Authors: Rohit Saxena, Pasquale Minervini, Frank Keller
Abstract: Generating accurate and concise textual summaries from multimodal documents is challenging, especially when dealing with visually complex content like scientific posters. We introduce PosterSum, a novel benchmark to advance the development of vision-language models that can understand and summarize scientific posters into research paper abstracts. Our dataset contains 16,305 conference posters paired with their corresponding abstracts as summaries. Each poster is provided in image format and presents diverse visual understanding challenges, such as complex layouts, dense text regions, tables, and figures. We benchmark state-of-the-art Multimodal Large Language Models (MLLMs) on PosterSum and demonstrate that they struggle to accurately interpret and summarize scientific posters. We propose Segment & Summarize, a hierarchical method that outperforms current MLLMs on automated metrics, achieving a 3.14% gain in ROUGE-L. This will serve as a starting point for future research on poster summarization.
Authors: Cito Balsells, Beatrice Riviere, David Fuentes
Abstract: We formulate truncated singular value decompositions of entire convolutional neural networks. We demonstrate the computed left and right singular vectors are useful in identifying which images the convolutional neural network is likely to perform poorly on. To create this diagnostic tool, we define two metrics: the Right Projection Ratio and the Left Projection Ratio. The Right (Left) Projection Ratio evaluates the fidelity of the projection of an image (label) onto the computed right (left) singular vectors. We observe that both ratios are able to identify the presence of class imbalance for an image classification problem. Additionally, the Right Projection Ratio, which only requires unlabeled data, is found to be correlated to the model's performance when applied to image segmentation. This suggests the Right Projection Ratio could be a useful metric to estimate how likely the model is to perform well on a sample.
Authors: Lei Chenga, Lihao Guoa, Tianya Zhangb, Tam Bangb, Austin Harrisb, Mustafa Hajijc, Mina Sartipib, Siyang Cao
Abstract: Accurate multi-sensor calibration is essential for deploying robust perception systems in applications such as autonomous driving, robotics, and intelligent transportation. Existing LiDAR-camera calibration methods often rely on manually placed targets, preliminary parameter estimates, or intensive data preprocessing, limiting their scalability and adaptability in real-world settings. In this work, we propose a fully automatic, targetless, and online calibration framework, CalibRefine, which directly processes raw LiDAR point clouds and camera images. Our approach is divided into four stages: (1) a Common Feature Discriminator that trains on automatically detected objects--using relative positions, appearance embeddings, and semantic classes--to generate reliable LiDAR-camera correspondences, (2) a coarse homography-based calibration, (3) an iterative refinement to incrementally improve alignment as additional data frames become available, and (4) an attention-based refinement that addresses non-planar distortions by leveraging a Vision Transformer and cross-attention mechanisms. Through extensive experiments on two urban traffic datasets, we show that CalibRefine delivers high-precision calibration results with minimal human involvement, outperforming state-of-the-art targetless methods and remaining competitive with, or surpassing, manually tuned baselines. Our findings highlight how robust object-level feature matching, together with iterative and self-supervised attention-based adjustments, enables consistent sensor fusion in complex, real-world conditions without requiring ground-truth calibration matrices or elaborate data preprocessing.
Authors: Bingxuan Li, Yiwei Wang, Jiuxiang Gu, Kai-Wei Chang, Nanyun Peng
Abstract: Chart generation aims to generate code to produce charts satisfying the desired visual properties, e.g., texts, layout, color, and type. It has great potential to empower the automatic professional report generation in financial analysis, research presentation, education, and healthcare. In this work, we build a vision-language model (VLM) based multi-agent framework for effective automatic chart generation. Generating high-quality charts requires both strong visual design skills and precise coding capabilities that embed the desired visual properties into code. Such a complex multi-modal reasoning process is difficult for direct prompting of VLMs. To resolve these challenges, we propose METAL, a multi-agent framework that decomposes the task of chart generation into the iterative collaboration among specialized agents. METAL achieves 5.2% improvement in accuracy over the current best result in the chart generation task. The METAL framework exhibits the phenomenon of test-time scaling: its performance increases monotonically as the logarithmic computational budget grows from 512 to 8192 tokens. In addition, we find that separating different modalities during the critique process of METAL boosts the self-correction capability of VLMs in the multimodal context.
Authors: Boyang Deng, Yuzhen Lu
Abstract: Robust weed detection remains a challenging task in precision weeding, requiring not only potent weed detection models but also large-scale, labeled data. However, the labeled data adequate for model training is practically difficult to come by due to the time-consuming, labor-intensive process that requires specialized expertise to recognize plant species. This study introduces semi-supervised object detection (SSOD) methods for leveraging unlabeled data for enhanced weed detection and proposes a new YOLOv8-based SSOD method, i.e., WeedTeacher. An experimental comparison of four SSOD methods, including three existing frameworks (i.e., DenseTeacher, EfficientTeacher, and SmallTeacher) and WeedTeacher, alongside fully supervised baselines, was conducted for weed detection in both in-domain and cross-domain contexts. A new, diverse weed dataset was created as the testbed, comprising a total of 19,931 field images from two differing domains, including 8,435 labeled (basic-domain) images acquired by handholding devices from 2021 to 2023 and 11,496 unlabeled (new-domain) images acquired by a ground-based mobile platform in 2024. The in-domain experiment with models trained using 10% of the labeled, basic-domain images and tested on the remaining 90% of the data, showed that the YOLOv8-basedWeedTeacher achieved the highest accuracy among all four SSOD methods, with an improvement of 2.6% mAP@50 and 3.1% mAP@50:95 over its supervised baseline (i.e., YOLOv8l). In the cross-domain experiment where the unlabeled new-domain data was incorporated, all four SSOD methods, however, resulted in no or limited improvements over their supervised counterparts. Research is needed to address the difficulty of cross-domain data utilization for robust weed detection.
Authors: Jungseok Hong, Sakshi Singh, Junaed Sattar
Abstract: We present an image blending pipeline, \textit{IBURD}, that creates realistic synthetic images to assist in the training of deep detectors for use on underwater autonomous vehicles (AUVs) for marine debris detection tasks. Specifically, IBURD generates both images of underwater debris and their pixel-level annotations, using source images of debris objects, their annotations, and target background images of marine environments. With Poisson editing and style transfer techniques, IBURD is even able to robustly blend transparent objects into arbitrary backgrounds and automatically adjust the style of blended images using the blurriness metric of target background images. These generated images of marine debris in actual underwater backgrounds address the data scarcity and data variety problems faced by deep-learned vision algorithms in challenging underwater conditions, and can enable the use of AUVs for environmental cleanup missions. Both quantitative and robotic evaluations of IBURD demonstrate the efficacy of the proposed approach for robotic detection of marine debris.
Authors: Yu Zhou, Bingxuan Li, Mohan Tang, Xiaomeng Jin, Te-Lin Wu, Kuan-Hao Huang, Heng Ji, Kai-Wei Chang, Nanyun Peng
Abstract: Large multimodal models (LMMs) often struggle to recognize novel concepts, as they rely on pre-trained knowledge and have limited ability to capture subtle visual details. Domain-specific knowledge gaps in training also make them prone to confusing visually similar, commonly misrepresented, or low-resource concepts. To help LMMs better align nuanced visual features with language, improving their ability to recognize and reason about novel or rare concepts, we propose a Contrastive visual Data Augmentation (CoDA) strategy. CoDA extracts key contrastive textual and visual features of target concepts against the known concepts they are misrecognized as, and then uses multimodal generative models to produce targeted synthetic data. Automatic filtering of extracted features and augmented images is implemented to guarantee their quality, as verified by human annotators. We show the effectiveness and efficiency of CoDA on low-resource concept and diverse scene recognition datasets including INaturalist and SUN. We additionally collect NovelSpecies, a benchmark dataset consisting of newly discovered animal species that are guaranteed to be unseen by LMMs. LLaVA-1.6 1-shot updating results on these three datasets show CoDA significantly improves SOTA visual data augmentation strategies by 12.3% (NovelSpecies), 5.1% (SUN), and 6.0% (iNat) absolute gains in accuracy.
Authors: Sushmita Sarker, Prithul Sarker, George Bebis, Alireza Tavakkoli
Abstract: The remarkable success of deep learning in recent years has prompted applications in medical image classification and diagnosis tasks. While classification models have demonstrated robustness in classifying simpler datasets like MNIST or natural images such as ImageNet, this resilience is not consistently observed in complex medical image datasets where data is more scarce and lacks diversity. Moreover, previous findings on natural image datasets have indicated a potential trade-off between data likelihood and classification accuracy. In this study, we explore the use of score-based generative models as classifiers for medical images, specifically mammographic images. Our findings suggest that our proposed generative classifier model not only achieves superior classification results on CBIS-DDSM, INbreast and Vin-Dr Mammo datasets, but also introduces a novel approach to image classification in a broader context. Our code is publicly available at https://github.com/sushmitasarker/sgc_for_medical_image_classification
URLs: https://github.com/sushmitasarker/sgc_for_medical_image_classification
Authors: Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari
Abstract: We introduce a gradient-based approach for learning task graphs from procedural activities, improving over hand-crafted methods. Our method directly optimizes edge weights via maximum likelihood, enabling integration into neural architectures. We validate our approach on CaptainCook4D, EgoPER, and EgoProceL, achieving +14.5%, +10.2%, and +13.6% F1-score improvements. Our feature-based approach for predicting task graphs from textual/video embeddings demonstrates emerging video understanding abilities. We also achieved top performance on the procedure understanding benchmark on Ego-Exo4D and significantly improved online mistake detection (+19.8% on Assembly101-O, +6.4% on EPIC-Tent-O). Code: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.
URLs: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.
Authors: Cristina Almagro-P\'erez, Andrew H. Song, Luca Weishaupt, Ahrong Kim, Guillaume Jaume, Drew F. K. Williamson, Konstantin Hemker, Ming Y. Lu, Kritika Singh, Bowen Chen, Long Phi Le, Alexander S. Baras, Sizun Jiang, Ali Bashashati, Jonathan T. C. Liu, Faisal Mahmood
Abstract: A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology-transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://vortex-demo.github.io/
Authors: Juan Ni\~no, Luis Guayac\'an, Santiago G\'omez, Fabio Mart\'inez
Abstract: Oculomotor alterations constitute a promising biomarker to detect and characterize Parkinson's disease (PD), even in prodromal stages. Currently, only global and simplified eye movement trajectories are employed to approximate the complex and hidden kinematic relationships of the oculomotor function. Recent advances on machine learning and video analysis have encouraged novel characterizations of eye movement patterns to quantify PD. These schemes enable the identification of spatiotemporal segments primarily associated with PD. However, they rely on discriminative models that require large training datasets and depend on balanced class distributions. This work introduces a novel video analysis scheme to quantify Parkinsonian eye fixation patterns with an anomaly detection framework. Contrary to classical deep discriminative schemes that learn differences among labeled classes, the proposed approach is focused on one-class learning, avoiding the necessity of a significant amount of data. The proposed approach focuses only on Parkinson's representation, considering any other class sample as an anomaly of the distribution. This approach was evaluated for an ocular fixation task, in a total of 13 control subjects and 13 patients on different stages of the disease. The proposed digital biomarker achieved an average sensitivity and specificity of 0.97 and 0.63, respectively, yielding an AUC-ROC of 0.95. A statistical test shows significant differences (p < 0.05) among predicted classes, evidencing a discrimination between patients and control subjects.
Authors: Xin Tong, Shi Peng, Baojie Tian, Yufei Guo, Xuhui Huang, Zhe Ma
Abstract: Classical Transformer-based line segment detection methods have delivered impressive results. However, we observe that some accurately detected line segments are assigned low confidence scores during prediction, causing them to be ranked lower and potentially suppressed. Additionally, these models often require prolonged training periods to achieve strong performance, largely due to the necessity of bipartite matching. In this paper, we introduce RANK-LETR, a novel Transformer-based line segment detection method. Our approach leverages learnable geometric information to refine the ranking of predicted line segments by enhancing the confidence scores of high-quality predictions in a posterior verification step. We also propose a new line segment proposal method, wherein the feature point nearest to the centroid of the line segment directly predicts the location, significantly improving training efficiency and stability. Moreover, we introduce a line segment ranking loss to stabilize rankings during training, thereby enhancing the generalization capability of the model. Experimental results demonstrate that our method outperforms other Transformer-based and CNN-based approaches in prediction accuracy while requiring fewer training epochs than previous Transformer-based models.
Authors: Xiaomeng Jin, Hyeonjeong Ha, Jeonghwan Kim, Jiateng Liu, Zhenhailong Wang, Khanh Duy Nguyen, Ansel Blume, Nanyun Peng, Kai-wei Chang, Heng Ji
Abstract: Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of given design concepts, functional coherence--the integration of multiple affordances into a single coherent concept--remains largely overlooked. In this paper, we introduce SYNTHIA, a framework for generating novel, functionally coherent designs based on desired affordances. Our approach leverages a hierarchical concept ontology that decomposes concepts into parts and affordances, serving as a crucial building block for functionally coherent design. We also develop a curriculum learning scheme based on our ontology that contrastively fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. To elaborate, we (i) gradually increase affordance distance, guiding models from basic concept-affordance association to complex affordance compositions that integrate parts of distinct affordances into a single, coherent form, and (ii) enforce visual novelty by employing contrastive objectives to push learned representations away from existing concepts. Experimental results show that SYNTHIA outperforms state-of-the-art T2I models, demonstrating absolute gains of 25.1% and 14.7% for novelty and functional coherence in human evaluation, respectively.
Authors: Yisheng He, Xiaodong Gu, Xiaodan Ye, Chao Xu, Zhengyi Zhao, Yuan Dong, Weihao Yuan, Zilong Dong, Liefeng Bo
Abstract: We present LAM, an innovative Large Avatar Model for animatable Gaussian head reconstruction from a single image. Unlike previous methods that require extensive training on captured video sequences or rely on auxiliary neural networks for animation and rendering during inference, our approach generates Gaussian heads that are immediately animatable and renderable. Specifically, LAM creates an animatable Gaussian head in a single forward pass, enabling reenactment and rendering without additional networks or post-processing steps. This capability allows for seamless integration into existing rendering pipelines, ensuring real-time animation and rendering across a wide range of platforms, including mobile phones. The centerpiece of our framework is the canonical Gaussian attributes generator, which utilizes FLAME canonical points as queries. These points interact with multi-scale image features through a Transformer to accurately predict Gaussian attributes in the canonical space. The reconstructed canonical Gaussian avatar can then be animated utilizing standard linear blend skinning (LBS) with corrective blendshapes as the FLAME model did and rendered in real-time on various platforms. Our experimental results demonstrate that LAM outperforms state-of-the-art methods on existing benchmarks.
Authors: Peng Zhang, Xin Li, Xin Lin, Liang He
Abstract: Recent advancements in 3D multi-object tracking (3D MOT) have predominantly relied on tracking-by-detection pipelines. However, these approaches often neglect potential enhancements in 3D detection processes, leading to high false positives (FP), missed detections (FN), and identity switches (IDS), particularly in challenging scenarios such as crowded scenes, small-object configurations, and adverse weather conditions. Furthermore, limitations in data preprocessing, association mechanisms, motion modeling, and life-cycle management hinder overall tracking robustness. To address these issues, we present Easy-Poly, a real-time, filter-based 3D MOT framework for multiple object categories. Our contributions include: (1) An Augmented Proposal Generator utilizing multi-modal data augmentation and refined SpConv operations, significantly improving mAP and NDS on nuScenes; (2) A Dynamic Track-Oriented (DTO) data association algorithm that effectively manages uncertainties and occlusions through optimal assignment and multiple hypothesis handling; (3) A Dynamic Motion Modeling (DMM) incorporating a confidence-weighted Kalman filter and adaptive noise covariances, enhancing MOTA and AMOTA in challenging conditions; and (4) An extended life-cycle management system with adjustive thresholds to reduce ID switches and false terminations. Experimental results show that Easy-Poly outperforms state-of-the-art methods such as Poly-MOT and Fast-Poly, achieving notable gains in mAP (e.g., from 63.30% to 64.96% with LargeKernel3D) and AMOTA (e.g., from 73.1% to 74.5%), while also running in real-time. These findings highlight Easy-Poly's adaptability and robustness in diverse scenarios, making it a compelling choice for autonomous driving and related 3D MOT applications. The source code of this paper will be published upon acceptance.
Authors: Basma Nasir, Tehseen Zia, Muhammad Nawaz, Catarina Moreira
Abstract: Medical image annotation is essential for diagnosing diseases, yet manual annotation is time-consuming, costly, and prone to variability among experts. To address these challenges, we propose an automated explainable annotation system that integrates ensemble learning, visual explainability, and uncertainty quantification. Our approach combines three pre-trained deep learning models - ResNet50, EfficientNet, and DenseNet - enhanced with XGrad-CAM for visual explanations and Monte Carlo Dropout for uncertainty quantification. This ensemble mimics the consensus of multiple radiologists by intersecting saliency maps from models that agree on the diagnosis while uncertain predictions are flagged for human review. We evaluated our system using the TBX11K medical imaging dataset and a Fire segmentation dataset, demonstrating its robustness across different domains. Experimental results show that our method outperforms baseline models, achieving 93.04% accuracy on TBX11K and 96.4% accuracy on the Fire dataset. Moreover, our model produces precise pixel-level annotations despite being trained with only image-level labels, achieving Intersection over Union IoU scores of 36.07% and 64.7%, respectively. By enhancing the accuracy and interpretability of image annotations, our approach offers a reliable and transparent solution for medical diagnostics and other image analysis tasks.
