Authors: Miriam Doh (UMONS, ULB), Caroline Mazini Rodrigues (LRDE, LIGM), N. Boutry (LRDE), L. Najman (LIGM), Matei Mancas (UMONS), Bernard Gosselin (UMONS)
Abstract: The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to enhance interpretability and transparency. This study extends previous work by integrating semantic concepts derived from human cognitive processes into XAI frameworks to bridge the comprehension gap between model outputs and human understanding. We propose a novel approach combining global and local explanations, using semantic features defined by user-selected facial landmarks to generate similarity maps and textual explanations via large language models (LLMs). The methodology was validated through quantitative experiments and user feedback, demonstrating improved interpretability. Results indicate that our semantic-based approach, particularly the most detailed set, offers a more nuanced understanding of model decisions than traditional methods. User studies highlight a preference for our semantic explanations over traditional pixelbased heatmaps, emphasizing the benefits of human-centric interpretability in AI. This work contributes to the ongoing efforts to create XAI frameworks that align AI models behaviour with human cognitive processes, fostering trust and acceptance in critical applications.
Authors: Qing Wu
Abstract: 3D semantic segmentation is one of the most crucial tasks in driving perception. The ability of a learning-based model to accurately perceive dense 3D surroundings often ensures the safe operation of autonomous vehicles. However, existing LiDAR-based 3D semantic segmentation databases consist of sequentially acquired LiDAR scans that are long-tailed and lack training diversity. In this report, we introduce MixSeg3D, a sophisticated combination of the strong point cloud segmentation model with advanced 3D data mixing strategies. Specifically, our approach integrates the MinkUNet family with LaserMix and PolarMix, two scene-scale data augmentation methods that blend LiDAR point clouds along the ego-scene's inclination and azimuth directions. Through empirical experiments, we demonstrate the superiority of MixSeg3D over the baseline and prior arts. Our team achieved 2nd place in the 3D semantic segmentation track of the 2024 Waymo Open Dataset Challenge.
Authors: Jingyuan Tang, Yuhuan Zhao, Songlin Sun, Yangang Cai
Abstract: Point clouds, a prominent method of 3D representation, are extensively utilized across industries such as autonomous driving, surveying, electricity, architecture, and gaming, and have been rigorously investigated for their accuracy and resilience. The extraction of semantic information from scenes enhances both human understanding and machine perception. By integrating semantic information from two-dimensional scenes with three-dimensional point clouds, researchers aim to improve the precision and efficiency of various tasks. This paper provides a comprehensive review of the diverse applications and recent advancements in the integration of semantic information within point clouds. We explore the dual roles of semantic information in point clouds, encompassing both implicit guidance and explicit representation, across traditional and emerging tasks. Additionally, we offer a comparative analysis of publicly available datasets tailored to specific tasks and present notable observations. In conclusion, we discuss several challenges and potential issues that may arise in the future when fully utilizing semantic information in point clouds, providing our perspectives on these obstacles. The classified and organized articles related to semantic based point cloud tasks, and continuously followed up on relevant achievements in different fields, which can be accessed through https://github.com/Jasmine-tjy/Semantic-based-Point-Cloud-Tasks.
URLs: https://github.com/Jasmine-tjy/Semantic-based-Point-Cloud-Tasks.
Authors: Yongjia Ma, Junlin Chen, Donglin Di, Qi Xie, Lei Fan, Wei Chen, Xiaofei Gou, Na Zhao, Xun Yang
Abstract: Creating high-fidelity, coherent long videos is a sought-after aspiration. While recent video diffusion models have shown promising potential, they still grapple with spatiotemporal inconsistencies and high computational resource demands. We propose GLC-Diffusion, a tuning-free method for long video generation. It models the long video denoising process by establishing denoising trajectories through Global-Local Collaborative Denoising to ensure overall content consistency and temporal coherence between frames. Additionally, we introduce a Noise Reinitialization strategy which combines local noise shuffling with frequency fusion to improve global content consistency and visual diversity. Further, we propose a Video Motion Consistency Refinement (VMCR) module that computes the gradient of pixel-wise and frequency-wise losses to enhance visual consistency and temporal smoothness. Extensive experiments, including quantitative and qualitative evaluations on videos of varying lengths (\textit{e.g.}, 3\times and 6\times longer), demonstrate that our method effectively integrates with existing video diffusion models, producing coherent, high-fidelity long videos superior to previous approaches.
Authors: Yifei Li, Junbo Niu, Ziyang Miao, Chunjiang Ge, Yuanhang Zhou, Qihao He, Xiaoyi Dong, Haodong Duan, Shuangrui Ding, Rui Qian, Pan Zhang, Yuhang Zang, Yuhang Cao, Conghui He, Jiaqi Wang
Abstract: Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc analysis, online models process video streams incrementally and dynamically adapt their responses based on the timestamp at which the question is posed. Despite its significance, temporal awareness has not been adequately evaluated in existing benchmarks. To fill this gap, we present OVO-Bench (Online-VideO-Benchmark), a novel video benchmark that emphasizes the importance of timestamps for advanced online video understanding capability benchmarking. OVO-Bench evaluates the ability of video LLMs to reason and respond to events occurring at specific timestamps under three distinct scenarios: (1) Backward tracing: trace back to past events to answer the question. (2) Real-time understanding: understand and respond to events as they unfold at the current timestamp. (3) Forward active responding: delay the response until sufficient future information becomes available to answer the question accurately. OVO-Bench comprises 12 tasks, featuring 644 unique videos and approximately human-curated 2,800 fine-grained meta-annotations with precise timestamps. We combine automated generation pipelines with human curation. With these high-quality samples, we further developed an evaluation pipeline to systematically query video LLMs along the video timeline. Evaluations of nine Video-LLMs reveal that, despite advancements on traditional benchmarks, current models struggle with online video understanding, showing a significant gap compared to human agents. We hope OVO-Bench will drive progress in video LLMs and inspire future research in online video reasoning. Our benchmark and code can be accessed at https://github.com/JoeLeelyf/OVO-Bench.
Authors: Hung Huy Nguyen, Pooyan Rahmanzadehgervi, Long Mail, Anh Totti Nguyen
Abstract: Detecting object-level changes between two images across possibly different views is a core task in many applications that involve visual inspection or camera surveillance. Existing change-detection approaches suffer from three major limitations: (1) lack of evaluation on image pairs that contain no changes, leading to unreported false positive rates; (2) lack of correspondences (\ie, localizing the regions before and after a change); and (3) poor zero-shot generalization across different domains. To address these issues, we introduce a novel method that leverages change correspondences (a) during training to improve change detection accuracy, and (b) at test time, to minimize false positives. That is, we harness the supervision labels of where an object is added or removed to supervise change detectors, improving their accuracy over previous work by a large margin. Our work is also the first to predict correspondences between pairs of detected changes using estimated homography and the Hungarian algorithm. Our model demonstrates superior performance over existing methods, achieving state-of-the-art results in change detection and change correspondence accuracy across both in-distribution and zero-shot benchmarks.
Authors: Mohammed Elhenawy, Huthaifa I. Ashqar, Andry Rakotonirainy, Taqwa I. Alhadidi, Ahmed Jaber, Mohammad Abu Tami
Abstract: Scene understanding is essential for enhancing driver safety, generating human-centric explanations for Automated Vehicle (AV) decisions, and leveraging Artificial Intelligence (AI) for retrospective driving video analysis. This study developed a dynamic scene retrieval system using Contrastive Language-Image Pretraining (CLIP) models, which can be optimized for real-time deployment on edge devices. The proposed system outperforms state-of-the-art in-context learning methods, including the zero-shot capabilities of GPT-4o, particularly in complex scenarios. By conducting frame-level analysis on the Honda Scenes Dataset, which contains a collection of about 80 hours of annotated driving videos capturing diverse real-world road and weather conditions, our study highlights the robustness of CLIP models in learning visual concepts from natural language supervision. Results also showed that fine-tuning the CLIP models, such as ViT-L/14 and ViT-B/32, significantly improved scene classification, achieving a top F1 score of 91.1%. These results demonstrate the ability of the system to deliver rapid and precise scene recognition, which can be used to meet the critical requirements of Advanced Driver Assistance Systems (ADAS). This study shows the potential of CLIP models to provide scalable and efficient frameworks for dynamic scene understanding and classification. Furthermore, this work lays the groundwork for advanced autonomous vehicle technologies by fostering a deeper understanding of driver behavior, road conditions, and safety-critical scenarios, marking a significant step toward smarter, safer, and more context-aware autonomous driving systems.
Authors: Benjamin Kiefer, Yitong Quan, Andreas Zell
Abstract: Unmanned surface vehicles (USVs) and boats are increasingly important in maritime operations, yet their deployment is limited due to costly sensors and complexity. LiDAR, radar, and depth cameras are either costly, yield sparse point clouds or are noisy, and require extensive calibration. Here, we introduce a novel approach for approximate distance estimation in USVs using supervised object detection. We collected a dataset comprising images with manually annotated bounding boxes and corresponding distance measurements. Leveraging this data, we propose a specialized branch of an object detection model, not only to detect objects but also to predict their distances from the USV. This method offers a cost-efficient and intuitive alternative to conventional distance measurement techniques, aligning more closely with human estimation capabilities. We demonstrate its application in a marine assistance system that alerts operators to nearby objects such as boats, buoys, or other waterborne hazards.
Authors: Anant Mehta, Bryant McArthur, Nagarjuna Kolloju, Zhengzhong Tu
Abstract: The rapid progress in deep generative models has led to the creation of incredibly realistic synthetic images that are becoming increasingly difficult to distinguish from real-world data. The widespread use of Variational Models, Diffusion Models, and Generative Adversarial Networks has made it easier to generate convincing fake images and videos, which poses significant challenges for detecting and mitigating the spread of misinformation. As a result, developing effective methods for detecting AI-generated fakes has become a pressing concern. In our research, we propose HFMF, a comprehensive two-stage deepfake detection framework that leverages both hierarchical cross-modal feature fusion and multi-stream feature extraction to enhance detection performance against imagery produced by state-of-the-art generative AI models. The first component of our approach integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism. The second component of our framework combines object-level information and a fine-tuned convolutional net model. We then fuse the outputs from both components via an ensemble deep neural net, enabling robust classification performances. We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks while maintaining calibration and interoperability.
Authors: Chen Wang, Yanfeng Gu, Xian Li
Abstract: LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively, offering complementary advantages and heterogeneous. Due to the fundamental differences in sensing mechanisms, spatial distributions and coordinate systems, their point clouds exhibit significant discrepancies in density, precision, noise, and overlap. Coupled with the lack of ground truth for large-scale scenes, integrating the heterogeneous point clouds is a highly challenging task. This paper proposes a self-supervised registration network based on a masked autoencoder, focusing on heterogeneous LiDAR and photogrammetric point clouds. At its core, the method introduces a multi-scale masked training strategy to extract robust features from heterogeneous point clouds under self-supervision. To further enhance registration performance, a rotation-translation embedding module is designed to effectively capture the key features essential for accurate rigid transformations. Building upon the robust representations, a transformer-based architecture seamlessly integrates local and global features, fostering precise alignment across diverse point cloud datasets. The proposed method demonstrates strong feature extraction capabilities for both LiDAR and photogrammetric point clouds, addressing the challenges of acquiring ground truth at the scene level. Experiments conducted on two real-world datasets validate the effectiveness of the proposed method in solving heterogeneous point cloud registration problems.
Authors: Ruitao Pu, Yang Qin, Dezhong Peng, Xiaomin Song, Huiming Zheng
Abstract: Cross-modal retrieval (CMR) typically involves learning common representations to directly measure similarities between multimodal samples. Most existing CMR methods commonly assume multimodal samples in pairs and employ joint training to learn common representations, limiting the flexibility of CMR. Although some methods adopt independent training strategies for each modality to improve flexibility in CMR, they utilize the randomly initialized orthogonal matrices to guide representation learning, which is suboptimal since they assume inter-class samples are independent of each other, limiting the potential of semantic alignments between sample representations and ground-truth labels. To address these issues, we propose a novel method termed Deep Reversible Consistency Learning (DRCL) for cross-modal retrieval. DRCL includes two core modules, \ie Selective Prior Learning (SPL) and Reversible Semantic Consistency learning (RSC). More specifically, SPL first learns a transformation weight matrix on each modality and selects the best one based on the quality score as the Prior, which greatly avoids blind selection of priors learned from low-quality modalities. Then, RSC employs a Modality-invariant Representation Recasting mechanism (MRR) to recast the potential modality-invariant representations from sample semantic labels by the generalized inverse matrix of the prior. Since labels are devoid of modal-specific information, we utilize the recast features to guide the representation learning, thus maintaining semantic consistency to the fullest extent possible. In addition, a feature augmentation mechanism (FA) is introduced in RSC to encourage the model to learn over a wider data distribution for diversity. Finally, extensive experiments conducted on five widely used datasets and comparisons with 15 state-of-the-art baselines demonstrate the effectiveness and superiority of our DRCL.
Authors: Xinyao Liao, Wei Wei, Dangyang Chen, Yuanyuan Fu
Abstract: Scene Graph Generation(SGG) is a scene understanding task that aims at identifying object entities and reasoning their relationships within a given image. In contrast to prevailing two-stage methods based on a large object detector (e.g., Faster R-CNN), one-stage methods integrate a fixed-size set of learnable queries to jointly reason relational triplets
Authors: Shuolong Chen, Xingxing Li, Liu Yuan, Ziao Liu
Abstract: The bio-inspired event camera has garnered extensive research attention in recent years, owing to its significant potential derived from its high dynamic range and low latency characteristics. Similar to the standard camera, the event camera requires precise intrinsic calibration to facilitate further high-level visual applications, such as pose estimation and mapping. While several calibration methods for event cameras have been proposed, most of them are either (i) engineering-driven, heavily relying on conventional image-based calibration pipelines, or (ii) inconvenient, requiring complex instrumentation. To this end, we propose an accurate and convenient intrinsic calibration method for event cameras, named eKalibr, which builds upon a carefully designed event-based circle grid pattern recognition algorithm. To extract target patterns from events, we perform event-based normal flow estimation to identify potential events generated by circle edges, and cluster them spatially. Subsequently, event clusters associated with the same grid circles are matched and grouped using normal flows, for subsequent time-varying ellipse estimation. Fitted ellipse centers are time-synchronized, for final grid pattern recognition. We conducted extensive experiments to evaluate the performance of eKalibr in terms of pattern extraction and intrinsic calibration. The implementation of eKalibr is open-sourced at (https://github.com/Unsigned-Long/eKalibr) to benefit the research community.
Authors: Daowan Peng, Wei Wei
Abstract: Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions. In this context, predictions often depend on linguistic shortcuts rather than a comprehensive grasp of multimodal knowledge, which diminishes their generalization ability. In this paper, we propose a novel method, namely, KDAR, leveraging knowledge distillation to address the prior-dependency dilemmas within the VQA task. Specifically, the regularization effect facilitated by soft labels from a well-trained teacher is employed to penalize overfitting to the most common answers. The soft labels, which serve a regularization role, also provide semantic guidance that narrows the range of candidate answers. Additionally, we design an adaptive sample-wise reweighting learning strategy to further mitigate bias by dynamically adjusting the importance of each sample. Experimental results demonstrate that our method enhances performance in both OOD and IID settings. Our method achieves state-of-the-art performance on the VQA-CPv2 out-of-distribution (OOD) benchmark, significantly outperforming previous state-of-the-art approaches.
Authors: Yi He, Shengqi Dang, Long Ling, Ziqing Qian, Nanxuan Zhao, Nan Cao
Abstract: Recent research shows that emotions can enhance users' cognition and influence information communication. While research on visual emotion analysis is extensive, limited work has been done on helping users generate emotionally rich image content. Existing work on emotional image generation relies on discrete emotion categories, making it challenging to capture complex and subtle emotional nuances accurately. Additionally, these methods struggle to control the specific content of generated images based on text prompts. In this work, we introduce the new task of continuous emotional image content generation (C-EICG) and present EmotiCrafter, an emotional image generation model that generates images based on text prompts and Valence-Arousal values. Specifically, we propose a novel emotion-embedding mapping network that embeds Valence-Arousal values into textual features, enabling the capture of specific emotions in alignment with intended input prompts. Additionally, we introduce a loss function to enhance emotion expression. The experimental results show that our method effectively generates images representing specific emotions with the desired content and outperforms existing techniques.
Authors: Dominick Reilly, Manish Kumar Govind, Srijan Das
Abstract: Large Vision Language Models (LVLMs) have demonstrated impressive capabilities in video understanding, yet their adoption for Activities of Daily Living (ADL) remains limited by their inability to capture fine-grained interactions and spatial relationships. This limitation is particularly evident in ADL tasks, where understanding detailed human-object interaction and human-centric motion is crucial for applications such as elderly monitoring and cognitive assessment. To address this, we aim to leverage the complementary nature of egocentric views to enhance LVLM's understanding of exocentric ADL videos. Consequently, we propose an online ego2exo distillation approach to learn ego-augmented exo representations in LVLMs. While effective, this approach requires paired ego-exo training data, which is impractical to collect for real-world ADL scenarios. Consequently, we develop EgoMimic, a skeleton-guided method that can generate mimicked ego views from exocentric videos. We find that the exo representations of our ego-augmented LVLMs successfully learn to extract ego-perspective cues, demonstrated through comprehensive evaluation on six ADL benchmarks and our proposed EgoPerceptionMCQ benchmark designed specifically to assess egocentric understanding from exocentric videos. Code, models, and data will be open-sourced at https://github.com/dominickrei/EgoExo4ADL.
Authors: Chinmay K Lalgudi, Mark E Leone, Jaden V Clark, Sergio Madrigal-Mora, Mario Espinoza
Abstract: The recent widespread adoption of drones for studying marine animals provides opportunities for deriving biological information from aerial imagery. The large scale of imagery data acquired from drones is well suited for machine learning (ML) analysis. Development of ML models for analyzing marine animal aerial imagery has followed the classical paradigm of training, testing, and deploying a new model for each dataset, requiring significant time, human effort, and ML expertise. We introduce Frame Level ALIgment and tRacking (FLAIR), which leverages the video understanding of Segment Anything Model 2 (SAM2) and the vision-language capabilities of Contrastive Language-Image Pre-training (CLIP). FLAIR takes a drone video as input and outputs segmentation masks of the species of interest across the video. Notably, FLAIR leverages a zero-shot approach, eliminating the need for labeled data, training a new model, or fine-tuning an existing model to generalize to other species. With a dataset of 18,000 drone images of Pacific nurse sharks, we trained state-of-the-art object detection models to compare against FLAIR. We show that FLAIR massively outperforms these object detectors and performs competitively against two human-in-the-loop methods for prompting SAM2, achieving a Dice score of 0.81. FLAIR readily generalizes to other shark species without additional human effort and can be combined with novel heuristics to automatically extract relevant information including length and tailbeat frequency. FLAIR has significant potential to accelerate aerial imagery analysis workflows, requiring markedly less human effort and expertise than traditional machine learning workflows, while achieving superior accuracy. By reducing the effort required for aerial imagery analysis, FLAIR allows scientists to spend more time interpreting results and deriving insights about marine ecosystems.
