 3.28 % increase over non-adapted baselines, without these improvements, the increase would be 1.7 and 2.16 % only.
Authors: Jue Jiang, Aneesh Rangnekar, Chloe Min Seo Choi, Harini Veeraraghavan
Abstract: Pretraining vision transformers (ViT) with attention guided masked image modeling (MIM) has shown to increase downstream accuracy for natural image analysis. Hierarchical shifted window (Swin) transformer, often used in medical image analysis cannot use attention guided masking as it lacks an explicit [CLS] token, needed for computing attention maps for selective masking. We thus enhanced Swin with semantic class attention. We developed a co-distilled Swin transformer that combines a noisy momentum updated teacher to guide selective masking for MIM. Our approach called \textsc{s}e\textsc{m}antic \textsc{a}ttention guided co-distillation with noisy teacher \textsc{r}egularized Swin \textsc{T}rans\textsc{F}ormer (SMARTFormer) was applied for analyzing 3D computed tomography datasets with lung nodules and malignant lung cancers (LC). We also analyzed the impact of semantic attention and noisy teacher on pretraining and downstream accuracy. SMARTFormer classified lesions (malignant from benign) with a high accuracy of 0.895 of 1000 nodules, predicted LC treatment response with accuracy of 0.74, and achieved high accuracies even in limited data regimes. Pretraining with semantic attention and noisy teacher improved ability to distinguish semantically meaningful structures such as organs in a unsupervised clustering task and localize abnormal structures like tumors. Code, models will be made available through GitHub upon paper acceptance.
Authors: Zhili Liu, Kai Chen, Yifan Zhang, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung, James Kwok
Abstract: Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed as the "implicit concepts", could be unintentionally learned during training and then be generated uncontrollably during inference. Existing removal methods still struggle to eliminate implicit concepts primarily due to their dependency on the model's ability to recognize concepts it actually can not discern. To address this, we utilize the intrinsic geometric characteristics of implicit concepts and present the Geom-Erasing, a novel concept removal method based on the geometric-driven control. Specifically, once an unwanted implicit concept is identified, we integrate the existence and geometric information of the concept into the text prompts with the help of an accessible classifier or detector model. Subsequently, the model is optimized to identify and disentangle this information, which is then adopted as negative prompts during generation. Moreover, we introduce the Implicit Concept Dataset (ICD), a novel image-text dataset imbued with three typical implicit concepts (i.e., QR codes, watermarks, and text), reflecting real-life situations where implicit concepts are easily injected. Geom-Erasing effectively mitigates the generation of implicit concepts, achieving the state-of-the-art results on the Inappropriate Image Prompts (I2P) and our challenging Implicit Concept Dataset (ICD) benchmarks.
Authors: Shuai Yang, Zhifei Chen, Pengguang Chen, Xi Fang, Shu Liu, Yingcong Chen
Abstract: Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models.
Authors: Zhenbang Du, Jiayu An, Yunlu Tu, Jiahao Hong, Dongrui Wu
Abstract: Open Set Domain Adaptation (OSDA) aims to cope with the distribution and label shifts between the source and target domains simultaneously, performing accurate classification for known classes while identifying unknown class samples in the target domain. Most existing OSDA approaches, depending on the final image feature space of deep models, require manually-tuned thresholds, and may easily misclassify unknown samples as known classes. Mixture-of-Experts (MoE) could be a remedy. Within a MoE, different experts handle distinct input features, producing unique expert routing patterns for various classes in a routing feature space. As a result, unknown class samples may display different expert routing patterns to known classes. In this paper, we propose Dual-Space Detection, which exploits the inconsistencies between the image feature space and the routing feature space to detect unknown class samples without any threshold. Graph Router is further introduced to better make use of the spatial information among image patches. Experiments on three different datasets validated the effectiveness and superiority of our approach.
Authors: Xiaobao Wei, Jiajun Cao, Yizhu Jin, Ming Lu, Guangyu Wang, Shanghang Zhang
Abstract: With the development of Deep Neural Networks (DNNs), many efforts have been made to handle medical image segmentation. Traditional methods such as nnUNet train specific segmentation models on the individual datasets. Plenty of recent methods have been proposed to adapt the foundational Segment Anything Model (SAM) to medical image segmentation. However, they still focus on discrete representations to generate pixel-wise predictions, which are spatially inflexible and scale poorly to higher resolution. In contrast, implicit methods learn continuous representations for segmentation, which is crucial for medical image segmentation. In this paper, we propose I-MedSAM, which leverages the benefits of both continuous representations and SAM, to obtain better cross-domain ability and accurate boundary delineation. Since medical image segmentation needs to predict detailed segmentation boundaries, we designed a novel adapter to enhance the SAM features with high-frequency information during Parameter-Efficient Fine-Tuning (PEFT). To convert the SAM features and coordinates into continuous segmentation output, we utilize Implicit Neural Representation (INR) to learn an implicit segmentation decoder. We also propose an uncertainty-guided sampling strategy for efficient learning of INR. Extensive evaluations on 2D medical image segmentation tasks have shown that our proposed method with only 1.6M trainable parameters outperforms existing methods including discrete and implicit methods. The code will be available at: https://github.com/ucwxb/I-MedSAM.
Authors: En Yu, Liang Zhao, Yana Wei, Jinrong Yang, Dongming Wu, Lingyu Kong, Haoran Wei, Tiancai Wang, Zheng Ge, Xiangyu Zhang, Wenbing Tao
Abstract: Humans possess the remarkable ability to foresee the future to a certain extent based on present observations, a skill we term as foresight minds. However, this capability remains largely under explored within existing Multimodal Large Language Models (MLLMs), hindering their capacity to learn the fundamental principles of how things operate and the intentions behind the observed subjects. To address this issue, we introduce the integration of future modeling into the existing learning frameworks of MLLMs. By utilizing the subject trajectory, a highly structured representation of a consecutive frame sequence, as a learning objective, we aim to bridge the gap between the past and the future. We propose two innovative methods to empower MLLMs with foresight minds, Foresight Pre-Training (FPT) and Foresight Instruction-Tuning (FIT), which are inspired by the modern learning paradigm of LLMs. Specifically, FPT jointly training various tasks centered on trajectories, enabling MLLMs to learn how to attend and predict entire trajectories from a given initial observation. Then, FIT requires MLLMs to first predict trajectories of related objects and then reason about potential future events based on them. Aided by FPT and FIT, we build a novel and unified MLLM named Merlin that supports multi-images input and analysis about potential actions of multiple objects for the future reasoning. Experimental results show Merlin powerful foresight minds with impressive performance on both future reasoning and visual comprehension tasks.
Authors: Alonso Urbano, David W. Romero
Abstract: Group equivariance can overly constrain models if the symmetries in the group differ from those observed in data. While common methods address this by determining the appropriate level of symmetry at the dataset level, they are limited to supervised settings and ignore scenarios in which multiple levels of symmetry co-exist in the same dataset. In this paper, we propose a method able to detect the level of symmetry of each input without the need for labels. Our framework is general enough to accommodate different families of both continuous and discrete symmetry distributions, such as arbitrary unimodal, symmetric distributions and discrete groups. We validate the effectiveness of our approach on synthetic datasets with different per-class levels of symmetries, and demonstrate practical applications such as the detection of out-of-distribution symmetries. Our code is publicly available at https://github.com/aurban0/ssl-sym.