Authors: Istiaq Ahmed Fahad, Abdullah Ibne Hanif Arean, Nazmus Sakib Ahmed, Mahmudul Hasan
Abstract: Automatic Vehicle Detection (AVD) in diverse driving environments presents unique challenges due to varying lighting conditions, road types, and vehicle types. Traditional methods, such as YOLO and Faster R-CNN, often struggle to cope with these complexities. As computer vision evolves, combining Convolutional Neural Networks (CNNs) with Transformer-based approaches offers promising opportunities for improving detection accuracy and efficiency. This study is the first to experiment with Detection Transformer (DETR) for automatic vehicle detection in complex and varied settings. We employ a Collaborative Hybrid Assignments Training scheme, Co-DETR, to enhance feature learning and attention mechanisms in DETR. By leveraging versatile label assignment strategies and introducing multiple parallel auxiliary heads, we provide more effective supervision during training and extract positive coordinates to boost training efficiency. Through extensive experiments on DETR variants and YOLO models, conducted using the BadODD dataset, we demonstrate the advantages of our approach. Our method achieves superior results, and improved accuracy in diverse conditions, making it practical for real-world deployment. This work significantly advances autonomous navigation technology and opens new research avenues in object detection for autonomous vehicles. By integrating the strengths of CNNs and Transformers, we highlight the potential of DETR for robust and efficient vehicle detection in challenging driving environments.
Authors: Adnan Shaout, Jiho Han
Abstract: The vascular structure in retinal images plays a crucial role in ophthalmic diagnostics, and its accuracies are directly influenced by the quality of the retinal image. Contrast enhancement is one of the crucial steps in any segmentation algorithm - the more so since the retinal images are related to medical diagnosis. Contrast enhancement is a vital step that not only intensifies the darkness of the blood vessels but also prevents minor capillaries from being disregarded during the process. This paper proposes a novel model that utilizes the linear blending of Fuzzy Contrast Enhancement (FCE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the retinal image for retinal vascular structure segmentation. The scheme is tested using the Digital Retinal Images for Vessel Extraction (DRIVE) dataset. The assertion was then evaluated through performance comparison among other methodologies which are Gray-scaling, Histogram Equalization (HE), FCE, and CLAHE. It was evident in this paper that the combination of FCE and CLAHE methods showed major improvement. Both FCE and CLAHE methods dominating with 88% as better enhancement methods proved that preprocessing through fuzzy logic is effective.
Authors: Liting Wen, Zimo Yang, Xianlin Zhang, Chi Ding, Yue Zhang, Mingdao Wang, Xueming Li
Abstract: 3D face reconstruction from a single sketch is a critical yet underexplored task with significant practical applications. The primary challenges stem from the substantial modality gap between 2D sketches and 3D facial structures, including: (1) accurately extracting facial keypoints from 2D sketches; (2) preserving diverse facial expressions and fine-grained texture details; and (3) training a high-performing model with limited data. In this paper, we propose Sketch-1-to-3, a novel framework for realistic 3D face reconstruction from a single sketch, to address these challenges. Specifically, we first introduce the Geometric Contour and Texture Detail (GCTD) module, which enhances the extraction of geometric contours and texture details from facial sketches. Additionally, we design a deep learning architecture with a domain adaptation module and a tailored loss function to align sketches with the 3D facial space, enabling high-fidelity expression and texture reconstruction. To facilitate evaluation and further research, we construct SketchFaces, a real hand-drawn facial sketch dataset, and Syn-SketchFaces, a synthetic facial sketch dataset. Extensive experiments demonstrate that Sketch-1-to-3 achieves state-of-the-art performance in sketch-based 3D face reconstruction.
Authors: Haoyuan Li, Yanpeng Zhou, Tao Tang, Jifei Song, Yihan Zeng, Michael Kampffmeyer, Hang Xu, Xiaodan Liang
Abstract: Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images. To tackle this issue, we propose UniGS, integrating 3D Gaussian Splatting (3DGS) into multi-modal pre-training to enhance the 3D representation. We first rely on the 3DGS representation to model the 3D world as a collection of 3D Gaussians with color and opacity, incorporating all the information of the 3D scene while establishing a strong connection with 2D images. Then, to achieve Language-Image-3D pertaining, UniGS starts with a pre-trained vision-language model to establish a shared visual and textual space through extensive real-world image-text pairs. Subsequently, UniGS employs a 3D encoder to align the optimized 3DGS with the Language-Image representations to learn unified multi-modal representations. To facilitate the extraction of global explicit 3D features by the 3D encoder and achieve better cross-modal alignment, we additionally introduce a novel Gaussian-Aware Guidance module that guides the learning of fine-grained representations of the 3D domain. Through extensive experiments across the Objaverse, ABO, MVImgNet and SUN RGBD datasets with zero-shot classification, text-driven retrieval and open-world understanding tasks, we demonstrate the effectiveness of UniGS in learning a more general and stronger aligned multi-modal representation. Specifically, UniGS achieves leading results across different 3D tasks with remarkable improvements over previous SOTA, Uni3D, including on zero-shot classification (+9.36%), text-driven retrieval (+4.3%) and open-world understanding (+7.92%).
Authors: Peipei Yuan, Zijing Xie, Shuo Ye, Hong Chen, Yulong Wang
Abstract: Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and emphasizing the localization of synthetic regions, while neglecting the interference caused by image size and style on model learning. Our goal is to reach a fundamental conclusion: Is the image real or generated? To this end, we propose a diffusion model-based generative image detection framework termed Hierarchical Retrospection Refinement~(HRR). It designs a multi-scale style retrospection module that encourages the model to generate detailed and realistic multi-scale representations, while alleviating the learning biases introduced by dataset styles and generative models. Additionally, based on the principle of correntropy sparse additive machine, a feature refinement module is designed to reduce the impact of redundant features on learning and capture the intrinsic structure and patterns of the data, thereby improving the model's generalization ability. Extensive experiments demonstrate the HRR framework consistently delivers significant performance improvements, outperforming state-of-the-art methods in generated image detection task.
Authors: Zhiyu Yin, Kehai Chen, Xuefeng Bai, Ruili Jiang, Juntao Li, Hongdong Li, Jin Liu, Yang Xiang, Jun Yu, Min Zhang
Abstract: Video generation, by leveraging a dynamic visual generation method, pushes the boundaries of Artificial Intelligence Generated Content (AIGC). Video generation presents unique challenges beyond static image generation, requiring both high-quality individual frames and temporal coherence to maintain consistency across the spatiotemporal sequence. Recent works have aimed at addressing the spatiotemporal consistency issue in video generation, while few literature review has been organized from this perspective. This gap hinders a deeper understanding of the underlying mechanisms for high-quality video generation. In this survey, we systematically review the recent advances in video generation, covering five key aspects: foundation models, information representations, generation schemes, post-processing techniques, and evaluation metrics. We particularly focus on their contributions to maintaining spatiotemporal consistency. Finally, we discuss the future directions and challenges in this field, hoping to inspire further efforts to advance the development of video generation.
Authors: Rong Liu, Junye Liang, Jiaqi Yang, Jiang He, Peng Zhu
Abstract: Due to the difficulty of obtaining labeled data for hyperspectral images (HSIs), cross-scene classification has emerged as a widely adopted approach in the remote sensing community. It involves training a model using labeled data from a source domain (SD) and unlabeled data from a target domain (TD), followed by inferencing on the TD. However, variations in the reflectance spectrum of the same object between the SD and the TD, as well as differences in the feature distribution of the same land cover class, pose significant challenges to the performance of cross-scene classification. To address this issue, we propose a dual classification head self-training network (DHSNet). This method aligns class-wise features across domains, ensuring that the trained classifier can accurately classify TD data of different classes. We introduce a dual classification head self-training strategy for the first time in the cross-scene HSI classification field. The proposed approach mitigates domain gap while preventing the accumulation of incorrect pseudo-labels in the model. Additionally, we incorporate a novel central feature attention mechanism to enhance the model's capacity to learn scene-invariant features across domains. Experimental results on three cross-scene HSI datasets demonstrate that the proposed DHSNET significantly outperforms other state-of-the-art approaches. The code for DHSNet will be available at https://github.com/liurongwhm.
Authors: Matteo Contini, Victor Illien, Julien Barde, Sylvain Poulain, Serge Bernard, Alexis Joly, Sylvain Bonhommeau
Abstract: Drone-based remote sensing combined with AI-driven methodologies has shown great potential for accurate mapping and monitoring of coral reef ecosystems. This study presents a novel multi-scale approach to coral reef monitoring, integrating fine-scale underwater imagery with medium-scale aerial imagery. Underwater images are captured using an Autonomous Surface Vehicle (ASV), while aerial images are acquired with an aerial drone. A transformer-based deep-learning model is trained on underwater images to detect the presence of 31 classes covering various coral morphotypes, associated fauna, and habitats. These predictions serve as annotations for training a second model applied to aerial images. The transfer of information across scales is achieved through a weighted footprint method that accounts for partial overlaps between underwater image footprints and aerial image tiles. The results show that the multi-scale methodology successfully extends fine-scale classification to larger reef areas, achieving a high degree of accuracy in predicting coral morphotypes and associated habitats. The method showed a strong alignment between underwater-derived annotations and ground truth data, reflected by an AUC (Area Under the Curve) score of 0.9251. This shows that the integration of underwater and aerial imagery, supported by deep-learning models, can facilitate scalable and accurate reef assessments. This study demonstrates the potential of combining multi-scale imaging and AI to facilitate the monitoring and conservation of coral reefs. Our approach leverages the strengths of underwater and aerial imagery, ensuring the precision of fine-scale analysis while extending it to cover a broader reef area.
Authors: Syed Jubayer Jaman, Md. Zahurul Haque, Md Robiul Islam, Usama Abdun Noor
Abstract: Currency recognition plays a vital role in banking, commerce, and assistive technology for visually impaired individuals. Traditional methods, such as manual verification and optical scanning, often suffer from limitations in accuracy and efficiency. This study introduces an advanced currency recognition system utilizing Convolutional Neural Networks (CNNs) to accurately classify Bangladeshi banknotes. A dataset comprising 50,334 images was collected, preprocessed, and used to train a CNN model optimized for high performance classification. The trained model achieved an accuracy of 98.5%, surpassing conventional image based currency recognition approaches. To enable real time and offline functionality, the model was converted into TensorFlow Lite format and integrated into an Android mobile application. The results highlight the effectiveness of deep learning in currency recognition, providing a fast, secure, and accessible solution that enhances financial transactions and assistive technologies.
Authors: Mingyuan Sun, Zheng Fang, Jiaxu Wang, Junjie Jiang, Delei Kong, Chenming Hu, Yuetong Fang, Renjing Xu
Abstract: The increasing complexity and parameter count of Convolutional Neural Networks (CNNs) and Transformers pose challenges in terms of computational efficiency and resource demands. Pruning has been identified as an effective strategy to address these challenges by removing redundant elements such as neurons, channels, or connections, thereby enhancing computational efficiency without heavily compromising performance. This paper builds on the foundational work of Optimal Brain Damage (OBD) by advancing the methodology of parameter importance estimation using the Hessian matrix. Unlike previous approaches that rely on approximations, we introduce Optimal Brain Apoptosis (OBA), a novel pruning method that calculates the Hessian-vector product value directly for each parameter. By decomposing the Hessian matrix across network layers and identifying conditions under which inter-layer Hessian submatrices are non-zero, we propose a highly efficient technique for computing the second-order Taylor expansion of parameters. This approach allows for a more precise pruning process, particularly in the context of CNNs and Transformers, as validated in our experiments including VGG19, ResNet32, ResNet50, and ViT-B/16 on CIFAR10, CIFAR100 and Imagenet datasets. Our code is available at https://github.com/NEU-REAL/OBA.
Authors: Jia Yu, Yan Zhu, Peiyao Fu, Tianyi Chen, Junbo Huang, Quanlin Li, Pinghong Zhou, Zhihua Wang, Fei Wu, Shuo Wang, Xian Yang
Abstract: Colorectal cancer (CRC) is a significant global health concern, and early detection through screening plays a critical role in reducing mortality. While deep learning models have shown promise in improving polyp detection, classification, and segmentation, their generalization across diverse clinical environments, particularly with out-of-distribution (OOD) data, remains a challenge. Multi-center datasets like PolypGen have been developed to address these issues, but their collection is costly and time-consuming. Traditional data augmentation techniques provide limited variability, failing to capture the complexity of medical images. Diffusion models have emerged as a promising solution for generating synthetic polyp images, but the image generation process in current models mainly relies on segmentation masks as the condition, limiting their ability to capture the full clinical context. To overcome these limitations, we propose a Progressive Spectrum Diffusion Model (PSDM) that integrates diverse clinical annotations-such as segmentation masks, bounding boxes, and colonoscopy reports-by transforming them into compositional prompts. These prompts are organized into coarse and fine components, allowing the model to capture both broad spatial structures and fine details, generating clinically accurate synthetic images. By augmenting training data with PSDM-generated samples, our model significantly improves polyp detection, classification, and segmentation. For instance, on the PolypGen dataset, PSDM increases the F1 score by 2.12% and the mean average precision by 3.09%, demonstrating superior performance in OOD scenarios and enhanced generalization.
Authors: Jin Hou, Hao Tang
Abstract: The normal operation of power equipment plays a critical role in the power system, making anomaly detection for power equipment highly significant. This paper proposes an improved YOLOv7x-based anomaly detection algorithm for power equipment. First, the ACmix convolutional mixed attention mechanism module is introduced to effectively suppress background noise and irrelevant features, thereby enhancing the network's feature extraction capability. Second, the Biformer attention mechanism is added to the network to strengthen the focus on key features, improving the network's ability to flexibly recognize feature images. Finally, to more comprehensively evaluate the relationship between predicted and ground truth bounding boxes, the original loss function is replaced with the MPDIoU function, addressing the issue of mismatched predicted bounding boxes. The improved algorithm enhances detection accuracy, achieving a mAP@0.5/% of 93.5% for all target categories, a precision of 97.1%, and a recall of 97%.
Authors: Derek Ho, Haotian Feng
Abstract: The widespread distribution of microplastics (MPs) in the environment presents significant challenges for their detection and identification. Fluorescence imaging has emerged as a promising technique for enhancing plastic particle detectability and enabling accurate classification based on fluorescence behavior. However, conventional segmentation techniques face limitations, including poor signal-to-noise ratio, inconsistent illumination, thresholding difficulties, and false positives from natural organic matter (NOM). To address these challenges, this study introduces the Fluorescence Imaging Microplastic Analysis Platform (FIMAP), a retrofitted multispectral camera with four optical filters and five excitation wavelengths. FIMAP enables comprehensive characterization of the fluorescence behavior of ten Nile Red-stained MPs: HDPE, LDPE, PP, PS, EPS, ABS, PVC, PC, PET, and PA, while effectively excluding NOM. Using K-means clustering for robust segmentation (Intersection over Union = 0.877) and a 20-dimensional color coordinate multivariate nearest neighbor approach for MP classification (>3.14 mm), FIMAP achieves 90% precision, 90% accuracy, 100% recall, and an F1 score of 94.7%. Only PS was occasionally misclassified as EPS. For smaller MPs (35-104 microns), classification accuracy declined, likely due to reduced stain sorption, fewer detectable pixels, and camera instability. Integrating FIMAP with higher-magnification instruments, such as a microscope, may enhance MP identification. This study presents FIMAP as an automated, high-throughput framework for detecting and classifying MPs across large environmental sample volumes.
Authors: Shunkun Liang, Dongcai Tan, Banglei Guan, Zhang Li, Guangcheng Dai, Nianpeng Pan, Liang Shen, Yang Shang, Qifeng Yu
Abstract: Visual navigation devices require precise calibration to achieve high-precision localization and navigation, which includes camera and attitude calibration. To address the limitations of time-consuming camera calibration and complex attitude adjustment processes, this study presents a collimator-based calibration method and system. Based on the optical characteristics of the collimator, a single-image camera calibration algorithm is introduced. In addition, integrated with the precision adjustment mechanism of the calibration frame, a rotation transfer model between coordinate systems enables efficient attitude calibration. Experimental results demonstrate that the proposed method achieves accuracy and stability comparable to traditional multi-image calibration techniques. Specifically, the re-projection errors are less than 0.1463 pixels, and average attitude angle errors are less than 0.0586 degrees with a standard deviation less than 0.0257 degrees, demonstrating high precision and robustness.
Authors: Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie, Feng Zhao
Abstract: Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning. Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness. To address these challenges, we propose ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents. ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multi-modal retrieval. To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains. Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach. Notably, ViDoRAG outperforms existing methods by over 10% on the competitive ViDoSeek benchmark.