Authors: Sehyung Kim, Chanhyeong Yang, Jihwan Park, Taehoon Song, Hyunwoo J. Kim
Abstract: Attribute classification is crucial for identifying specific characteristics within image regions. Vision-Language Models (VLMs) have been effective in zero-shot tasks by leveraging their general knowledge from large-scale datasets. Recent studies demonstrate that transformer-based models with class-wise queries can effectively address zero-shot multi-label classification. However, poor utilization of the relationship between seen and unseen attributes makes the model lack generalizability. Additionally, attribute classification generally involves many attributes, making maintaining the model's scalability difficult. To address these issues, we propose Super-class guided transFormer (SugaFormer), a novel framework that leverages super-classes to enhance scalability and generalizability for zero-shot attribute classification. SugaFormer employs Super-class Query Initialization (SQI) to reduce the number of queries, utilizing common semantic information from super-classes, and incorporates Multi-context Decoding (MD) to handle diverse visual cues. To strengthen generalizability, we introduce two knowledge transfer strategies that utilize VLMs. During training, Super-class guided Consistency Regularization (SCR) aligns SugaFormer's features with VLMs using region-specific prompts, and during inference, Zero-shot Retrieval-based Score Enhancement (ZRSE) refines predictions for unseen attributes. Extensive experiments demonstrate that SugaFormer achieves state-of-the-art performance across three widely-used attribute classification benchmarks under zero-shot, and cross-dataset transfer settings. Our code is available at https://github.com/mlvlab/SugaFormer.
Authors: Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma, Kentaro Arai, Seiji Totsuka, Hiroshi Ino, Takayuki Okatani
Abstract: The application of Multi-modal Large Language Models (MLLMs) in Autonomous Driving (AD) faces significant challenges due to their limited training on traffic-specific data and the absence of dedicated benchmarks for spatiotemporal understanding. This study addresses these issues by proposing TB-Bench, a comprehensive benchmark designed to evaluate MLLMs on understanding traffic behaviors across eight perception tasks from ego-centric views. We also introduce vision-language instruction tuning datasets, TB-100k and TB-250k, along with simple yet effective baselines for the tasks. Through extensive experiments, we show that existing MLLMs underperform in these tasks, with even a powerful model like GPT-4o achieving less than 35% accuracy on average. In contrast, when fine-tuned with TB-100k or TB-250k, our baseline models achieve average accuracy up to 85%, significantly enhancing performance on the tasks. Additionally, we demonstrate performance transfer by co-training TB-100k with another traffic dataset, leading to improved performance on the latter. Overall, this study represents a step forward by introducing a comprehensive benchmark, high-quality datasets, and baselines, thus supporting the gradual integration of MLLMs into the perception, prediction, and planning stages of AD.
Authors: Loay Rashid, Siddharth Roheda, Amit Unde
Abstract: Video restoration plays a pivotal role in revitalizing degraded video content by rectifying imperfections caused by various degradations introduced during capturing (sensor noise, motion blur, etc.), saving/sharing (compression, resizing, etc.) and editing. This paper introduces a novel algorithm designed for scenarios where noise is introduced during video capture, aiming to enhance the visual quality of videos by reducing unwanted noise artifacts. We propose the Latent space LSTM Video Denoiser (LLVD), an end-to-end blind denoising model. LLVD uniquely combines spatial and temporal feature extraction, employing Long Short Term Memory (LSTM) within the encoded feature domain. This integration of LSTM layers is crucial for maintaining continuity and minimizing flicker in the restored video. Moreover, processing frames in the encoded feature domain significantly reduces computations, resulting in a very lightweight architecture. LLVD's blind nature makes it versatile for real, in-the-wild denoising scenarios where prior information about noise characteristics is not available. Experiments reveal that LLVD demonstrates excellent performance for both synthetic and captured noise. Specifically, LLVD surpasses the current State-Of-The-Art (SOTA) in RAW denoising by 0.3dB, while also achieving a 59\% reduction in computational complexity.
Authors: Seungjoo Shin, Jaesik Park, Sunghyun Cho
Abstract: We present LocoGS, a locality-aware 3D Gaussian Splatting (3DGS) framework that exploits the spatial coherence of 3D Gaussians for compact modeling of volumetric scenes. To this end, we first analyze the local coherence of 3D Gaussian attributes, and propose a novel locality-aware 3D Gaussian representation that effectively encodes locally-coherent Gaussian attributes using a neural field representation with a minimal storage requirement. On top of the novel representation, LocoGS is carefully designed with additional components such as dense initialization, an adaptive spherical harmonics bandwidth scheme and different encoding schemes for different Gaussian attributes to maximize compression performance. Experimental results demonstrate that our approach outperforms the rendering quality of existing compact Gaussian representations for representative real-world 3D datasets while achieving from 54.6$\times$ to 96.6$\times$ compressed storage size and from 2.1$\times$ to 2.4$\times$ rendering speed than 3DGS. Even our approach also demonstrates an averaged 2.4$\times$ higher rendering speed than the state-of-the-art compression method with comparable compression performance.
Authors: Shangjin Zhai, Zhichao Ye, Jialin Liu, Weijian Xie, Jiaqi Hu, Zhen Peng, Hua Xue, Danpeng Chen, Xiaomeng Wang, Lei Yang, Nan Wang, Haomin Liu, Guofeng Zhang
Abstract: Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small area, making long-range consistent scene generation challenging. To address this, we propose StarGen, a novel framework that employs a pre-trained video diffusion model in an autoregressive manner for long-range scene generation. The generation of each video clip is conditioned on the 3D warping of spatially adjacent images and the temporally overlapping image from previously generated clips, improving spatiotemporal consistency in long-range scene generation with precise pose control. The spatiotemporal condition is compatible with various input conditions, facilitating diverse tasks, including sparse view interpolation, perpetual view generation, and layout-conditioned city generation. Quantitative and qualitative evaluations demonstrate StarGen's superior scalability, fidelity, and pose accuracy compared to state-of-the-art methods.
Authors: Duanpeng Shi, Wendong Zheng, Di Guo, Huaping Liu
Abstract: Electrical impedance tomography (EIT) is a non-invasive imaging technique, which has been widely used in the fields of industrial inspection, medical monitoring and tactile sensing. However, due to the inherent non-linearity and ill-conditioned nature of the EIT inverse problem, the reconstructed image is highly sensitive to the measured data, and random noise artifacts often appear in the reconstructed image, which greatly limits the application of EIT. To address this issue, a conditional diffusion model with voltage consistency (CDMVC) is proposed in this study. The method consists of a pre-imaging module, a conditional diffusion model for reconstruction, a forward voltage constraint network and a scheme of voltage consistency constraint during sampling process. The pre-imaging module is employed to generate the initial reconstruction. This serves as a condition for training the conditional diffusion model. Finally, based on the forward voltage constraint network, a voltage consistency constraint is implemented in the sampling phase to incorporate forward information of EIT, thereby enhancing imaging quality. A more complete dataset, including both common and complex concave shapes, is generated. The proposed method is validated using both simulation and physical experiments. Experimental results demonstrate that our method can significantly improves the quality of reconstructed images. In addition, experimental results also demonstrate that our method has good robustness and generalization performance.
Authors: Yachao Li, Dong Liang, Tianyu Ding, Sheng-Jun Huang
Abstract: Diffusion-based models have shown great promise in real-world image super-resolution (Real-ISR), but often generate content with structural errors and spurious texture details due to the empirical priors and illusions of these models. To address this issue, we introduce StructSR, a simple, effective, and plug-and-play method that enhances structural fidelity and suppresses spurious details for diffusion-based Real-ISR. StructSR operates without the need for additional fine-tuning, external model priors, or high-level semantic knowledge. At its core is the Structure-Aware Screening (SAS) mechanism, which identifies the image with the highest structural similarity to the low-resolution (LR) input in the early inference stage, allowing us to leverage it as a historical structure knowledge to suppress the generation of spurious details. By intervening in the diffusion inference process, StructSR seamlessly integrates with existing diffusion-based Real-ISR models. Our experimental results demonstrate that StructSR significantly improves the fidelity of structure and texture, improving the PSNR and SSIM metrics by an average of 5.27% and 9.36% on a synthetic dataset (DIV2K-Val) and 4.13% and 8.64% on two real-world datasets (RealSR and DRealSR) when integrated with four state-of-the-art diffusion-based Real-ISR methods.
Authors: Yanjie Li, Wenxuan Zhang, Kaisheng Liang, Bin Xiao
Abstract: In recent research, adversarial attacks on person detectors using patches or static 3D model-based texture modifications have struggled with low success rates due to the flexible nature of human movement. Modeling the 3D deformations caused by various actions has been a major challenge. Fortunately, advancements in Neural Radiance Fields (NeRF) for dynamic human modeling offer new possibilities. In this paper, we introduce UV-Attack, a groundbreaking approach that achieves high success rates even with extensive and unseen human actions. We address the challenge above by leveraging dynamic-NeRF-based UV mapping. UV-Attack can generate human images across diverse actions and viewpoints, and even create novel actions by sampling from the SMPL parameter space. While dynamic NeRF models are capable of modeling human bodies, modifying clothing textures is challenging because they are embedded in neural network parameters. To tackle this, UV-Attack generates UV maps instead of RGB images and modifies the texture stacks. This approach enables real-time texture edits and makes the attack more practical. We also propose a novel Expectation over Pose Transformation loss (EoPT) to improve the evasion success rate on unseen poses and views. Our experiments show that UV-Attack achieves a 92.75% attack success rate against the FastRCNN model across varied poses in dynamic video settings, significantly outperforming the state-of-the-art AdvCamou attack, which only had a 28.50% ASR. Moreover, we achieve 49.5% ASR on the latest YOLOv8 detector in black-box settings. This work highlights the potential of dynamic NeRF-based UV mapping for creating more effective adversarial attacks on person detectors, addressing key challenges in modeling human movement and texture modification.
Authors: Xinting Hu, Haoran Wang, Jan Eric Lenssen, Bernt Schiele
Abstract: We introduce PersonaHOI, a training- and tuning-free framework that fuses a general StableDiffusion model with a personalized face diffusion (PFD) model to generate identity-consistent human-object interaction (HOI) images. While existing PFD models have advanced significantly, they often overemphasize facial features at the expense of full-body coherence, PersonaHOI introduces an additional StableDiffusion (SD) branch guided by HOI-oriented text inputs. By incorporating cross-attention constraints in the PFD branch and spatial merging at both latent and residual levels, PersonaHOI preserves personalized facial details while ensuring interactive non-facial regions. Experiments, validated by a novel interaction alignment metric, demonstrate the superior realism and scalability of PersonaHOI, establishing a new standard for practical personalized face with HOI generation. Our code will be available at https://github.com/JoyHuYY1412/PersonaHOI
Authors: Felix Duelmer, Mohammad Farid Azampour, Nassir Navab
Abstract: Traditional ultrasound simulators solve the wave equation to model pressure distribution fields, achieving high accuracy but requiring significant computational time and resources. To address this, ray tracing approaches have been introduced, modeling wave propagation as rays interacting with boundaries and scatterers. However, existing models simplify ray propagation, generating echoes at interaction points without considering return paths to the sensor. This can result in unrealistic artifacts and necessitates careful scene tuning for plausible results. We propose a novel ultrasound simulation pipeline that utilizes a ray tracing algorithm to generate echo data, tracing each ray from the transducer through the scene and back to the sensor. To replicate advanced ultrasound imaging, we introduce a ray emission scheme optimized for plane wave imaging, incorporating delay and steering capabilities. Furthermore, we integrate a standard signal processing pipeline to simulate end-to-end ultrasound image formation. We showcase the efficacy of the proposed pipeline by modeling synthetic scenes featuring highly reflective objects, such as bones. In doing so, our proposed approach, UltraRay, not only enhances the overall visual quality but also improves the realism of the simulated images by accurately capturing secondary reflections and reducing unnatural artifacts. By building on top of a differentiable framework, the proposed pipeline lays the groundwork for a fast and differentiable ultrasound simulation tool necessary for gradient-based optimization, enabling advanced ultrasound beamforming strategies, neural network integration, and accurate inverse scene reconstruction.
Authors: Sofia Jamil, Bollampalli Areen Reddy, Raghvendra Kumar, Sriparna Saha, K J Joseph, Koustava Goswami
Abstract: The task of text-to-image generation has encountered significant challenges when applied to literary works, especially poetry. Poems are a distinct form of literature, with meanings that frequently transcend beyond the literal words. To address this shortcoming, we propose a PoemToPixel framework designed to generate images that visually represent the inherent meanings of poems. Our approach incorporates the concept of prompt tuning in our image generation framework to ensure that the resulting images closely align with the poetic content. In addition, we propose the PoeKey algorithm, which extracts three key elements in the form of emotions, visual elements, and themes from poems to form instructions which are subsequently provided to a diffusion model for generating corresponding images. Furthermore, to expand the diversity of the poetry dataset across different genres and ages, we introduce MiniPo, a novel multimodal dataset comprising 1001 children's poems and images. Leveraging this dataset alongside PoemSum, we conducted both quantitative and qualitative evaluations of image generation using our PoemToPixel framework. This paper demonstrates the effectiveness of our approach and offers a fresh perspective on generating images from literary sources.
Authors: Haoxuan Xu, Bo Li, Guanglin Niu
Abstract: Clothing-change person re-identification (CC Re-ID) has attracted increasing attention in recent years due to its application prospect. Most existing works struggle to adequately extract the ID-related information from the original RGB images. In this paper, we propose an Identity-aware Feature Decoupling (IFD) learning framework to mine identity-related features. Particularly, IFD exploits a dual stream architecture that consists of a main stream and an attention stream. The attention stream takes the clothing-masked images as inputs and derives the identity attention weights for effectively transferring the spatial knowledge to the main stream and highlighting the regions with abundant identity-related information. To eliminate the semantic gap between the inputs of two streams, we propose a clothing bias diminishing module specific to the main stream to regularize the features of clothing-relevant regions. Extensive experimental results demonstrate that our framework outperforms other baseline models on several widely-used CC Re-ID datasets.
Authors: Aswini Kumar Patra, Soraisham Elizabeth Devi, Tejashwini Gajurel
Abstract: Alzheimer's disease (AD) progresses through distinct stages, from early mild cognitive impairment (EMCI) to late mild cognitive impairment (LMCI) and eventually to AD. Accurate identification of these stages, especially distinguishing LMCI from EMCI, is crucial for developing pre-dementia treatments but remains challenging due to subtle and overlapping imaging features. This study proposes a minimal-feature machine learning framework that leverages structural MRI data, focusing on the hippocampus and amygdala as regions of interest. The framework addresses the curse of dimensionality through feature selection, utilizes region-specific voxel information, and implements innovative data organization to enhance classification performance by reducing noise. The methodology integrates dimensionality reduction techniques such as PCA and t-SNE with state-of-the-art classifiers, achieving the highest accuracy of 88.46%. This framework demonstrates the potential for efficient and accurate staging of AD progression while providing valuable insights for clinical applications.
Authors: Yifan Zhao, Jia Li, Zeyin Song, Yonghong Tian
Abstract: Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems. This lifelong learning capability helps to distinguish new knowledge from old ones through the increase of open-world learning, namely Few-Shot Class-Incremental Learning (FSCIL). Existing works to solve this problem mainly rely on the careful tuning of visual encoders, which shows an evident trade-off between the base knowledge and incremental ones. Motivated by human learning systems, we propose a new Language-inspired Relation Transfer (LRT) paradigm to understand objects by joint visual clues and text depictions, composed of two major steps. We first transfer the pretrained text knowledge to the visual domains by proposing a graph relation transformation module and then fuse the visual and language embedding by a text-vision prototypical fusion module. Second, to mitigate the domain gap caused by visual finetuning, we propose context prompt learning for fast domain alignment and imagined contrastive learning to alleviate the insufficient text data during alignment. With collaborative learning of domain alignments and text-image transfer, our proposed LRT outperforms the state-of-the-art models by over $13\%$ and $7\%$ on the final session of mini-ImageNet and CIFAR-100 FSCIL benchmarks.
Authors: Soyeong Jeong, Kangsan Kim, Jinheon Baek, Sung Ju Hwang
Abstract: Retrieval-Augmented Generation (RAG) is a powerful strategy to address the issue of generating factually incorrect outputs in foundation models by retrieving external knowledge relevant to queries and incorporating it into their generation process. However, existing RAG approaches have primarily focused on textual information, with some recent advancements beginning to consider images, and they largely overlook videos, a rich source of multimodal knowledge capable of representing events, processes, and contextual details more effectively than any other modality. While a few recent studies explore the integration of videos in the response generation process, they either predefine query-associated videos without retrieving them according to queries, or convert videos into the textual descriptions without harnessing their multimodal richness. To tackle these, we introduce VideoRAG, a novel framework that not only dynamically retrieves relevant videos based on their relevance with queries but also utilizes both visual and textual information of videos in the output generation. Further, to operationalize this, our method revolves around the recent advance of Large Video Language Models (LVLMs), which enable the direct processing of video content to represent it for retrieval and seamless integration of the retrieved videos jointly with queries. We experimentally validate the effectiveness of VideoRAG, showcasing that it is superior to relevant baselines.
Authors: Daniel Rossi, Guido Borghi, Roberto Vezzani
Abstract: Designing efficient neural networks for embedded devices is a critical challenge, particularly in applications requiring real-time performance, such as aerial imaging with drones and UAVs for emergency responses. In this work, we introduce TakuNet, a novel light-weight architecture which employs techniques such as depth-wise convolutions and an early downsampling stem to reduce computational complexity while maintaining high accuracy. It leverages dense connections for fast convergence during training and uses 16-bit floating-point precision for optimization on embedded hardware accelerators. Experimental evaluation on two public datasets shows that TakuNet achieves near-state-of-the-art accuracy in classifying aerial images of emergency situations, despite its minimal parameter count. Real-world tests on embedded devices, namely Jetson Orin Nano and Raspberry Pi, confirm TakuNet's efficiency, achieving more than 650 fps on the 15W Jetson board, making it suitable for real-time AI processing on resource-constrained platforms and advancing the applicability of drones in emergency scenarios. The code and implementation details are publicly released.
Authors: Dabing Cheng, Haosen Zhan, Xingchen Zhao, Guisheng Liu, Zemin Li, Jinghui Xie, Zhao Song, Weiguo Feng, Bingyue Peng
Abstract: The exponential growth of short-video content has ignited a surge in the necessity for efficient, automated solutions to video editing, with challenges arising from the need to understand videos and tailor the editing according to user requirements. Addressing this need, we propose an innovative end-to-end foundational framework, ultimately actualizing precise control over the final video content editing. Leveraging the flexibility and generalizability of Multimodal Large Language Models (MLLMs), we defined clear input-output mappings for efficient video creation. To bolster the model's capability in processing and comprehending video content, we introduce a strategic combination of a denser frame rate and a slow-fast processing technique, significantly enhancing the extraction and understanding of both temporal and spatial video information. Furthermore, we introduce a text-to-edit mechanism that allows users to achieve desired video outcomes through textual input, thereby enhancing the quality and controllability of the edited videos. Through comprehensive experimentation, our method has not only showcased significant effectiveness within advertising datasets, but also yields universally applicable conclusions on public datasets.