Authors: Dingkun Yan, Liang Yuan, Erwin Wu, Yuma Nishioka, Issei Fujishiro, Suguru Saito
Abstract: Diffusion models have recently demonstrated their effectiveness in generating extremely high-quality images and are now utilized in a wide range of applications, including automatic sketch colorization. Although many methods have been developed for guided sketch colorization, there has been limited exploration of the potential conflicts between image prompts and sketch inputs, which can lead to severe deterioration in the results. Therefore, this paper exhaustively investigates reference-based sketch colorization models that aim to colorize sketch images using reference color images. We specifically investigate two critical aspects of reference-based diffusion models: the "distribution problem", which is a major shortcoming compared to text-based counterparts, and the capability in zero-shot sequential text-based manipulation. We introduce two variations of an image-guided latent diffusion model utilizing different image tokens from the pre-trained CLIP image encoder and propose corresponding manipulation methods to adjust their results sequentially using weighted text inputs. We conduct comprehensive evaluations of our models through qualitative and quantitative experiments as well as a user study.
Authors: Ronglai Zuo, Fangyun Wei, Zenggui Chen, Brian Mak, Jiaolong Yang, Xin Tong
Abstract: The objective of this paper is to develop a functional system for translating spoken languages into sign languages, referred to as Spoken2Sign translation. The Spoken2Sign task is orthogonal and complementary to traditional sign language to spoken language (Sign2Spoken) translation. To enable Spoken2Sign translation, we present a simple baseline consisting of three steps: 1) creating a gloss-video dictionary using existing Sign2Spoken benchmarks; 2) estimating a 3D sign for each sign video in the dictionary; 3) training a Spoken2Sign model, which is composed of a Text2Gloss translator, a sign connector, and a rendering module, with the aid of the yielded gloss-3D sign dictionary. The translation results are then displayed through a sign avatar. As far as we know, we are the first to present the Spoken2Sign task in an output format of 3D signs. In addition to its capability of Spoken2Sign translation, we also demonstrate that two by-products of our approach-3D keypoint augmentation and multi-view understanding-can assist in keypoint-based sign language understanding. Code and models are available at https://github.com/FangyunWei/SLRT.
Authors: Rafal K. Mantiuk, Param Hanji, Maliha Ashraf, Yuta Asano, Alexandre Chapiro
Abstract: ColorVideoVDP is a video and image quality metric that models spatial and temporal aspects of vision, for both luminance and color. The metric is built on novel psychophysical models of chromatic spatiotemporal contrast sensitivity and cross-channel contrast masking. It accounts for the viewing conditions, geometric, and photometric characteristics of the display. It was trained to predict common video streaming distortions (e.g. video compression, rescaling, and transmission errors), and also 8 new distortion types related to AR/VR displays (e.g. light source and waveguide non-uniformities). To address the latter application, we collected our novel XR-Display-Artifact-Video quality dataset (XR-DAVID), comprised of 336 distorted videos. Extensive testing on XR-DAVID, as well as several datasets from the literature, indicate a significant gain in prediction performance compared to existing metrics. ColorVideoVDP opens the doors to many novel applications which require the joint automated spatiotemporal assessment of luminance and color distortions, including video streaming, display specification and design, visual comparison of results, and perceptually-guided quality optimization.
Authors: Anna Yoo Jeong Ha, Josephine Passananti, Ronik Bhaskar, Shawn Shan, Reid Southen, Haitao Zheng, Ben Y. Zhao
Abstract: The advent of generative AI images has completely disrupted the art world. Distinguishing AI generated images from human art is a challenging problem whose impact is growing over time. A failure to address this problem allows bad actors to defraud individuals paying a premium for human art and companies whose stated policies forbid AI imagery. It is also critical for content owners to establish copyright, and for model trainers interested in curating training data in order to avoid potential model collapse. There are several different approaches to distinguishing human art from AI images, including classifiers trained by supervised learning, research tools targeting diffusion models, and identification by professional artists using their knowledge of artistic techniques. In this paper, we seek to understand how well these approaches can perform against today's modern generative models in both benign and adversarial settings. We curate real human art across 7 styles, generate matching images from 5 generative models, and apply 8 detectors (5 automated detectors and 3 different human groups including 180 crowdworkers, 4000+ professional artists, and 13 expert artists experienced at detecting AI). Both Hive and expert artists do very well, but make mistakes in different ways (Hive is weaker against adversarial perturbations while Expert artists produce higher false positives). We believe these weaknesses will remain as models continue to evolve, and use our data to demonstrate why a combined team of human and automated detectors provides the best combination of accuracy and robustness.
Authors: Shuchen Xue, Zhaoqiang Liu, Fei Chen, Shifeng Zhang, Tianyang Hu, Enze Xie, Zhenguo Li
Abstract: Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization problem that seeks more appropriate time steps for a specific numerical ODE solver for DPMs. This optimization problem aims to minimize the distance between the ground-truth solution to the ODE and an approximate solution corresponding to the numerical solver. It can be efficiently solved using the constrained trust region method, taking less than $15$ seconds. Our extensive experiments on both unconditional and conditional sampling using pixel- and latent-space DPMs demonstrate that, when combined with the state-of-the-art sampling method UniPC, our optimized time steps significantly improve image generation performance in terms of FID scores for datasets such as CIFAR-10 and ImageNet, compared to using uniform time steps.
Authors: Yang Liu, Changzhen Qiu, Zhiyong Zhang
Abstract: 3D human pose estimation and mesh recovery have attracted widespread research interest in many areas, such as computer vision, autonomous driving, and robotics. Deep learning on 3D human pose estimation and mesh recovery has recently thrived, with numerous methods proposed to address different problems in this area. In this paper, to stimulate future research, we present a comprehensive review of recent progress over the past five years in deep learning methods for this area by delving into over 200 references. To the best of our knowledge, this survey is arguably the first to comprehensively cover deep learning methods for 3D human pose estimation, including both single-person and multi-person approaches, as well as human mesh recovery, encompassing methods based on explicit models and implicit representations. We also present comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions. A regularly updated project page can be found at https://github.com/liuyangme/SOTA-3DHPE-HMR.
Authors: Xin Liu, Jiamin Wu, Tianzhu Zhang
Abstract: Large pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet overlooking multi-modal attribute characteristics. This limitation hinders the model's ability to perceive fine-grained visual details and restricts its generalization ability to a broader range of unseen classes. To address this issue, we propose a Multi-modal Attribute Prompting method (MAP) by jointly exploring textual attribute prompting, visual attribute prompting, and attribute-level alignment. The proposed MAP enjoys several merits. First, we introduce learnable visual attribute prompts enhanced by textual attribute semantics to adaptively capture visual attributes for images from unknown categories, boosting fine-grained visual perception capabilities for CLIP. Second, the proposed attribute-level alignment complements the global alignment to enhance the robustness of cross-modal alignment for open-vocabulary objects. To our knowledge, this is the first work to establish cross-modal attribute-level alignment for CLIP-based few-shot adaptation. Extensive experimental results on 11 datasets demonstrate that our method performs favorably against state-of-the-art approaches.
Authors: Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu
Abstract: Text-to-image (T2I) generation models have significantly advanced in recent years. However, effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation, hindering a dynamic and iterative creation process. Recent attempts have tried to equip Multi-modal Large Language Models (MLLMs) with T2I models to bring the user's natural language instructions into reality. Hence, the output modality of MLLMs is extended, and the multi-turn generation quality of T2I models is enhanced thanks to the strong multi-modal comprehension ability of MLLMs. However, many of these works face challenges in identifying correct output modalities and generating coherent images accordingly as the number of output modalities increases and the conversations go deeper. Therefore, we propose DialogGen, an effective pipeline to align off-the-shelf MLLMs and T2I models to build a Multi-modal Interactive Dialogue System (MIDS) for multi-turn Text-to-Image generation. It is composed of drawing prompt alignment, careful training data curation, and error correction. Moreover, as the field of MIDS flourishes, comprehensive benchmarks are urgently needed to evaluate MIDS fairly in terms of output modality correctness and multi-modal output coherence. To address this issue, we introduce the Multi-modal Dialogue Benchmark (DialogBen), a comprehensive bilingual benchmark designed to assess the ability of MLLMs to generate accurate and coherent multi-modal content that supports image editing. It contains two evaluation metrics to measure the model's ability to switch modalities and the coherence of the output images. Our extensive experiments on DialogBen and user study demonstrate the effectiveness of DialogGen compared with other State-of-the-Art models.