Authors: Yunpeng Gao, Chenhui Li, Zhongrui You, Junli Liu, Zhen Li, Pengan Chen, Qizhi Chen, Zhonghan Tang, Liansheng Wang, Penghui Yang, Yiwen Tang, Yuhang Tang, Shuai Liang, Songyi Zhu, Ziqin Xiong, Yifei Su, Xinyi Ye, Jianan Li, Yan Ding, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li
Abstract: Vision-Language Navigation (VLN) aims to guide agents through an environment by leveraging both language instructions and visual cues, playing a pivotal role in embodied AI. Indoor VLN has been extensively studied, whereas outdoor aerial VLN remains underexplored. The potential reason is that outdoor aerial view encompasses vast areas, making data collection more challenging, which results in a lack of benchmarks. To address this problem, we propose OpenFly, a platform comprising a versatile toolchain and large-scale benchmark for aerial VLN. Firstly, we develop a highly automated toolchain for data collection, enabling automatic point cloud acquisition, scene semantic segmentation, flight trajectory creation, and instruction generation. Secondly, based on the toolchain, we construct a large-scale aerial VLN dataset with 100k trajectories, covering diverse heights and lengths across 18 scenes. The corresponding visual data are generated using various rendering engines and advanced techniques, including Unreal Engine, GTA V, Google Earth, and 3D Gaussian Splatting (3D GS). All data exhibit high visual quality. Particularly, 3D GS supports real-to-sim rendering, further enhancing the realism of the dataset. Thirdly, we propose OpenFly-Agent, a keyframe-aware VLN model, which takes language instructions, current observations, and historical keyframes as input, and outputs flight actions directly. Extensive analyses and experiments are conducted, showcasing the superiority of our OpenFly platform and OpenFly-Agent. The toolchain, dataset, and codes will be open-sourced.
Authors: Pei Liu (The Hong Kong University of Science and Technology), Haipeng Liu (Li Auto Inc), Haichao Liu (The Hong Kong University of Science and Technology), Xin Liu (The Hong Kong University of Science and Technology), Jinxin Ni (Xiamen University), Jun Ma (The Hong Kong University of Science and Technology, The Hong Kong University of Science and Technology)
Abstract: Human drivers adeptly navigate complex scenarios by utilizing rich attentional semantics, but the current autonomous systems struggle to replicate this ability, as they often lose critical semantic information when converting 2D observations into 3D space. In this sense, it hinders their effective deployment in dynamic and complex environments. Leveraging the superior scene understanding and reasoning abilities of Vision-Language Models (VLMs), we propose VLM-E2E, a novel framework that uses the VLMs to enhance training by providing attentional cues. Our method integrates textual representations into Bird's-Eye-View (BEV) features for semantic supervision, which enables the model to learn richer feature representations that explicitly capture the driver's attentional semantics. By focusing on attentional semantics, VLM-E2E better aligns with human-like driving behavior, which is critical for navigating dynamic and complex environments. Furthermore, we introduce a BEV-Text learnable weighted fusion strategy to address the issue of modality importance imbalance in fusing multimodal information. This approach dynamically balances the contributions of BEV and text features, ensuring that the complementary information from visual and textual modality is effectively utilized. By explicitly addressing the imbalance in multimodal fusion, our method facilitates a more holistic and robust representation of driving environments. We evaluate VLM-E2E on the nuScenes dataset and demonstrate its superiority over state-of-the-art approaches, showcasing significant improvements in performance.
Authors: Huimin Yan, Xian Yang, Liang Bai, Jiye Liang
Abstract: Local alignment between medical images and text is essential for accurate diagnosis, though it remains challenging due to the absence of natural local pairings and the limitations of rigid region recognition methods. Traditional approaches rely on hard boundaries, which introduce uncertainty, whereas medical imaging demands flexible soft region recognition to handle irregular structures. To overcome these challenges, we propose the Progressive Local Alignment Network (PLAN), which designs a novel contrastive learning-based approach for local alignment to establish meaningful word-pixel relationships and introduces a progressive learning strategy to iteratively refine these relationships, enhancing alignment precision and robustness. By combining these techniques, PLAN effectively improves soft region recognition while suppressing noise interference. Extensive experiments on multiple medical datasets demonstrate that PLAN surpasses state-of-the-art methods in phrase grounding, image-text retrieval, object detection, and zero-shot classification, setting a new benchmark for medical image-text alignment.
Authors: Carlos V\'elez Garc\'ia, Miguel Cazorla, Jorge Pomares
Abstract: The reliance on large-scale datasets and extensive computational resources has become a major barrier to advancing representation learning in vision, especially in data-scarce domains. In this paper, we address the critical question: Can we escape the big data paradigm in self-supervised representation learning from images? We introduce SCOTT (Sparse Convolutional Tokenizer for Transformers), a shallow tokenization architecture that is compatible with Masked Image Modeling (MIM) tasks. SCOTT injects convolutional inductive biases into Vision Transformers (ViTs), enhancing their efficacy in small-scale data regimes. Alongside, we propose to train on a Joint-Embedding Predictive Architecture within a MIM framework (MIM-JEPA), operating in latent representation space to capture more semantic features. Our approach enables ViTs to be trained from scratch on datasets orders of magnitude smaller than traditionally required --without relying on massive external datasets for pretraining. We validate our method on three small-size, standard-resoultion, fine-grained datasets: Oxford Flowers-102, Oxford IIIT Pets-37, and ImageNet-100. Despite the challenges of limited data and high intra-class similarity, frozen SCOTT models pretrained with MIM-JEPA significantly outperform fully supervised methods and achieve competitive results with SOTA approaches that rely on large-scale pretraining, complex image augmentations and bigger model sizes. By demonstrating that robust off-the-shelf representations can be learned with limited data, compute, and model sizes, our work paves the way for computer applications in resource constrained environments such as medical imaging or robotics. Our findings challenge the prevailing notion that vast amounts of data are indispensable for effective representation learning in vision, offering a new pathway toward more accessible and inclusive advancements in the field.
Authors: Ankita Raj, Deepankar Varma, Chetan Arora
Abstract: Foundation models (FMs) for computer vision learn rich and robust representations, enabling their adaptation to task/domain-specific deployments with little to no fine-tuning. However, we posit that the very same strength can make applications based on FMs vulnerable to model stealing attacks. Through empirical analysis, we reveal that models fine-tuned from FMs harbor heightened susceptibility to model stealing, compared to conventional vision architectures like ResNets. We hypothesize that this behavior is due to the comprehensive encoding of visual patterns and features learned by FMs during pre-training, which are accessible to both the attacker and the victim. We report that an attacker is able to obtain 94.28% agreement (matched predictions with victim) for a Vision Transformer based victim model (ViT-L/16) trained on CIFAR-10 dataset, compared to only 73.20% agreement for a ResNet-18 victim, when using ViT-L/16 as the thief model. We arguably show, for the first time, that utilizing FMs for downstream tasks may not be the best choice for deployment in commercial APIs due to their susceptibility to model theft. We thereby alert model owners towards the associated security risks, and highlight the need for robust security measures to safeguard such models against theft. Code is available at https://github.com/rajankita/foundation_model_stealing.
URLs: https://github.com/rajankita/foundation_model_stealing.
Authors: Zhenyu Wang, Heng Song
Abstract: The recognition of art styles and authors is crucial in areas like cultural heritage protection, art market analysis, and historical research. With the advancement of deep learning, Convolutional Neural Networks (CNNs) and Transformer models have become key tools for image classification. While CNNs excel in local feature extraction, they struggle with global context, and Transformers are strong in capturing global dependencies but weak in fine-grained local details. To address these challenges, this paper proposes a fusion model combining CNNs and Transformers for art style and author recognition. The model first extracts local features using CNNs, then captures global context with a Transformer, followed by a feature fusion mechanism to enhance classification accuracy. Experiments on Chinese and oil painting datasets show the fusion model outperforms individual CNN and Transformer models, improving classification accuracy by 9.7% and 7.1%, respectively, and increasing F1 scores by 0.06 and 0.05. The results demonstrate the model's effectiveness and potential for future improvements, such as multimodal integration and architecture optimization.
Authors: Shengtian Mian, Ya Wang, Nannan Gu, Yuping Wang, Xiaoqing Li
Abstract: Windowed attention mechanisms were introduced to mitigate the issue of excessive computation inherent in global attention mechanisms. However, In this paper, we present FwNet-ECA, a novel method that utilizes Fourier transforms paired with learnable weight matrices to enhance the spectral features of images. This strategy facilitates inter-window connectivity, thereby maximizing the receptive field. Additionally, we incorporate the Efficient Channel Attention (ECA) module to improve communication between different channels. Instead of relying on physically shifted windows, our approach leverages frequency domain enhancement to implicitly bridge information across spatial regions. We validate our model on the iCartoonFace dataset and conduct downstream tasks on ImageNet, demonstrating that our model achieves lower parameter counts and computational overheads compared to shifted window approaches, while maintaining competitive accuracy. This work offers a more efficient and effective alternative for leveraging attention mechanisms in visual processing tasks, alleviating the challenges associated with windowed attention models. Code is available at https://github.com/qingxiaoli/FwNet-ECA.
Authors: Cao Yuxuan, Wu Jiayang, Alistair Cheong Liang Chuen, Bryan Shan Guanrong, Theodore Lee Chong Jen, Sherman Chann Zhi Shen
Abstract: Traditional online content moderation systems struggle to classify modern multimodal means of communication, such as memes, a highly nuanced and information-dense medium. This task is especially hard in a culturally diverse society like Singapore, where low-resource languages are used and extensive knowledge on local context is needed to interpret online content. We curate a large collection of 112K memes labeled by GPT-4V for fine-tuning a VLM to classify offensive memes in Singapore context. We show the effectiveness of fine-tuned VLMs on our dataset, and propose a pipeline containing OCR, translation and a 7-billion parameter-class VLM. Our solutions reach 80.62% accuracy and 0.8192 AUROC on a held-out test set, and can greatly aid human in moderating online contents. The dataset, code, and model weights will be open-sourced at https://github.com/aliencaocao/vlm-for-memes-aisg.
Authors: Han Nie, Bin Luo, Jun Liu, Zhitao Fu, Huan Zhou, Shuo Zhang, Weixing Liu
Abstract: The ideal goal of image matching is to achieve stable and efficient performance in unseen domains. However, many existing learning-based optical-SAR image matching methods, despite their effectiveness in specific scenarios, exhibit limited generalization and struggle to adapt to practical applications. Repeatedly training or fine-tuning matching models to address domain differences is not only not elegant enough but also introduces additional computational overhead and data production costs. In recent years, general foundation models have shown great potential for enhancing generalization. However, the disparity in visual domains between natural and remote sensing images poses challenges for their direct application. Therefore, effectively leveraging foundation models to improve the generalization of optical-SAR image matching remains challenge. To address the above challenges, we propose PromptMID, a novel approach that constructs modality-invariant descriptors using text prompts based on land use classification as priors information for optical and SAR image matching. PromptMID extracts multi-scale modality-invariant features by leveraging pre-trained diffusion models and visual foundation models (VFMs), while specially designed feature aggregation modules effectively fuse features across different granularities. Extensive experiments on optical-SAR image datasets from four diverse regions demonstrate that PromptMID outperforms state-of-the-art matching methods, achieving superior results in both seen and unseen domains and exhibiting strong cross-domain generalization capabilities. The source code will be made publicly available https://github.com/HanNieWHU/PromptMID.
Authors: Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Serge Belongie, Lei Li
Abstract: In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. To address these challenges, we propose BayesGenie, an off-the-shelf approach that integrates Large Language Models (LLMs) with Bayesian Optimization to facilitate precise and user-friendly image editing. Our method enables users to modify images through natural language descriptions without manual area marking, while preserving the original image's semantic integrity. Unlike existing techniques that require extensive pre-training or fine-tuning, our approach demonstrates remarkable adaptability across various LLMs through its model-agnostic design. BayesGenie employs an adapted Bayesian optimization strategy to automatically refine the inference process parameters, achieving high-precision image editing with minimal user intervention. Through extensive experiments across diverse scenarios, we demonstrate that our framework significantly outperforms existing methods in both editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4.
Authors: Yuhu Feng, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Abstract: Egocentric video gaze estimation requires models to capture individual gaze patterns while adapting to diverse user data. Our approach leverages a transformer-based architecture, integrating it into a PFL framework where only the most significant parameters, those exhibiting the highest rate of change during training, are selected and frozen for personalization in client models. Through extensive experimentation on the EGTEA Gaze+ and Ego4D datasets, we demonstrate that FedCPF significantly outperforms previously reported federated learning methods, achieving superior recall, precision, and F1-score. These results confirm the effectiveness of our comprehensive parameters freezing strategy in enhancing model personalization, making FedCPF a promising approach for tasks requiring both adaptability and accuracy in federated learning settings.
Authors: Yunfeng Li, Bo Wang, Ye Li
Abstract: Despite great progress in multimodal tracking, these trackers remain too heavy and expensive for resource-constrained devices. To alleviate this problem, we propose LightFC-X, a family of lightweight convolutional RGB-X trackers that explores a unified convolutional architecture for lightweight multimodal tracking. Our core idea is to achieve lightweight cross-modal modeling and joint refinement of the multimodal features and the spatiotemporal appearance features of the target. Specifically, we propose a novel efficient cross-attention module (ECAM) and a novel spatiotemporal template aggregation module (STAM). The ECAM achieves lightweight cross-modal interaction of template-search area integrated feature with only 0.08M parameters. The STAM enhances the model's utilization of temporal information through module fine-tuning paradigm. Comprehensive experiments show that our LightFC-X achieves state-of-the-art performance and the optimal balance between parameters, performance, and speed. For example, LightFC-T-ST outperforms CMD by 4.3% and 5.7% in SR and PR on the LasHeR benchmark, which it achieves 2.6x reduction in parameters and 2.7x speedup. It runs in real-time on the CPU at a speed of 22 fps. The code is available at https://github.com/LiYunfengLYF/LightFC-X.
Authors: Ayushi Dutta, Marco Pesavento, Marco Volino, Adrian Hilton, Armin Mustafa
Abstract: Recent advances in human shape learning have focused on achieving accurate human reconstruction from single-view images. However, in the real world, humans share space with other objects. Reconstructing images with humans and objects is challenging due to the occlusions and lack of 3D spatial awareness, which leads to depth ambiguity in the reconstruction. Existing methods in monocular human-object reconstruction fail to capture intricate details of clothed human bodies and object surfaces due to their template-based nature. In this paper, we jointly reconstruct clothed humans and objects in a spatially coherent manner from single-view images, while addressing human-object occlusions. A novel attention-based neural implicit model is proposed that leverages image pixel alignment to retrieve high-quality details, and incorporates semantic features extracted from the human-object pose to enable 3D spatial awareness. A generative diffusion model is used to handle human-object occlusions. For training and evaluation, we introduce a synthetic dataset with rendered scenes of inter-occluded 3D human scans and diverse objects. Extensive evaluation on both synthetic and real datasets demonstrates the superior quality of proposed human-object reconstructions over competitive methods.
Authors: Filippo Maria Bianchi, Jakob Grahn
Abstract: Snow avalanches present significant risks to human life and infrastructure, particularly in mountainous regions, making effective monitoring crucial. Traditional monitoring methods, such as field observations, are limited by accessibility, weather conditions, and cost. Satellite-borne Synthetic Aperture Radar (SAR) data has become an important tool for large-scale avalanche detection, as it can capture data in all weather conditions and across remote areas. However, traditional processing methods struggle with the complexity and variability of avalanches. This chapter reviews the application of deep learning for detecting and segmenting snow avalanches from SAR data. Early efforts focused on the binary classification of SAR images, while recent advances have enabled pixel-level segmentation, providing greater accuracy and spatial resolution. A case study using Sentinel-1 SAR data demonstrates the effectiveness of deep learning models for avalanche segmentation, achieving superior results over traditional methods. We also present an extension of this work, testing recent state-of-the-art segmentation architectures on an expanded dataset of over 4,500 annotated SAR images. The best-performing model among those tested was applied for large-scale avalanche detection across the whole of Norway, revealing important spatial and temporal patterns over several winter seasons.
Authors: Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng
Abstract: In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts ``a photo of a
Authors: Anh-Khoa Nguyen Vu, Quoc-Truong Truong, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do, Tam V. Nguyen
Abstract: Recent few-shot object detection (FSOD) methods have focused on augmenting synthetic samples for novel classes, show promising results to the rise of diffusion models. However, the diversity of such datasets is often limited in representativeness because they lack awareness of typical and hard samples, especially in the context of foreground and background relationships. To tackle this issue, we propose a Multi-Perspective Data Augmentation (MPAD) framework. In terms of foreground-foreground relationships, we propose in-context learning for object synthesis (ICOS) with bounding box adjustments to enhance the detail and spatial information of synthetic samples. Inspired by the large margin principle, support samples play a vital role in defining class boundaries. Therefore, we design a Harmonic Prompt Aggregation Scheduler (HPAS) to mix prompt embeddings at each time step of the generation process in diffusion models, producing hard novel samples. For foreground-background relationships, we introduce a Background Proposal method (BAP) to sample typical and hard backgrounds. Extensive experiments on multiple FSOD benchmarks demonstrate the effectiveness of our approach. Our framework significantly outperforms traditional methods, achieving an average increase of $17.5\%$ in nAP50 over the baseline on PASCAL VOC. Code is available at https://github.com/nvakhoa/MPAD.