Authors: Zhifan Song, Yuan Zhang, Abd Al Rahman M. Abu Ebayyeh
Abstract: Detecting small targets in drone imagery is challenging due to low resolution, complex backgrounds, and dynamic scenes. We propose EDNet, a novel edge-target detection framework built on an enhanced YOLOv10 architecture, optimized for real-time applications without post-processing. EDNet incorporates an XSmall detection head and a Cross Concat strategy to improve feature fusion and multi-scale context awareness for detecting tiny targets in diverse environments. Our unique C2f-FCA block employs Faster Context Attention to enhance feature extraction while reducing computational complexity. The WIoU loss function is employed for improved bounding box regression. With seven model sizes ranging from Tiny to XL, EDNet accommodates various deployment environments, enabling local real-time inference and ensuring data privacy. Notably, EDNet achieves up to a 5.6% gain in mAP@50 with significantly fewer parameters. On an iPhone 12, EDNet variants operate at speeds ranging from 16 to 55 FPS, providing a scalable and efficient solution for edge-based object detection in challenging drone imagery. The source code and pre-trained models are available at: https://github.com/zsniko/EDNet.
Authors: Minxing Luo, Zixun Xia, Liaojun Chen, Zhenhang Li, Weichao Zeng, Jianye Wang, Wentao Cheng, Yaxing Wang, Yu Zhou, Jian Yang
Abstract: In real-world images, slanted or curved texts, especially those on cans, banners, or badges, appear as frequently, if not more so, than flat texts due to artistic design or layout constraints. While high-quality visual text generation has become available with the advanced generative capabilities of diffusion models, these models often produce distorted text and inharmonious text background when given slanted or curved text layouts due to training data limitation. In this paper, we introduce a new training-free framework, STGen, which accurately generates visual texts in challenging scenarios (\eg, slanted or curved text layouts) while harmonizing them with the text background. Our framework decomposes the visual text generation process into two branches: (i) \textbf{Semantic Rectification Branch}, which leverages the ability in generating flat but accurate visual texts of the model to guide the generation of challenging scenarios. The generated latent of flat text is abundant in accurate semantic information related both to the text itself and its background. By incorporating this, we rectify the semantic information of the texts and harmonize the integration of the text with its background in complex layouts. (ii) \textbf{Structure Injection Branch}, which reinforces the visual text structure during inference. We incorporate the latent information of the glyph image, rich in glyph structure, as a new condition to further strengthen the text structure. To enhance image harmony, we also apply an effective combination method to merge the priors, providing a solid foundation for generation. Extensive experiments across a variety of visual text layouts demonstrate that our framework achieves superior accuracy and outstanding quality.
Authors: Ziheng Wu, Zhenghao Chen, Ruipu Luo, Can Zhang, Yuan Gao, Zhentao He, Xian Wang, Haoran Lin, Minghui Qiu
Abstract: Recently, vision-language models have made remarkable progress, demonstrating outstanding capabilities in various tasks such as image captioning and video understanding. We introduce Valley2, a novel multimodal large language model designed to enhance performance across all domains and extend the boundaries of practical applications in e-commerce and short video scenarios. Notably, Valley2 achieves state-of-the-art (SOTA) performance on e-commerce benchmarks, surpassing open-source models of similar size by a large margin (79.66 vs. 72.76). Additionally, Valley2 ranks second on the OpenCompass leaderboard among models with fewer than 10B parameters, with an impressive average score of 67.4. The code and model weights are open-sourced at https://github.com/bytedance/Valley.
Authors: Honglin Cao, Zijian Zhou, Wenjie Wei, Ammar Belatreche, Yu Liang, Dehao Zhang, Malu Zhang, Yang Yang, Haizhou Li
Abstract: Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased computational demands of the Transformer structure limit their practicality in resource-constrained scenarios. In this paper, we integrate binarization techniques into Transformer-based SNNs and propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer. The proposed BESTformer can significantly reduce storage and computational demands by representing weights and attention maps with a mere 1-bit. However, BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization. To address this issue, we propose a Coupled Information Enhancement (CIE) method, which consists of a reversible framework and information enhancement distillation. By maximizing the mutual information between the binary model and its full-precision counterpart, the CIE method effectively mitigates the performance degradation of the BESTformer. Extensive experiments on static and neuromorphic datasets demonstrate that our method achieves superior performance to other binary SNNs, showcasing its potential as a compact yet high-performance model for resource-limited edge devices.
Authors: Olivier Morelle (B-IT and Department of Computer Science, University of Bonn, Department of Ophthalmology, University Hospital Bonn), Justus Bisten (B-IT and Department of Computer Science, University of Bonn), Maximilian W. M. Wintergerst (Department of Ophthalmology, University Hospital Bonn, Augenzentrum Grischun, Chur, Switzerland), Robert P. Finger (Department of Ophthalmology, University Hospital Bonn, Department of Ophthalmology, University Medical Center Mannheim, Heidelberg University), Thomas Schultz (B-IT and Department of Computer Science, University of Bonn, Lamarr Institute for Machine Learning and Artificial Intelligence)
Abstract: Weakly supervised segmentation has the potential to greatly reduce the annotation effort for training segmentation models for small structures such as hyper-reflective foci (HRF) in optical coherence tomography (OCT). However, most weakly supervised methods either involve a strong downsampling of input images, or only achieve localization at a coarse resolution, both of which are unsatisfactory for small structures. We propose a novel framework that increases the spatial resolution of a traditional attention-based Multiple Instance Learning (MIL) approach by using Layer-wise Relevance Propagation (LRP) to prompt the Segment Anything Model (SAM~2), and increases recall with iterative inference. Moreover, we demonstrate that replacing MIL with a Compact Convolutional Transformer (CCT), which adds a positional encoding, and permits an exchange of information between different regions of the OCT image, leads to a further and substantial increase in segmentation accuracy.
Authors: Naval Kishore Mehta, Arvind, Himanshu Kumar, Abeer Banerjee, Sumeet Saurav, Sanjay Singh
Abstract: Detecting and interpreting operator actions, engagement, and object interactions in dynamic industrial workflows remains a significant challenge in human-robot collaboration research, especially within complex, real-world environments. Traditional unimodal methods often fall short of capturing the intricacies of these unstructured industrial settings. To address this gap, we present a novel Multimodal Industrial Activity Monitoring (MIAM) dataset that captures realistic assembly and disassembly tasks, facilitating the evaluation of key meta-tasks such as action localization, object interaction, and engagement prediction. The dataset comprises multi-view RGB, depth, and Inertial Measurement Unit (IMU) data collected from 22 sessions, amounting to 290 minutes of untrimmed video, annotated in detail for task performance and operator behavior. Its distinctiveness lies in the integration of multiple data modalities and its emphasis on real-world, untrimmed industrial workflows-key for advancing research in human-robot collaboration and operator monitoring. Additionally, we propose a multimodal network that fuses RGB frames, IMU data, and skeleton sequences to predict engagement levels during industrial tasks. Our approach improves the accuracy of recognizing engagement states, providing a robust solution for monitoring operator performance in dynamic industrial environments. The dataset and code can be accessed from https://github.com/navalkishoremehta95/MIAM/.
Authors: Hongyuan Dong, Zijian Kang, Weijie Yin, Xiao Liang, Chao Feng, Jiao Ran
Abstract: In this paper, we introduce SAIL-VL (ScAlable Vision Language Model TraIning via High QuaLity Data Curation), an open-source vision language model (VLM) of state-of-the-art (SOTA) performance with 2B parameters. We introduce three key improvements that contribute to SAIL-VL's leading performance: (1) Scalable high-quality visual understanding data construction: We implement a visual understanding data construction pipeline, which enables hundred-million-scale high-quality recaption data annotation. Equipped with this pipeline, we curate SAIL-Caption, a large-scale caption dataset with large quantity and the highest data quality compared with opensource caption datasets. (2) Scalable Pretraining with High-Quality Visual Understanding Data: We scale SAIL-VL's pretraining budget up to 131B tokens and show that even a 2B VLM benefits from scaled up training data sizes, exhibiting expected data size scaling laws in visual understanding and instruction following performance. (3) Scalable SFT via quantity and quality scaling: We introduce general guidance for instruction data curation to scale up instruction data continuously, allowing us to construct a large SFT dataset with the highest quality. To further improve SAIL-VL's performance, we propose quality scaling, a multi-stage training recipe with curriculum learning, to improve model performance scaling curves w.r.t. data sizes from logarithmic to be near-linear. SAIL-VL obtains the highest average score in 19 commonly used benchmarks in our evaluation and achieves top1 performance among VLMs of comparable sizes on OpenCompass (https://rank.opencompass.org.cn/leaderboard-multimodal). We release our SAIL-VL-2B model at HuggingFace (https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B).
URLs: https://rank.opencompass.org.cn/leaderboard-multimodal)., https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B).
Authors: Kuan Liu, Zongyuan Ying, Jie Jin, Dongyan Li, Ping Huang, Wenjian Wu, Zhe Chen, Jin Qi, Yong Lu, Lianfu Deng, Bo Chen
Abstract: The conversion from 2D X-ray to 3D shape holds significant potential for improving diagnostic efficiency and safety. However, existing reconstruction methods often rely on hand-crafted features, manual intervention, and prior knowledge, resulting in unstable shape errors and additional processing costs. In this paper, we introduce Swin-X2S, an end-to-end deep learning method for directly reconstructing 3D segmentation and labeling from 2D biplanar orthogonal X-ray images. Swin-X2S employs an encoder-decoder architecture: the encoder leverages 2D Swin Transformer for X-ray information extraction, while the decoder employs 3D convolution with cross-attention to integrate structural features from orthogonal views. A dimension-expanding module is introduced to bridge the encoder and decoder, ensuring a smooth conversion from 2D pixels to 3D voxels. We evaluate proposed method through extensive qualitative and quantitative experiments across nine publicly available datasets covering four anatomies (femur, hip, spine, and rib), with a total of 54 categories. Significant improvements over previous methods have been observed not only in the segmentation and labeling metrics but also in the clinically relevant parameters that are of primary concern in practical applications, which demonstrates the promise of Swin-X2S to provide an effective option for anatomical shape reconstruction in clinical scenarios. Code implementation is available at: \url{https://github.com/liukuan5625/Swin-X2S}.
Authors: Sanjay Kumar, Hiep Truong, Sushil Sharma, Ganesh Sistu, Tony Scanlan, Eoin Grua, Ciar\'an Eising
Abstract: Autonomous driving technology is rapidly evolving, offering the potential for safer and more efficient transportation. However, the performance of these systems can be significantly compromised by the occlusion on sensors due to environmental factors like dirt, dust, rain, and fog. These occlusions severely affect vision-based tasks such as object detection, vehicle segmentation, and lane recognition. In this paper, we investigate the impact of various kinds of occlusions on camera sensor by projecting their effects from multi-view camera images of the nuScenes dataset into the Bird's-Eye View (BEV) domain. This approach allows us to analyze how occlusions spatially distribute and influence vehicle segmentation accuracy within the BEV domain. Despite significant advances in sensor technology and multi-sensor fusion, a gap remains in the existing literature regarding the specific effects of camera occlusions on BEV-based perception systems. To address this gap, we use a multi-sensor fusion technique that integrates LiDAR and radar sensor data to mitigate the performance degradation caused by occluded cameras. Our findings demonstrate that this approach significantly enhances the accuracy and robustness of vehicle segmentation tasks, leading to more reliable autonomous driving systems.
Authors: Fedor Taggenbrock, Gertjan Burghouts, Ronald Poppe
Abstract: Matching objects across partially overlapping camera views is crucial in multi-camera systems and requires a view-invariant feature extraction network. Training such a network with cycle-consistency circumvents the need for labor-intensive labeling. In this paper, we extend the mathematical formulation of cycle-consistency to handle partial overlap. We then introduce a pseudo-mask which directs the training loss to take partial overlap into account. We additionally present several new cycle variants that complement each other and present a time-divergent scene sampling scheme that improves the data input for this self-supervised setting. Cross-camera matching experiments on the challenging DIVOTrack dataset show the merits of our approach. Compared to the self-supervised state-of-the-art, we achieve a 4.3 percentage point higher F1 score with our combined contributions. Our improvements are robust to reduced overlap in the training data, with substantial improvements in challenging scenes that need to make few matches between many people. Self-supervised feature networks trained with our method are effective at matching objects in a range of multi-camera settings, providing opportunities for complex tasks like large-scale multi-camera scene understanding.
Authors: Yin Wang, Zixuan Wang, Hao Lu, Zhen Qin, Hailiang Zhao, Guanjie Cheng, Ge Su, Li Kuang, Mengchu Zhou, Shuiguang Deng
Abstract: Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation. Existing class-imbalanced semi-supervised learning (CISSL) methods mainly focus on rebalancing datasets but ignore the potential of using hard examples to enhance performance, making it difficult to fully harness the power of unlabeled data even with sophisticated algorithms. To address this issue, we propose a method that enhances the performance of Imbalanced Semi-Supervised Learning by Mining Hard Examples (SeMi). This method distinguishes the entropy differences among logits of hard and easy examples, thereby identifying hard examples and increasing the utility of unlabeled data, better addressing the imbalance problem in CISSL. In addition, we maintain a class-balanced memory bank with confidence decay for storing high-confidence embeddings to enhance the pseudo-labels' reliability. Although our method is simple, it is effective and seamlessly integrates with existing approaches. We perform comprehensive experiments on standard CISSL benchmarks and experimentally demonstrate that our proposed SeMi outperforms existing state-of-the-art methods on multiple benchmarks, especially in reversed scenarios, where our best result shows approximately a 54.8\% improvement over the baseline methods.
Authors: Stefan Popov, Amit Raj, Michael Krainin, Yuanzhen Li, William T. Freeman, Michael Rubinstein
Abstract: We propose a method for generating fly-through videos of a scene, from a single image and a given camera trajectory. We build upon an image-to-video latent diffusion model. We condition its UNet denoiser on the camera trajectory, using four techniques. (1) We condition the UNet's temporal blocks on raw camera extrinsics, similar to MotionCtrl. (2) We use images containing camera rays and directions, similar to CameraCtrl. (3) We reproject the initial image to subsequent frames and use the resulting video as a condition. (4) We use 2D<=>3D transformers to introduce a global 3D representation, which implicitly conditions on the camera poses. We combine all conditions in a ContolNet-style architecture. We then propose a metric that evaluates overall video quality and the ability to preserve details with view changes, which we use to analyze the trade-offs of individual and combined conditions. Finally, we identify an optimal combination of conditions. We calibrate camera positions in our datasets for scale consistency across scenes, and we train our scene exploration model, CamCtrl3D, demonstrating state-of-theart results.
Authors: David Bojani\'c, Stefanie Wuhrer, Tomislav Petkovi\'c, Tomislav Pribani\'c
Abstract: 3D digital anthropometry is the study of estimating human body measurements from 3D scans. Precise body measurements are important health indicators in the medical industry, and guiding factors in the fashion, ergonomic and entertainment industries. The measuring protocol consists of scanning the whole subject in the static A-pose, which is maintained without breathing or movement during the scanning process. However, the A-pose is not easy to maintain during the whole scanning process, which can last even up to a couple of minutes. This constraint affects the final quality of the scan, which in turn affects the accuracy of the estimated body measurements obtained from methods that rely on dense geometric data. Additionally, this constraint makes it impossible to develop a digital anthropometry method for subjects unable to assume the A-pose, such as those with injuries or disabilities. We propose a method that can obtain body measurements from sparse landmarks acquired in any pose. We make use of the sparse landmarks of the posed subject to create pose-independent features, and train a network to predict the body measurements as taken from the standard A-pose. We show that our method achieves comparable results to competing methods that use dense geometry in the standard A-pose, but has the capability of estimating the body measurements from any pose using sparse landmarks only. Finally, we address the lack of open-source 3D anthropometry methods by making our method available to the research community at https://github.com/DavidBoja/pose-independent-anthropometry.
URLs: https://github.com/DavidBoja/pose-independent-anthropometry.
Authors: Hongruixuan Chen, Jian Song, Olivier Dietrich, Clifford Broni-Bediako, Weihao Xuan, Junjue Wang, Xinlei Shao, Yimin Wei, Junshi Xia, Cuiling Lan, Konrad Schindler, Naoto Yokoya
Abstract: Disaster events occur around the world and cause significant damage to human life and property. Earth observation (EO) data enables rapid and comprehensive building damage assessment (BDA), an essential capability in the aftermath of a disaster to reduce human casualties and to inform disaster relief efforts. Recent research focuses on the development of AI models to achieve accurate mapping of unseen disaster events, mostly using optical EO data. However, solutions based on optical data are limited to clear skies and daylight hours, preventing a prompt response to disasters. Integrating multimodal (MM) EO data, particularly the combination of optical and SAR imagery, makes it possible to provide all-weather, day-and-night disaster responses. Despite this potential, the development of robust multimodal AI models has been constrained by the lack of suitable benchmark datasets. In this paper, we present a BDA dataset using veRy-hIGH-resoluTion optical and SAR imagery (BRIGHT) to support AI-based all-weather disaster response. To the best of our knowledge, BRIGHT is the first open-access, globally distributed, event-diverse MM dataset specifically curated to support AI-based disaster response. It covers five types of natural disasters and two types of man-made disasters across 12 regions worldwide, with a particular focus on developing countries where external assistance is most needed. The optical and SAR imagery in BRIGHT, with a spatial resolution between 0.3-1 meters, provides detailed representations of individual buildings, making it ideal for precise BDA. In our experiments, we have tested seven advanced AI models trained with our BRIGHT to validate the transferability and robustness. The dataset and code are available at https://github.com/ChenHongruixuan/BRIGHT. BRIGHT also serves as the official dataset for the 2025 IEEE GRSS Data Fusion Contest.
Authors: Bernat Galm\'es, Gabriel Moy\`a-Alcover, Pedro Bibiloni, Javier Varona, Antoni Jaume-i-Cap\'o
Abstract: A robust segmentation method that can be used to perform measurements on toenails is presented. The proposed method is used as the first step in a clinical trial to objectively quantify the incidence of a particular pathology. For such an assessment, it is necessary to distinguish a nail, which locally appears to be similar to the skin. Many algorithms have been used, each of which leverages different aspects of toenail appearance. We used the Hough transform to locate the tip of the toe and estimate the nail location and size. Subsequently, we classified the super-pixels of the image based on their geometric and photometric information. Thereafter, the watershed transform delineated the border of the nail. The method was validated using a 348-image medical dataset, achieving an accuracy of 0.993 and an F-measure of 0.925. The proposed method is considerably robust across samples, with respect to factors such as nail shape, skin pigmentation, illumination conditions, and appearance of large regions affected by a medical condition
Authors: Oindrila Saha, Logan Lawrence, Grant Van Horn, Subhransu Maji
Abstract: Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the structure of the language space in this context. We propose GTA-CLIP, a novel technique that incorporates supervision from language models for joint transduction in language and vision spaces. Our approach is iterative and consists of three steps: (i) incrementally exploring the attribute space by querying language models, (ii) an attribute-augmented transductive inference procedure, and (iii) fine-tuning the language and vision encoders based on inferred labels within the dataset. Through experiments with CLIP encoders, we demonstrate that GTA-CLIP, yields an average performance improvement of 8.6% and 3.7% across 12 datasets and 3 encoders, over CLIP and transductive CLIP respectively in the zero-shot setting. We also observe similar improvements in a few-shot setting. We present ablation studies that demonstrate the value of each step and visualize how the vision and language spaces evolve over iterations driven by the transductive learning.