Authors: Souradeep Chakraborty, Dimitris Samaras
Abstract: Our paper introduces a novel two-stage self-supervised approach for detecting co-occurring salient objects (CoSOD) in image groups without requiring segmentation annotations. Unlike existing unsupervised methods that rely solely on patch-level information (e.g. clustering patch descriptors) or on computation heavy off-the-shelf components for CoSOD, our lightweight model leverages feature correspondences at both patch and region levels, significantly improving prediction performance. In the first stage, we train a self-supervised network that detects co-salient regions by computing local patch-level feature correspondences across images. We obtain the segmentation predictions using confidence-based adaptive thresholding. In the next stage, we refine these intermediate segmentations by eliminating the detected regions (within each image) whose averaged feature representations are dissimilar to the foreground feature representation averaged across all the cross-attention maps (from the previous stage). Extensive experiments on three CoSOD benchmark datasets show that our self-supervised model outperforms the corresponding state-of-the-art models by a huge margin (e.g. on the CoCA dataset, our model has a 13.7% F-measure gain over the SOTA unsupervised CoSOD model). Notably, our self-supervised model also outperforms several recent fully supervised CoSOD models on the three test datasets (e.g., on the CoCA dataset, our model has a 4.6% F-measure gain over a recent supervised CoSOD model).
Authors: Weipeng Deng, Jihan Yang, Runyu Ding, Jiahui Liu, Yijiang Li, Xiaojuan Qi, Edith Ngai
Abstract: Rapid advancements in 3D vision-language (3D-VL) tasks have opened up new avenues for human interaction with embodied agents or robots using natural language. Despite this progress, we find a notable limitation: existing 3D-VL models exhibit sensitivity to the styles of language input, struggling to understand sentences with the same semantic meaning but written in different variants. This observation raises a critical question: Can 3D vision-language models truly understand natural language? To test the language understandability of 3D-VL models, we first propose a language robustness task for systematically assessing 3D-VL models across various tasks, benchmarking their performance when presented with different language style variants. Importantly, these variants are commonly encountered in applications requiring direct interaction with humans, such as embodied robotics, given the diversity and unpredictability of human language. We propose a 3D Language Robustness Dataset, designed based on the characteristics of human language, to facilitate the systematic study of robustness. Our comprehensive evaluation uncovers a significant drop in the performance of all existing models across various 3D-VL tasks. Even the state-of-the-art 3D-LLM fails to understand some variants of the same sentences. Further in-depth analysis suggests that the existing models have a fragile and biased fusion module, which stems from the low diversity of the existing dataset. Finally, we propose a training-free module driven by LLM, which improves language robustness. Datasets and code will be available at github.
Authors: Tanvir Mahmud, Burhaneddin Yaman, Chun-Hao Liu, Diana Marculescu
Abstract: As deep neural networks evolve from convolutional neural networks (ConvNets) to advanced vision transformers (ViTs), there is an increased need to eliminate redundant data for faster processing without compromising accuracy. Previous methods are often architecture-specific or necessitate re-training, restricting their applicability with frequent model updates. To solve this, we first introduce a novel property of lightweight ConvNets: their ability to identify key discriminative patch regions in images, irrespective of model's final accuracy or size. We demonstrate that fully-connected layers are the primary bottleneck for ConvNets performance, and their suppression with simple weight recalibration markedly enhances discriminative patch localization performance. Using this insight, we introduce PaPr, a method for substantially pruning redundant patches with minimal accuracy loss using lightweight ConvNets across a variety of deep learning architectures, including ViTs, ConvNets, and hybrid transformers, without any re-training. Moreover, the simple early-stage one-step patch pruning with PaPr enhances existing patch reduction methods. Through extensive testing on diverse architectures, PaPr achieves significantly higher accuracy over state-of-the-art patch reduction methods with similar FLOP count reduction. More specifically, PaPr reduces about 70% of redundant patches in videos with less than 0.8% drop in accuracy, and up to 3.7x FLOPs reduction, which is a 15% more reduction with 2.5% higher accuracy. Code is released at https://github.com/tanvir-utexas/PaPr.
Authors: Pulkit Khandelwal, Michael Tran Duong, Lisa Levorse, Constanza Fuentes, Amanda Denning, Winifred Trotman, Ranjit Ittyerah, Alejandra Bahena, Theresa Schuck, Marianna Gabrielyan, Karthik Prabhakaran, Daniel Ohm, Gabor Mizsei, John Robinson, Monica Munoz, John Detre, Edward Lee, David Irwin, Corey McMillan, M. Dylan Tisdall, Sandhitsu Das, David Wolk, Paul A. Yushkevich
Abstract: Magnetic resonance imaging (MRI) is the standard modality to understand human brain structure and function in vivo (antemortem). Decades of research in human neuroimaging has led to the widespread development of methods and tools to provide automated volume-based segmentations and surface-based parcellations which help localize brain functions to specialized anatomical regions. Recently ex vivo (postmortem) imaging of the brain has opened-up avenues to study brain structure at sub-millimeter ultra high-resolution revealing details not possible to observe with in vivo MRI. Unfortunately, there has been limited methodological development in ex vivo MRI primarily due to lack of datasets and limited centers with such imaging resources. Therefore, in this work, we present one-of-its-kind dataset of 82 ex vivo T2w whole brain hemispheres MRI at 0.3 mm isotropic resolution spanning Alzheimer's disease and related dementias. We adapted and developed a fast and easy-to-use automated surface-based pipeline to parcellate, for the first time, ultra high-resolution ex vivo brain tissue at the native subject space resolution using the Desikan-Killiany-Tourville (DKT) brain atlas. This allows us to perform vertex-wise analysis in the template space and thereby link morphometry measures with pathology measurements derived from histology. We will open-source our dataset docker container, Jupyter notebooks for ready-to-use out-of-the-box set of tools and command line options to advance ex vivo MRI clinical brain imaging research on the project webpage.
Authors: Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A. Smith, Wei-Chiu Ma, Ranjay Krishna
Abstract: We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the Blink tasks can be solved by humans "within a blink" (e.g., relative depth estimation, visual correspondence, forensics detection, and multi-view reasoning). However, we find these perception-demanding tasks cast significant challenges for current multimodal LLMs because they resist mediation through natural language. Blink reformats 14 classic computer vision tasks into 3,807 multiple-choice questions, paired with single or multiple images and visual prompting. While humans get 95.70% accuracy on average, Blink is surprisingly challenging for existing multimodal LLMs: even the best-performing GPT-4V and Gemini achieve accuracies of 51.26% and 45.72%, only 13.17% and 7.63% higher than random guessing, indicating that such perception abilities have not "emerged" yet in recent multimodal LLMs. Our analysis also highlights that specialist CV models could solve these problems much better, suggesting potential pathways for future improvements. We believe Blink will stimulate the community to help multimodal LLMs catch up with human-level visual perception.