Authors: Tianyang Xu, Jiyong Rao, Xiaoning Song, Zhenhua Feng, Xiao-Jun Wu
Abstract: General mammal pose estimation is an important and challenging task in computer vision, which is essential for understanding mammal behaviour in real-world applications. However, existing studies are at their preliminary research stage, which focus on addressing the problem for only a few specific mammal species. In principle, from specific to general mammal pose estimation, the biggest issue is how to address the huge appearance and pose variances for different species. We argue that given appearance context, instance-level prior and the structural relation among keypoints can serve as complementary evidence. To this end, we propose a Keypoint Interactive Transformer (KIT) to learn instance-level structure-supporting dependencies for general mammal pose estimation. Specifically, our KITPose consists of two coupled components. The first component is to extract keypoint features and generate body part prompts. The features are supervised by a dedicated generalised heatmap regression loss (GHRL). Instead of introducing external visual/text prompts, we devise keypoints clustering to generate body part biases, aligning them with image context to generate corresponding instance-level prompts. Second, we propose a novel interactive transformer that takes feature slices as input tokens without performing spatial splitting. In addition, to enhance the capability of the KIT model, we design an adaptive weight strategy to address the imbalance issue among different keypoints.
Authors: Botao Ye, Sifei Liu, Xueting Li, Marc Pollefeys, Ming-Hsuan Yang
Abstract: Large diffusion models demonstrate remarkable zero-shot capabilities in novel view synthesis from a single image. However, these models often face challenges in maintaining consistency across novel and reference views. A crucial factor leading to this issue is the limited utilization of contextual information from reference views. Specifically, when there is an overlap in the viewing frustum between two views, it is essential to ensure that the corresponding regions maintain consistency in both geometry and appearance. This observation leads to a simple yet effective approach, where we propose to use epipolar geometry to locate and retrieve overlapping information from the input view. This information is then incorporated into the generation of target views, eliminating the need for training or fine-tuning, as the process requires no learnable parameters. Furthermore, to enhance the overall consistency of generated views, we extend the utilization of epipolar attention to a multi-view setting, allowing retrieval of overlapping information from the input view and other target views. Qualitative and quantitative experimental results demonstrate the effectiveness of our method in significantly improving the consistency of synthesized views without the need for any fine-tuning. Moreover, This enhancement also boosts the performance of downstream applications such as 3D reconstruction. The code is available at https://github.com/botaoye/ConsisSyn.
Authors: He Wang, Tianyang Xu, Zhangyong Tang, Xiao-Jun Wu, Josef Kittler
Abstract: Multi-modal tracking is essential in single-object tracking (SOT), as different sensor types contribute unique capabilities to overcome challenges caused by variations in object appearance. However, existing unified RGB-X trackers (X represents depth, event, or thermal modality) either rely on the task-specific training strategy for individual RGB-X image pairs or fail to address the critical importance of modality-adaptive perception in real-world applications. In this work, we propose UASTrack, a unified adaptive selection framework that facilitates both model and parameter unification, as well as adaptive modality discrimination across various multi-modal tracking tasks. To achieve modality-adaptive perception in joint RGB-X pairs, we design a Discriminative Auto-Selector (DAS) capable of identifying modality labels, thereby distinguishing the data distributions of auxiliary modalities. Furthermore, we propose a Task-Customized Optimization Adapter (TCOA) tailored to various modalities in the latent space. This strategy effectively filters noise redundancy and mitigates background interference based on the specific characteristics of each modality. Extensive comparisons conducted on five benchmarks including LasHeR, GTOT, RGBT234, VisEvent, and DepthTrack, covering RGB-T, RGB-E, and RGB-D tracking scenarios, demonstrate our innovative approach achieves comparative performance by introducing only additional training parameters of 1.87M and flops of 1.95G. The code will be available at https://github.com/wanghe/UASTrack.
Authors: Eduardo Aguilar, Bogdan Raducanu, Petia Radeva
Abstract: A crucial requirement for machine learning algorithms is not only to perform well, but also to show robustness and adaptability when encountering novel scenarios. One way to achieve these characteristics is to endow the deep learning models with the ability to detect out-of-distribution (OOD) data, i.e. data that belong to distributions different from the one used during their training. It is even a more complicated situation, when these data usually are multi-label. In this paper, we propose an approach based on evidential deep learning in order to meet these challenges applied to visual recognition problems. More concretely, we designed a CNN architecture that uses a Beta Evidential Neural Network to compute both the likelihood and the predictive uncertainty of the samples. Based on these results, we propose afterwards two new uncertainty-based scores for OOD data detection: (i) OOD - score Max, based on the maximum evidence; and (ii) OOD score - Sum, which considers the evidence from all outputs. Extensive experiments have been carried out to validate the proposed approach using three widely-used datasets: PASCAL-VOC, MS-COCO and NUS-WIDE, demonstrating its outperformance over several State-of-the-Art methods.
Authors: Zhaoyi Liu, Huan Zhang
Abstract: Self-supervised learning (SSL) vision encoders learn high-quality image representations and thus have become a vital part of developing vision modality of large vision language models (LVLMs). Due to the high cost of training such encoders, pre-trained encoders are widely shared and deployed into many LVLMs, which are security-critical or bear societal significance. Under this practical scenario, we reveal a new backdoor threat that significant visual hallucinations can be induced into these LVLMs by merely compromising vision encoders. Because of the sharing and reuse of these encoders, many downstream LVLMs may inherit backdoor behaviors from encoders, leading to widespread backdoors. In this work, we propose BadVision, the first method to exploit this vulnerability in SSL vision encoders for LVLMs with novel trigger optimization and backdoor learning techniques. We evaluate BadVision on two types of SSL encoders and LVLMs across eight benchmarks. We show that BadVision effectively drives the LVLMs to attacker-chosen hallucination with over 99% attack success rate, causing a 77.6% relative visual understanding error while maintaining the stealthiness. SoTA backdoor detection methods cannot detect our attack effectively.
Authors: Pengzhi Li, Pengfei Yu, Zide Liu, Wei He, Xuhao Pan, Xudong Rao, Tao Wei, Wei Chen
Abstract: In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit limitations in multilingual processing, hindering image generation across diverse languages. We address these challenges by leveraging the advanced capabilities of LLMs. Our approach employs a language representation strategy that applies hierarchical caption optimization and human instruction techniques to derive precise semantic information,. Subsequently, we incorporate a lightweight adapter and a cross-modal refiner to facilitate efficient feature alignment and interaction between LLMs and image features. LDGen reduces training time and enables zero-shot multilingual image generation. Experimental results indicate that our method surpasses baseline models in both prompt adherence and image aesthetic quality, while seamlessly supporting multiple languages. Project page: https://zrealli.github.io/LDGen.
Authors: Leonardo Saraceni, Ionut Marian Motoi, Daniele Nardi, Thomas Alessandro Ciarfuglia
Abstract: In precision agriculture, the scarcity of labeled data and significant covariate shifts pose unique challenges for training machine learning models. This scarcity is particularly problematic due to the dynamic nature of the environment and the evolving appearance of agricultural subjects as living things. We propose a novel system for generating realistic synthetic data to address these challenges. Utilizing a vineyard simulator based on the Unity engine, our system employs a cut-and-paste technique with geometrical consistency considerations to produce accurate photo-realistic images and labels from synthetic environments to train detection algorithms. This approach generates diverse data samples across various viewpoints and lighting conditions. We demonstrate considerable performance improvements in training a state-of-the-art detector by applying our method to table grapes cultivation. The combination of techniques can be easily automated, an increasingly important consideration for adoption in agricultural practice.
Authors: Yifan Pu, Yiming Zhao, Zhicong Tang, Ruihong Yin, Haoxing Ye, Yuhui Yuan, Dong Chen, Jianmin Bao, Sirui Zhang, Yanbin Wang, Lin Liang, Lijuan Wang, Ji Li, Xiu Li, Zhouhui Lian, Gao Huang, Baining Guo
Abstract: Multi-layer image generation is a fundamental task that enables users to isolate, select, and edit specific image layers, thereby revolutionizing interactions with generative models. In this paper, we introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images based on a global text prompt and an anonymous region layout. Inspired by Schema theory suggests that knowledge is organized in frameworks (schemas) that enable people to interpret and learn from new information by linking it to prior knowledge.}, this anonymous region layout allows the generative model to autonomously determine which set of visual tokens should align with which text tokens, which is in contrast to the previously dominant semantic layout for the image generation task. In addition, the layer-wise region crop mechanism, which only selects the visual tokens belonging to each anonymous region, significantly reduces attention computation costs and enables the efficient generation of images with numerous distinct layers (e.g., 50+). When compared to the full attention approach, our method is over 12 times faster and exhibits fewer layer conflicts. Furthermore, we propose a high-quality multi-layer transparent image autoencoder that supports the direct encoding and decoding of the transparency of variable multi-layer images in a joint manner. By enabling precise control and scalable layer generation, ART establishes a new paradigm for interactive content creation.
Authors: Nicholas Dalhaug, Annette Stahl, Rudolf Mester, Edmund F{\o}rland Brekke
Abstract: For an autonomous surface vessel (ASV) to dock, it must track other vessels close to the docking area. Kayaks present a particular challenge due to their proximity to the dock and relatively small size. Maritime target tracking has typically employed land masking to filter out land and the dock. However, imprecise land masking makes it difficult to track close-to-dock objects. Our approach uses Light Detection And Ranging (LiDAR) data and maps the docking area offline. The precise 3D measurements allow for precise map creation. However, the mapping could result in static, yet potentially moving, objects being mapped. We detect and filter out potentially moving objects from the LiDAR data by utilizing image data. The visual vessel detection and segmentation method is a neural network that is trained on our labeled data. Close-to-shore tracking improves with an accurate map and is demonstrated on a recently gathered real-world dataset. The dataset contains multiple sequences of a kayak and a day cruiser moving close to the dock, in a collision path with an autonomous ferry prototype.
Authors: Dominik Hollidt, Paul Streli, Jiaxi Jiang, Yasaman Haghighi, Changlin Qian, Xintong Liu, Christian Holz
Abstract: Research on egocentric tasks in computer vision has mostly focused on head-mounted cameras, such as fisheye cameras or embedded cameras inside immersive headsets. We argue that the increasing miniaturization of optical sensors will lead to the prolific integration of cameras into many more body-worn devices at various locations. This will bring fresh perspectives to established tasks in computer vision and benefit key areas such as human motion tracking, body pose estimation, or action recognition -- particularly for the lower body, which is typically occluded. In this paper, we introduce EgoSim, a novel simulator of body-worn cameras that generates realistic egocentric renderings from multiple perspectives across a wearer's body. A key feature of EgoSim is its use of real motion capture data to render motion artifacts, which are especially noticeable with arm- or leg-worn cameras. In addition, we introduce MultiEgoView, a dataset of egocentric footage from six body-worn cameras and ground-truth full-body 3D poses during several activities: 119 hours of data are derived from AMASS motion sequences in four high-fidelity virtual environments, which we augment with 5 hours of real-world motion data from 13 participants using six GoPro cameras and 3D body pose references from an Xsens motion capture suit. We demonstrate EgoSim's effectiveness by training an end-to-end video-only 3D pose estimation network. Analyzing its domain gap, we show that our dataset and simulator substantially aid training for inference on real-world data. EgoSim code & MultiEgoView dataset: https://siplab.org/projects/EgoSim
Authors: Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosong Cao, Weiyun Wang, Jiaqi Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Haodong Duan, Hua Yang, Kai Chen
Abstract: Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human preference alignment. This paper introduces OmniAlign-V, a comprehensive dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs' alignment with human preferences. We also present MM-AlignBench, a human-annotated benchmark specifically designed to evaluate MLLMs' alignment with human values. Experimental results show that finetuning MLLMs with OmniAlign-V, using Supervised Fine-Tuning (SFT) or Direct Preference Optimization (DPO), significantly enhances human preference alignment while maintaining or enhancing performance on standard VQA benchmarks, preserving their fundamental capabilities. Our datasets, benchmark, code and checkpoints have been released at https://github.com/PhoenixZ810/OmniAlign-V.
Authors: Zhuoqin Yang, Jiansong Zhang, Xiaoling Luo, Zheng Lu, Linlin Shen
Abstract: Recent advancements in deep learning for image classification predominantly rely on convolutional neural networks (CNNs) or Transformer-based architectures. However, these models face notable challenges in medical imaging, particularly in capturing intricate texture details and contextual features. Kolmogorov-Arnold Networks (KANs) represent a novel class of architectures that enhance nonlinear transformation modeling, offering improved representation of complex features. In this work, we present MedKAN, a medical image classification framework built upon KAN and its convolutional extensions. MedKAN features two core modules: the Local Information KAN (LIK) module for fine-grained feature extraction and the Global Information KAN (GIK) module for global context integration. By combining these modules, MedKAN achieves robust feature modeling and fusion. To address diverse computational needs, we introduce three scalable variants--MedKAN-S, MedKAN-B, and MedKAN-L. Experimental results on nine public medical imaging datasets demonstrate that MedKAN achieves superior performance compared to CNN- and Transformer-based models, highlighting its effectiveness and generalizability in medical image analysis.
Authors: Alexander Groshev (SberAI), Anastasiia Iashchenko (SberAI), Pavel Paramonov (SberAI), Denis Dimitrov (SberAI, AIRI), Andrey Kuznetsov (SberAI, AIRI)
Abstract: While the task of face swapping has recently gained attention in the research community, a related problem of head swapping remains largely unexplored. In addition to skin color transfer, head swap poses extra challenges, such as the need to preserve structural information of the whole head during synthesis and inpaint gaps between swapped head and background. In this paper, we address these concerns with GHOST 2.0, which consists of two problem-specific modules. First, we introduce enhanced Aligner model for head reenactment, which preserves identity information at multiple scales and is robust to extreme pose variations. Secondly, we use a Blender module that seamlessly integrates the reenacted head into the target background by transferring skin color and inpainting mismatched regions. Both modules outperform the baselines on the corresponding tasks, allowing to achieve state of the art results in head swapping. We also tackle complex cases, such as large difference in hair styles of source and target.
Authors: Ziheng Ouyang, Zhen Li, Qibin Hou
Abstract: Recent studies have explored combining different LoRAs to jointly generate learned style and content. However, existing methods either fail to effectively preserve both the original subject and style simultaneously or require additional training. In this paper, we argue that the intrinsic properties of LoRA can effectively guide diffusion models in merging learned subject and style. Building on this insight, we propose K-LoRA, a simple yet effective training-free LoRA fusion approach. In each attention layer, K-LoRA compares the Top-K elements in each LoRA to be fused, determining which LoRA to select for optimal fusion. This selection mechanism ensures that the most representative features of both subject and style are retained during the fusion process, effectively balancing their contributions. Experimental results demonstrate that the proposed method effectively integrates the subject and style information learned by the original LoRAs, outperforming state-of-the-art training-based approaches in both qualitative and quantitative results.
Authors: Yunpeng Zhang, Qiang Wang, Fan Jiang, Yaqi Fan, Mu Xu, Yonggang Qi
Abstract: Tuning-free approaches adapting large-scale pre-trained video diffusion models for identity-preserving text-to-video generation (IPT2V) have gained popularity recently due to their efficacy and scalability. However, significant challenges remain to achieve satisfied facial dynamics while keeping the identity unchanged. In this work, we present a novel tuning-free IPT2V framework by enhancing face knowledge of the pre-trained video model built on diffusion transformers (DiT), dubbed FantasyID. Essentially, 3D facial geometry prior is incorporated to ensure plausible facial structures during video synthesis. To prevent the model from learning copy-paste shortcuts that simply replicate reference face across frames, a multi-view face augmentation strategy is devised to capture diverse 2D facial appearance features, hence increasing the dynamics over the facial expressions and head poses. Additionally, after blending the 2D and 3D features as guidance, instead of naively employing cross-attention to inject guidance cues into DiT layers, a learnable layer-aware adaptive mechanism is employed to selectively inject the fused features into each individual DiT layers, facilitating balanced modeling of identity preservation and motion dynamics. Experimental results validate our model's superiority over the current tuning-free IPT2V methods.
Authors: Thomas Screven, Andras Necz, Jason Smucny, Ian Davidson
Abstract: Although great advances in the analysis of neuroimaging data have been made, a major challenge is a lack of training data. This is less problematic in tasks such as diagnosis, where much data exists, but particularly prevalent in harder problems such as predicting treatment responses (prognosis), where data is focused and hence limited. Here, we address the learning from small data problems for medical imaging using graph neural networks. This is particularly challenging as the information about the patients is themselves graphs (regions of interest connectivity graphs). We show how a spectral representation of the connectivity data allows for efficient propagation that can yield approximately 12\% improvement over traditional deep learning methods using the exact same data. We show that our method's superior performance is due to a data smoothing result that can be measured by closing the number of triangle inequalities and thereby satisfying transitivity.