Authors: Cecilia Curreli, Dominik Muhle, Abhishek Saroha, Zhenzhang Ye, Riccardo Marin, Daniel Cremers
Abstract: Probabilistic human motion prediction aims to forecast multiple possible future movements from past observations. While current approaches report high diversity and realism, they often generate motions with undetected limb stretching and jitter. To address this, we introduce SkeletonDiffusion, a latent diffusion model that embeds an explicit inductive bias on the human body within its architecture and training. Our model is trained with a novel nonisotropic Gaussian diffusion formulation that aligns with the natural kinematic structure of the human skeleton. Results show that our approach outperforms conventional isotropic alternatives, consistently generating realistic predictions while avoiding artifacts such as limb distortion. Additionally, we identify a limitation in commonly used diversity metrics, which may inadvertently favor models that produce inconsistent limb lengths within the same sequence. SkeletonDiffusion sets a new benchmark on three real-world datasets, outperforming various baselines across multiple evaluation metrics. Visit our project page: https://ceveloper.github.io/publications/skeletondiffusion/
URLs: https://ceveloper.github.io/publications/skeletondiffusion/
Authors: Tsui Qin Mok, Shuyong Gao, Haozhe Xing, Miaoyang He, Yan Wang, Wenqiang Zhang
Abstract: Weakly-Supervised Camouflaged Object Detection (WSCOD) has gained popularity for its promise to train models with weak labels to segment objects that visually blend into their surroundings. Recently, some methods using sparsely-annotated supervision shown promising results through scribbling in WSCOD, while point-text supervision remains underexplored. Hence, this paper introduces a novel holistically point-guided text framework for WSCOD by decomposing into three phases: segment, choose, train. Specifically, we propose Point-guided Candidate Generation (PCG), where the point's foreground serves as a correction for the text path to explicitly correct and rejuvenate the loss detection object during the mask generation process (SEGMENT). We also introduce a Qualified Candidate Discriminator (QCD) to choose the optimal mask from a given text prompt using CLIP (CHOOSE), and employ the chosen pseudo mask for training with a self-supervised Vision Transformer (TRAIN). Additionally, we developed a new point-supervised dataset (P2C-COD) and a text-supervised dataset (T-COD). Comprehensive experiments on four benchmark datasets demonstrate our method outperforms state-of-the-art methods by a large margin, and also outperforms some existing fully-supervised camouflaged object detection methods.
Authors: Bowei Zhang, Yi Zhang
Abstract: Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real applications, the large-scale datasets are not always available, and ViT performs worse than Convolutional Neural Networks (CNNs) if it is only trained on small scale dataset (called tiny dataset), since it requires large amount of training data to ensure its representational capacity. In this paper, a small-size ViT architecture with multi-scale self-attention mechanism and convolution blocks is presented (dubbed MSCViT) to model different scales of attention at each layer. Firstly, we introduced wavelet convolution, which selectively combines the high-frequency components obtained by frequency division with our convolution channel to extract local features. Then, a lightweight multi-head attention module is developed to reduce the number of tokens and computational costs. Finally, the positional encoding (PE) in the backbone is replaced by a local feature extraction module. Compared with the original ViT, it is parameter-efficient and is particularly suitable for tiny datasets. Extensive experiments have been conducted on tiny datasets, in which our model achieves an accuracy of 84.68% on CIFAR-100 with 14.0M parameters and 2.5 GFLOPs, without pre-training on large datasets.
Authors: Congxia Zhao, Xiongjun Fu, Jian Dong, Shen Cao, Chunyan Zhang
Abstract: Synthetic aperture radar (SAR) imaging, celebrated for its high resolution, all-weather capability, and day-night operability, is indispensable for maritime applications. However, ship detection in SAR imagery faces significant challenges, including complex backgrounds, densely arranged targets, and large scale variations. To address these issues, we propose a novel framework, Center-Aware SAR Ship Detector (CASS-Det), designed for robust multi-scale and densely packed ship detection. CASS-Det integrates three key innovations: (1) a center enhancement module (CEM) that employs rotational convolution to emphasize ship centers, improving localization while suppressing background interference; (2) a neighbor attention module (NAM) that leverages cross-layer dependencies to refine ship boundaries in densely populated scenes; and (3) a cross-connected feature pyramid network (CC-FPN) that enhances multi-scale feature fusion by integrating shallow and deep features. Extensive experiments on the SSDD, HRSID, and LS-SSDD-v1.0 datasets demonstrate the state-of-the-art performance of CASS-Det, excelling at detecting multi-scale and densely arranged ships.
Authors: Arkaprava Sinha, Monish Soundar Raj, Pu Wang, Ahmed Helmy, Srijan Das
Abstract: Action detection in real-world scenarios is particularly challenging due to densely distributed actions in hour-long untrimmed videos. It requires modeling both short- and long-term temporal relationships while handling significant intra-class temporal variations. Previous state-of-the-art (SOTA) Transformer-based architectures, though effective, are impractical for real-world deployment due to their high parameter count, GPU memory usage, and limited throughput, making them unsuitable for very long videos. In this work, we innovatively adapt the Mamba architecture for action detection and propose Multi-scale Temporal Mamba (MS-Temba), comprising two key components: Temporal Mamba (Temba) Blocks and the Temporal Mamba Fuser. Temba Blocks include the Temporal Local Module (TLM) for short-range temporal modeling and the Dilated Temporal SSM (DTS) for long-range dependencies. By introducing dilations, a novel concept for Mamba, TLM and DTS capture local and global features at multiple scales. The Temba Fuser aggregates these scale-specific features using Mamba to learn comprehensive multi-scale representations of untrimmed videos. MS-Temba is validated on three public datasets, outperforming SOTA methods on long videos and matching prior methods on short videos while using only one-eighth of the parameters.
Authors: Junfei Xiao, Feng Cheng, Lu Qi, Liangke Gui, Jiepeng Cen, Zhibei Ma, Alan Yuille, Lu Jiang
Abstract: Recent video generation models have shown promising results in producing high-quality video clips lasting several seconds. However, these models face challenges in generating long sequences that convey clear and informative events, limiting their ability to support coherent narrations. In this paper, we present a large-scale cooking video dataset designed to advance long-form narrative generation in the cooking domain. We validate the quality of our proposed dataset in terms of visual fidelity and textual caption accuracy using state-of-the-art Vision-Language Models (VLMs) and video generation models, respectively. We further introduce a Long Narrative Video Director to enhance both visual and semantic coherence in generated videos and emphasize the role of aligning visual embeddings to achieve improved overall video quality. Our method demonstrates substantial improvements in generating visually detailed and semantically aligned keyframes, supported by finetuning techniques that integrate text and image embeddings within the video generation process. Project page: https://videoauteur.github.io/
Authors: Yangyu Huang, Tianyi Gao, Haoran Xu, Qihao Zhao, Yang Song, Zhipeng Gui, Tengchao Lv, Hao Chen, Lei Cui, Scarlett Li, Furu Wei
Abstract: Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface. These maps are indispensable in various fields, including disaster detection, resource exploration, and civil engineering. Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding. This gap is primarily due to the challenging nature of cartographic generalization, which involves handling high-resolution map, managing multiple associated components, and requiring domain-specific knowledge. To quantify this gap, we construct GeoMap-Bench, the first-ever benchmark for evaluating MLLMs in geologic map understanding, which assesses the full-scale abilities in extracting, referring, grounding, reasoning, and analyzing. To bridge this gap, we introduce GeoMap-Agent, the inaugural agent designed for geologic map understanding, which features three modules: Hierarchical Information Extraction (HIE), Domain Knowledge Injection (DKI), and Prompt-enhanced Question Answering (PEQA). Inspired by the interdisciplinary collaboration among human scientists, an AI expert group acts as consultants, utilizing a diverse tool pool to comprehensively analyze questions. Through comprehensive experiments, GeoMap-Agent achieves an overall score of 0.811 on GeoMap-Bench, significantly outperforming 0.369 of GPT-4o. Our work, emPowering gEologic mAp holistiC undErstanding (PEACE) with MLLMs, paves the way for advanced AI applications in geology, enhancing the efficiency and accuracy of geological investigations.
Authors: Omkar Thawakar, Dinura Dissanayake, Ketan More, Ritesh Thawkar, Ahmed Heakl, Noor Ahsan, Yuhao Li, Mohammed Zumri, Jean Lahoud, Rao Muhammad Anwer, Hisham Cholakkal, Ivan Laptev, Mubarak Shah, Fahad Shahbaz Khan, Salman Khan
Abstract: Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse set of challenges with eight different categories ranging from complex visual perception to scientific reasoning with over 4k reasoning steps in total, enabling robust evaluation of LLMs' abilities to perform accurate and interpretable visual reasoning across multiple steps. Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps, emphasizing both correctness and logical coherence. The proposed metric offers deeper insights into reasoning performance compared to traditional end-task accuracy metrics. Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach, where tasks are progressively organized to facilitate incremental skill acquisition and problem-solving. The proposed LlamaV-o1 is designed for multi-step reasoning and learns step-by-step through a structured training paradigm. Extensive experiments show that our LlamaV-o1 outperforms existing open-source models and performs favorably against close-source proprietary models. Compared to the recent Llava-CoT, our LlamaV-o1 achieves an average score of 67.3 with an absolute gain of 3.8\% across six benchmarks while being 5 times faster during inference scaling. Our benchmark, model, and code are publicly available.
Authors: Tsai-Shien Chen, Aliaksandr Siarohin, Willi Menapace, Yuwei Fang, Kwot Sin Lee, Ivan Skorokhodov, Kfir Aberman, Jun-Yan Zhu, Ming-Hsuan Yang, Sergey Tulyakov
Abstract: Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist $-$ a video model with built-in multi-subject, open-set personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt with cross-attention layers. Developing such a large model presents two main challenges: dataset and evaluation. First, as paired datasets of reference images and videos are extremely hard to collect, we sample selected video frames as reference images and synthesize a clip of the target video. However, while models can easily denoise training videos given reference frames, they fail to generalize to new contexts. To mitigate this issue, we design a new automatic data construction pipeline with extensive image augmentations. Second, evaluating open-set video personalization is a challenge in itself. To address this, we introduce a personalization benchmark that focuses on accurate subject fidelity and supports diverse personalization scenarios. Finally, our extensive experiments show that our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations.
Authors: Gursimran Singh, Xinglu Wang, Ivan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang, Zhenan Fan
Abstract: Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead. This step helps convert raw inputs into tokenized representations that inflate the token sequence for the prefill phase, negatively impacting key Service Level Objectives (SLOs) like time to first token (TTFT) and end-to-end throughput. We introduce Encode-Prefill-Decode (EPD) Disaggregation, a novel framework that separates the encoding, prefill, and decode stages onto dedicated resources. Unlike current systems, which bundle encoding and prefill together, our disaggregation approach alleviates memory bottlenecks, mitigates synchronization delays, and supports flexible batching. Specifically, we employ a new caching mechanism for multimodal tokens, enabling asynchronous transfer of multimodal tokens and introduce an integrated module to find optimal config for EPD system and minimize resource usage while maximizing SLO-based performance metric. Experimental evaluations with popular LMMs show substantial gains in memory efficiency (up to 15$\times$ lesser for encoding-stage GPUs), that supports upto 22$\times$ higher batch sizes, 10$\times$ more number of images/ request, 2.2$\times$ higher kv cache size. Further, it leads to significant improvements in end-to-end throughput (up to 57\% better), and latency metrics (TTFT up to 71\% lower), compared to systems that do not disaggregate. Our findings underscore the potential of EPD disaggregation to enable resource-efficient and high-performance multimodal inference at scale.
Authors: Nilesh Kumar Sahu, Nandigramam Sai Harshit, Rishabh Uikey, Haroon R. Lone
Abstract: Social Anxiety Disorder (SAD) significantly impacts individuals' daily lives and relationships. The conventional methods for SAD detection involve physical consultations and self-reported questionnaires, but they have limitations such as time consumption and bias. This paper introduces video analysis as a promising method for early SAD detection. Specifically, we present a new approach for detecting SAD in individuals from various bodily features extracted from the video data. We conducted a study to collect video data of 92 participants performing impromptu speech in a controlled environment. Using the video data, we studied the behavioral change in participants' head, body, eye gaze, and action units. By applying a range of machine learning and deep learning algorithms, we achieved an accuracy rate of up to 74\% in classifying participants as SAD or non-SAD. Video-based SAD detection offers a non-intrusive and scalable approach that can be deployed in real-time, potentially enhancing early detection and intervention capabilities.
Authors: Malak Mansour, Ahmed Aly, Bahey Tharwat, Sarim Hashmi, Dong An, Ian Reid
Abstract: Large Language Models (LLMs) such as GPT-4, trained on huge amount of datasets spanning multiple domains, exhibit significant reasoning, understanding, and planning capabilities across various tasks. This study presents the first-ever work in Arabic language integration within the Vision-and-Language Navigation (VLN) domain in robotics, an area that has been notably underexplored in existing research. We perform a comprehensive evaluation of state-of-the-art multi-lingual Small Language Models (SLMs), including GPT-4o mini, Llama 3 8B, and Phi-3 medium 14B, alongside the Arabic-centric LLM, Jais. Our approach utilizes the NavGPT framework, a pure LLM-based instruction-following navigation agent, to assess the impact of language on navigation reasoning through zero-shot sequential action prediction using the R2R dataset. Through comprehensive experiments, we demonstrate that our framework is capable of high-level planning for navigation tasks when provided with instructions in both English and Arabic. However, certain models struggled with reasoning and planning in the Arabic language due to inherent limitations in their capabilities, sub-optimal performance, and parsing issues. These findings highlight the importance of enhancing planning and reasoning capabilities in language models for effective navigation, emphasizing this as a key area for further development while also unlocking the potential of Arabic-language models for impactful real-world applications.
Authors: Patrick Dermyer, Angad Kalra, Matt Schwartz
Abstract: In this work, we present EndoDINO, a foundation model for GI endoscopy tasks that achieves strong generalizability by pre-training on a well-curated image dataset sampled from the largest known GI endoscopy video dataset in the literature. Specifically, we pre-trained ViT models with 1B, 307M, and 86M parameters using datasets ranging from 100K to 10M curated images. Using EndoDINO as a frozen feature encoder, we achieved state-of-the-art performance in anatomical landmark classification, polyp segmentation, and Mayo endoscopic scoring (MES) for ulcerative colitis with only simple decoder heads.
Authors: Xuanshuo Fu, Danna Xue, Javier Vazquez-Corral
Abstract: Advancements in imaging technology have enabled hardware to support 10 to 16 bits per channel, facilitating precise manipulation in applications like image editing and video processing. While deep neural networks promise to recover high bit-depth representations, existing methods often rely on scale-invariant image information, limiting performance in certain scenarios. In this paper, we introduce a novel approach that integrates a super-resolution architecture to extract detailed a priori information from images. By leveraging interpolated data generated during the super-resolution process, our method achieves pixel-level recovery of fine-grained color details. Additionally, we demonstrate that spatial features learned through the super-resolution process significantly contribute to the recovery of detailed color depth information. Experiments on benchmark datasets demonstrate that our approach outperforms state-of-the-art methods, highlighting the potential of super-resolution for high-fidelity color restoration.
Authors: Sonia Raychaudhuri, Angel X. Chang
Abstract: Intelligent embodied agents (e.g. robots) need to perform complex semantic tasks in unfamiliar environments. Among many skills that the agents need to possess, building and maintaining a semantic map of the environment is most crucial in long-horizon tasks. A semantic map captures information about the environment in a structured way, allowing the agent to reference it for advanced reasoning throughout the task. While existing surveys in embodied AI focus on general advancements or specific tasks like navigation and manipulation, this paper provides a comprehensive review of semantic map-building approaches in embodied AI, specifically for indoor navigation. We categorize these approaches based on their structural representation (spatial grids, topological graphs, dense point-clouds or hybrid maps) and the type of information they encode (implicit features or explicit environmental data). We also explore the strengths and limitations of the map building techniques, highlight current challenges, and propose future research directions. We identify that the field is moving towards developing open-vocabulary, queryable, task-agnostic map representations, while high memory demands and computational inefficiency still remaining to be open challenges. This survey aims to guide current and future researchers in advancing semantic mapping techniques for embodied AI systems.
Authors: You Li, Heyu Huang, Chi Chen, Kaiyu Huang, Chao Huang, Zonghao Guo, Zhiyuan Liu, Jinan Xu, Yuhua Li, Ruixuan Li, Maosong Sun
Abstract: The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce Migician, the first multi-image grounding model capable of performing free-form and accurate grounding across multiple images. To support this, we present the MGrounding-630k dataset, which comprises data for several multi-image grounding tasks derived from existing datasets, along with newly generated free-form grounding instruction-following data. Furthermore, we propose MIG-Bench, a comprehensive benchmark specifically designed for evaluating multi-image grounding capabilities. Experimental results demonstrate that our model achieves significantly superior multi-image grounding capabilities, outperforming the best existing MLLMs by 21.61% and even surpassing much larger 70B models. Our code, model, dataset, and benchmark are fully open-sourced.
Authors: Patrick Lacharme, Kevin Thiry-Atighehchi
Abstract: Cancelable Biometrics (CB) stands for a range of biometric transformation schemes combining biometrics with user specific tokens to generate secure templates. Required properties are the irreversibility, unlikability and recognition accuracy of templates while making their revocation possible. In biometrics, a key-binding scheme is used for protecting a cryptographic key using a biometric data. The key can be recomputed only if a correct biometric data is acquired during authentication. Applications of key-binding schemes are typically disk encryption, where the cryptographic key is used to encrypt and decrypt the disk. In this paper, we cryptanalyze a recent key-binding scheme, called Cancelable Biometrics Vault (CBV) based on cancelable biometrics. More precisely, the introduced cancelable transformation, called BioEncoding scheme, for instantiating the CBV framework is attacked in terms of reversibility and linkability of templates. Subsequently, our linkability attack enables to recover the key in the vault without additional assumptions. Our cryptanalysis introduces a new perspective by uncovering the CBV scheme's revocability and linkability vulnerabilities, which were not previously identified in comparable biometric-based key-binding schemes.
Authors: Sunwoo Kim, Minkyu Kim, Dongmin Park
Abstract: Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively. Addressing these limitations, we propose a training-free sampling method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution. Our approach, tailored for diffusion sampling and incorporating tempering techniques, achieves comparable or superior target rewards to fine-tuning methods while preserving diversity and cross-reward generalization. We demonstrate its effectiveness in single-reward optimization, multi-objective scenarios, and online black-box optimization. This work offers a robust solution for aligning diffusion models with diverse downstream objectives without compromising their general capabilities. Code is available at https://github.com/krafton-ai/DAS .