Authors: Zesheng Hong, Yubiao Yue, Yubin Chen, Lele Cong, Huanjie Lin, Yuanmei Luo, Mini Han Wang, Weidong Wang, Jialong Xu, Xiaoqi Yang, Hechang Chen, Zhenzhang Li, Sihong Xie
Abstract: Computer-aided diagnostics has benefited from the development of deep learning-based computer vision techniques in these years. Traditional supervised deep learning methods assume that the test sample is drawn from the identical distribution as the training data. However, it is possible to encounter out-of-distribution samples in real-world clinical scenarios, which may cause silent failure in deep learning-based medical image analysis tasks. Recently, research has explored various out-of-distribution (OOD) detection situations and techniques to enable a trustworthy medical AI system. In this survey, we systematically review the recent advances in OOD detection in medical image analysis. We first explore several factors that may cause a distributional shift when using a deep-learning-based model in clinic scenarios, with three different types of distributional shift well defined on top of these factors. Then a framework is suggested to categorize and feature existing solutions, while the previous studies are reviewed based on the methodology taxonomy. Our discussion also includes evaluation protocols and metrics, as well as the challenge and a research direction lack of exploration.
Authors: Zhihao Guo, Peng Wang
Abstract: Neural Radiance Fields (NeRF) have achieved impressive results in 3D reconstruction and novel view generation. A significant challenge within NeRF involves editing reconstructed 3D scenes, such as object removal, which demands consistency across multiple views and the synthesis of high-quality perspectives. Previous studies have integrated depth priors, typically sourced from LiDAR or sparse depth estimates from COLMAP, to enhance NeRF's performance in object removal. However, these methods are either expensive or time-consuming. This paper proposes a new pipeline that leverages SpinNeRF and monocular depth estimation models like ZoeDepth to enhance NeRF's performance in complex object removal with improved efficiency. A thorough evaluation of COLMAP's dense depth reconstruction on the KITTI dataset is conducted to demonstrate that COLMAP can be viewed as a cost-effective and scalable alternative for acquiring depth ground truth compared to traditional methods like LiDAR. This serves as the basis for evaluating the performance of monocular depth estimation models to determine the best one for generating depth priors for SpinNeRF. The new pipeline is tested in various scenarios involving 3D reconstruction and object removal, and the results indicate that our pipeline significantly reduces the time required for the acquisition of depth priors for object removal and enhances the fidelity of the synthesized views, suggesting substantial potential for building high-fidelity digital twin systems with increased efficiency in the future.
Authors: Gabriele Berton, Gabriele Goletto, Gabriele Trivigno, Alex Stoken, Barbara Caputo, Carlo Masone
Abstract: Precise, pixel-wise geolocalization of astronaut photography is critical to unlocking the potential of this unique type of remotely sensed Earth data, particularly for its use in disaster management and climate change research. Recent works have established the Astronaut Photography Localization task, but have either proved too costly for mass deployment or generated too coarse a localization. Thus, we present EarthMatch, an iterative homography estimation method that produces fine-grained localization of astronaut photographs while maintaining an emphasis on speed. We refocus the astronaut photography benchmark, AIMS, on the geolocalization task itself, and prove our method's efficacy on this dataset. In addition, we offer a new, fair method for image matcher comparison, and an extensive evaluation of different matching models within our localization pipeline. Our method will enable fast and accurate localization of the 4.5 million and growing collection of astronaut photography of Earth. Webpage with code and data at https://earthloc-and-earthmatch.github.io
Authors: Hongwei Ren, Yue Zhou, Jiadong Zhu, Haotian Fu, Yulong Huang, Xiaopeng Lin, Yuetong Fang, Fei Ma, Hao Yu, Bojun Cheng
Abstract: Event cameras, drawing inspiration from biological systems, efficiently detect changes in ambient light with low latency and high dynamic range while consuming minimal power. The most current approach to processing event data often involves converting it into frame-based representations, which is well-established in traditional vision. However, this approach neglects the sparsity of event data, loses fine-grained temporal information during the transformation process, and increases the computational burden, making it ineffective for characterizing event camera properties. In contrast, Point Cloud is a popular representation for 3D processing and is better suited to match the sparse and asynchronous nature of the event camera. Nevertheless, despite the theoretical compatibility of point-based methods with event cameras, the results show a performance gap that is not yet satisfactory compared to frame-based methods. In order to bridge the performance gap, we propose EventMamba, an efficient and effective Point Cloud framework that achieves competitive results even compared to the state-of-the-art (SOTA) frame-based method in both classification and regression tasks. This notable accomplishment is facilitated by our rethinking of the distinction between Event Cloud and Point Cloud, emphasizing effective temporal information extraction through optimized network structures. Specifically, EventMamba leverages temporal aggregation and State Space Model (SSM) based Mamba boasting enhanced temporal information extraction capabilities. Through a hierarchical structure, EventMamba is adept at abstracting local and global spatial features and implicit and explicit temporal features. By adhering to the lightweight design principle, EventMamba delivers impressive results with minimal computational resource utilization, demonstrating its efficiency and effectiveness.
Authors: Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, Min Yang, Binyuan Hui
Abstract: The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs). While LMMs have achieved tremendous success by promoting the synergy between multimodal comprehension and creation, they often face challenges when confronted with out-of-distribution data. This is primarily due to their reliance on image encoders trained to encode images into task-relevant features, which may lead them to disregard irrelevant details. Delving into the modeling capabilities of diffusion models for images naturally prompts the question: Can diffusion models serve as the eyes of large language models for image perception? In this paper, we propose DEEM, a simple and effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. This addresses the drawbacks of previous methods that solely relied on image encoders like ViT, thereby enhancing the model's resilience against out-of-distribution samples and reducing visual hallucinations. Importantly, this is achieved without requiring additional training modules and with fewer training parameters. We extensively evaluated DEEM on both our newly constructed RobustVQA benchmark and another well-known benchmark, POPE, for object hallucination. Compared to the state-of-the-art interleaved content generation models, DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data (10%), and a smaller base model size.
Authors: Wei Dong, Han Zhou, Yuqiong Tian, Jingke Sun, Xiaohong Liu, Guangtao Zhai, Jun Chen
Abstract: Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and segmentation systems. To effectively eliminate shadows in real-world images while preserving intricate details and producing visually compelling outcomes, we introduce a mask-free Shadow Removal and Refinement network (ShadowRefiner) via Fast Fourier Transformer. Specifically, the Shadow Removal module in our method aims to establish effective mappings between shadow-affected and shadow-free images via spatial and frequency representation learning. To mitigate the pixel misalignment and further improve the image quality, we propose a novel Fast-Fourier Attention based Transformer (FFAT) architecture, where an innovative attention mechanism is designed for meticulous refinement. Our method wins the championship in the Perceptual Track and achieves the second best performance in the Fidelity Track of NTIRE 2024 Image Shadow Removal Challenge. Besides, comprehensive experiment result also demonstrate the compelling effectiveness of our proposed method. The code is publicly available: https://github.com/movingforward100/Shadow_R.
Authors: Scott Geng, Cheng-Yu Hsieh, Vivek Ramanujan, Matthew Wallingford, Chun-Liang Li, Pang Wei Koh, Ranjay Krishna
Abstract: Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic data. However, every synthetic image ultimately originates from the upstream data used to train the generator. What additional value does the intermediate generator provide over directly training on relevant parts of the upstream data? Grounding this question in the setting of image classification,a we compare finetuning on task-relevant, targeted synthetic data generated by Stable Diffusion -- a generative model trained on the LAION-2B dataset -- against finetuning on targeted real images retrieved directly from LAION-2B. We show that while synthetic data can benefit some downstream tasks, it is universally matched or outperformed by real data from our simple retrieval baseline. Our analysis suggests that this underperformance is partially due to generator artifacts and inaccurate task-relevant visual details in the synthetic images. Overall, we argue that retrieval is a critical baseline to consider when training with synthetic data -- a baseline that current methods do not yet surpass. We release code, data, and models at https://github.com/scottgeng00/unmet-promise.