Authors: Alice Natalina Caragliano, Filippo Ruffini, Carlo Greco, Edy Ippolito, Michele Fiore, Claudia Tacconi, Lorenzo Nibid, Giuseppe Perrone, Sara Ramella, Paolo Soda, Valerio Guarrasi
Abstract: Non-small cell lung cancer (NSCLC) remains a major global health challenge, with high post-surgical recurrence rates underscoring the need for accurate pathological response predictions to guide personalized treatments. Although artificial intelligence models show promise in this domain, their clinical adoption is limited by the lack of medically grounded guidance during training, often resulting in non-explainable intrinsic predictions. To address this, we propose Doctor-in-the-Loop, a novel framework that integrates expert-driven domain knowledge with explainable artificial intelligence techniques, directing the model toward clinically relevant anatomical regions and improving both interpretability and trustworthiness. Our approach employs a gradual multi-view strategy, progressively refining the model's focus from broad contextual features to finer, lesion-specific details. By incorporating domain insights at every stage, we enhance predictive accuracy while ensuring that the model's decision-making process aligns more closely with clinical reasoning. Evaluated on a dataset of NSCLC patients, Doctor-in-the-Loop delivers promising predictive performance and provides transparent, justifiable outputs, representing a significant step toward clinically explainable artificial intelligence in oncology.
Authors: Zeev Yampolsky, Ofir Kruzel, Victoria Khalfin Fekson, Itzik Klein
Abstract: Inertial sensors are crucial for recognizing pedestrian activity. Recent advances in deep learning have greatly improved inertial sensing performance and robustness. Different domains and platforms use deep-learning techniques to enhance network performance, but there is no common benchmark. The latter is crucial for fair comparison and evaluation within a standardized framework. The aim of this paper is to fill this gap by defining and analyzing ten data-driven techniques for improving neural inertial classification networks. In order to accomplish this, we focused on three aspects of neural networks: network architecture, data augmentation, and data preprocessing. The experiments were conducted across four datasets collected from 78 participants. In total, over 936 minutes of inertial data sampled between 50-200Hz were analyzed. Data augmentation through rotation and multi-head architecture consistently yields the most significant improvements. Additionally, this study outlines benchmarking strategies for enhancing neural inertial classification networks.
Authors: Hongyu Zhou, Zorah L\"ahner
Abstract: With the rising popularity of 3D Gaussian splatting and the expanse of applications from rendering to 3D reconstruction, there comes also a need for geometry processing applications directly on this new representation. While considering the centers of Gaussians as a point cloud or meshing them is an option that allows to apply existing algorithms, this might ignore information present in the data or be unnecessarily expensive. Additionally, Gaussian splatting tends to contain a large number of outliers which do not affect the rendering quality but need to be handled correctly in order not to produce noisy results in geometry processing applications. In this work, we propose a formulation to compute the Laplace-Beltrami operator, a widely used tool in geometry processing, directly on Gaussian splatting using the Mahalanobis distance. While conceptually similar to a point cloud Laplacian, our experiments show superior accuracy on the point clouds encoded in the Gaussian splatting centers and, additionally, the operator can be used to evaluate the quality of the output during optimization.
Authors: Christopher Zerafa, Pauline Galea, Cristiana Sebu
Abstract: FWI seeks to achieve a high-resolution model of the subsurface through the application of multi-variate optimization to the seismic inverse problem. Although now a mature technology, FWI has limitations related to the choice of the appropriate solver for the forward problem in challenging environments requiring complex assumptions, and very wide angle and multi-azimuth data necessary for full reconstruction are often not available. Deep Learning techniques have emerged as excellent optimization frameworks. These exist between data and theory-guided methods. Data-driven methods do not impose a wave propagation model and are not exposed to modelling errors. On the contrary, deterministic models are governed by the laws of physics. Application of seismic FWI has recently started to be investigated within Deep Learning. This has focussed on the time-domain approach, while the pseudo-spectral domain has not been yet explored. However, classical FWI experienced major breakthroughs when pseudo-spectral approaches were employed. This work addresses the lacuna that exists in incorporating the pseudo-spectral approach within Deep Learning. This has been done by re-formulating the pseudo-spectral FWI problem as a Deep Learning algorithm for a data-driven pseudo-spectral approach. A novel DNN framework is proposed. This is formulated theoretically, qualitatively assessed on synthetic data, applied to a two-dimensional Marmousi dataset and evaluated against deterministic and time-based approaches. Inversion of data-driven pseudo-spectral DNN was found to outperform classical FWI for deeper and over-thrust areas. This is due to the global approximator nature of the technique and hence not bound by forward-modelling physical constraints from ray-tracing.
Authors: Adrian Thummerer, Erik van der Bijl, Arthur Jr Galapon, Florian Kamp, Mark Savenije, Christina Muijs, Shafak Aluwini, Roel J. H. M. Steenbakkers, Stephanie Beuel, Martijn P. W. Intven, Johannes A. Langendijk, Stefan Both, Stefanie Corradini, Viktor Rogowski, Maarten Terpstra, Niklas Wahl, Christopher Kurz, Guillaume Landry, Matteo Maspero
Abstract: Medical imaging is essential in modern radiotherapy, supporting diagnosis, treatment planning, and monitoring. Synthetic imaging, particularly synthetic computed tomography (sCT), is gaining traction in radiotherapy. The SynthRAD2025 dataset and Grand Challenge promote advancements in sCT generation by providing a benchmarking platform for algorithms using cone-beam CT (CBCT) and magnetic resonance imaging (MRI). The dataset includes 2362 cases: 890 MRI-CT and 1472 CBCT-CT pairs from head-and-neck, thoracic, and abdominal cancer patients treated at five European university medical centers (UMC Groningen, UMC Utrecht, Radboud UMC, LMU University Hospital Munich, and University Hospital of Cologne). Data were acquired with diverse scanners and protocols. Pre-processing, including rigid and deformable image registration, ensures high-quality, modality-aligned images. Extensive quality assurance validates image consistency and usability. All imaging data is provided in MetaImage (.mha) format, ensuring compatibility with medical image processing tools. Metadata, including acquisition parameters and registration details, is available in structured CSV files. To maintain dataset integrity, SynthRAD2025 is divided into training (65%), validation (10%), and test (25%) sets. The dataset is accessible at https://doi.org/10.5281/zenodo.14918089 under the SynthRAD2025 collection. This dataset supports benchmarking and the development of synthetic imaging techniques for radiotherapy applications. Use cases include sCT generation for MRI-only and MR-guided photon/proton therapy, CBCT-based dose calculations, and adaptive radiotherapy workflows. By integrating diverse acquisition settings, SynthRAD2025 fosters robust, generalizable image synthesis algorithms, advancing personalized cancer care and adaptive radiotherapy.
Authors: Akhila Yerukola, Saadia Gabriel, Nanyun Peng, Maarten Sap
Abstract: Gestures are an integral part of non-verbal communication, with meanings that vary across cultures, and misinterpretations that can have serious social and diplomatic consequences. As AI systems become more integrated into global applications, ensuring they do not inadvertently perpetuate cultural offenses is critical. To this end, we introduce Multi-Cultural Set of Inappropriate Gestures and Nonverbal Signs (MC-SIGNS), a dataset of 288 gesture-country pairs annotated for offensiveness, cultural significance, and contextual factors across 25 gestures and 85 countries. Through systematic evaluation using MC-SIGNS, we uncover critical limitations: text-to-image (T2I) systems exhibit strong US-centric biases, performing better at detecting offensive gestures in US contexts than in non-US ones; large language models (LLMs) tend to over-flag gestures as offensive; and vision-language models (VLMs) default to US-based interpretations when responding to universal concepts like wishing someone luck, frequently suggesting culturally inappropriate gestures. These findings highlight the urgent need for culturally-aware AI safety mechanisms to ensure equitable global deployment of AI technologies.
Authors: Liang Xu, Pengwu Song, Shilu Zhu, Yang Zhang, Ru Zhang, Zhiyuan Zheng, Qingdong Zhang, Jie Gao, Chen Han, Mingzhai Sun, Peng Yao, Min Ye, Ronald X. Xu
Abstract: Continuous monitoring and in-situ assessment of microvascular connectivity have significant implications for culturing vascularized organoids and optimizing the therapeutic strategies. However, commonly used methods for vascular connectivity assessment heavily rely on fluorescent labels that may either raise biocompatibility concerns or interrupt the normal cell growth process. To address this issue, a Vessel Connectivity Network (VC-Net) was developed for label-free assessment of vascular connectivity. To validate the VC-Net, microvascular networks (MVNs) were cultured in vitro and their microscopic images were acquired at different culturing conditions as a training dataset. The VC-Net employs a Vessel Queue Contrastive Learning (VQCL) method and a class imbalance algorithm to address the issues of limited sample size, indistinctive class features and imbalanced class distribution in the dataset. The VC-Net successfully evaluated the vascular connectivity with no significant deviation from that by fluorescence imaging. In addition, the proposed VC-Net successfully differentiated the connectivity characteristics between normal and tumor-related MVNs. In comparison with those cultured in the regular microenvironment, the averaged connectivity of MVNs cultured in the tumor-related microenvironment decreased by 30.8%, whereas the non-connected area increased by 37.3%. This study provides a new avenue for label-free and continuous assessment of organoid or tumor vascularization in vitro.
Authors: Chris Dongjoo Kim, Sangwoo Moon, Jihwan Moon, Dongyeon Woo, Gunhee Kim
Abstract: As with many other problems, real-world regression is plagued by the presence of noisy labels, an inevitable issue that demands our attention. Fortunately, much real-world data often exhibits an intrinsic property of continuously ordered correlations between labels and features, where data points with similar labels are also represented with closely related features. In response, we propose a novel approach named ConFrag, where we collectively model the regression data by transforming them into disjoint yet contrasting fragmentation pairs. This enables the training of more distinctive representations, enhancing the ability to select clean samples. Our ConFrag framework leverages a mixture of neighboring fragments to discern noisy labels through neighborhood agreement among expert feature extractors. We extensively perform experiments on six newly curated benchmark datasets of diverse domains, including age prediction, price prediction, and music production year estimation. We also introduce a metric called Error Residual Ratio (ERR) to better account for varying degrees of label noise. Our approach consistently outperforms fourteen state-of-the-art baselines, being robust against symmetric and random Gaussian label noise.
Authors: Hyeonjeong Ha, Qiusi Zhan, Jeonghwan Kim, Dimitrios Bralios, Saikrishna Sanniboina, Nanyun Peng, Kai-wei Chang, Daniel Kang, Heng Ji
Abstract: Multimodal large language models (MLLMs) equipped with Retrieval Augmented Generation (RAG) leverage both their rich parametric knowledge and the dynamic, external knowledge to excel in tasks such as Question Answering. While RAG enhances MLLMs by grounding responses in query-relevant external knowledge, this reliance poses a critical yet underexplored safety risk: knowledge poisoning attacks, where misinformation or irrelevant knowledge is intentionally injected into external knowledge bases to manipulate model outputs to be incorrect and even harmful. To expose such vulnerabilities in multimodal RAG, we propose MM-PoisonRAG, a novel knowledge poisoning attack framework with two attack strategies: Localized Poisoning Attack (LPA), which injects query-specific misinformation in both text and images for targeted manipulation, and Globalized Poisoning Attack (GPA) to provide false guidance during MLLM generation to elicit nonsensical responses across all queries. We evaluate our attacks across multiple tasks, models, and access settings, demonstrating that LPA successfully manipulates the MLLM to generate attacker-controlled answers, with a success rate of up to 56% on MultiModalQA. Moreover, GPA completely disrupts model generation to 0% accuracy with just a single irrelevant knowledge injection. Our results highlight the urgent need for robust defenses against knowledge poisoning to safeguard multimodal RAG frameworks.
Authors: Muhammad Nawaz, Basma Nasir, Tehseen Zia, Zawar Hussain, Catarina Moreira
Abstract: Precise identification and localization of disease-specific features at the pixel-level are particularly important for early diagnosis, disease progression monitoring, and effective treatment in medical image analysis. However, conventional diagnostic AI systems lack decision transparency and cannot operate well in environments where there is a lack of pixel-level annotations. In this study, we propose a novel Generative Adversarial Networks (GANs)-based framework, TagGAN, which is tailored for weakly-supervised fine-grained disease map generation from purely image-level labeled data. TagGAN generates a pixel-level disease map during domain translation from an abnormal image to a normal representation. Later, this map is subtracted from the input abnormal image to convert it into its normal counterpart while preserving all the critical anatomical details. Our method is first to generate fine-grained disease maps to visualize disease lesions in a weekly supervised setting without requiring pixel-level annotations. This development enhances the interpretability of diagnostic AI by providing precise visualizations of disease-specific regions. It also introduces automated binary mask generation to assist radiologists. Empirical evaluations carried out on the benchmark datasets, CheXpert, TBX11K, and COVID-19, demonstrate the capability of TagGAN to outperform current top models in accurately identifying disease-specific pixels. This outcome highlights the capability of the proposed model to tag medical images, significantly reducing the workload for radiologists by eliminating the need for binary masks during training.
Authors: Rui Lu, Bihai Zhang, Dan Wang
Abstract: With the popularity of 3D volumetric video applications, such as Autonomous Driving, Virtual Reality, and Mixed Reality, current developers have turned to deep learning for compressing volumetric video frames, i.e., point clouds for video upstreaming. The latest deep learning-based solutions offer higher efficiency, lower distortion, and better hardware support compared to traditional ones like MPEG and JPEG. However, privacy threats arise, especially reconstruction attacks targeting to recover the original input point cloud from the intermediate results. In this paper, we design VVRec, to the best of our knowledge, which is the first targeting DL-based Volumetric Video Reconstruction attack scheme. VVRec demonstrates the ability to reconstruct high-quality point clouds from intercepted transmission intermediate results using four well-trained neural network modules we design. Leveraging the latest latent diffusion models with Gamma distribution and a refinement algorithm, VVRec excels in reconstruction quality, color recovery, and surpasses existing defenses. We evaluate VVRec using three volumetric video datasets. The results demonstrate that VVRec achieves 64.70dB reconstruction accuracy, with an impressive 46.39% reduction of distortion over baselines.
Authors: Qinghua He, Hongyang Jiang, Danqi Fang, Dawei Yang, Truong X. Nguyen, Anran Ran, Clement C. Tham, Simon K. H. Szeto, Sobha Sivaprasad, Carol Y. Cheung
Abstract: Diabetic macular ischemia (DMI), marked by the loss of retinal capillaries in the macular area, contributes to vision impairment in patients with diabetes. Although color fundus photographs (CFPs), combined with artificial intelligence (AI), have been extensively applied in detecting various eye diseases, including diabetic retinopathy (DR), their applications in detecting DMI remain unexplored, partly due to skepticism among ophthalmologists regarding its feasibility. In this study, we propose a graph neural network-based multispectral view learning (GNN-MSVL) model designed to detect DMI from CFPs. The model leverages higher spectral resolution to capture subtle changes in fundus reflectance caused by ischemic tissue, enhancing sensitivity to DMI-related features. The proposed approach begins with computational multispectral imaging (CMI) to reconstruct 24-wavelength multispectral fundus images from CFPs. ResNeXt101 is employed as the backbone for multi-view learning to extract features from the reconstructed images. Additionally, a GNN with a customized jumper connection strategy is designed to enhance cross-spectral relationships, facilitating comprehensive and efficient multispectral view learning. The study included a total of 1,078 macula-centered CFPs from 1,078 eyes of 592 patients with diabetes, of which 530 CFPs from 530 eyes of 300 patients were diagnosed with DMI. The model achieved an accuracy of 84.7 percent and an area under the receiver operating characteristic curve (AUROC) of 0.900 (95 percent CI: 0.852-0.937) on eye-level, outperforming both the baseline model trained from CFPs and human experts (p-values less than 0.01). These findings suggest that AI-based CFP analysis holds promise for detecting DMI, contributing to its early and low-cost screening.