Authors: Amit Kr Dey, Pradeep Walia, Girish Somvanshi, Abrar Ali, Sagarnil Das, Pallabi Paul, Minakhi Ghosh
Abstract: Purpose: Diabetic retinopathy (DR) is a major cause of vision loss, particularly in India, where access to retina specialists is limited in rural areas. This study aims to evaluate the Artificial Intelligence-based Diabetic Retinopathy Screening System (AIDRSS) for DR detection and prevalence assessment, addressing the growing need for scalable, automated screening solutions in resource-limited settings. Approach: A multicentric, cross-sectional study was conducted in Kolkata, India, involving 5,029 participants and 10,058 macula-centric retinal fundus images. The AIDRSS employed a deep learning algorithm with 50 million trainable parameters, integrated with Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing for enhanced image quality. DR was graded using the International Clinical Diabetic Retinopathy (ICDR) Scale, categorizing disease into five stages (DR0 to DR4). Statistical metrics including sensitivity, specificity, and prevalence rates were evaluated against expert retina specialist assessments. Results: The prevalence of DR in the general population was 13.7%, rising to 38.2% among individuals with elevated random blood glucose levels. The AIDRSS achieved an overall sensitivity of 92%, specificity of 88%, and 100% sensitivity for detecting referable DR (DR3 and DR4). These results demonstrate the system's robust performance in accurately identifying and grading DR in a diverse population. Conclusions: AIDRSS provides a reliable, scalable solution for early DR detection in resource-constrained environments. Its integration of advanced AI techniques ensures high diagnostic accuracy, with potential to significantly reduce the burden of diabetes-related vision loss in underserved regions.
Authors: Jakub R. Kaczmarzyk, Rishul Sharma, Peter K. Koo, Joel H. Saltz
Abstract: Foundation models for computational pathology have shown great promise for specimen-level tasks and are increasingly accessible to researchers. However, specimen-level models built on these foundation models remain largely unavailable, hindering their broader utility and impact. To address this gap, we developed SpinPath, a toolkit designed to democratize specimen-level deep learning by providing a zoo of pretrained specimen-level models, a Python-based inference engine, and a JavaScript-based inference platform. We demonstrate the utility of SpinPath in metastasis detection tasks across nine foundation models. SpinPath may foster reproducibility, simplify experimentation, and accelerate the adoption of specimen-level deep learning in computational pathology research.
Authors: Sauda Adiv Hanum, Ashim Dey, Muhammad Ashad Kabir
Abstract: The skin, as the largest organ of the human body, is vulnerable to a diverse array of conditions collectively known as skin lesions, which encompass various dermatoses. Diagnosing these lesions presents significant challenges for medical practitioners due to the subtle visual differences that are often imperceptible to the naked eye. While not all skin lesions are life-threatening, certain types can act as early indicators of severe diseases, including skin cancers, underscoring the critical need for timely and accurate diagnostic methods. Deep learning algorithms have demonstrated remarkable potential in facilitating the early detection and prognosis of skin lesions. This study advances the field by curating a comprehensive and diverse dataset comprising 39 categories of skin lesions, synthesized from five publicly available datasets. Using this dataset, the performance of five state-of-the-art deep learning models -- MobileNetV2, Xception, InceptionV3, EfficientNetB1, and Vision Transformer - is rigorously evaluated. To enhance the accuracy and robustness of these models, attention mechanisms such as the Efficient Channel Attention (ECA) and the Convolutional Block Attention Module (CBAM) are incorporated into their architectures. Comprehensive evaluation across multiple performance metrics reveals that the Vision Transformer model integrated with CBAM outperforms others, achieving an accuracy of 93.46%, precision of 94%, recall of 93%, F1-score of 93%, and specificity of 93.67%. These results underscore the significant potential of the proposed system in supporting medical professionals with accurate and efficient prognostic tools for diagnosing a broad spectrum of skin lesions. The dataset and code used in this study can be found at https://github.com/akabircs/Skin-Lesions-Classification.
URLs: https://github.com/akabircs/Skin-Lesions-Classification.
Authors: Johann Wenckstern, Eeshaan Jain, Kiril Vasilev, Matteo Pariset, Andreas Wicki, Gabriele Gut, Charlotte Bunne
Abstract: Spatial proteomics technologies have transformed our understanding of complex tissue architectures by enabling simultaneous analysis of multiple molecular markers and their spatial organization. The high dimensionality of these data, varying marker combinations across experiments and heterogeneous study designs pose unique challenges for computational analysis. Here, we present Virtual Tissues (VirTues), a foundation model framework for biological tissues that operates across the molecular, cellular and tissue scale. VirTues introduces innovations in transformer architecture design, including a novel tokenization scheme that captures both spatial and marker dimensions, and attention mechanisms that scale to high-dimensional multiplex data while maintaining interpretability. Trained on diverse cancer and non-cancer tissue datasets, VirTues demonstrates strong generalization capabilities without task-specific fine-tuning, enabling cross-study analysis and novel marker integration. As a generalist model, VirTues outperforms existing approaches across clinical diagnostics, biological discovery and patient case retrieval tasks, while providing insights into tissue function and disease mechanisms.
Authors: Yuechen Yang, Yu Wang, Tianyuan Yao, Ruining Deng, Mengmeng Yin, Shilin Zhao, Haichun Yang, Yuankai Huo
Abstract: Whole Slide Image (WSI) analysis plays a crucial role in modern digital pathology, enabling large-scale feature extraction from tissue samples. However, traditional feature extraction pipelines based on tools like CellProfiler often involve lengthy workflows, requiring WSI segmentation into patches, feature extraction at the patch level, and subsequent mapping back to the original WSI. To address these challenges, we present PySpatial, a high-speed pathomics toolkit specifically designed for WSI-level analysis. PySpatial streamlines the conventional pipeline by directly operating on computational regions of interest, reducing redundant processing steps. Utilizing rtree-based spatial indexing and matrix-based computation, PySpatial efficiently maps and processes computational regions, significantly accelerating feature extraction while maintaining high accuracy. Our experiments on two datasets-Perivascular Epithelioid Cell (PEC) and data from the Kidney Precision Medicine Project (KPMP)-demonstrate substantial performance improvements. For smaller and sparse objects in PEC datasets, PySpatial achieves nearly a 10-fold speedup compared to standard CellProfiler pipelines. For larger objects, such as glomeruli and arteries in KPMP datasets, PySpatial achieves a 2-fold speedup. These results highlight PySpatial's potential to handle large-scale WSI analysis with enhanced efficiency and accuracy, paving the way for broader applications in digital pathology.
Authors: Nikhil Parthasarathy, S. M. Ali Eslami, Jo\~ao Carreira, Olivier J. H\'enaff
Abstract: Humans learn powerful representations of objects and scenes by observing how they evolve over time. Yet, outside of specific tasks that require explicit temporal understanding, static image pretraining remains the dominant paradigm for learning visual foundation models. We question this mismatch, and ask whether video pretraining can yield visual representations that bear the hallmarks of human perception: generalisation across tasks, robustness to perturbations, and consistency with human judgements. To that end we propose a novel procedure for curating videos, and develop a contrastive framework which learns from the complex transformations therein. This simple paradigm for distilling knowledge from videos, called VITO, yields general representations that far outperform prior video pretraining methods on image understanding tasks, and image pretraining methods on video understanding tasks. Moreover, VITO representations are significantly more robust to natural and synthetic deformations than image-, video-, and adversarially-trained ones. Finally, VITO's predictions are strongly aligned with human judgements, surpassing models that were specifically trained for that purpose. Together, these results suggest that video pretraining could be a simple way of learning unified, robust, and human-aligned representations of the visual world.
Authors: Idan Schwartz, V\'esteinn Sn{\ae}bjarnarson, Hila Chefer, Ryan Cotterell, Serge Belongie, Lior Wolf, Sagie Benaim
Abstract: Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in the input text. One way of alleviating these issues is to train diffusion models on class-labeled datasets. This approach has two disadvantages: (i) supervised datasets are generally small compared to large-scale scraped text-image datasets on which text-to-image models are trained, affecting the quality and diversity of the generated images, or (ii) the input is a hard-coded label, as opposed to free-form text, limiting the control over the generated images. In this work, we propose a non-invasive fine-tuning technique that capitalizes on the expressive potential of free-form text while achieving high accuracy through discriminative signals from a pretrained classifier. This is done by iteratively modifying the embedding of an added input token of a text-to-image diffusion model, by steering generated images toward a given target class according to a classifier. Our method is fast compared to prior fine-tuning methods and does not require a collection of in-class images or retraining of a noise-tolerant classifier. We evaluate our method extensively, showing that the generated images are: (i) more accurate and of higher quality than standard diffusion models, (ii) can be used to augment training data in a low-resource setting, and (iii) reveal information about the data used to train the guiding classifier. The code is available at \url{https://github.com/idansc/discriminative_class_tokens}.
Authors: Sharath Koorathota, Nikolas Papadopoulos, Jia Li Ma, Shruti Kumar, Xiaoxiao Sun, Arunesh Mittal, Patrick Adelman, Paul Sajda
Abstract: Vision Transformers (ViT) have advanced computer vision, yet their efficacy in complex tasks like driving remains less explored. This study enhances ViT by integrating human eye gaze, captured via eye-tracking, to increase prediction accuracy in driving scenarios under uncertainty in both real-world and virtual reality scenarios. First, we establish the significance of human eye gaze in left-right driving decisions, as observed in both human subjects and a ViT model. By comparing the similarity between human fixation maps and ViT attention weights, we reveal the dynamics of overlap across individual heads and layers. This overlap demonstrates that fixation data can guide the model in distributing its attention weights more effectively. We introduce the fixation-attention intersection (FAX) loss, a novel loss function that significantly improves ViT performance under high uncertainty conditions. Our results show that ViT, when trained with FAX loss, aligns its attention with human gaze patterns. This gaze-informed approach has significant potential for driver behavior analysis, as well as broader applications in human-centered AI systems, extending ViT's use to complex visual environments.
Authors: Keegan Quigley, Miriam Cha, Josh Barua, Geeticka Chauhan, Seth Berkowitz, Steven Horng, Polina Golland
Abstract: Vision-language pretraining has been shown to produce high-quality visual encoders which transfer efficiently to downstream computer vision tasks. Contrastive learning approaches have increasingly been adopted for medical vision language pretraining (MVLP), yet recent developments in generative AI offer new modeling alternatives. This paper introduces RadTex, a CNN-encoder transformer-decoder architecture optimized for radiology. We explore bidirectional captioning as an alternative MVLP strategy and demonstrate that RadTex's captioning pretraining is competitive with established contrastive methods, achieving a CheXpert macro-AUC of 89.4%. Additionally, RadTex's lightweight text decoder not only generates clinically relevant radiology reports (macro-F1 score of 0.349), but also provides targeted, interactive responses, highlighting the utility of bidirectional captioning in advancing medical image analysis.
Authors: Daniel Geng, Inbum Park, Andrew Owens
Abstract: Given a factorization of an image into a sum of linear components, we present a zero-shot method to control each individual component through diffusion model sampling. For example, we can decompose an image into low and high spatial frequencies and condition these components on different text prompts. This produces hybrid images, which change appearance depending on viewing distance. By decomposing an image into three frequency subbands, we can generate hybrid images with three prompts. We also use a decomposition into grayscale and color components to produce images whose appearance changes when they are viewed in grayscale, a phenomena that naturally occurs under dim lighting. And we explore a decomposition by a motion blur kernel, which produces images that change appearance under motion blurring. Our method works by denoising with a composite noise estimate, built from the components of noise estimates conditioned on different prompts. We also show that for certain decompositions, our method recovers prior approaches to compositional generation and spatial control. Finally, we show that we can extend our approach to generate hybrid images from real images. We do this by holding one component fixed and generating the remaining components, effectively solving an inverse problem.
Authors: Jiaxin Zhuang, Linshan Wu, Qiong Wang, Peng Fei, Varut Vardhanabhuti, Lin Luo, Hao Chen
Abstract: The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various medical vision tasks. However, due to large spatial sizes with much higher dimensions of 3D medical images, the lack of hierarchical design for MAE may hinder the performance of downstream tasks. In this paper, we propose a novel \textit{Mask in Mask (MiM)} pre-training framework for 3D medical images, which aims to advance MAE by learning discriminative representation from hierarchical visual tokens across varying scales. We introduce multiple levels of granularity for masked inputs from the volume, which are then reconstructed simultaneously ranging at both fine and coarse levels. Additionally, a cross-level alignment mechanism is applied to adjacent level volumes to enforce anatomical similarity hierarchically. Furthermore, we adopt a hybrid backbone to enhance the hierarchical representation learning efficiently during the pre-training. MiM was pre-trained on a large scale of available 3D volumetric images, \textit{i.e.,} Computed Tomography (CT) images containing various body parts. Extensive experiments on thirteen public datasets demonstrate the superiority of MiM over other SSL methods in organ/lesion/tumor segmentation and disease classification. We further scale up the MiM to large pre-training datasets with more than 10k volumes, showing that large-scale pre-training can further enhance the performance of downstream tasks. The improvement also concluded that the research community should pay more attention to the scale of the pre-training dataset towards the healthcare foundation model for 3D medical images.
Authors: Halid Ziya Yerebakan, Yoshihisa Shinagawa, Gerardo Hermosillo Valadez
Abstract: Organ segmentation is a fundamental task in medical imaging since it is useful for many clinical automation pipelines. However, some tasks do not require full segmentation. Instead, a classifier can identify the selected organ without segmenting the entire volume. In this study, we demonstrate a classifier based method to obtain organ labels in real time by using a large context size with a sparse data sampling strategy. Although our method operates as an independent classifier at query locations, it can generate full segmentations by querying grid locations at any resolution, offering faster performance than segmentation algorithms. We compared our method with existing segmentation techniques, demonstrating its superior runtime potential for practical applications in medical imaging.
Authors: Danpeng Chen, Hai Li, Weicai Ye, Yifan Wang, Weijian Xie, Shangjin Zhai, Nan Wang, Haomin Liu, Hujun Bao, Guofeng Zhang
Abstract: Recently, 3D Gaussian Splatting (3DGS) has attracted widespread attention due to its high-quality rendering, and ultra-fast training and rendering speed. However, due to the unstructured and irregular nature of Gaussian point clouds, it is difficult to guarantee geometric reconstruction accuracy and multi-view consistency simply by relying on image reconstruction loss. Although many studies on surface reconstruction based on 3DGS have emerged recently, the quality of their meshes is generally unsatisfactory. To address this problem, we propose a fast planar-based Gaussian splatting reconstruction representation (PGSR) to achieve high-fidelity surface reconstruction while ensuring high-quality rendering. Specifically, we first introduce an unbiased depth rendering method, which directly renders the distance from the camera origin to the Gaussian plane and the corresponding normal map based on the Gaussian distribution of the point cloud, and divides the two to obtain the unbiased depth. We then introduce single-view geometric, multi-view photometric, and geometric regularization to preserve global geometric accuracy. We also propose a camera exposure compensation model to cope with scenes with large illumination variations. Experiments on indoor and outdoor scenes show that our method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods.
Authors: Ridouane Ghermi, Xi Wang, Vicky Kalogeiton, Ivan Laptev
Abstract: Recent developments in vision-language models have significantly advanced video understanding. Existing datasets and tasks, however, have notable limitations. Most datasets are confined to short videos with limited events and narrow narratives. For example, datasets with instructional and egocentric videos often depict activities of one person in a single scene. Although existing movie datasets offer richer content, they are often limited to short-term tasks, lack publicly available videos, and frequently encounter data leakage issues given the use of subtitles and other information about commercial movies during LLM pretraining. To address the above limitations, we propose Short-Films 20K (SF20K), the largest publicly available movie dataset. SF20K is composed of 20,143 amateur films and offers long-term video tasks in the form of multiple-choice and open-ended question answering. Our extensive analysis of SF20K reveals minimal data leakage, emphasizes the need for long-term reasoning, and demonstrates the strong performance of recent VLMs. Finally, we show that instruction tuning on the SF20K-Train set substantially improves model performance, paving the way for future progress in long-term video understanding.
Authors: Faxu Guo, Quan Feng, Sen Yang, Wanxia Yang
Abstract: Hyperspectral remote sensing (HIS) enables the detailed capture of spectral information from the Earth's surface, facilitating precise classification and identification of surface crops due to its superior spectral diagnostic capabilities. However, current convolutional neural networks (CNNs) focus on local features in hyperspectral data, leading to suboptimal performance when classifying intricate crop types and addressing imbalanced sample distributions. In contrast, the Transformer framework excels at extracting global features from hyperspectral imagery. To leverage the strengths of both approaches, this research introduces the Convolutional Meet Transformer Network (CMTNet). This innovative model includes a spectral-spatial feature extraction module for shallow feature capture, a dual-branch structure combining CNN and Transformer branches for local and global feature extraction, and a multi-output constraint module that enhances classification accuracy through multi-output loss calculations and cross constraints across local, international, and joint features. Extensive experiments conducted on three datasets (WHU-Hi-LongKou, WHU-Hi-HanChuan, and WHU-Hi-HongHu) demonstrate that CTDBNet significantly outperforms other state-of-the-art networks in classification performance, validating its effectiveness in hyperspectral crop classification.
Authors: Panagiotis Alimisis, Ioannis Mademlis, Panagiotis Radoglou-Grammatikis, Panagiotis Sarigiannidis, Georgios Th. Papadopoulos
Abstract: Image data augmentation constitutes a critical methodology in modern computer vision tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; thereby, improving the performance and robustness of machine learning models in downstream tasks. In parallel, augmentation approaches can also be used for editing/modifying a given image in a context- and semantics-aware way. Diffusion Models (DMs), which comprise one of the most recent and highly promising classes of methods in the field of generative Artificial Intelligence (AI), have emerged as a powerful tool for image data augmentation, capable of generating realistic and diverse images by learning the underlying data distribution. The current study realizes a systematic, comprehensive and in-depth review of DM-based approaches for image augmentation, covering a wide range of strategies, tasks and applications. In particular, a comprehensive analysis of the fundamental principles, model architectures and training strategies of DMs is initially performed. Subsequently, a taxonomy of the relevant image augmentation methods is introduced, focusing on techniques regarding semantic manipulation, personalization and adaptation, and application-specific augmentation tasks. Then, performance assessment methodologies and respective evaluation metrics are analyzed. Finally, current challenges and future research directions in the field are discussed.
Authors: Ruiyi Wang, Wenhao Li, Xiaohong Liu, Chunyi Li, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai
Abstract: Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets. However, they often struggle with real-world hazy images due to domain shift, limiting their practical applicability. This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks. Inspired by the Contrastive Language-Image Pre-training (CLIP) model's ability to distinguish between hazy and clean images, we leverage it to evaluate dehazing results. Combined with a region-specific dehazing technique and tailored prompt sets, the CLIP model accurately identifies hazy areas, providing a high-quality, human-like prior that guides the fine-tuning process of pre-trained networks. Extensive experiments demonstrate that HazeCLIP achieves state-of-the-art performance in real-word image dehazing, evaluated through both visual quality and image quality assessment metrics. Codes are available at https://github.com/Troivyn/HazeCLIP.