Authors: Yufan Zhu, Chongzhi Ran, Mingtao Feng, Fangfang Wu, Le Dong, Weisheng Dong, Antonio M. L\'opez, Guangming Shi
Abstract: Virtual engines can generate dense depth maps for various synthetic scenes, making them invaluable for training depth estimation models. However, discrepancies between synthetic and real-world colors pose significant challenges for depth estimation in real-world scenes, especially in complex and uncertain environments encountered in unsupervised monocular depth estimation tasks. To address this issue, we propose Back2Color, a framework that predicts realistic colors from depth using a model trained on real-world data, thus transforming synthetic colors into their real-world counterparts. Additionally, we introduce the Syn-Real CutMix method for joint training with both real-world unsupervised and synthetic supervised depth samples, enhancing monocular depth estimation performance in real-world scenes. Furthermore, to mitigate the impact of non-rigid motions on depth estimation, we present an auto-learning uncertainty temporal-spatial fusion method (Auto-UTSF), which leverages the strengths of unsupervised learning in both temporal and spatial dimensions. We also designed VADepth, based on the Vision Attention Network, which offers lower computational complexity and higher accuracy than transformers. Our Back2Color framework achieves state-of-the-art performance on the Kitti dataset, as evidenced by improvements in performance metrics and the production of fine-grained details. This is particularly evident on more challenging datasets such as Cityscapes for unsupervised depth estimation.
Authors: Yansheng Li, Linlin Wang, Tingzhu Wang, Xue Yang, Junwei Luo, Qi Wang, Youming Deng, Wenbin Wang, Xian Sun, Haifeng Li, Bo Dang, Yongjun Zhang, Yi Yu, Junchi Yan
Abstract: Scene graph generation (SGG) in satellite imagery (SAI) benefits promoting understanding of geospatial scenarios from perception to cognition. In SAI, objects exhibit great variations in scales and aspect ratios, and there exist rich relationships between objects (even between spatially disjoint objects), which makes it attractive to holistically conduct SGG in large-size very-high-resolution (VHR) SAI. However, there lack such SGG datasets. Due to the complexity of large-size SAI, mining triplets
Authors: Lei Li, Julia Camps, Blanca Rodriguez, Vicente Grau
Abstract: Cardiac digital twins are personalized virtual representations used to understand complex heart mechanisms. Solving the ECG inverse problem is crucial for accurate virtual heart modelling, enabling the derivation of internal electrical activity information from recorded surface potentials. Despite challenges from cardiac complexity, noisy ECG data, and computational efficiency, recent advancements hold significant promise for enhancing virtual heart modelling, ultimately advancing precision medicine in cardiology. This paper aims to provide a comprehensive review of the methods of solving ECG inverse problem, the validation strategies, the clinical applications, and future perspectives. For the computing methodologies, we broadly classify state-of-the-art approaches into two categories: deterministic and probabilistic methods, including conventional and deep learning-based techniques. Integrating physics laws with deep learning models holds promise, but challenges such as capturing dynamic electrophysiology accurately, accessing accurate domain knowledge, and quantifying prediction uncertainty persist. Integrating models into clinical workflows while ensuring interpretability and usability for healthcare professionals is essential. Overcoming these challenges will drive further research in cardiac digital twins.
Authors: Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li, Yuhang Wu, Xiaoshuai Sun, Rongrong Ji
Abstract: The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by introducing object detectors. However, these efforts neglect hallucinations in inter-object relationships, which is essential for visual comprehension. In this work, we introduce R-Bench, a novel benchmark for evaluating Vision Relationship Hallucination. R-Bench features image-level questions that focus on the existence of relationships and instance-level questions that assess local visual comprehension. We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object. The visual instruction tuning dataset's long-tail distribution significantly impacts LVLMs' understanding of visual relationships. Furthermore, our analysis reveals that current LVLMs tend to disregard visual content and overly rely on the common sense knowledge of Large Language Models. They also struggle with reasoning about spatial relationships based on contextual information.
Authors: Yuhang Ma, Wenting Xu, Jiji Tang, Qinfeng Jin, Rongsheng Zhang, Zeng Zhao, Changjie Fan, Zhipeng Hu
Abstract: Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encountered challenges in preserving characters with high-fidelity consistency due to inadequate feature extraction and concept confusion of reference characters. Therefore, we propose Character-Adapter, a plug-and-play framework designed to generate images that preserve the details of reference characters, ensuring high-fidelity consistency. Character-Adapter employs prompt-guided segmentation to ensure fine-grained regional features of reference characters and dynamic region-level adapters to mitigate concept confusion. Extensive experiments are conducted to validate the effectiveness of Character-Adapter. Both quantitative and qualitative results demonstrate that Character-Adapter achieves the state-of-the-art performance of consistent character generation, with an improvement of 24.8% compared with other methods. Our code will be released at https://github.com/Character-Adapter/Character-Adapter
URLs: https://github.com/Character-Adapter/Character-Adapter
Authors: Yuxuan Zhang, Tianheng Cheng, Rui Hu, Lei Liu, Heng Liu, Longjin Ran, Xiaoxin Chen, Wenyu Liu, Xinggang Wang
Abstract: Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what text prompt encoders (e.g., CLIP or LLM) are good for adapting SAM for referring expression segmentation and introduce the Early Vision-language Fusion-based SAM (EVF-SAM). EVF-SAM is a simple yet effective referring segmentation method which exploits multimodal prompts (i.e., image and text) and comprises a pre-trained vision-language model to generate referring prompts and a SAM model for segmentation. Surprisingly, we observe that: (1) multimodal prompts and (2) vision-language models with early fusion (e.g., BEIT-3) are beneficial for prompting SAM for accurate referring segmentation. Our experiments show that the proposed EVF-SAM based on BEIT-3 can obtain state-of-the-art performance on RefCOCO/+/g for referring expression segmentation and demonstrate the superiority of prompting SAM with early vision-language fusion. In addition, the proposed EVF-SAM with 1.32B parameters achieves remarkably higher performance while reducing nearly 82% of parameters compared to previous SAM methods based on large multimodal models.
Authors: Ruinan Jin, Zikang Xu, Yuan Zhong, Qiongsong Yao, Qi Dou, S. Kevin Zhou, Xiaoxiao Li
Abstract: The advent of foundation models (FMs) in healthcare offers unprecedented opportunities to enhance medical diagnostics through automated classification and segmentation tasks. However, these models also raise significant concerns about their fairness, especially when applied to diverse and underrepresented populations in healthcare applications. Currently, there is a lack of comprehensive benchmarks, standardized pipelines, and easily adaptable libraries to evaluate and understand the fairness performance of FMs in medical imaging, leading to considerable challenges in formulating and implementing solutions that ensure equitable outcomes across diverse patient populations. To fill this gap, we introduce FairMedFM, a fairness benchmark for FM research in medical imaging.FairMedFM integrates with 17 popular medical imaging datasets, encompassing different modalities, dimensionalities, and sensitive attributes. It explores 20 widely used FMs, with various usages such as zero-shot learning, linear probing, parameter-efficient fine-tuning, and prompting in various downstream tasks -- classification and segmentation. Our exhaustive analysis evaluates the fairness performance over different evaluation metrics from multiple perspectives, revealing the existence of bias, varied utility-fairness trade-offs on different FMs, consistent disparities on the same datasets regardless FMs, and limited effectiveness of existing unfairness mitigation methods. Checkout FairMedFM's project page and open-sourced codebase, which supports extendible functionalities and applications as well as inclusive for studies on FMs in medical imaging over the long term.