Authors: Weiheng Liu, Yuxuan Wan, Jilong Wang, Yuxuan Kuang, Xuesong Shi, Haoran Li, Dongbin Zhao, Zhizheng Zhang, He Wang
Abstract: Object fetching from cluttered shelves is an important capability for robots to assist humans in real-world scenarios. Achieving this task demands robotic behaviors that prioritize safety by minimizing disturbances to surrounding objects, an essential but highly challenging requirement due to restricted motion space, limited fields of view, and complex object dynamics. In this paper, we introduce FetchBot, a sim-to-real framework designed to enable zero-shot generalizable and safety-aware object fetching from cluttered shelves in real-world settings. To address data scarcity, we propose an efficient voxel-based method for generating diverse simulated cluttered shelf scenes at scale and train a dynamics-aware reinforcement learning (RL) policy to generate object fetching trajectories within these scenes. This RL policy, which leverages oracle information, is subsequently distilled into a vision-based policy for real-world deployment. Considering that sim-to-real discrepancies stem from texture variations mostly while from geometric dimensions rarely, we propose to adopt depth information estimated by full-fledged depth foundation models as the input for the vision-based policy to mitigate sim-to-real gap. To tackle the challenge of limited views, we design a novel architecture for learning multi-view representations, allowing for comprehensive encoding of cluttered shelf scenes. This enables FetchBot to effectively minimize collisions while fetching objects from varying positions and depths, ensuring robust and safety-aware operation. Both simulation and real-robot experiments demonstrate FetchBot's superior generalization ability, particularly in handling a broad range of real-world scenarios, includ
Authors: Vishal Nedungadi, Muhammad Akhtar Munir, Marc Ru{\ss}wurm, Ron Sarafian, Ioannis N. Athanasiadis, Yinon Rudich, Fahad Shahbaz Khan, Salman Khan
Abstract: Air pollution remains a leading global health risk, exacerbated by rapid industrialization and urbanization, contributing significantly to morbidity and mortality rates. In this paper, we introduce AirCast, a novel multi-variable air pollution forecasting model, by combining weather and air quality variables. AirCast employs a multi-task head architecture that simultaneously forecasts atmospheric conditions and pollutant concentrations, improving its understanding of how weather patterns affect air quality. Predicting extreme pollution events is challenging due to their rare occurrence in historic data, resulting in a heavy-tailed distribution of pollution levels. To address this, we propose a novel Frequency-weighted Mean Absolute Error (fMAE) loss, adapted from the class-balanced loss for regression tasks. Informed from domain knowledge, we investigate the selection of key variables known to influence pollution levels. Additionally, we align existing weather and chemical datasets across spatial and temporal dimensions. AirCast's integrated approach, combining multi-task learning, frequency weighted loss and domain informed variable selection, enables more accurate pollution forecasts. Our source code and models are made public here (https://github.com/vishalned/AirCast.git)
Authors: Xinrui Ma, Jian Cheng, Wenxin Fan, Ruoyou Wu, Yongquan Ye, Shanshan Wang
Abstract: Diffusion magnetic resonance imaging (dMRI) is a crucial non-invasive technique for exploring the microstructure of the living human brain. Traditional hand-crafted and model-based tissue microstructure reconstruction methods often require extensive diffusion gradient sampling, which can be time-consuming and limits the clinical applicability of tissue microstructure information. Recent advances in deep learning have shown promise in microstructure estimation; however, accurately estimating tissue microstructure from clinically feasible dMRI scans remains challenging without appropriate constraints. This paper introduces a novel framework that achieves high-fidelity and rapid diffusion microstructure imaging by simultaneously leveraging anatomical information from macro-level priors and mutual information across parameters. This approach enhances time efficiency while maintaining accuracy in microstructure estimation. Experimental results demonstrate that our method outperforms four state-of-the-art techniques, achieving a peak signal-to-noise ratio (PSNR) of 30.51$\pm$0.58 and a structural similarity index measure (SSIM) of 0.97$\pm$0.004 in estimating parametric maps of multiple diffusion models. Notably, our method achieves a 15$\times$ acceleration compared to the dense sampling approach, which typically utilizes 270 diffusion gradients.
Authors: Yun Zhang, Zixi Guo, Linwei Zhu, C. -C. Jay Kuo
Abstract: Colored point cloud becomes a fundamental representation in the realm of 3D vision. Effective Point Cloud Compression (PCC) is urgently needed due to huge amount of data. In this paper, we propose an end-to-end Deep Joint Geometry and Attribute point cloud Compression (Deep-JGAC) framework for dense colored point clouds, which exploits the correlation between the geometry and attribute for high compression efficiency. Firstly, we propose a flexible Deep-JGAC framework, where the geometry and attribute sub-encoders are compatible to either learning or non-learning based geometry and attribute encoders. Secondly, we propose an attribute-assisted deep geometry encoder that enhances the geometry latent representation with the help of attribute, where the geometry decoding remains unchanged. Moreover, Attribute Information Fusion Module (AIFM) is proposed to fuse attribute information in geometry coding. Thirdly, to solve the mismatch between the point cloud geometry and attribute caused by the geometry compression distortion, we present an optimized re-colorization module to attach the attribute to the geometrically distorted point cloud for attribute coding. It enhances the colorization and lowers the computational complexity. Extensive experimental results demonstrate that in terms of the geometry quality metric D1-PSNR, the proposed Deep-JGAC achieves an average of 82.96%, 36.46%, 41.72%, and 31.16% bit-rate reductions as compared to the state-of-the-art G-PCC, V-PCC, GRASP, and PCGCv2, respectively. In terms of perceptual joint quality metric MS-GraphSIM, the proposed Deep-JGAC achieves an average of 48.72%, 14.67%, and 57.14% bit-rate reductions compared to the G-PCC, V-PCC, and IT-DL-PCC, respectively. The encoding/decoding time costs are also reduced by 94.29%/24.70%, and 96.75%/91.02% on average as compared with the V-PCC and IT-DL-PCC.
Authors: Bo Zhang, Heye Huang, Chunyang Liu, Yaqin Zhang, Zhenhua Xu
Abstract: End-to-end autonomous driving with its holistic optimization capabilities, has gained increasing traction in academia and industry. Vectorized representations, which preserve instance-level topological information while reducing computational overhead, have emerged as a promising paradigm. While existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points, resulting in geometrically inconsistent outputs (e.g., fragmented HD map elements or oscillatory trajectories). To address these limitations, we propose InVDriver, a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers, thereby enhancing planning accuracy and trajectory smoothness. Across all core modules, i.e., perception, prediction, and planning, InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions, enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise. Experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance, surpassing prior methods in both accuracy and safety, while maintaining high computational efficiency. Our work validates that explicit modeling of intra-instance geometric coherence is critical for advancing vectorized autonomous driving systems, bridging the gap between theoretical advantages of end-to-end frameworks and practical deployment requirements.
Authors: Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer, Javier Civera, Holger Voos
Abstract: Works based on localization and mapping do not exploit the inherent semantic-relational information from the environment for faster and efficient management and optimization of the robot poses and its map elements, often leading to pose and map inaccuracies and computational inefficiencies in large scale environments. 3D scene graph representations which distributes the environment in an hierarchical manner can be exploited to enhance the management/optimization of underlying robot poses and its map. In this direction, we present our work Situational Graphs 2.0, which leverages the hierarchical structure of indoor scenes for efficient data management and optimization. Our algorithm begins by constructing a situational graph that organizes the environment into four layers: Keyframes, Walls, Rooms, and Floors. Our first novelty lies in the front-end which includes a floor detection module capable of identifying stairways and assigning a floor-level semantic-relations to the underlying layers. This floor-level semantic enables a floor-based loop closure strategy, rejecting false-positive loop closures in visually similar areas on different floors. Our second novelty is in exploiting the hierarchy for an improved optimization. It consists of: (1) local optimization, optimizing a window of recent keyframes and their connected components, (2) floor-global optimization, which focuses only on keyframes and their connections within the current floor during loop closures, and (3) room-local optimization, marginalizing redundant keyframes that share observations within the room. We validate our algorithm extensively in different real multi-floor environments. Our approach can demonstrate state-of-art-art results in large scale multi-floor environments creating hierarchical maps while bounding the computational complexity where several baseline works fail to execute efficiently.
Authors: Ryo Takizawa, Izumi Karino, Koki Nakagawa, Yoshiyuki Ohmura, Yasuo Kuniyoshi
Abstract: Autonomous agents capable of diverse object manipulations should be able to acquire a wide range of manipulation skills with high reusability. Although advances in deep learning have made it increasingly feasible to replicate the dexterity of human teleoperation in robots, generalizing these acquired skills to previously unseen scenarios remains a significant challenge. In this study, we propose a novel algorithm, Gaze-based Bottleneck-aware Robot Manipulation (GazeBot), which enables high reusability of the learned motions even when the object positions and end-effector poses differ from those in the provided demonstrations. By leveraging gaze information and motion bottlenecks, both crucial features for object manipulation, GazeBot achieves high generalization performance compared with state-of-the-art imitation learning methods, without sacrificing its dexterity and reactivity. Furthermore, the training process of GazeBot is entirely data-driven once a demonstration dataset with gaze data is provided. Videos and code are available at https://crumbyrobotics.github.io/gazebot.
Authors: Jintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu, Jianfei Chen
Abstract: An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of corresponding computations. Many studies have utilized the sparse pattern to accelerate attention. However, most existing works focus on optimizing attention within specific models by exploiting certain sparse patterns of the attention map. A universal sparse attention that guarantees both the speedup and end-to-end performance of diverse models remains elusive. In this paper, we propose SpargeAttn, a universal sparse and quantized attention for any model. Our method uses a two-stage online filter: in the first stage, we rapidly and accurately predict the attention map, enabling the skip of some matrix multiplications in attention. In the second stage, we design an online softmax-aware filter that incurs no extra overhead and further skips some matrix multiplications. Experiments show that our method significantly accelerates diverse models, including language, image, and video generation, without sacrificing end-to-end metrics. The codes are available at https://github.com/thu-ml/SpargeAttn.
Authors: Adnan Iltaf, Rayan Merghani Ahmed, Bin Li, Shoujun Zhou
Abstract: Medical image segmentation is crucial for clinical diagnosis and treatment planning, particularly for complex anatomical structures like vessels. In this work, we propose VesselSAM, a modified version of the Segmentation Anything Model (SAM), specifically designed for aortic vessel segmentation. VesselSAM incorporates AtrousLoRA, a novel module that combines Atrous Attention with Low-Rank Adaptation (LoRA), to improve segmentation performance. Atrous Attention enables the model to capture multi-scale contextual information, preserving both fine local details and broader global context. At the same time, LoRA facilitates efficient fine-tuning of the frozen SAM image encoder, reducing the number of trainable parameters and ensuring computational efficiency. We evaluate VesselSAM on two challenging datasets: the Aortic Vessel Tree (AVT) dataset and the Type-B Aortic Dissection (TBAD) dataset. VesselSAM achieves state-of-the-art performance with DSC scores of 93.50\%, 93.25\%, 93.02\%, and 93.26\% across multiple medical centers. Our results demonstrate that VesselSAM delivers high segmentation accuracy while significantly reducing computational overhead compared to existing large-scale models. This development paves the way for enhanced AI-based aortic vessel segmentation in clinical environments. The code and models will be released at https://github.com/Adnan-CAS/AtrousLora.
Authors: Gianluigi Silvestri, Luca Ambrogioni, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji
Abstract: Consistency Training (CT) has recently emerged as a promising alternative to diffusion models, achieving competitive performance in image generation tasks. However, non-distillation consistency training often suffers from high variance and instability, and analyzing and improving its training dynamics is an active area of research. In this work, we propose a novel CT training approach based on the Flow Matching framework. Our main contribution is a trained noise-coupling scheme inspired by the architecture of Variational Autoencoders (VAE). By training a data-dependent noise emission model implemented as an encoder architecture, our method can indirectly learn the geometry of the noise-to-data mapping, which is instead fixed by the choice of the forward process in classical CT. Empirical results across diverse image datasets show significant generative improvements, with our model outperforming baselines and achieving the state-of-the-art (SoTA) non-distillation CT FID on CIFAR-10, and attaining FID on par with SoTA on ImageNet at $64 \times 64$ resolution in 2-step generation. Our code is available at https://github.com/sony/vct .
Authors: Jun Zeng, Debesh Jha, Ertugrul Aktas, Elif Keles, Alpay Medetalibeyoglu, Matthew Antalek, Amir A. Borhani, Daniela P. Ladner, Gorkem Durak, Ulas Bagci
Abstract: We present an end-to-end deep learning framework for automated liver cirrhosis stage estimation from multi-sequence MRI. Cirrhosis is the severe scarring (fibrosis) of the liver and a common endpoint of various chronic liver diseases. Early diagnosis is vital to prevent complications such as decompensation and cancer, which significantly decreases life expectancy. However, diagnosing cirrhosis in its early stages is challenging, and patients often present with life-threatening complications. Our approach integrates multi-scale feature learning with sequence-specific attention mechanisms to capture subtle tissue variations across cirrhosis progression stages. Using CirrMRI600+, a large-scale publicly available dataset of 628 high-resolution MRI scans from 339 patients, we demonstrate state-of-the-art performance in three-stage cirrhosis classification. Our best model achieves 72.8% accuracy on T1W and 63.8% on T2W sequences, significantly outperforming traditional radiomics-based approaches. Through extensive ablation studies, we show that our architecture effectively learns stage-specific imaging biomarkers. We establish new benchmarks for automated cirrhosis staging and provide insights for developing clinically applicable deep learning systems. The source code will be available at https://github.com/JunZengz/CirrhosisStage.
Authors: Jun Zeng, Ulas Bagci, Debesh Jha
Abstract: We present RMA-Mamba, a novel architecture that advances the capabilities of vision state space models through a specialized reverse mamba attention module (RMA). The key innovation lies in RMA-Mamba's ability to capture long-range dependencies while maintaining precise local feature representation through its hierarchical processing pipeline. By integrating Vision Mamba (VMamba)'s efficient sequence modeling with RMA's targeted feature refinement, our architecture achieves superior feature learning across multiple scales. This dual-mechanism approach enables robust handling of complex morphological patterns while maintaining computational efficiency. We demonstrate RMA-Mamba's effectiveness in the challenging domain of pathological liver segmentation (from both CT and MRI), where traditional segmentation approaches often fail due to tissue variations. When evaluated on a newly introduced cirrhotic liver dataset (CirrMRI600+) of T2-weighted MRI scans, RMA-Mamba achieves the state-of-the-art performance with a Dice coefficient of 92.08%, mean IoU of 87.36%, and recall of 92.96%. The architecture's generalizability is further validated on the cancerous liver segmentation from CT scans (LiTS: Liver Tumor Segmentation dataset), yielding a Dice score of 92.9% and mIoU of 88.99%. The source code of the proposed RMA-Mamba is available at https://github.com/JunZengz/RMAMamba.
Authors: Xinran Liu, Xu Dong, Diptesh Kanojia, Wenwu Wang, Zhenhua Feng
Abstract: Generating high-quality full-body dance sequences from music is a challenging task as it requires strict adherence to genre-specific choreography. Moreover, the generated sequences must be both physically realistic and precisely synchronized with the beats and rhythm of the music. To overcome these challenges, we propose GCDance, a classifier-free diffusion framework for generating genre-specific dance motions conditioned on both music and textual prompts. Specifically, our approach extracts music features by combining high-level pre-trained music foundation model features with hand-crafted features for multi-granularity feature fusion. To achieve genre controllability, we leverage CLIP to efficiently embed genre-based textual prompt representations at each time step within our dance generation pipeline. Our GCDance framework can generate diverse dance styles from the same piece of music while ensuring coherence with the rhythm and melody of the music. Extensive experimental results obtained on the FineDance dataset demonstrate that GCDance significantly outperforms the existing state-of-the-art approaches, which also achieve competitive results on the AIST++ dataset. Our ablation and inference time analysis demonstrate that GCDance provides an effective solution for high-quality music-driven dance generation.
Authors: Manuel Barusco, Francesco Borsatti, Davide Dalle Pezze, Francesco Paissan, Elisabetta Farella, Gian Antonio Susto
Abstract: Recent advances in Visual Anomaly Detection (VAD) have introduced sophisticated algorithms leveraging embeddings generated by pre-trained feature extractors. Inspired by these developments, we investigate the adaptation of such algorithms to the audio domain to address the problem of Audio Anomaly Detection (AAD). Unlike most existing AAD methods, which primarily classify anomalous samples, our approach introduces fine-grained temporal-frequency localization of anomalies within the spectrogram, significantly improving explainability. This capability enables a more precise understanding of where and when anomalies occur, making the results more actionable for end users. We evaluate our approach on industrial and environmental benchmarks, demonstrating the effectiveness of VAD techniques in detecting anomalies in audio signals. Moreover, they improve explainability by enabling localized anomaly identification, making audio anomaly detection systems more interpretable and practical.
Authors: Qiaojie Zheng, Xiaoli Zhang
Abstract: Deep learning appearance-based 3D gaze estimation is gaining popularity due to its minimal hardware requirements and being free of constraint. Unreliable and overconfident inferences, however, still limit the adoption of this gaze estimation method. To address the unreliable and overconfident issues, we introduce a confidence-aware model that predicts uncertainties together with gaze angle estimations. We also introduce a novel effectiveness evaluation method based on the causality between eye feature degradation and the rise in inference uncertainty to assess the uncertainty estimation. Our confidence-aware model demonstrates reliable uncertainty estimations while providing angular estimation accuracies on par with the state-of-the-art. Compared with the existing statistical uncertainty-angular-error evaluation metric, the proposed effectiveness evaluation approach can more effectively judge inferred uncertainties' performance at each prediction.
Authors: Sijia Chen, Baochun Li
Abstract: Visual grounding (VG) tasks involve explicit cross-modal alignment, as semantically corresponding image regions are to be located for the language phrases provided. Existing approaches complete such visual-text reasoning in a single-step manner. Their performance causes high demands on large-scale anchors and over-designed multi-modal fusion modules based on human priors, leading to complicated frameworks that may be difficult to train and overfit to specific scenarios. Even worse, such once-for-all reasoning mechanisms are incapable of refining boxes continuously to enhance query-region matching. In contrast, in this paper, we formulate an iterative reasoning process by denoising diffusion modeling. Specifically, we propose a language-guided diffusion framework for visual grounding, LG-DVG, which trains the model to progressively reason queried object boxes by denoising a set of noisy boxes with the language guide. To achieve this, LG-DVG gradually perturbs query-aligned ground truth boxes to noisy ones and reverses this process step by step, conditional on query semantics. Extensive experiments for our proposed framework on five widely used datasets validate the superior performance of solving visual grounding, a cross-modal alignment task, in a generative way. The source codes are available at https://github.com/iQua/vgbase/tree/main/examples/DiffusionVG.