Authors: Yu-Yun Tseng, Tanusree Sharma, Lotus Zhang, Abigale Stangl, Leah Findlater, Yang Wang, Danna Gurari
Abstract: Individuals who are blind or have low vision (BLV) are at a heightened risk of sharing private information if they share photographs they have taken. To facilitate developing technologies that can help them preserve privacy, we introduce BIV-Priv-Seg, the first localization dataset originating from people with visual impairments that shows private content. It contains 1,028 images with segmentation annotations for 16 private object categories. We first characterize BIV-Priv-Seg and then evaluate modern models' performance for locating private content in the dataset. We find modern models struggle most with locating private objects that are not salient, small, and lack text as well as recognizing when private content is absent from an image. We facilitate future extensions by sharing our new dataset with the evaluation server at https://vizwiz.org/tasks-and-datasets/object-localization.
URLs: https://vizwiz.org/tasks-and-datasets/object-localization.
Authors: Vlad Hondru, Florinel Alin Croitoru, Shervin Minaee, Radu Tudor Ionescu, Nicu Sebe
Abstract: In this work, we survey recent studies on masked image modeling (MIM), an approach that emerged as a powerful self-supervised learning technique in computer vision. The MIM task involves masking some information, e.g.~pixels, patches, or even latent representations, and training a model, usually an autoencoder, to predicting the missing information by using the context available in the visible part of the input. We identify and formalize two categories of approaches on how to implement MIM as a pretext task, one based on reconstruction and one based on contrastive learning. Then, we construct a taxonomy and review the most prominent papers in recent years. We complement the manually constructed taxonomy with a dendrogram obtained by applying a hierarchical clustering algorithm. We further identify relevant clusters via manually inspecting the resulting dendrogram. Our review also includes datasets that are commonly used in MIM research. We aggregate the performance results of various masked image modeling methods on the most popular datasets, to facilitate the comparison of competing methods. Finally, we identify research gaps and propose several interesting directions of future work. We supplement our survey with the following public repository containing organized references: https://github.com/vladhondru25/MIM-Survey.
Authors: Chun-Yen Shih, Li-Xuan Peng, Jia-Wei Liao, Ernie Chu, Cheng-Fu Chou, Jun-Cheng Chen
Abstract: Diffusion Models have emerged as powerful generative models for high-quality image synthesis, with many subsequent image editing techniques based on them. However, the ease of text-based image editing introduces significant risks, such as malicious editing for scams or intellectual property infringement. Previous works have attempted to safeguard images from diffusion-based editing by adding imperceptible perturbations. These methods are costly and specifically target prevalent Latent Diffusion Models (LDMs), while Pixel-domain Diffusion Models (PDMs) remain largely unexplored and robust against such attacks. Our work addresses this gap by proposing a novel attack framework, AtkPDM. AtkPDM is mainly composed of a feature representation attacking loss that exploits vulnerabilities in denoising UNets and a latent optimization strategy to enhance the naturalness of adversarial images. Extensive experiments demonstrate the effectiveness of our approach in attacking dominant PDM-based editing methods (e.g., SDEdit) while maintaining reasonable fidelity and robustness against common defense methods. Additionally, our framework is extensible to LDMs, achieving comparable performance to existing approaches.
Authors: Mingyuan Yao, Yukang Huo, Qingbin Tian, Jiayin Zhao, Xiao Liu, Ruifeng Wang, Lin Xue, Haihua Wang
Abstract: Early detection of abnormal fish behavior caused by disease or hunger can be achieved through fish tracking using deep learning techniques, which holds significant value for industrial aquaculture. However, underwater reflections and some reasons with fish, such as the high similarity, rapid swimming caused by stimuli and mutual occlusion bring challenges to multi-target tracking of fish. To address these challenges, this paper establishes a complex multi-scenario sturgeon tracking dataset and introduces the FMRFT model, a real-time end-to-end fish tracking solution. The model incorporates the low video memory consumption Mamba In Mamba (MIM) architecture, which facilitates multi-frame temporal memory and feature extraction, thereby addressing the challenges to track multiple fish across frames. Additionally, the FMRFT model with the Query Time Sequence Intersection (QTSI) module effectively manages occluded objects and reduces redundant tracking frames using the superior feature interaction and prior frame processing capabilities of RT-DETR. This combination significantly enhances the accuracy and stability of fish tracking. Trained and tested on the dataset, the model achieves an IDF1 score of 90.3% and a MOTA accuracy of 94.3%. Experimental results show that the proposed FMRFT model effectively addresses the challenges of high similarity and mutual occlusion in fish populations, enabling accurate tracking in factory farming environments.
Authors: Yin Chen, Jia Li, Yu Zhang, Zhenzhen Hu, Shiguang Shan, Meng Wang, Richang Hong
Abstract: Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multi-task learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65\%, 58.44\%, and 76.68\%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER.
Authors: Kushal Vyas, Ahmed Imtiaz Humayun, Aniket Dashpute, Richard G. Baraniuk, Ashok Veeraraghavan, Guha Balakrishnan
Abstract: Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is typically trained to capture one signal of interest, resulting in learned neural features that are highly attuned to that signal. Assumed to be less generalizable, we explore the aspect of transferability of such learned neural features for fitting similar signals. We introduce a new INR training framework, STRAINER that learns transferrable features for fitting INRs to new signals from a given distribution, faster and with better reconstruction quality. Owing to the sequential layer-wise affine operations in an INR, we propose to learn transferable representations by sharing initial encoder layers across multiple INRs with independent decoder layers. At test time, the learned encoder representations are transferred as initialization for an otherwise randomly initialized INR. We find STRAINER to yield extremely powerful initialization for fitting images from the same domain and allow for $\approx +10dB$ gain in signal quality early on compared to an untrained INR itself. STRAINER also provides a simple way to encode data-driven priors in INRs. We evaluate STRAINER on multiple in-domain and out-of-domain signal fitting tasks and inverse problems and further provide detailed analysis and discussion on the transferability of STRAINER's features. Our demo can be accessed at https://kushalvyas.github.io/strainer.html .
Authors: Awj Twam, Megan Jacobsen, Rachel Glenn, Peng Wei, Jia Sun, Ann Klopp, Aradhana M. Venkatesan, David Fuentes
Abstract: Cervical cancer remains the fourth most common malignancy amongst women worldwide.1 Concurrent chemoradiotherapy (CRT) serves as the mainstay definitive treatment regimen for locally advanced cervical cancers and includes external beam radiation followed by brachytherapy.2 Integral to radiotherapy treatment planning is the routine contouring of both the target tumor at the level of the cervix, associated gynecologic anatomy and the adjacent organs at risk (OARs). However, manual contouring of these structures is both time and labor intensive and associated with known interobserver variability that can impact treatment outcomes. While multiple tools have been developed to automatically segment OARs and the high-risk clinical tumor volume (HR-CTV) using computed tomography (CT) images,3,4,5,6 the development of deep learning-based tumor segmentation tools using routine T2-weighted (T2w) magnetic resonance imaging (MRI) addresses an unmet clinical need to improve the routine contouring of both anatomical structures and cervical cancers, thereby increasing quality and consistency of radiotherapy planning. This work applied a novel deep-learning model (PocketNet) to segment the cervix, vagina, uterus, and tumor(s) on T2w MRI. The performance of the PocketNet architecture was evaluated, when trained on data via 5-fold cross validation. PocketNet achieved a mean Dice-Sorensen similarity coefficient (DSC) exceeding 70% for tumor segmentation and 80% for organ segmentation. These results suggest that PocketNet is robust to variations in contrast protocols, providing reliable segmentation of the regions of interest.
Authors: Zhecan Wang, Junzhang Liu, Chia-Wei Tang, Hani Alomari, Anushka Sivakumar, Rui Sun, Wenhao Li, Md. Atabuzzaman, Hammad Ayyubi, Haoxuan You, Alvi Ishmam, Kai-Wei Chang, Shih-Fu Chang, Chris Thomas
Abstract: Existing vision-language understanding benchmarks largely consist of images of objects in their usual contexts. As a consequence, recent multimodal large language models can perform well with only a shallow visual understanding by relying on background language biases. Thus, strong performance on these benchmarks does not necessarily correlate with strong visual understanding. In this paper, we release JourneyBench, a comprehensive human-annotated benchmark of generated images designed to assess the model's fine-grained multimodal reasoning abilities across five tasks: complementary multimodal chain of thought, multi-image VQA, imaginary image captioning, VQA with hallucination triggers, and fine-grained retrieval with sample-specific distractors. Unlike existing benchmarks, JourneyBench explicitly requires fine-grained multimodal reasoning in unusual imaginary scenarios where language bias and holistic image gist are insufficient. We benchmark state-of-the-art models on JourneyBench and analyze performance along a number of fine-grained dimensions. Results across all five tasks show that JourneyBench is exceptionally challenging for even the best models, indicating that models' visual reasoning abilities are not as strong as they first appear. We discuss the implications of our findings and propose avenues for further research.
Authors: Eleonora Lopez, Luigi Sigillo, Federica Colonnese, Massimo Panella, Danilo Comminiello
Abstract: Generating images from brain waves is gaining increasing attention due to its potential to advance brain-computer interface (BCI) systems by understanding how brain signals encode visual cues. Most of the literature has focused on fMRI-to-Image tasks as fMRI is characterized by high spatial resolution. However, fMRI is an expensive neuroimaging modality and does not allow for real-time BCI. On the other hand, electroencephalography (EEG) is a low-cost, non-invasive, and portable neuroimaging technique, making it an attractive option for future real-time applications. Nevertheless, EEG presents inherent challenges due to its low spatial resolution and susceptibility to noise and artifacts, which makes generating images from EEG more difficult. In this paper, we address these problems with a streamlined framework based on the ControlNet adapter for conditioning a latent diffusion model (LDM) through EEG signals. We conduct experiments and ablation studies on popular benchmarks to demonstrate that the proposed method beats other state-of-the-art models. Unlike these methods, which often require extensive preprocessing, pretraining, different losses, and captioning models, our approach is efficient and straightforward, requiring only minimal preprocessing and a few components. The code is available at https://github.com/LuigiSigillo/GWIT.
Authors: Dongxu Li, Yudong Liu, Haoning Wu, Yue Wang, Zhiqi Shen, Bowen Qu, Xinyao Niu, Fan Zhou, Chengen Huang, Yanpeng Li, Chongyan Zhu, Xiaoyi Ren, Chao Li, Yifan Ye, Peng Liu, Lihuan Zhang, Hanshu Yan, Guoyin Wang, Bei Chen, Junnan Li
Abstract: Information comes in diverse modalities. Multimodal native AI models are essential to integrate real-world information and deliver comprehensive understanding. While proprietary multimodal native models exist, their lack of openness imposes obstacles for adoptions, let alone adaptations. To fill this gap, we introduce Aria, an open multimodal native model with best-in-class performance across a wide range of multimodal, language, and coding tasks. Aria is a mixture-of-expert model with 3.9B and 3.5B activated parameters per visual token and text token, respectively. It outperforms Pixtral-12B and Llama3.2-11B, and is competitive against the best proprietary models on various multimodal tasks. We pre-train Aria from scratch following a 4-stage pipeline, which progressively equips the model with strong capabilities in language understanding, multimodal understanding, long context window, and instruction following. We open-source the model weights along with a codebase that facilitates easy adoptions and adaptations of Aria in real-world applications.
Authors: Chen Liu, Tobias Ritschel
Abstract: We propose a method to reproduce dynamic appearance textures with space-stationary but time-varying visual statistics. While most previous work decomposes dynamic textures into static appearance and motion, we focus on dynamic appearance that results not from motion but variations of fundamental properties, such as rusting, decaying, melting, and weathering. To this end, we adopt the neural ordinary differential equation (ODE) to learn the underlying dynamics of appearance from a target exemplar. We simulate the ODE in two phases. At the "warm-up" phase, the ODE diffuses a random noise to an initial state. We then constrain the further evolution of this ODE to replicate the evolution of visual feature statistics in the exemplar during the generation phase. The particular innovation of this work is the neural ODE achieving both denoising and evolution for dynamics synthesis, with a proposed temporal training scheme. We study both relightable (BRDF) and non-relightable (RGB) appearance models. For both we introduce new pilot datasets, allowing, for the first time, to study such phenomena: For RGB we provide 22 dynamic textures acquired from free online sources; For BRDFs, we further acquire a dataset of 21 flash-lit videos of time-varying materials, enabled by a simple-to-construct setup. Our experiments show that our method consistently yields realistic and coherent results, whereas prior works falter under pronounced temporal appearance variations. A user study confirms our approach is preferred to previous work for such exemplars.
Authors: Zitian Zhang, Fr\'ed\'eric Fortier-Chouinard, Mathieu Garon, Anand Bhattad, Jean-Fran\c{c}ois Lalonde
Abstract: We present ZeroComp, an effective zero-shot 3D object compositing approach that does not require paired composite-scene images during training. Our method leverages ControlNet to condition from intrinsic images and combines it with a Stable Diffusion model to utilize its scene priors, together operating as an effective rendering engine. During training, ZeroComp uses intrinsic images based on geometry, albedo, and masked shading, all without the need for paired images of scenes with and without composite objects. Once trained, it seamlessly integrates virtual 3D objects into scenes, adjusting shading to create realistic composites. We developed a high-quality evaluation dataset and demonstrate that ZeroComp outperforms methods using explicit lighting estimations and generative techniques in quantitative and human perception benchmarks. Additionally, ZeroComp extends to real and outdoor image compositing, even when trained solely on synthetic indoor data, showcasing its effectiveness in image compositing.
Authors: Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti, Marco Grangetto, Pamela Cosman
Abstract: Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a pair of base-quality and top-quality latent representations. Next, a residual latent representation is encoded as the element-wise difference between the top and base representations. Our scheme enables progressive image compression with element-wise granularity by introducing a masking system that ranks each element of the residual latent representation from most to least important, dividing it into complementary components, which can be transmitted separately to the decoder in order to obtain different reconstruction quality. The masking system does not add further parameters nor complexity. At the receiver, any elements of the top latent representation excluded from the transmitted components can be independently replaced with the mean predicted by the hyperprior architecture, ensuring reliable reconstructions at any intermediate quality level. We also introduced Rate Enhancement Modules (REMs), which refine the estimation of entropy parameters using already decoded components. We obtain results competitive with state-of-the-art competitors, while significantly reducing computational complexity, decoding time, and number of parameters.
Authors: Gorkem Polat, \"Umit Mert \c{C}a\u{g}lar, Alptekin Temizel
Abstract: Assessing disease severity involving ordinal classes, where each class represents increasing levels of severity, benefit from loss functions that account for this ordinal structure. Traditional categorical loss functions, like Cross-Entropy (CE), often perform suboptimally in these scenarios. To address this, we propose a novel loss function, Class Distance Weighted Cross-Entropy (CDW-CE), which penalizes misclassifications more harshly when classes are farther apart. We evaluated CDW-CE on the Labeled Images for Ulcerative Colitis (LIMUC) dataset using various deep architectures. Its performance was compared against several categorical and ordinal loss functions. To analyze the quality of latent representations, we used t-distributed stochastic neighbor embedding (t-SNE) visualizations and quantified their clustering with the Silhouette Score. We also compared Class Activation Maps (CAM) generated by models trained with CDW-CE and CE loss, incorporating domain expert feedback to evaluate alignment with expert knowledge. Our results show that CDW-CE consistently improves performance in ordinal image classification tasks. It achieves higher Silhouette Scores, indicating better differentiation of class representations, and its CAM visualizations demonstrate a stronger focus on clinically significant regions, as confirmed by domain experts.
Authors: Abulikemu Abuduweili, Chenyang Yuan, Changliu Liu, Frank Permenter
Abstract: The denoising process of diffusion models can be interpreted as an approximate projection of noisy samples onto the data manifold. Moreover, the noise level in these samples approximates their distance to the underlying manifold. Building on this insight, we propose a novel method to enhance sample generation by aligning the estimated noise level with the true distance of noisy samples to the manifold. Specifically, we introduce a noise level correction network, leveraging a pre-trained denoising network, to refine noise level estimates during the denoising process. Additionally, we extend this approach to various image restoration tasks by integrating task-specific constraints, including inpainting, deblurring, super-resolution, colorization, and compressed sensing. Experimental results demonstrate that our method significantly improves sample quality in both unconstrained and constrained generation scenarios. Notably, the proposed noise level correction framework is compatible with existing denoising schedulers (e.g., DDIM), offering additional performance improvements.
Authors: Tianshuo Peng, Mingsheng Li, Hongbin Zhou, Renqiu Xia, Renrui Zhang, Lei Bai, Song Mao, Bin Wang, Conghui He, Aojun Zhou, Botian Shi, Tao Chen, Bo Zhang, Xiangyu Yue
Abstract: Recent advancements in Large Multi-modal Models (LMMs) underscore the importance of scaling by increasing image-text paired data, achieving impressive performance on general tasks. Despite their effectiveness in broad applications, generalist models are primarily trained on web-scale datasets dominated by natural images, resulting in the sacrifice of specialized capabilities for domain-specific tasks that require extensive domain prior knowledge. Moreover, directly integrating expert models tailored for specific domains is challenging due to the representational gap and imbalanced optimization between the generalist model and experts. To address these challenges, we introduce Chimera, a scalable and low-cost multi-modal pipeline designed to boost the ability of existing LMMs with domain-specific experts. Specifically, we design a progressive training strategy to integrate features from expert models into the input of a generalist LMM. To address the imbalanced optimization caused by the well-aligned general visual encoder, we introduce a novel Generalist-Specialist Collaboration Masking (GSCM) mechanism. This results in a versatile model that excels across the chart, table, math, and document domains, achieving state-of-the-art performance on multi-modal reasoning and visual content extraction tasks, both of which are challenging tasks for assessing existing LMMs.
Authors: Yi Yu, Song Xia, Xun Lin, Wenhan Yang, Shijian Lu, Yap-peng Tan, Alex Kot
Abstract: No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and optimizing computer vision systems, e.g., low-light enhancement. Recent research indicates that NR-IQA models are susceptible to adversarial attacks, which can significantly alter predicted scores with visually imperceptible perturbations. Despite revealing vulnerabilities, these attack methods have limitations, including high computational demands, untargeted manipulation, limited practical utility in white-box scenarios, and reduced effectiveness in black-box scenarios. To address these challenges, we shift our focus to another significant threat and present a novel poisoning-based backdoor attack against NR-IQA (BAIQA), allowing the attacker to manipulate the IQA model's output to any desired target value by simply adjusting a scaling coefficient $\alpha$ for the trigger. We propose to inject the trigger in the discrete cosine transform (DCT) domain to improve the local invariance of the trigger for countering trigger diminishment in NR-IQA models due to widely adopted data augmentations. Furthermore, the universal adversarial perturbations (UAP) in the DCT space are designed as the trigger, to increase IQA model susceptibility to manipulation and improve attack effectiveness. In addition to the heuristic method for poison-label BAIQA (P-BAIQA), we explore the design of clean-label BAIQA (C-BAIQA), focusing on $\alpha$ sampling and image data refinement, driven by theoretical insights we reveal. Extensive experiments on diverse datasets and various NR-IQA models demonstrate the effectiveness of our attacks. Code can be found at https://github.com/yuyi-sd/BAIQA.