Authors: Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Jun Chen, Mohamed Elhoseiny, Ruohan Gao, Dinesh Manocha
Abstract: Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio. However, the progress in these directions has been mostly focused on tasks that only require a coarse-grained understanding of the audio-visual semantics. We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio both spatially and temporally. With a new modality alignment module based on optimal transport and a cross-attention module that enforces audio-visual consistency, Meerkat can tackle challenging tasks such as audio referred image grounding, image guided audio temporal localization, and audio-visual fact-checking. Moreover, we carefully curate a large dataset AVFIT that comprises 3M instruction tuning samples collected from open-source datasets, and introduce MeerkatBench that unifies five challenging audio-visual tasks. We achieve state-of-the-art performance on all these downstream tasks with a relative improvement of up to 37.12%.
Authors: Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Yunquan Sun, Lizhe Qi
Abstract: Novel Class Discovery (NCD) aims to discover unknown and novel classes in an unlabeled set by leveraging knowledge already learned about known classes. Existing works focus on instance-level or class-level knowledge representation and build a shared representation space to achieve performance improvements. However, a long-neglected issue is the potential imbalanced number of samples from known and novel classes, pushing the model towards dominant classes. Therefore, these methods suffer from a challenging trade-off between reviewing known classes and discovering novel classes. Based on this observation, we propose a Self-Cooperation Knowledge Distillation (SCKD) method to utilize each training sample (whether known or novel, labeled or unlabeled) for both review and discovery. Specifically, the model's feature representations of known and novel classes are used to construct two disjoint representation spaces. Through spatial mutual information, we design a self-cooperation learning to encourage model learning from the two feature representation spaces from itself. Extensive experiments on six datasets demonstrate that our method can achieve significant performance improvements, achieving state-of-the-art performance.
Authors: Badr-Eddine Marani, Mohamed Hanini, Nihitha Malayarukil, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante
Abstract: The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many occasions they are associated with hidden spurious correlations which are not easy to spot. Standard approaches rely on bias audits performed by analyzing model performance in pre-defined subgroups of data samples, usually characterized by common attributes like gender or ethnicity when it comes to people, or other specific attributes defining semantically coherent groups of images. However, it is not always possible to know a-priori the specific attributes defining the failure modes of visual recognition systems. Recent approaches propose to discover these groups by leveraging large vision language models, which enable the extraction of cross-modal embeddings and the generation of textual descriptions to characterize the subgroups where a certain model is underperforming. In this work, we argue that incorporating visual explanations (e.g. heatmaps generated via GradCAM or other approaches) can boost the performance of such bias discovery and mitigation frameworks. To this end, we introduce Visually Grounded Bias Discovery and Mitigation (ViG-Bias), a simple yet effective technique which can be integrated to a variety of existing frameworks to improve both, discovery and mitigation performance. Our comprehensive evaluation shows that incorporating visual explanations enhances existing techniques like DOMINO, FACTS and Bias-to-Text, across several challenging datasets, including CelebA, Waterbirds, and NICO++.
Authors: Wenxuan Guo, Yingping Liang, Zhiyu Pan, Ziheng Xi, Jianjiang Feng, Jie Zhou
Abstract: Gait recognition is a crucial biometric identification technique. Camera-based gait recognition has been widely applied in both research and industrial fields. LiDAR-based gait recognition has also begun to evolve most recently, due to the provision of 3D structural information. However, in certain applications, cameras fail to recognize persons, such as in low-light environments and long-distance recognition scenarios, where LiDARs work well. On the other hand, the deployment cost and complexity of LiDAR systems limit its wider application. Therefore, it is essential to consider cross-modality gait recognition between cameras and LiDARs for a broader range of applications. In this work, we propose the first cross-modality gait recognition framework between Camera and LiDAR, namely CL-Gait. It employs a two-stream network for feature embedding of both modalities. This poses a challenging recognition task due to the inherent matching between 3D and 2D data, exhibiting significant modality discrepancy. To align the feature spaces of the two modalities, i.e., camera silhouettes and LiDAR points, we propose a contrastive pre-training strategy to mitigate modality discrepancy. To make up for the absence of paired camera-LiDAR data for pre-training, we also introduce a strategy for generating data on a large scale. This strategy utilizes monocular depth estimated from single RGB images and virtual cameras to generate pseudo point clouds for contrastive pre-training. Extensive experiments show that the cross-modality gait recognition is very challenging but still contains potential and feasibility with our proposed model and pre-training strategy. To the best of our knowledge, this is the first work to address cross-modality gait recognition.
Authors: Jintu Zheng, Yi Ding, Qizhe Liu, Yi Cao, Ying Hu, Zenan Wang
Abstract: Traditional fluorescence staining is phototoxic to live cells, slow, and expensive; thus, the subcellular structure prediction (SSP) from transmitted light (TL) images is emerging as a label-free, faster, low-cost alternative. However, existing approaches utilize 3D networks for one-to-one voxel level dense prediction, which necessitates a frequent and time-consuming Z-axis imaging process. Moreover, 3D convolutions inevitably lead to significant computation and GPU memory overhead. Therefore, we propose an efficient framework, SparseSSP, predicting fluorescent intensities within the target voxel grid in an efficient paradigm instead of relying entirely on 3D topologies. In particular, SparseSSP makes two pivotal improvements to prior works. First, SparseSSP introduces a one-to-many voxel mapping paradigm, which permits the sparse TL slices to reconstruct the subcellular structure. Secondly, we propose a hybrid dimensions topology, which folds the Z-axis information into channel features, enabling the 2D network layers to tackle SSP under low computational cost. We conduct extensive experiments to validate the effectiveness and advantages of SparseSSP on diverse sparse imaging ratios, and our approach achieves a leading performance compared to pure 3D topologies. SparseSSP reduces imaging frequencies compared to previous dense-view SSP (i.e., the number of imaging is reduced up to 87.5% at most), which is significant in visualizing rapid biological dynamics on low-cost devices and samples.
Authors: Wenpu Li, Pian Wan, Peng Wang, Jinghang Li, Yi Zhou, Peidong Liu
Abstract: Neural implicit representation of visual scenes has attracted a lot of attention in recent research of computer vision and graphics. Most prior methods focus on how to reconstruct 3D scene representation from a set of images. In this work, we demonstrate the possibility to recover the neural radiance fields (NeRF) from a single blurry image and its corresponding event stream. We model the camera motion with a cubic B-Spline in SE(3) space. Both the blurry image and the brightness change within a time interval, can then be synthesized from the 3D scene representation given the 6-DoF poses interpolated from the cubic B-Spline. Our method can jointly learn both the implicit neural scene representation and recover the camera motion by minimizing the differences between the synthesized data and the real measurements without pre-computed camera poses from COLMAP. We evaluate the proposed method with both synthetic and real datasets. The experimental results demonstrate that we are able to render view-consistent latent sharp images from the learned NeRF and bring a blurry image alive in high quality. Code and data are available at https://github.com/WU-CVGL/BeNeRF.