URLs: https://github.com/iQua/vgbase/tree/main/examples/DiffusionVG.
Authors: Che Liu, Cheng Ouyang, Yinda Chen, Cesar C\'esar Quilodr\'an-Casas, Lei Ma, Jie Fu, Yike Guo, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: While 3D visual self-supervised learning (vSSL) shows promising results in capturing visual representations, it overlooks the clinical knowledge from radiology reports. Meanwhile, 3D medical vision-language pre-training (MedVLP) remains underexplored due to the lack of a large-scale, publicly available 3D medical image-report dataset. To bridge this gap, we introduce **CT-3DVLP**, the first and largest **public** 3D volume-report dataset, establishing a comprehensive benchmark for 3D MedVLP research. Meanwhile, we propose the **T3D** framework, which enhances 3D MedVLP beyond naive CLIP-style alignment that directly pairs volumes with reports but neglects local visual representations. Instead, we introduce **Text-informed Multi-view Alignment (TMA)**, a novel approach that clusters volumetric data while enforcing consistency across different views of the same volume-report pair. TMA integrates textual features into fine-grained visual representations, ensuring contextual coherence across views. We evaluate T3D across multiple downstream tasks in both unimodal and cross-modal settings, including zero-shot and fine-tuned classification, cross-modal retrieval, report generation, and semantic segmentation. Our results show that T3D consistently outperforms existing vSSL and multimodal methods, demonstrating superior zero-shot and fine-tuning capabilities and setting a new benchmark for 3D medical image understanding.
Authors: Youssef Mourchid, Marc Donias, Yannick Berthoumieu, Mohamed Najim
Abstract: This paper addresses the automatic colorization problem, which converts a gray-scale image to a colorized one. Recent deep-learning approaches can colorize automatically grayscale images. However, when it comes to different scenes which contain distinct color styles, it is difficult to accurately capture the color characteristics. In this work, we propose a fully automatic colorization approach based on Symmetric Positive Definite (SPD) Manifold Learning with a generative adversarial network (SPDGAN) that improves the quality of the colorization results. Our SPDGAN model establishes an adversarial game between two discriminators and a generator. The latter is based on ResNet architecture with few alterations. Its goal is to generate fake colorized images without losing color information across layers through residual connections. Then, we employ two discriminators from different domains. The first one is devoted to the image pixel domain, while the second one is to the Riemann manifold domain which helps to avoid color misalignment. Extensive experiments are conducted on the Places365 and COCO-stuff databases to test the effect of each component of our SPDGAN. In addition, quantitative and qualitative comparisons with state-of-the-art methods demonstrate the effectiveness of our model by achieving more realistic colorized images with less artifacts visually, and good results of PSNR, SSIM, and FID values.
Authors: Youssef Mourchid, Rim Slama
Abstract: Accurate assessment of patient actions plays a crucial role in healthcare as it contributes significantly to disease progression monitoring and treatment effectiveness. However, traditional approaches to assess patient actions often rely on manual observation and scoring, which are subjective and time-consuming. In this paper, we propose an automated approach for patient action assessment using a Multi-Residual Spatio Temporal Graph Network (MR-STGN) that incorporates both angular and positional 3D skeletons. The MR-STGN is specifically designed to capture the spatio-temporal dynamics of patient actions. It achieves this by integrating information from multiple residual layers, with each layer extracting features at distinct levels of abstraction. Furthermore, we integrate an attention fusion mechanism into the network, which facilitates the adaptive weighting of various features. This empowers the model to concentrate on the most pertinent aspects of the patient's movements, offering precise instructions regarding specific body parts or movements that require attention. Ablation studies are conducted to analyze the impact of individual components within the proposed model. We evaluate our model on the UI-PRMD dataset demonstrating its performance in accurately predicting real-time patient action scores, surpassing state-of-the-art methods.
Authors: Xin Gu, Libo Zhang, Fan Chen, Longyin Wen, Yufei Wang, Tiejian Luo, Sijie Zhu
Abstract: This paper focuses on understanding the predominant video creation pipeline, i.e., compositional video editing with six main types of editing components, including video effects, animation, transition, filter, sticker, and text. In contrast to existing visual representation learning of visual materials (i.e., images/videos), we aim to learn visual representations of editing actions/components that are generally applied on raw materials. We start by proposing the first large-scale dataset for editing components of video creation, which covers about $3,094$ editing components with $618,800$ videos. Each video in our dataset is rendered by various image/video materials with a single editing component, which supports atomic visual understanding of different editing components. It can also benefit several downstream tasks, e.g., editing component recommendation, editing component recognition/retrieval, etc. Existing visual representation methods perform poorly because it is difficult to disentangle the visual appearance of editing components from raw materials. To that end, we benchmark popular alternative solutions and propose a novel method that learns to attend to the appearance of editing components regardless of raw materials. Our method achieves favorable results on editing component retrieval/recognition compared to the alternative solutions. A user study is also conducted to show that our representations cluster visually similar editing components better than other alternatives. Furthermore, our learned representations used to transition recommendation tasks achieve state-of-the-art results on the AutoTransition dataset. The code and dataset are available at https://github.com/GX77/Edit3K .
Authors: Junsong Zhang, Zisong Chen, Chunyu Lin, Lang Nie, Zhijie Shen, Kang Liao, Junda Huang, Yao Zhao
Abstract: Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusion strategy to remove distortions or model long-range dependencies to capture global structures, which can result in either unclear structure or insufficient local perception. In this paper, we propose a spherical geometry transformer, named SGFormer, to address the above issues, with an innovative step to integrate spherical geometric priors into vision transformers. To this end, we retarget the transformer decoder to a spherical prior decoder (termed SPDecoder), which endeavors to uphold the integrity of spherical structures during decoding. Concretely, we leverage bipolar re-projection, circular rotation, and curve local embedding to preserve the spherical characteristics of equidistortion, continuity, and surface distance, respectively. Furthermore, we present a query-based global conditional position embedding to compensate for spatial structure at varying resolutions. It not only boosts the global perception of spatial position but also sharpens the depth structure across different patches. Finally, we conduct extensive experiments on popular benchmarks, demonstrating our superiority over state-of-the-art solutions.
Authors: Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji
Abstract: This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of the optimal discriminator, which distinguishes real audio-video pairs from fake ones independently generated by the base models. Based on this analysis, we construct a joint guidance module by training this discriminator. Additionally, we adopt a loss function to stabilize the discriminator's gradient and make it work as a noise estimator, as in standard diffusion models. Empirical evaluations on several benchmark datasets demonstrate that our method improves both single-modal fidelity and multimodal alignment with relatively few parameters. The code is available at: https://github.com/SonyResearch/MMDisCo.
Authors: Dujian Ding, Bicheng Xu, Laks V. S. Lakshmanan
Abstract: Classification tasks play a fundamental role in various applications, spanning domains such as healthcare, natural language processing and computer vision. With the growing popularity and capacity of machine learning models, people can easily access trained classifiers as a service online or offline. However, model use comes with a cost and classifiers of higher capacity (such as large foundation models) usually incur higher inference costs. To harness the respective strengths of different classifiers, we propose a principled approach, OCCAM, to compute the best classifier assignment strategy over classification queries (termed as the optimal model portfolio) so that the aggregated accuracy is maximized, under user-specified cost budgets. Our approach uses an unbiased and low-variance accuracy estimator and effectively computes the optimal solution by solving an integer linear programming problem. On a variety of real-world datasets, OCCAM achieves 40% cost reduction with little to no accuracy drop.
Authors: Che Liu, Zhongwei Wan, Yuqi Wang, Hui Shen, Haozhe Wang, Kangyu Zheng, Mi Zhang, Rossella Arcucci
Abstract: Automatic radiology report generation holds significant potential to streamline the labor-intensive process of report writing by radiologists, particularly for 3D radiographs such as CT scans. While CT scans are critical for clinical diagnostics, they remain less explored compared to 2D radiographs. To date, there has been no comprehensive benchmark for 3D radiograph report generation (3DRRG), nor sufficient investigation into the optimal training strategies for Vision Language Models (VLMs) in this context, particularly with respect to vision encoder choices, visual token compression, and model scaling. In this work, we make three key contributions. We curate **CT-3DRRG**, the largest **publicly** available 3D CT-report dataset, establishing a robust and diverse benchmark for evaluating VLM performance on 3DRRG. Furthermore, we propose a comprehensive training recipe for building high-performing VLMs for 3DRRG, exploring key factors such as vision encoder pretraining strategies, visual token compression, and the impact of data & model scale. Guided by these findings, we introduce **Argus**, a state-of-the-art family of VLMs that achieve superior performance across different model sizes and input 3D medical image resolutions, efficiently processing high-resolution 3D images up to $512 \times 512 \times 256$[^1].
Authors: Chen Hou, Zhibo Chen
Abstract: We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any supervised finetuning on camera-annotated datasets or self-supervised training via data augmentation. Instead, it can be plug-and-play with most pretrained video diffusion models and generate camera-controllable videos with a single image or text prompt as input. The inspiration for our work comes from the layout prior that intermediate latents encode for the generated results, thus rearranging noisy pixels in them will cause the output content to relocate as well. As camera moving could also be seen as a type of pixel rearrangement caused by perspective change, videos can be reorganized following specific camera motion if their noisy latents change accordingly. Building on this, we propose CamTrol, which enables robust camera control for video diffusion models. It is achieved by a two-stage process. First, we model image layout rearrangement through explicit camera movement in 3D point cloud space. Second, we generate videos with camera motion by leveraging the layout prior of noisy latents formed by a series of rearranged images. Extensive experiments have demonstrated its superior performance in both video generation and camera motion alignment compared with other finetuned methods. Furthermore, we show the capability of CamTrol to generalize to various base models, as well as its impressive applications in scalable motion control, dealing with complicated trajectories and unsupervised 3D video generation. Videos available at https://lifedecoder.github.io/CamTrol/.
Authors: Chunming He, Yuqi Shen, Chengyu Fang, Fengyang Xiao, Longxiang Tang, Yulun Zhang, Wangmeng Zuo, Zhenhua Guo, Xiu Li
Abstract: Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising process, have emerged as widely acclaimed for their ability to produce samples of superior quality and diversity. This ensures the generation of visually compelling results with intricate texture information. Despite their remarkable success, a noticeable gap exists in a comprehensive survey that amalgamates these pioneering diffusion model-based works and organizes the corresponding threads. This paper proposes the comprehensive review of diffusion model-based techniques. We present three generic diffusion modeling frameworks and explore their correlations with other deep generative models, establishing the theoretical foundation. Following this, we introduce a multi-perspective categorization of diffusion models, considering both the underlying framework and the target task. Additionally, we summarize extended diffusion models applied in other tasks, including medical, remote sensing, and video scenarios. Moreover, we provide an overview of commonly used benchmarks and evaluation metrics. We conduct a thorough evaluation, encompassing both performance and efficiency, of diffusion model-based techniques in three prominent tasks. Finally, we elucidate the limitations of current diffusion models and propose seven intriguing directions for future research. This comprehensive examination aims to facilitate a profound understanding of the landscape surrounding denoising diffusion models in the context of low-level vision tasks. A curated list of diffusion model-based techniques in over 20 low-level vision tasks can be found at https://github.com/ChunmingHe/awesome-diffusion-models-in-low-level-vision.
URLs: https://github.com/ChunmingHe/awesome-diffusion-models-in-low-level-vision.
Authors: Gang Pan, Chen Wang, Zhijie Sui, Shuai Guo, Yaozhi Lv, Honglie Li, Di Sun, Zixia Xia
Abstract: The Quick-view (QV) technique serves as a primary method for detecting defects within sewerage systems. However, the effectiveness of QV is impeded by the limited visual range of its hardware, resulting in suboptimal image quality for distant portions of the sewer network. Image super-resolution is an effective way to improve image quality and has been applied in a variety of scenes. However, research on super-resolution for sewer images remains considerably unexplored. In response, this study leverages the inherent depth relationships present within QV images and introduces a novel Depth-guided, Reference-based Super-Resolution framework denoted as DSRNet. It comprises two core components: a depth extraction module and a depth information matching module (DMM). DSRNet utilizes the adjacent frames of the low-resolution image as reference images and helps them recover texture information based on the correlation. By combining these modules, the integration of depth priors significantly enhances both visual quality and performance benchmarks. Besides, in pursuit of computational efficiency and compactness, a super-resolution knowledge distillation model based on an attention mechanism is introduced. This mechanism facilitates the acquisition of feature similarity between a more complex teacher model and a streamlined student model, with the latter being a lightweight version of DSRNet. Experimental results demonstrate that DSRNet significantly improves PSNR and SSIM compared with other methods. This study also conducts experiments on sewer defect semantic segmentation, object detection, and classification on the Pipe dataset and Sewer-ML dataset. Experiments show that the method can improve the performance of low-resolution sewer images in these tasks.
Authors: Long Zhao, Sanghyun Woo, Ziyu Wan, Yandong Li, Han Zhang, Boqing Gong, Hartwig Adam, Xuhui Jia, Ting Liu
Abstract: In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for high-quality generation. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. In this work, we offer a new perspective by proposing denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder. We evaluate our approach by assessing both reconstruction (rFID) and generation quality (FID), comparing it to state-of-the-art autoencoding approaches. By adopting iterative reconstruction through diffusion, our autoencoder, namely $\epsilon$-VAE, achieves high reconstruction quality, which in turn enhances downstream generation quality by 22% and provides 2.3$\times$ inference speedup. We hope this work offers new insights into integrating iterative generation and autoencoding for improved compression and generation.
Authors: Dennis Hein, Zhihong Chen, Sophie Ostmeier, Justin Xu, Maya Varma, Eduardo Pontes Reis, Arne Edward Michalson, Christian Bluethgen, Hyun Joo Shin, Curtis Langlotz, Akshay S Chaudhari
Abstract: Radiologists play a crucial role in translating medical images into actionable reports. However, the field faces staffing shortages and increasing workloads. While automated approaches using vision-language models (VLMs) show promise as assistants, they require exceptionally high accuracy. Most current VLMs in radiology rely solely on supervised fine-tuning. Meanwhile, additional preference fine-tuning in the post-training pipeline has become standard practice in the general domain. The challenge in radiology lies in the prohibitive cost of obtaining radiologist feedback at scale. To address this challenge, we propose an automated pipeline for preference feedback, focusing on chest X-ray radiology report generation (RRG). Specifically, our method leverages publicly available datasets containing pairs of images and radiologist-written reference reports with reference-based metrics, or Judges, eliminating the need for additional radiologist feedback. We investigate reward overoptimization via length exploitation in this setting and introduce a length-controlled version of the GREEN score. Our best-performing setup achieves state-of-the-art CheXbert scores on the MIMIC-CXR dataset for the RRG task while on average maintaining robust performance across six additional image perception and reasoning tasks.
Authors: Anirudh Sundara Rajan, Utkarsh Ojha, Jedidiah Schloesser, Yong Jae Lee
Abstract: As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic content, resolution, file format, etc. Fake image detectors are usually built in a data driven way, where a model is trained to separate real from fake images. Existing works primarily investigate network architecture choices and training recipes. In this work, we argue that in addition to these algorithmic choices, we also require a well aligned dataset of real/fake images to train a robust detector. For the family of LDMs, we propose a very simple way to achieve this: we reconstruct all the real images using the LDMs autoencoder, without any denoising operation. We then train a model to separate these real images from their reconstructions. The fakes created this way are extremely similar to the real ones in almost every aspect (e.g., size, aspect ratio, semantic content), which forces the model to look for the LDM decoders artifacts. We empirically show that this way of creating aligned real/fake datasets, which also sidesteps the computationally expensive denoising process, helps in building a detector that focuses less on spurious correlations, something that a very popular existing method is susceptible to. Finally, to demonstrate just how effective the alignment in a dataset can be, we build a detector using images that are not natural objects, and present promising results. Overall, our work identifies the subtle but significant issues that arise when training a fake image detector and proposes a simple and inexpensive solution to address these problems.
Authors: Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen, Talha Qaiser, Chen Jin, Fariba Yousefi, Nikolay Burlutskiy, Rossella Arcucci
Abstract: Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired, high-quality image-text data, which are scarce in the medical domain. Recent advancements in Large Language Models (LLMs) and diffusion models have made it possible to generate large-scale synthetic image-text pairs. This raises the question: "Can MedVLP succeed using purely synthetic data?" To address this, we use off-the-shelf generative models to create synthetic radiology reports and paired Chest X-ray (CXR) images, and propose an automated pipeline to build a diverse, high-quality synthetic dataset, enabling a rigorous study that isolates model and training settings, focusing entirely from the data perspective. Our results show that MedVLP models trained exclusively on synthetic data outperform those trained on real data by 3.8% in averaged AUC on zero-shot classification. Moreover, using a combination of synthetic and real data leads to a further improvement of 9.07%. Additionally, MedVLP models trained on synthetic or mixed data consistently outperform those trained on real data in zero-shot grounding, as well as in fine-tuned classification and segmentation tasks. Our analysis suggests MedVLP trained on well-designed synthetic data can outperform models trained on real datasets, which may be limited by low-quality samples and long-tailed distributions.