Authors: Preetish Kakkar, Srijani Mukherjee, Hariharan Ragothaman, Vishal Mehta
Abstract: Physics-based differentiable rendering (PBDR) has become an efficient method in computer vision, graphics, and machine learning for addressing an array of inverse problems. PBDR allows patterns to be generated from perceptions which can be applied to enhance object attributes like geometry, substances, and lighting by adding physical models of light propagation and materials interaction. Due to these capabilities, distinguished rendering has been employed in a wider range of sectors such as autonomous navigation, scene reconstruction, and material design. We provide an extensive overview of PBDR techniques in this study, emphasizing their creation, effectiveness, and limitations while managing inverse situations. We demonstrate modern techniques and examine their value in everyday situations.
Authors: Kyle Stein, Andrew Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through weight fine-tuning, much less attention has been given to detecting backdoored samples directly. Given the vast datasets used in training, manual inspection for backdoor triggers is impractical, and even state-of-the-art defense mechanisms fail to fully neutralize their impact. To address this gap, we introduce a groundbreaking method to detect unseen backdoored images during both training and inference. Leveraging the transformative success of prompt tuning in Vision Language Models (VLMs), our approach trains learnable text prompts to differentiate clean images from those with hidden backdoor triggers. Experiments demonstrate the exceptional efficacy of this method, achieving an impressive average accuracy of 86% across two renowned datasets for detecting unseen backdoor triggers, establishing a new standard in backdoor defense.
Authors: Xiaoshuang Huang, Lingdong Shen, Jia Liu, Fangxin Shang, Hongxiang Li, Haifeng Huang, Yehui Yang
Abstract: In recent years, Multimodal Large Language Models (MLLM) have achieved notable advancements, demonstrating the feasibility of developing an intelligent biomedical assistant. However, current biomedical MLLMs predominantly focus on image-level understanding and restrict interactions to textual commands, thus limiting their capability boundaries and the flexibility of usage. In this paper, we introduce a novel end-to-end multimodal large language model for the biomedical domain, named MedPLIB, which possesses pixel-level understanding. Excitingly, it supports visual question answering (VQA), arbitrary pixel-level prompts (points, bounding boxes, and free-form shapes), and pixel-level grounding. We propose a novel Mixture-of-Experts (MoE) multi-stage training strategy, which divides MoE into separate training phases for a visual-language expert model and a pixel-grounding expert model, followed by fine-tuning using MoE. This strategy effectively coordinates multitask learning while maintaining the computational cost at inference equivalent to that of a single expert model. To advance the research of biomedical MLLMs, we introduce the Medical Complex Vision Question Answering Dataset (MeCoVQA), which comprises an array of 8 modalities for complex medical imaging question answering and image region understanding. Experimental results indicate that MedPLIB has achieved state-of-the-art outcomes across multiple medical visual language tasks. More importantly, in zero-shot evaluations for the pixel grounding task, MedPLIB leads the best small and large models by margins of 19.7 and 15.6 respectively on the mDice metric. The codes, data, and model checkpoints will be made publicly available at https://github.com/ShawnHuang497/MedPLIB.
Authors: Cong Wan, Xiangyang Luo, Zijian Cai, Yiren Song, Yunlong Zhao, Yifan Bai, Yuhang He, Yihong Gong
Abstract: In this paper, we introduce GRID, a novel paradigm that reframes a broad range of visual generation tasks as the problem of arranging grids, akin to film strips. At its core, GRID transforms temporal sequences into grid layouts, enabling image generation models to process visual sequences holistically. To achieve both layout consistency and motion coherence, we develop a parallel flow-matching training strategy that combines layout matching and temporal losses, guided by a coarse-to-fine schedule that evolves from basic layouts to precise motion control. Our approach demonstrates remarkable efficiency, achieving up to 35 faster inference speeds while using 1/1000 of the computational resources compared to specialized models. Extensive experiments show that GRID exhibits exceptional versatility across diverse visual generation tasks, from Text-to-Video to 3D Editing, while maintaining its foundational image generation capabilities. This dual strength in both expanded applications and preserved core competencies establishes GRID as an efficient and versatile omni-solution for visual generation.
Authors: Yi Feng, Yu Han, Xijing Zhang, Tanghui Li, Yanting Zhang, Rui Fan
Abstract: Inferring the 3D structure of a scene from a single image is an ill-posed and challenging problem in the field of vision-centric autonomous driving. Existing methods usually employ neural radiance fields to produce voxelized 3D occupancy, lacking instance-level semantic reasoning and temporal photometric consistency. In this paper, we propose ViPOcc, which leverages the visual priors from vision foundation models (VFMs) for fine-grained 3D occupancy prediction. Unlike previous works that solely employ volume rendering for RGB and depth image reconstruction, we introduce a metric depth estimation branch, in which an inverse depth alignment module is proposed to bridge the domain gap in depth distribution between VFM predictions and the ground truth. The recovered metric depth is then utilized in temporal photometric alignment and spatial geometric alignment to ensure accurate and consistent 3D occupancy prediction. Additionally, we also propose a semantic-guided non-overlapping Gaussian mixture sampler for efficient, instance-aware ray sampling, which addresses the redundant and imbalanced sampling issue that still exists in previous state-of-the-art methods. Extensive experiments demonstrate the superior performance of ViPOcc in both 3D occupancy prediction and depth estimation tasks on the KITTI-360 and KITTI Raw datasets. Our code is available at: \url{https://mias.group/ViPOcc}.
Authors: Renqiu Xia, Mingsheng Li, Hancheng Ye, Wenjie Wu, Hongbin Zhou, Jiakang Yuan, Tianshuo Peng, Xinyu Cai, Xiangchao Yan, Bin Wang, Conghui He, Botian Shi, Tao Chen, Junchi Yan, Bo Zhang
Abstract: Despite their proficiency in general tasks, Multi-modal Large Language Models (MLLMs) struggle with automatic Geometry Problem Solving (GPS), which demands understanding diagrams, interpreting symbols, and performing complex reasoning. This limitation arises from their pre-training on natural images and texts, along with the lack of automated verification in the problem-solving process. Besides, current geometric specialists are limited by their task-specific designs, making them less effective for broader geometric problems. To this end, we present GeoX, a multi-modal large model focusing on geometric understanding and reasoning tasks. Given the significant differences between geometric diagram-symbol and natural image-text, we introduce unimodal pre-training to develop a diagram encoder and symbol decoder, enhancing the understanding of geometric images and corpora. Furthermore, we introduce geometry-language alignment, an effective pre-training paradigm that bridges the modality gap between unimodal geometric experts. We propose a Generator-And-Sampler Transformer (GS-Former) to generate discriminative queries and eliminate uninformative representations from unevenly distributed geometric signals. Finally, GeoX benefits from visual instruction tuning, empowering it to take geometric images and questions as input and generate verifiable solutions. Experiments show that GeoX outperforms both generalists and geometric specialists on publicly recognized benchmarks, such as GeoQA, UniGeo, Geometry3K, and PGPS9k.
Authors: Maheswar Bora, Tushar Anand, Saurabh Atreya, Aritra Mukherjee, Abhijit Das
Abstract: In this work we propose a Visual Mamba (ViM) based architecture, to dissolve the existing trade-off for real-time and accurate model with low computation overhead for disparity map generation (DMG). Moreover, we proposed a performance measure that can jointly evaluate the inference speed, computation overhead and the accurateness of a DMG model. The code implementation and corresponding models are available at: https://github.com/MBora/ViM-Disparity.
Authors: Ryo Ide, Lei Yang
Abstract: Smoke detection using Deep Neural Networks (DNNs) is an effective approach for early wildfire detection. However, because smoke is temporally and spatially anomalous, there are limitations in collecting sufficient training data. This raises overfitting and bias concerns in existing DNN-based wildfire detection models. Thus, we introduce WARP (Wildfire Adversarial Robustness Procedure), the first model-agnostic framework for evaluating the adversarial robustness of DNN-based wildfire detection models. WARP addresses limitations in smoke image diversity using global and local adversarial attack methods. The global attack method uses image-contextualized Gaussian noise, while the local attack method uses patch noise injection, tailored to address critical aspects of wildfire detection. Leveraging WARP's model-agnostic capabilities, we assess the adversarial robustness of real-time Convolutional Neural Networks (CNNs) and Transformers. The analysis revealed valuable insights into the models' limitations. Specifically, the global attack method demonstrates that the Transformer model has more than 70% precision degradation than the CNN against global noise. In contrast, the local attack method shows that both models are susceptible to cloud image injections when detecting smoke-positive instances, suggesting a need for model improvements through data augmentation. WARP's comprehensive robustness analysis contributed to the development of wildfire-specific data augmentation strategies, marking a step toward practicality.
Authors: Xi Yang, Pai Peng, Wulin Xie, Xiaohuan Lu, Jie Wen
Abstract: In few-shot image classification tasks, methods based on pretrained vision-language models (such as CLIP) have achieved significant progress. Many existing approaches directly utilize visual or textual features as class prototypes, however, these features fail to adequately represent their respective classes. We identify that this limitation arises from the modality gap inherent in pretrained vision-language models, which weakens the connection between the visual and textual modalities. To eliminate this modality gap and enable textual features to fully represent class prototypes, we propose a simple and efficient Cross-Modal Mapping (CMM) method. This method employs a linear transformation to map image features into the textual feature space, ensuring that both modalities are comparable within the same feature space. Nevertheless, the modality gap diminishes the effectiveness of this mapping. To address this, we further introduce a triplet loss to optimize the spatial relationships between image features and class textual features, allowing class textual features to naturally serve as class prototypes for image features. Experimental results on 11 benchmark demonstrate an average improvement of approximately 3.5% compared to conventional methods and exhibit competitive performance on 4 distribution shift benchmarks.
Authors: Xinhao Li, Yi Wang, Jiashuo Yu, Xiangyu Zeng, Yuhan Zhu, Haian Huang, Jianfei Gao, Kunchang Li, Yinan He, Chenting Wang, Yu Qiao, Yali Wang, Limin Wang
Abstract: Long-context modeling is a critical capability for multimodal large language models (MLLMs), enabling them to process long-form contents with implicit memorization. Despite its advances, handling extremely long videos remains challenging due to the difficulty in maintaining crucial features over extended sequences. This paper introduces a Hierarchical visual token Compression (HiCo) method designed for high-fidelity representation and a practical context modeling system VideoChat-Flash tailored for multimodal long-sequence processing. HiCo capitalizes on the redundancy of visual information in long videos to compress long video context from the clip-level to the video-level, reducing the compute significantly while preserving essential details. VideoChat-Flash features a multi-stage short-to-long learning scheme, a rich dataset of real-world long videos named LongVid, and an upgraded "Needle-In-A-video-Haystack" (NIAH) for evaluating context capacities. In extensive experiments, VideoChat-Flash shows the leading performance on both mainstream long and short video benchmarks at the 2B and 7B model scale. It firstly gets 99.1% accuracy over 10,000 frames in NIAH among open-source models.
Authors: Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo, Xi Xiao, Bo Han, Yongjie Yin, Feng Zheng
Abstract: Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models--a common and practical real world scenario--remains unexplored. In this paper, we pioneer an investigation into the transferability of adversarial video samples across V-MLLMs. We find that existing adversarial attack methods face significant limitations when applied in black-box settings for V-MLLMs, which we attribute to the following shortcomings: (1) lacking generalization in perturbing video features, (2) focusing only on sparse key-frames, and (3) failing to integrate multimodal information. To address these limitations and deepen the understanding of V-MLLM vulnerabilities in black-box scenarios, we introduce the Image-to-Video MLLM (I2V-MLLM) attack. In I2V-MLLM, we utilize an image-based multimodal model (IMM) as a surrogate model to craft adversarial video samples. Multimodal interactions and temporal information are integrated to disrupt video representations within the latent space, improving adversarial transferability. In addition, a perturbation propagation technique is introduced to handle different unknown frame sampling strategies. Experimental results demonstrate that our method can generate adversarial examples that exhibit strong transferability across different V-MLLMs on multiple video-text multimodal tasks. Compared to white-box attacks on these models, our black-box attacks (using BLIP-2 as surrogate model) achieve competitive performance, with average attack success rates of 55.48% on MSVD-QA and 58.26% on MSRVTT-QA for VideoQA tasks, respectively. Our code will be released upon acceptance.
Authors: Pu Yang, Bin Dong
Abstract: Image captioning is a critical task at the intersection of computer vision and natural language processing, with wide-ranging applications across various domains. For complex tasks such as diagnostic report generation, deep learning models require not only domain-specific image-caption datasets but also the incorporation of relevant general knowledge to provide contextual accuracy. Existing approaches exhibit inherent limitations: specialized models excel in capturing domain-specific details but lack generalization, while vision-language models (VLMs) built on large language models (LLMs) leverage general knowledge but struggle with domain-specific adaptation. To address these limitations, this paper proposes a novel agent-enhanced model collaboration framework, which we call MoColl, designed to effectively integrate domain-specific and general knowledge. Specifically, our approach is to decompose complex image captioning tasks into a series of interconnected question-answer subtasks. A trainable visual question answering (VQA) model is employed as a specialized tool to focus on domain-specific visual analysis, answering task-specific questions based on image content. Concurrently, an LLM-based agent with general knowledge formulates these questions and synthesizes the resulting question-answer pairs into coherent captions. Beyond its role in leveraging the VQA model, the agent further guides its training to enhance its domain-specific capabilities. Experimental results on radiology report generation validate the effectiveness of the proposed framework, demonstrating significant improvements in the quality of generated reports.
Authors: Mohammad Nadeem, Shahab Saquib Sohail, Erik Cambria, Bj\"orn W. Schuller, Amir Hussain
Abstract: The advent of text-to-video generation models has revolutionized content creation as it produces high-quality videos from textual prompts. However, concerns regarding inherent biases in such models have prompted scrutiny, particularly regarding gender representation. Our study investigates the presence of gender bias in OpenAI's Sora, a state-of-the-art text-to-video generation model. We uncover significant evidence of bias by analyzing the generated videos from a diverse set of gender-neutral and stereotypical prompts. The results indicate that Sora disproportionately associates specific genders with stereotypical behaviors and professions, which reflects societal prejudices embedded in its training data.
Authors: Zongxia Li, Xiyang Wu, Hongyang Du, Huy Nghiem, Guangyao Shi
Abstract: Multimodal Vision Language Models (VLMs) have emerged as a transformative technology at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification. Despite their rapid advancements in research and growing popularity in applications, a comprehensive survey of existing studies on VLMs is notably lacking, particularly for researchers aiming to leverage VLMs in their specific domains. To this end, we provide a systematic overview of VLMs in the following aspects: model information of the major VLMs developed over the past five years (2019-2024); the main architectures and training methods of these VLMs; summary and categorization of the popular benchmarks and evaluation metrics of VLMs; the applications of VLMs including embodied agents, robotics, and video generation; the challenges and issues faced by current VLMs such as hallucination, fairness, and safety. Detailed collections including papers and model repository links are listed in https://github.com/zli12321/Awesome-VLM-Papers-And-Models.git.
URLs: https://github.com/zli12321/Awesome-VLM-Papers-And-Models.git.
Authors: Zhenglai Li, Jun Wang, Chang Tang, Xinzhong Zhu, Wei Zhang, Xinwang Liu
Abstract: Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC is potentially not fully leverage the multi-view information, since the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, a theoretical analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches both on eight benchmark MvC datasets and two spatially resolved transcriptomics datasets.
Authors: Junsheng Luan, Guangyuan Li, Lei Zhao, Wei Xing
Abstract: Virtual try-on methods based on diffusion models achieve realistic try-on effects. They use an extra reference network or an additional image encoder to process multiple conditional image inputs, which adds complexity pre-processing and additional computational costs. Besides, they require more than 25 inference steps, bringing longer inference time. In this work, with the development of diffusion transformer (DiT), we rethink the necessity of additional reference network or image encoder and introduce MC-VTON, which leverages DiT's intrinsic backbone to seamlessly integrate minimal conditional try-on inputs. Compared to existing methods, the superiority of MC-VTON is demonstrated in four aspects: (1) Superior detail fidelity. Our DiT-based MC-VTON exhibits superior fidelity in preserving fine-grained details. (2) Simplified network and inputs. We remove any extra reference network or image encoder. We also remove unnecessary conditions like the long prompt, pose estimation, human parsing, and depth map. We require only the masked person image and the garment image. (3) Parameter-efficient training. To process the try-on task, we fine-tune the FLUX.1-dev with only 39.7M additional parameters (0.33% of the backbone parameters). (4) Less inference steps. We apply distillation diffusion on MC-VTON and only need 8 steps to generate a realistic try-on image, with only 86.8M additional parameters (0.72% of the backbone parameters). Experiments show that MC-VTON achieves superior qualitative and quantitative results with fewer condition inputs, trainable parameters, and inference steps than baseline methods.
Authors: Xinbin Yuan, Zhaohui Zheng, Yuxuan Li, Xialei Liu, Li Liu, Xiang Li, Qibin Hou, Ming-Ming Cheng
Abstract: While witnessed with rapid development, remote sensing object detection remains challenging for detecting high aspect ratio objects. This paper shows that large strip convolutions are good feature representation learners for remote sensing object detection and can detect objects of various aspect ratios well. Based on large strip convolutions, we build a new network architecture called Strip R-CNN, which is simple, efficient, and powerful. Unlike recent remote sensing object detectors that leverage large-kernel convolutions with square shapes, our Strip R-CNN takes advantage of sequential orthogonal large strip convolutions to capture spatial information. In addition, we enhance the localization capability of remote-sensing object detectors by decoupling the detection heads and equipping the localization head with strip convolutions to better localize the target objects. Extensive experiments on several benchmarks, e.g., DOTA, FAIR1M, HRSC2016, and DIOR, show that our Strip R-CNN can largely improve previous works. Notably, our 30M model achieves 82.75% mAP on DOTA-v1.0, setting a new state-of-the-art record.Code is available at https://github.com/YXB-NKU/Strip-R-CNN.