Authors: Sufen Ren, Yule Hu, Shengchao Chen, Guanjun Wang
Abstract: Medical image classification plays a crucial role in computer-aided clinical diagnosis. While deep learning techniques have significantly enhanced efficiency and reduced costs, the privacy-sensitive nature of medical imaging data complicates centralized storage and model training. Furthermore, low-resource healthcare organizations face challenges related to communication overhead and efficiency due to increasing data and model scales. This paper proposes a novel privacy-preserving medical image classification framework based on federated learning to address these issues, named FedMIC. The framework enables healthcare organizations to learn from both global and local knowledge, enhancing local representation of private data despite statistical heterogeneity. It provides customized models for organizations with diverse data distributions while minimizing communication overhead and improving efficiency without compromising performance. Our FedMIC enhances robustness and practical applicability under resource-constrained conditions. We demonstrate FedMIC's effectiveness using four public medical image datasets for classical medical image classification tasks.
Authors: Huiyu Gao, Jiahao Ma, David Ahmedt-Aristizabal, Chuong Nguyen, Miaomiao Liu
Abstract: This paper tackles the problem of novel view audio-visual synthesis along an arbitrary trajectory in an indoor scene, given the audio-video recordings from other known trajectories of the scene. Existing methods often overlook the effect of room geometry, particularly wall occlusion to sound propagation, making them less accurate in multi-room environments. In this work, we propose a new approach called Scene Occlusion-aware Acoustic Field (SOAF) for accurate sound generation. Our approach derives a prior for sound energy field using distance-aware parametric sound-propagation modelling and then transforms it based on scene transmittance learned from the input video. We extract features from the local acoustic field centred around the receiver using a Fibonacci Sphere to generate binaural audio for novel views with a direction-aware attention mechanism. Extensive experiments on the real dataset RWAVS and the synthetic dataset SoundSpaces demonstrate that our method outperforms previous state-of-the-art techniques in audio generation. Project page: https://github.com/huiyu-gao/SOAF/.
Authors: Yangyang Xiang, Nannan Wu, Li Yu, Xin Yang, Kwang-Ting Cheng, Zengqiang Yan
Abstract: Federated learning has emerged as a compelling paradigm for medical image segmentation, particularly in light of increasing privacy concerns. However, most of the existing research relies on relatively stringent assumptions regarding the uniformity and completeness of annotations across clients. Contrary to this, this paper highlights a prevalent challenge in medical practice: incomplete annotations. Such annotations can introduce incorrectly labeled pixels, potentially undermining the performance of neural networks in supervised learning. To tackle this issue, we introduce a novel solution, named FedIA. Our insight is to conceptualize incomplete annotations as noisy data (i.e., low-quality data), with a focus on mitigating their adverse effects. We begin by evaluating the completeness of annotations at the client level using a designed indicator. Subsequently, we enhance the influence of clients with more comprehensive annotations and implement corrections for incomplete ones, thereby ensuring that models are trained on accurate data. Our method's effectiveness is validated through its superior performance on two extensively used medical image segmentation datasets, outperforming existing solutions. The code is available at https://github.com/HUSTxyy/FedIA.
Authors: Antoine Deckyvere, Anthony Cioppa, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck
Abstract: Slow-motion replays provide a thrilling perspective on pivotal moments within sports games, offering a fresh and captivating visual experience. However, capturing slow-motion footage typically demands high-tech, expensive cameras and infrastructures. Deep learning Video Frame Interpolation (VFI) techniques have emerged as a promising avenue, capable of generating high-speed footage from regular camera feeds. Moreover, the utilization of event-based cameras has recently gathered attention as they provide valuable motion information between frames, further enhancing the VFI performances. In this work, we present a first investigation of event-based VFI models for generating sports slow-motion videos. Particularly, we design and implement a bi-camera recording setup, including an RGB and an event-based camera to capture sports videos, to temporally align and spatially register both cameras. Our experimental validation demonstrates that TimeLens, an off-the-shelf event-based VFI model, can effectively generate slow-motion footage for sports videos. This first investigation underscores the practical utility of event-based cameras in producing sports slow-motion content and lays the groundwork for future research endeavors in this domain.
Authors: Shuohao Shi, Qiang Fang, Tong Zhao, Xin Xu
Abstract: Tiny object detection is becoming one of the most challenging tasks in computer vision because of the limited object size and lack of information. The label assignment strategy is a key factor affecting the accuracy of object detection. Although there are some effective label assignment strategies for tiny objects, most of them focus on reducing the sensitivity to the bounding boxes to increase the number of positive samples and have some fixed hyperparameters need to set. However, more positive samples may not necessarily lead to better detection results, in fact, excessive positive samples may lead to more false positives. In this paper, we introduce a simple but effective strategy named the Similarity Distance (SimD) to evaluate the similarity between bounding boxes. This proposed strategy not only considers both location and shape similarity but also learns hyperparameters adaptively, ensuring that it can adapt to different datasets and various object sizes in a dataset. Our approach can be simply applied in common anchor-based detectors in place of the IoU for label assignment and Non Maximum Suppression (NMS). Extensive experiments on four mainstream tiny object detection datasets demonstrate superior performance of our method, especially, 1.8 AP points and 4.1 AP points of very tiny higher than the state-of-the-art competitors on AI-TOD. Code is available at: \url{https://github.com/cszzshi/SimD}.
Authors: Jinmin Li, Kuofeng Gao, Yang Bai, Jingyun Zhang, Shu-Tao Xia
Abstract: The advent of video-based Large Language Models (LLMs) has significantly enhanced video understanding. However, it has also raised some safety concerns regarding data protection, as videos can be more easily annotated, even without authorization. This paper introduces Video Watermarking, a novel technique to protect videos from unauthorized annotations by such video-based LLMs, especially concerning the video content and description, in response to specific queries. By imperceptibly embedding watermarks into key video frames with multi-modal flow-based losses, our method preserves the viewing experience while preventing misuse by video-based LLMs. Extensive experiments show that Video Watermarking significantly reduces the comprehensibility of videos with various video-based LLMs, demonstrating both stealth and robustness. In essence, our method provides a solution for securing video content, ensuring its integrity and confidentiality in the face of evolving video-based LLMs technologies.
Authors: Aahlad Puli, Nitish Joshi, Yoav Wald, He He, Rajesh Ranganath
Abstract: In prediction tasks, there exist features that are related to the label in the same way across different settings for that task; these are semantic features or semantics. Features with varying relationships to the label are nuisances. For example, in detecting cows from natural images, the shape of the head is semantic but because images of cows often have grass backgrounds but not always, the background is a nuisance. Models that exploit nuisance-label relationships face performance degradation when these relationships change. Building models robust to such changes requires additional knowledge beyond samples of the features and labels. For example, existing work uses annotations of nuisances or assumes ERM-trained models depend on nuisances. Approaches to integrate new kinds of additional knowledge enlarge the settings where robust models can be built. We develop an approach to use knowledge about the semantics by corrupting them in data, and then using the corrupted data to produce models which identify correlations between nuisances and the label. Once these correlations are identified, they can be used to adjust for where nuisances drive predictions. We study semantic corruptions in powering different spurious-correlation avoiding methods on multiple out-of-distribution (OOD) tasks like classifying waterbirds, natural language inference (NLI), and detecting cardiomegaly in chest X-rays.
Authors: Francesco Cagnetta, Leonardo Petrini, Umberto M. Tomasini, Alessandro Favero, Matthieu Wyart
Abstract: Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representations. However, how many training examples are required to learn such representations remains unknown. To quantitatively study this question, we introduce the Random Hierarchy Model: a family of synthetic tasks inspired by the hierarchical structure of language and images. The model is a classification task where each class corresponds to a group of high-level features, chosen among several equivalent groups associated with the same class. In turn, each feature corresponds to a group of sub-features chosen among several equivalent ones and so on, following a hierarchy of composition rules. We find that deep networks learn the task by developing internal representations invariant to exchanging equivalent groups. Moreover, the number of data required corresponds to the point where correlations between low-level features and classes become detectable. Overall, our results indicate how deep networks overcome the curse of dimensionality by building invariant representations, and provide an estimate of the number of data required to learn a hierarchical task.