Authors: Zhenghui Zhao, Chen Wu, Lixiang Ru, Di Wang, Hongruixuan Chen, Cuiqun Chen
Abstract: Existing Weakly-Supervised Change Detection (WSCD) methods often encounter the problem of "instance lumping" under scene-level supervision, particularly in scenarios with a dense distribution of changed instances (i.e., changed objects). In these scenarios, unchanged pixels between changed instances are also mistakenly identified as changed, causing multiple changes to be mistakenly viewed as one. In practical applications, this issue prevents the accurate quantification of the number of changes. To address this issue, we propose a Dense Instance Separation (DISep) method as a plug-and-play solution, refining pixel features from a unified instance perspective under scene-level supervision. Specifically, our DISep comprises a three-step iterative training process: 1) Instance Localization: We locate instance candidate regions for changed pixels using high-pass class activation maps. 2) Instance Retrieval: We identify and group these changed pixels into different instance IDs through connectivity searching. Then, based on the assigned instance IDs, we extract corresponding pixel-level features on a per-instance basis. 3) Instance Separation: We introduce a separation loss to enforce intra-instance pixel consistency in the embedding space, thereby ensuring separable instance feature representations. The proposed DISep adds only minimal training cost and no inference cost. It can be seamlessly integrated to enhance existing WSCD methods. We achieve state-of-the-art performance by enhancing {three Transformer-based and four ConvNet-based methods} on the LEVIR-CD, WHU-CD, DSIFN-CD, SYSU-CD, and CDD datasets. Additionally, our DISep can be used to improve fully-supervised change detection methods. Code is available at https://github.com/zhenghuizhao/Plug-and-Play-DISep-for-Change-Detection.
URLs: https://github.com/zhenghuizhao/Plug-and-Play-DISep-for-Change-Detection.
Authors: Shiqi Cao, Liangjian Deng, Shangqi Deng
Abstract: The implementation of diffusion-based pansharpening task is predominantly constrained by its slow inference speed, which results from numerous sampling steps. Despite the existing techniques aiming to accelerate sampling, they often compromise performance when fusing multi-source images. To ease this limitation, we introduce a novel and efficient diffusion model named Diffusion Model for Pansharpening by Inferring Residual Inference (ResPanDiff), which significantly reduces the number of diffusion steps without sacrificing the performance to tackle pansharpening task. In ResPanDiff, we innovatively propose a Markov chain that transits from noisy residuals to the residuals between the LRMS and HRMS images, thereby reducing the number of sampling steps and enhancing performance. Additionally, we design the latent space to help model extract more features at the encoding stage, Shallow Cond-Injection~(SC-I) to help model fetch cond-injected hidden features with higher dimensions, and loss functions to give a better guidance for the residual generation task. enabling the model to achieve superior performance in residual generation. Furthermore, experimental evaluations on pansharpening datasets demonstrate that the proposed method achieves superior outcomes compared to recent state-of-the-art~(SOTA) techniques, requiring only 15 sampling steps, which reduces over $90\%$ step compared with the benchmark diffusion models. Our experiments also include thorough discussions and ablation studies to underscore the effectiveness of our approach.
Authors: Siyu Liu, Zheng-Peng Duan, Jia OuYang, Jiayi Fu, Hyunhee Park, Zikun Liu, Chun-Le Guo, Chongyi Li
Abstract: Blind face restoration is a highly ill-posed problem due to the lack of necessary context. Although existing methods produce high-quality outputs, they often fail to faithfully preserve the individual's identity. In this paper, we propose a personalized face restoration method, FaceMe, based on a diffusion model. Given a single or a few reference images, we use an identity encoder to extract identity-related features, which serve as prompts to guide the diffusion model in restoring high-quality and identity-consistent facial images. By simply combining identity-related features, we effectively minimize the impact of identity-irrelevant features during training and support any number of reference image inputs during inference. Additionally, thanks to the robustness of the identity encoder, synthesized images can be used as reference images during training, and identity changing during inference does not require fine-tuning the model. We also propose a pipeline for constructing a reference image training pool that simulates the poses and expressions that may appear in real-world scenarios. Experimental results demonstrate that our FaceMe can restore high-quality facial images while maintaining identity consistency, achieving excellent performance and robustness.
Authors: Maximilian Alber, Stephan Tietz, Jonas Dippel, Timo Milbich, Timoth\'ee Lesort, Panos Korfiatis, Moritz Kr\"ugener, Beatriz Perez Cancer, Neelay Shah, Alexander M\"ollers, Philipp Seegerer, Alexandra Carpen-Amarie, Kai Standvoss, Gabriel Dernbach, Edwin de Jong, Simon Schallenberg, Andreas Kunft, Helmut Hoffer von Ankershoffen, Gavin Schaeferle, Patrick Duffy, Matt Redlon, Philipp Jurmeister, David Horst, Lukas Ruff, Klaus-Robert M\"uller, Frederick Klauschen, Andrew Norgan
Abstract: Recent advances in digital pathology have demonstrated the effectiveness of foundation models across diverse applications. In this report, we present Atlas, a novel vision foundation model based on the RudolfV approach. Our model was trained on a dataset comprising 1.2 million histopathology whole slide images, collected from two medical institutions: Mayo Clinic and Charit\'e - Universt\"atsmedizin Berlin. Comprehensive evaluations show that Atlas achieves state-of-the-art performance across twenty-one public benchmark datasets, even though it is neither the largest model by parameter count nor by training dataset size.
Authors: David McAllister, Matthew Tancik, Jiaming Song, Angjoo Kanazawa
Abstract: Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up infrastructure costs and straining power systems. We propose Decentralized Diffusion Models, a scalable framework for distributing diffusion model training across independent clusters or datacenters by eliminating the dependence on a centralized, high-bandwidth networking fabric. Our method trains a set of expert diffusion models over partitions of the dataset, each in full isolation from one another. At inference time, the experts ensemble through a lightweight router. We show that the ensemble collectively optimizes the same objective as a single model trained over the whole dataset. This means we can divide the training burden among a number of "compute islands," lowering infrastructure costs and improving resilience to localized GPU failures. Decentralized diffusion models empower researchers to take advantage of smaller, more cost-effective and more readily available compute like on-demand GPU nodes rather than central integrated systems. We conduct extensive experiments on ImageNet and LAION Aesthetics, showing that decentralized diffusion models FLOP-for-FLOP outperform standard diffusion models. We finally scale our approach to 24 billion parameters, demonstrating that high-quality diffusion models can now be trained with just eight individual GPU nodes in less than a week.
Authors: T. Windeatt
Abstract: Despite being effective in many application areas, Deep Neural Networks (DNNs) are vulnerable to being attacked. In object recognition, the attack takes the form of a small perturbation added to an image, that causes the DNN to misclassify, but to a human appears no different. Adversarial attacks lead to defences that are themselves subject to attack, and the attack/ defence strategies provide important information about the properties of DNNs. In this paper, a novel method of detecting adversarial attacks is proposed for an ensemble of Deep Neural Networks (DNNs) solving two-class pattern recognition problems. The ensemble is combined using Walsh coefficients which are capable of approximating Boolean functions and thereby controlling the decision boundary complexity. The hypothesis in this paper is that decision boundaries with high curvature allow adversarial perturbations to be found, but change the curvature of the decision boundary, which is then approximated in a different way by Walsh coefficients compared to the clean images. Besides controlling boundary complexity, the coefficients also measure the correlation with class labels, which may aid in understanding the learning and transferability properties of DNNs. While the experiments here use images, the proposed approach of modelling two-class ensemble decision boundaries could in principle be applied to any application area.
Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi
Abstract: Image Super-Resolution (SR) is essential for a wide range of computer vision and image processing tasks. Investigating infrared (IR) image (or thermal images) super-resolution is a continuing concern within the development of deep learning. This survey aims to provide a comprehensive perspective of IR image super-resolution, including its applications, hardware imaging system dilemmas, and taxonomy of image processing methodologies. In addition, the datasets and evaluation metrics in IR image super-resolution tasks are also discussed. Furthermore, the deficiencies in current technologies and possible promising directions for the community to explore are highlighted. To cope with the rapid development in this field, we intend to regularly update the relevant excellent work at \url{https://github.com/yongsongH/Infrared_Image_SR_Survey
Authors: Xiaoying Zhi, Varun Babbar, Rundong Liu, Pheobe Sun, Fran Silavong, Ruibo Shi, Sean Moran
Abstract: The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at inference time usually involve pruning the network parameters. Pruning schemes often create extra overhead either by iterative training and fine-tuning for static pruning or repeated computation of a dynamic pruning graph. We propose a new parameter pruning strategy for learning a lighter-weight sub-network that minimizes the energy cost while maintaining comparable performance to the fully parameterised network on given downstream tasks. Our proposed pruning scheme is green-oriented, as it only requires a one-off training to discover the optimal static sub-networks by dynamic pruning methods. The pruning scheme consists of a binary gating module and a polarizing loss function to uncover sub-networks with user-defined sparsity. Our method enables pruning and training simultaneously, which saves energy in both the training and inference phases and avoids extra computational overhead from gating modules at inference time. Our results on CIFAR-10, CIFAR-100, and Tiny Imagenet suggest that our scheme can remove 50% of connections in deep networks with <1% reduction in classification accuracy. Compared to other related pruning methods, our method demonstrates a lower drop in accuracy for equivalent reductions in computational cost.
Authors: Zahra Alijani, Vojtech Molek
Abstract: Designing effective neural networks requires tuning architectural elements. This study integrates fractional calculus into neural networks by introducing fractional order derivatives (FDO) as tunable parameters in activation functions, allowing diverse activation functions by adjusting the FDO. We evaluate these fractional activation functions on various datasets and network architectures, comparing their performance with traditional and new activation functions. Our experiments assess their impact on accuracy, time complexity, computational overhead, and memory usage. Results suggest fractional activation functions, particularly fractional Sigmoid, offer benefits in some scenarios. Challenges related to consistency and efficiency remain. Practical implications and limitations are discussed.
Authors: Yannik Blei, Michael Krawez, Nisarga Nilavadi, Tanja Katharina Kaiser, Wolfram Burgard
Abstract: Nowadays, unmanned aerial vehicles (UAVs) are commonly used in search and rescue scenarios to gather information in the search area. The automatic identification of the person searched for in aerial footage could increase the autonomy of such systems, reduce the search time, and thus increase the missed person's chances of survival. In this paper, we present a novel approach to perform semantically conditioned open vocabulary object tracking that is specifically designed to cope with the limitations of UAV hardware. Our approach has several advantages. It can run with verbal descriptions of the missing person, e.g., the color of the shirt, it does not require dedicated training to execute the mission and can efficiently track a potentially moving person. Our experimental results demonstrate the versatility and efficacy of our approach.
Authors: Preetish Kakkar, Hariharan Ragothaman
Abstract: Volumetric video, the capture and display of three-dimensional (3D) imagery, has emerged as a revolutionary technology poised to transform the media landscape, enabling immersive experiences that transcend the limitations of traditional 2D video. One of the key challenges in this domain is the efficient delivery of these high-bandwidth, data-intensive volumetric video streams, which requires innovative transcoding and compression techniques. This research paper explores the state-of-the-art in volumetric video compression and delivery, with a focus on the potential of AI-driven solutions to address the unique challenges posed by this emerging medium.
Authors: Moyang Guo, Yuepeng Hu, Zhengyuan Jiang, Zeyu Li, Amir Sadovnik, Arka Daw, Neil Gong
Abstract: While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection methods can be broadly categorized into passive and watermark-based approaches: passive detectors rely on artifacts present in AI-generated images, whereas watermark-based detectors proactively embed watermarks into such images. A key question is which type of detector performs better in terms of effectiveness, robustness, and efficiency. However, the current literature lacks a comprehensive understanding of this issue. In this work, we aim to bridge that gap by developing ImageDetectBench, the first comprehensive benchmark to compare the effectiveness, robustness, and efficiency of passive and watermark-based detectors. Our benchmark includes four datasets, each containing a mix of AI-generated and non-AI-generated images. We evaluate five passive detectors and four watermark-based detectors against eight types of common perturbations and three types of adversarial perturbations. Our benchmark results reveal several interesting findings. For instance, watermark-based detectors consistently outperform passive detectors, both in the presence and absence of perturbations. Based on these insights, we provide recommendations for detecting AI-generated images, e.g., when both types of detectors are applicable, watermark-based detectors should be the preferred choice. Our code and data are publicly available at https://github.com/moyangkuo/ImageDetectBench.git.
Authors: Hao-Chun Yang, Sicheng Dai, Saige Rutherford, Christian Gaser, Andre F Marquand, Christian F Beckmann, Thomas Wolfers
Abstract: Unsupervised anomaly detection in brain imaging is challenging. In this paper, we propose a self-supervised masked mesh learning for unsupervised anomaly detection in 3D cortical surfaces. Our framework leverages the intrinsic geometry of the cortical surface to learn a self-supervised representation that captures the underlying structure of the brain. We introduce a masked mesh convolutional neural network (MMN) that learns to predict masked regions of the cortical surface. By training the MMN on a large dataset of healthy subjects, we learn a representation that captures the normal variation in the cortical surface. We then use this representation to detect anomalies in unseen individuals by calculating anomaly scores based on the reconstruction error of the MMN. We evaluate our framework by training on population-scale dataset UKB and HCP-Aging and testing on two datasets of Alzheimer's disease patients ADNI and OASIS3. Our results show that our framework can detect anomalies in cortical thickness, cortical volume, and cortical sulcus features, which are known to be sensitive biomarkers for Alzheimer's disease. Our proposed framework provides a promising approach for unsupervised anomaly detection based on normative variation of cortical features.
Authors: Simran Khanuja, Vivek Iyer, Claire He, Graham Neubig
Abstract: Beyond conventional paradigms of translating speech and text, recently, there has been interest in automated transcreation of images to facilitate localization of visual content across different cultures. Attempts to define this as a formal Machine Learning (ML) problem have been impeded by the lack of automatic evaluation mechanisms, with previous work relying solely on human evaluation. In this paper, we seek to close this gap by proposing a suite of automatic evaluation metrics inspired by machine translation (MT) metrics, categorized into: a) Object-based, b) Embedding-based, and c) VLM-based. Drawing on theories from translation studies and real-world transcreation practices, we identify three critical dimensions of image transcreation: cultural relevance, semantic equivalence and visual similarity, and design our metrics to evaluate systems along these axes. Our results show that proprietary VLMs best identify cultural relevance and semantic equivalence, while vision-encoder representations are adept at measuring visual similarity. Meta-evaluation across 7 countries shows our metrics agree strongly with human ratings, with average segment-level correlations ranging from 0.55-0.87. Finally, through a discussion of the merits and demerits of each metric, we offer a robust framework for automated image transcreation evaluation, grounded in both theoretical foundations and practical application. Our code can be found here: https://github.com/simran-khanuja/automatic-eval-transcreation
URLs: https://github.com/simran-khanuja/automatic-eval-transcreation
Authors: Yiliang Chen, Steven SC Ho, Cheng Xu, Yao Jie Xie, Wing-Fai Yeung, Shengfeng He, Jing Qin
Abstract: Tongue diagnosis is a vital tool in Western and Traditional Chinese Medicine, providing key insights into a patient's health by analyzing tongue attributes. The COVID-19 pandemic has heightened the need for accurate remote medical assessments, emphasizing the importance of precise tongue attribute recognition via telehealth. To address this, we propose a Sign-Oriented multi-label Attributes Detection framework. Our approach begins with an adaptive tongue feature extraction module that standardizes tongue images and mitigates environmental factors. This is followed by a Sign-oriented Network (SignNet) that identifies specific tongue attributes, emulating the diagnostic process of experienced practitioners and enabling comprehensive health evaluations. To validate our methodology, we developed an extensive tongue image dataset specifically designed for telemedicine. Unlike existing datasets, ours is tailored for remote diagnosis, with a comprehensive set of attribute labels. This dataset will be openly available, providing a valuable resource for research. Initial tests have shown improved accuracy in detecting various tongue attributes, highlighting our framework's potential as an essential tool for remote medical assessments.
Authors: Jiakang Yuan, Xiangchao Yan, Botian Shi, Tao Chen, Wanli Ouyang, Bo Zhang, Lei Bai, Yu Qiao, Bowen Zhou
Abstract: The scientific research paradigm is undergoing a profound transformation owing to the development of Artificial Intelligence (AI). Recent works demonstrate that various AI-assisted research methods can largely improve research efficiency by improving data analysis, accelerating computation, and fostering novel idea generation. To further move towards the ultimate goal (i.e., automatic scientific research), in this paper, we propose Dolphin, the first closed-loop open-ended auto-research framework to further build the entire process of human scientific research. Dolphin can generate research ideas, perform experiments, and get feedback from experimental results to generate higher-quality ideas. More specifically, Dolphin first generates novel ideas based on relevant papers which are ranked by the topic and task attributes. Then, the codes are automatically generated and debugged with the exception-traceback-guided local code structure. Finally, Dolphin automatically analyzes the results of each idea and feeds the results back to the next round of idea generation. Experiments are conducted on the benchmark datasets of different topics and results show that Dolphin can generate novel ideas continuously and complete the experiment in a loop. We highlight that Dolphin can automatically propose methods that are comparable to the state-of-the-art in some tasks such as 2D image classification and 3D point classification.
Authors: Naoki Wake, Atsushi Kanehira, Jun Takamatsu, Kazuhiro Sasabuchi, Katsushi Ikeuchi
Abstract: The use of Large Language Models (LLMs) for generating Behavior Trees (BTs) has recently gained attention in the robotics community, yet remains in its early stages of development. In this paper, we propose a novel framework that leverages Vision-Language Models (VLMs) to interactively generate and edit BTs that address visual conditions, enabling context-aware robot operations in visually complex environments. A key feature of our approach lies in the conditional control through self-prompted visual conditions. Specifically, the VLM generates BTs with visual condition nodes, where conditions are expressed as free-form text. Another VLM process integrates the text into its prompt and evaluates the conditions against real-world images during robot execution. We validated our framework in a real-world cafe scenario, demonstrating both its feasibility and limitations.
Authors: Eric Chen, Xi Chen, Arian Maleki, Shirin Jalali
Abstract: Unrolled networks have become prevalent in various computer vision and imaging tasks. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm, defining the loss function, and determining the number of convolutional layers, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train, fine-tune the neural network, and optimize for its performance. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive ablation study to discuss the impact of each of the choices involved in designing unrolled networks and present practical recommendations based on our findings. We anticipate that this study will help scientists and engineers design unrolled networks for their applications and diagnose problems within their networks efficiently.
Authors: Gianfranco Cortes, Xiaoda Qu, Baba C. Vemuri
Abstract: Nonrigid registration is vital to medical image analysis but remains challenging for diffusion MRI (dMRI) due to its high-dimensional, orientation-dependent nature. While classical methods are accurate, they are computationally demanding, and deep neural networks, though efficient, have been underexplored for nonrigid dMRI registration compared to structural imaging. We present a novel, deep learning framework for model-free, nonrigid registration of raw diffusion MRI data that does not require explicit reorientation. Unlike previous methods relying on derived representations such as diffusion tensors or fiber orientation distribution functions, in our approach, we formulate the registration as an equivariant diffeomorphism of position-and-orientation space. Central to our method is an $\mathsf{SE}(3)$-equivariant UNet that generates velocity fields while preserving the geometric properties of a raw dMRI's domain. We introduce a new loss function based on the maximum mean discrepancy in Fourier space, implicitly matching ensemble average propagators across images. Experimental results on Human Connectome Project dMRI data demonstrate competitive performance compared to state-of-the-art approaches, with the added advantage of bypassing the overhead for estimating derived representations. This work establishes a foundation for data-driven, geometry-aware dMRI registration directly in the acquisition space.