Authors: Ece Ozkan, Xavier Boix
Abstract: Current machine learning methods for medical image analysis primarily focus on developing models tailored for their specific tasks, utilizing data within their target domain. These specialized models tend to be data-hungry and often exhibit limitations in generalizing to out-of-distribution samples. In this work, we show that employing models that incorporate multiple domains instead of specialized ones significantly alleviates the limitations observed in specialized models. We refer to this approach as multi-domain model and compare its performance to that of specialized models. For this, we introduce the incorporation of diverse medical image domains, including different imaging modalities like X-ray, MRI, CT, and ultrasound images, as well as various viewpoints such as axial, coronal, and sagittal views. Our findings underscore the superior generalization capabilities of multi-domain models, particularly in scenarios characterized by limited data availability and out-of-distribution, frequently encountered in healthcare applications. The integration of diverse data allows multi-domain models to utilize information across domains, enhancing the overall outcomes substantially. To illustrate, for organ recognition, multi-domain model can enhance accuracy by up to 8% compared to conventional specialized models.
Authors: Farhad Maleki, Linda Moy, Reza Forghani, Tapotosh Ghosh, Katie Ovens, Steve Langer, Pouria Rouzrokh, Bardia Khosravi, Ali Ganjizadeh, Daniel Warren, Roxana Daneshjou, Mana Moassefi, Atlas Haddadi Avval, Susan Sotardi, Neil Tenenholtz, Felipe Kitamura, Timothy Kline
Abstract: Deep learning techniques hold immense promise for advancing medical image analysis, particularly in tasks like image segmentation, where precise annotation of regions or volumes of interest within medical images is crucial but manually laborious and prone to interobserver and intraobserver biases. As such, deep learning approaches could provide automated solutions for such applications. However, the potential of these techniques is often undermined by challenges in reproducibility and generalizability, which are key barriers to their clinical adoption. This paper introduces the RIDGE checklist, a comprehensive framework designed to assess the Reproducibility, Integrity, Dependability, Generalizability, and Efficiency of deep learning-based medical image segmentation models. The RIDGE checklist is not just a tool for evaluation but also a guideline for researchers striving to improve the quality and transparency of their work. By adhering to the principles outlined in the RIDGE checklist, researchers can ensure that their developed segmentation models are robust, scientifically valid, and applicable in a clinical setting.
Authors: Anton Kuznietsov, Balint Gyevnar, Cheng Wang, Steven Peters, Stefano V. Albrecht
Abstract: Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, inscrutable AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a modular framework called SafeX to integrate these contributions, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.
Authors: Zonghao Ying, Aishan Liu, Xianglong Liu, Dacheng Tao
Abstract: The recent release of GPT-4o has garnered widespread attention due to its powerful general capabilities. While its impressive performance is widely acknowledged, its safety aspects have not been sufficiently explored. Given the potential societal impact of risky content generated by advanced generative AI such as GPT-4o, it is crucial to rigorously evaluate its safety. In response to this question, this paper for the first time conducts a rigorous evaluation of GPT-4o against jailbreak attacks. Specifically, this paper adopts a series of multi-modal and uni-modal jailbreak attacks on 4 commonly used benchmarks encompassing three modalities (ie, text, speech, and image), which involves the optimization of over 4,000 initial text queries and the analysis and statistical evaluation of nearly 8,000+ response on GPT-4o. Our extensive experiments reveal several novel observations: (1) In contrast to the previous version (such as GPT-4V), GPT-4o has enhanced safety in the context of text modality jailbreak; (2) The newly introduced audio modality opens up new attack vectors for jailbreak attacks on GPT-4o; (3) Existing black-box multimodal jailbreak attack methods are largely ineffective against GPT-4o and GPT-4V. These findings provide critical insights into the safety implications of GPT-4o and underscore the need for robust alignment guardrails in large models. Our code is available at \url{https://github.com/NY1024/Jailbreak_GPT4o}.
Authors: Aditya Sharma, Michael Saxon, William Yang Wang
Abstract: We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recognition tasks with increasingly long visual contexts composed of both in-distribution and out-of-distribution distractor images. Across these tasks, a diverse set of VLMs rapidly lose performance as the visual context length grows, often exhibiting a striking logarithmic decay trend. This test assesses how well VLMs can ignore irrelevant information when answering queries -- a task that is quite easy for language models (LMs) in the text domain -- demonstrating that current state-of-the-art VLMs lack this essential capability for many long-context applications.
Authors: Daniel Reisenb\"uchler, Lucas Luttner, Nadine S. Schaadt, Friedrich Feuerhake, Dorit Merhof
Abstract: In computational pathology, deep learning (DL) models for tasks such as segmentation or tissue classification are known to suffer from domain shifts due to different staining techniques. Stain adaptation aims to reduce the generalization error between different stains by training a model on source stains that generalizes to target stains. Despite the abundance of target stain data, a key challenge is the lack of annotations. To address this, we propose a joint training between artificially labeled and unlabeled data including all available stained images called Unsupervised Latent Stain Adaptation (ULSA). Our method uses stain translation to enrich labeled source images with synthetic target images in order to increase the supervised signals. Moreover, we leverage unlabeled target stain images using stain-invariant feature consistency learning. With ULSA we present a semi-supervised strategy for efficient stain adaptation without access to annotated target stain data. Remarkably, ULSA is task agnostic in patch-level analysis for whole slide images (WSIs). Through extensive evaluation on external datasets, we demonstrate that ULSA achieves state-of-the-art (SOTA) performance in kidney tissue segmentation and breast cancer classification across a spectrum of staining variations. Our findings suggest that ULSA is an important framework for stain adaptation in computational pathology.
Authors: Youngmin Seo, Jinha Kim, Unsang Park
Abstract: We propose the Swish-T family, an enhancement of the existing non-monotonic activation function Swish. Swish-T is defined by adding a Tanh bias to the original Swish function. This modification creates a family of Swish-T variants, each designed to excel in different tasks, showcasing specific advantages depending on the application context. The Tanh bias allows for broader acceptance of negative values during initial training stages, offering a smoother non-monotonic curve than the original Swish. We ultimately propose the Swish-T$_{\textbf{C}}$ function, while Swish-T and Swish-T$_{\textbf{B}}$, byproducts of Swish-T$_{\textbf{C}}$, also demonstrate satisfactory performance. Furthermore, our ablation study shows that using Swish-T$_{\textbf{C}}$ as a non-parametric function can still achieve high performance. The superiority of the Swish-T family has been empirically demonstrated across various models and benchmark datasets, including MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. The code is publicly available at https://github.com/ictseoyoungmin/Swish-T-pytorch.
Authors: Chaoxing Huang, Ziqiang Yu, Zijian Gao, Qiuyi Shen, Queenie Chan, Vincent Wai-Sun Wong, Winnie Chiu-Wing Chu, Weitian Chen
Abstract: This study evaluated a deep learning-based method using Deep Image Prior (DIP) to quantify triglyceride double bonds from chemical-shift encoded multi-echo gradient echo images without network training. We employed a cost function based on signal constraints to iteratively update the neural network on a single dataset. The method was validated using phantom experiments and in vivo scans. Results showed close alignment between measured and reference double bond values, with phantom experiments yielding a Pearson correlation coefficient of 0.96 (p = .0005). In vivo results demonstrated good agreement in subcutaneous fat. We conclude that Deep Image Prior shows feasibility for quantifying double bonds and fatty acid content from chemical-shift encoded multi-echo MRI.