Authors: Zongyi Li, Shujie Hu, Shujie Liu, Long Zhou, Jeongsoo Choi, Lingwei Meng, Xun Guo, Jinyu Li, Hefei Ling, Furu Wei
Abstract: Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive models for long video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model. Specifically, ARLON incorporates several key innovations: 1) A latent Vector Quantized Variational Autoencoder (VQ-VAE) compresses the input latent space of the DiT model into compact visual tokens, bridging the AR and DiT models and balancing the learning complexity and information density; 2) An adaptive norm-based semantic injection module integrates the coarse discrete visual units from the AR model into the DiT model, ensuring effective guidance during video generation; 3) To enhance the tolerance capability of noise introduced from the AR inference, the DiT model is trained with coarser visual latent tokens incorporated with an uncertainty sampling module. Experimental results demonstrate that ARLON significantly outperforms the baseline OpenSora-V1.2 on eight out of eleven metrics selected from VBench, with notable improvements in dynamic degree and aesthetic quality, while delivering competitive results on the remaining three and simultaneously accelerating the generation process. In addition, ARLON achieves state-of-the-art performance in long video generation. Detailed analyses of the improvements in inference efficiency are presented, alongside a practical application that demonstrates the generation of long videos using progressive text prompts. See demos of ARLON at http://aka.ms/arlon.
URLs: http://aka.ms/arlon.
Authors: Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Min Wu, Ming-Ming Cheng, Ender Konukoglu, Serge Belongie
Abstract: Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
URLs: https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
Authors: Koichi Namekata, Sherwin Bahmani, Ziyi Wu, Yash Kant, Igor Gilitschenski, David B. Lindell
Abstract: Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error, e.g., involving re-generating videos with different random seeds. Recent techniques address this issue by fine-tuning a pre-trained model to follow conditioning signals, such as bounding boxes or point trajectories. Yet, this fine-tuning procedure can be computationally expensive, and it requires datasets with annotated object motion, which can be difficult to procure. In this work, we introduce SG-I2V, a framework for controllable image-to-video generation that is self-guided$\unicode{x2013}$offering zero-shot control by relying solely on the knowledge present in a pre-trained image-to-video diffusion model without the need for fine-tuning or external knowledge. Our zero-shot method outperforms unsupervised baselines while significantly narrowing down the performance gap with supervised models in terms of visual quality and motion fidelity. Additional details and video results are available on our project page: https://kmcode1.github.io/Projects/SG-I2V
Authors: Hana Bezalel, Dotan Ankri, Ruojin Cai, Hadar Averbuch-Elor
Abstract: We present a technique and benchmark dataset for estimating the relative 3D orientation between a pair of Internet images captured in an extreme setting, where the images have limited or non-overlapping field of views. Prior work targeting extreme rotation estimation assume constrained 3D environments and emulate perspective images by cropping regions from panoramic views. However, real images captured in the wild are highly diverse, exhibiting variation in both appearance and camera intrinsics. In this work, we propose a Transformer-based method for estimating relative rotations in extreme real-world settings, and contribute the ExtremeLandmarkPairs dataset, assembled from scene-level Internet photo collections. Our evaluation demonstrates that our approach succeeds in estimating the relative rotations in a wide variety of extreme-view Internet image pairs, outperforming various baselines, including dedicated rotation estimation techniques and contemporary 3D reconstruction methods.
Authors: Pura Peetathawatchai, Wei-Ning Chen, Berivan Isik, Sanmi Koyejo, Albert No
Abstract: We introduce a novel method for adapting diffusion models under differential privacy (DP) constraints, enabling privacy-preserving style and content transfer without fine-tuning model weights. Traditional approaches to private adaptation, such as DP-SGD, incur significant computational and memory overhead when applied to large, complex models. In addition, when adapting to small-scale specialized datasets, DP-SGD incurs large amount of noise that significantly degrades the performance. Our approach instead leverages an embedding-based technique derived from Textual Inversion (TI) and adapted with differentially private mechanisms. We apply TI to Stable Diffusion for style adaptation using two private datasets: a collection of artworks by a single artist and pictograms from the Paris 2024 Olympics. Experimental results show that the TI-based adaptation achieves superior fidelity in style transfer, even under strong privacy guarantees.
Authors: Florian Strohm, Mihai B\^ace, Andreas Bulling
Abstract: We present HAIFAI - a novel two-stage system where humans and AI interact to tackle the challenging task of reconstructing a visual representation of a face that exists only in a person's mind. In the first stage, users iteratively rank images our reconstruction system presents based on their resemblance to a mental image. These rankings, in turn, allow the system to extract relevant image features, fuse them into a unified feature vector, and use a generative model to produce an initial reconstruction of the mental image. The second stage leverages an existing face editing method, allowing users to manually refine and further improve this reconstruction using an easy-to-use slider interface for face shape manipulation. To avoid the need for tedious human data collection for training the reconstruction system, we introduce a computational user model of human ranking behaviour. For this, we collected a small face ranking dataset through an online crowd-sourcing study containing data from 275 participants. We evaluate HAIFAI and an ablated version in a 12-participant user study and demonstrate that our approach outperforms the previous state of the art regarding reconstruction quality, usability, perceived workload, and reconstruction speed. We further validate the reconstructions in a subsequent face ranking study with 18 participants and show that HAIFAI achieves a new state-of-the-art identification rate of 60.6%. These findings represent a significant advancement towards developing new interactive intelligent systems capable of reliably and effortlessly reconstructing a user's mental image.
Authors: Jinlu Zhang, Jiji Tang, Rongsheng Zhang, Tangjie Lv, Xiaoshuai Sun
Abstract: Story visualization has gained increasing attention in artificial intelligence. However, existing methods still struggle with maintaining a balance between character identity preservation and text-semantics alignment, largely due to a lack of detailed semantic modeling of the story scene. To tackle this challenge, we propose a novel knowledge graph, namely Character Graph (\textbf{CG}), which comprehensively represents various story-related knowledge, including the characters, the attributes related to characters, and the relationship between characters. We then introduce StoryWeaver, an image generator that achieve Customization via Character Graph (\textbf{C-CG}), capable of consistent story visualization with rich text semantics. To further improve the multi-character generation performance, we incorporate knowledge-enhanced spatial guidance (\textbf{KE-SG}) into StoryWeaver to precisely inject character semantics into generation. To validate the effectiveness of our proposed method, extensive experiments are conducted using a new benchmark called TBC-Bench. The experiments confirm that our StoryWeaver excels not only in creating vivid visual story plots but also in accurately conveying character identities across various scenarios with considerable storage efficiency, \emph{e.g.}, achieving an average increase of +9.03\% DINO-I and +13.44\% CLIP-T. Furthermore, ablation experiments are conducted to verify the superiority of the proposed module. Codes and datasets are released at https://github.com/Aria-Zhangjl/StoryWeaver.
Authors: Hongxiang Li, Yaowei Li, Yuhang Yang, Junjie Cao, Zhihong Zhu, Xuxin Cheng, Long Chen
Abstract: Controllable human image animation aims to generate videos from reference images using driving videos. Due to the limited control signals provided by sparse guidance (e.g., skeleton pose), recent works have attempted to introduce additional dense conditions (e.g., depth map) to ensure motion alignment. However, such strict dense guidance impairs the quality of the generated video when the body shape of the reference character differs significantly from that of the driving video. In this paper, we present DisPose to mine more generalizable and effective control signals without additional dense input, which disentangles the sparse skeleton pose in human image animation into motion field guidance and keypoint correspondence. Specifically, we generate a dense motion field from a sparse motion field and the reference image, which provides region-level dense guidance while maintaining the generalization of the sparse pose control. We also extract diffusion features corresponding to pose keypoints from the reference image, and then these point features are transferred to the target pose to provide distinct identity information. To seamlessly integrate into existing models, we propose a plug-and-play hybrid ControlNet that improves the quality and consistency of generated videos while freezing the existing model parameters. Extensive qualitative and quantitative experiments demonstrate the superiority of DisPose compared to current methods. Project page: \href{https://github.com/lihxxx/DisPose}{https://github.com/lihxxx/DisPose}.
URLs: https://github.com/lihxxx/DisPose, https://github.com/lihxxx/DisPose
Authors: Shizuka Akahori, Shotaro Teruya, Pragyan Shrestha, Yuichi Yoshii, Ryuhei Michinobu, Satoshi Iizuka, Itaru Kitahara
Abstract: Ultrasound imaging of the medial elbow is crucial for the early diagnosis of Ulnar Collateral Ligament (UCL) injuries. Specifically, measuring the elbow joint space in ultrasound images is used to assess the valgus instability of the elbow caused by UCL injuries. To automate this measurement, a model trained on a precisely annotated dataset is necessary; however, no publicly available dataset exists to date. This study introduces a novel ultrasound medial elbow dataset to measure the joint space. The dataset comprises 4,201 medial elbow ultrasound images from 22 subjects, with landmark annotations on the humerus and ulna, based on the expertise of three orthopedic surgeons. We evaluated joint space measurement methods on our proposed dataset using heatmap-based, regression-based, and token-based landmark detection methods. While heatmap-based landmark detection methods generally achieve high accuracy, they sometimes produce multiple peaks on a heatmap, leading to incorrect detection. To mitigate this issue and enhance landmark localization, we propose Shape Subspace (SS) landmark refinement by measuring geometrical similarities between the detected and reference landmark positions. The results show that the mean joint space measurement error is 0.116 mm when using HRNet. Furthermore, SS landmark refinement can reduce the mean absolute error of landmark positions by 0.010 mm with HRNet and by 0.103 mm with ViTPose on average. These highlight the potential for high-precision, real-time diagnosis of UCL injuries by accurately measuring joint space. Lastly, we demonstrate point-based segmentation for the humerus and ulna using the detected landmarks as inputs. Our dataset will be publicly available at https://github.com/Akahori000/Ultrasound-Medial-Elbow-Dataset
URLs: https://github.com/Akahori000/Ultrasound-Medial-Elbow-Dataset
Authors: Hansoo Park, Chanwoo Kim, Jihyeon Kim, Hoseong Cho, Nhat Nguyen Bao Truong, Taehwan Kim, Seungryul Baek
Abstract: RGB-based 3D pose estimation methods have been successful with the development of deep learning and the emergence of high-quality 3D pose datasets. However, most existing methods do not operate well for testing images whose distribution is far from that of training data. However, most existing methods do not operate well for testing images whose distribution is far from that of training data. This problem might be alleviated by involving diverse data during training, however it is non-trivial to collect such diverse data with corresponding labels (i.e. 3D pose). In this paper, we introduced an unsupervised domain adaptation framework for 3D pose estimation that utilizes the unlabeled data in addition to labeled data via masked image modeling (MIM) framework. Foreground-centric reconstruction and attention regularization are further proposed to increase the effectiveness of unlabeled data usage. Experiments are conducted on the various datasets in human and hand pose estimation tasks, especially using the cross-domain scenario. We demonstrated the effectiveness of ours by achieving the state-of-the-art accuracy on all datasets.
Authors: Chengyi Cai, Zesheng Ye, Lei Feng, Jianzhong Qi, Feng Liu
Abstract: Visual reprogramming (VR) reuses pre-trained vision models for downstream image classification tasks by adding trainable noise patterns to inputs. When applied to vision-language models (e.g., CLIP), existing VR approaches follow the same pipeline used in vision models (e.g., ResNet, ViT), where ground-truth class labels are inserted into fixed text templates to guide the optimization of VR patterns. This label-based approach, however, overlooks the rich information and diverse attribute-guided textual representations that CLIP can exploit, which may lead to the misclassification of samples. In this paper, we propose Attribute-based Visual Reprogramming (AttrVR) for CLIP, utilizing descriptive attributes (DesAttrs) and distinctive attributes (DistAttrs), which respectively represent common and unique feature descriptions for different classes. Besides, as images of the same class may reflect different attributes after VR, AttrVR iteratively refines patterns using the $k$-nearest DesAttrs and DistAttrs for each image sample, enabling more dynamic and sample-specific optimization. Theoretically, AttrVR is shown to reduce intra-class variance and increase inter-class separation. Empirically, it achieves superior performance in 12 downstream tasks for both ViT-based and ResNet-based CLIP. The success of AttrVR facilitates more effective integration of VR from unimodal vision models into vision-language models. Our code is available at https://github.com/tmlr-group/AttrVR.
Authors: Runyi Hu, Jie Zhang, Yiming Li, Jiwei Li, Qing Guo, Han Qiu, Tianwei Zhang
Abstract: Artificial Intelligence Generated Content (AIGC) has advanced significantly, particularly with the development of video generation models such as text-to-video (T2V) models and image-to-video (I2V) models. However, like other AIGC types, video generation requires robust content control. A common approach is to embed watermarks, but most research has focused on images, with limited attention given to videos. Traditional methods, which embed watermarks frame-by-frame in a post-processing manner, often degrade video quality. In this paper, we propose VideoShield, a novel watermarking framework specifically designed for popular diffusion-based video generation models. Unlike post-processing methods, VideoShield embeds watermarks directly during video generation, eliminating the need for additional training. To ensure video integrity, we introduce a tamper localization feature that can detect changes both temporally (across frames) and spatially (within individual frames). Our method maps watermark bits to template bits, which are then used to generate watermarked noise during the denoising process. Using DDIM Inversion, we can reverse the video to its original watermarked noise, enabling straightforward watermark extraction. Additionally, template bits allow precise detection for potential temporal and spatial modification. Extensive experiments across various video models (both T2V and I2V models) demonstrate that our method effectively extracts watermarks and detects tamper without compromising video quality. Furthermore, we show that this approach is applicable to image generation models, enabling tamper detection in generated images as well. Codes and models are available at https://github.com/hurunyi/VideoShield.
Authors: Qiaojie Zheng, Jiucai Zhang, Xiaoli Zhang
Abstract: Current deep learning powered appearance based uncertainty-aware gaze estimation models produce inconsistent and unreliable uncertainty estimation that limits their adoptions in downstream applications. In this study, we propose a workflow to improve the accuracy of uncertainty estimation using probability calibration with a few post hoc samples. The probability calibration process employs a simple secondary regression model to compensate for inaccuracies in estimated uncertainties from the deep learning model. Training of the secondary model is detached from the main deep learning model and thus no expensive weight tuning is required. The added calibration process is lightweight and relatively independent from the deep learning process, making it fast to run and easy to implement. We evaluated the effectiveness of the calibration process under four potential application scenarios with two datasets that have distinctive image characteristics due to the data collection setups. The calibration process is most effective when the calibration and testing data share similar characteristics. Even under suboptimal circumstances that calibration and testing data differ, the calibration process can still make corrections to reduce prediction errors in uncertainty estimates made by uncalibrated models.
Authors: Mohammadreza Baharani, Ghazal Alinezhad Noghre, Armin Danesh Pazho, Gabriel Maldonado, Hamed Tabkhi
Abstract: Foundation Models (FM) have increasingly drawn the attention of researchers due to their scalability and generalization across diverse tasks. Inspired by the success of FMs and the principles that have driven advancements in Large Language Models (LLMs), we introduce MoFM as a novel Motion Foundation Model. MoFM is designed for the semantic understanding of complex human motions in both time and space. To facilitate large-scale training, MotionBook, a comprehensive human motion dictionary of discretized motions is designed and employed. MotionBook utilizes Thermal Cubes to capture spatio-temporal motion heatmaps, applying principles from discrete variational models to encode human movements into discrete units for a more efficient and scalable representation. MoFM, trained on a large corpus of motion data, provides a foundational backbone adaptable to diverse downstream tasks, supporting paradigms such as one-shot, unsupervised, and supervised tasks. This versatility makes MoFM well-suited for a wide range of motion-based applications.
Authors: Onat \c{S}ahin, Mohammad Altillawi, George Eskandar, Carlos Carbone, Ziyuan Liu
Abstract: Recent advances in diffusion models have significantly improved 3D generation, enabling the use of assets generated from an image for embodied AI simulations. However, the one-to-many nature of the image-to-3D problem limits their use due to inconsistent content and quality across views. Previous models optimize a 3D model by sampling views from a view-conditioned diffusion prior, but diffusion models cannot guarantee view consistency. Instead, we present ConsistentDreamer, where we first generate a set of fixed multi-view prior images and sample random views between them with another diffusion model through a score distillation sampling (SDS) loss. Thereby, we limit the discrepancies between the views guided by the SDS loss and ensure a consistent rough shape. In each iteration, we also use our generated multi-view prior images for fine-detail reconstruction. To balance between the rough shape and the fine-detail optimizations, we introduce dynamic task-dependent weights based on homoscedastic uncertainty, updated automatically in each iteration. Additionally, we employ opacity, depth distortion, and normal alignment losses to refine the surface for mesh extraction. Our method ensures better view consistency and visual quality compared to the state-of-the-art.
Authors: Shutong Zhang
Abstract: Semantic segmentation is an important task for autonomous driving. A powerful autonomous driving system should be capable of handling images under all conditions, including nighttime. Generating accurate and diverse nighttime semantic segmentation datasets is crucial for enhancing the performance of computer vision algorithms in low-light conditions. In this thesis, we introduce a novel approach named NPSim, which enables the simulation of realistic nighttime images from real daytime counterparts with monocular inverse rendering and ray tracing. NPSim comprises two key components: mesh reconstruction and relighting. The mesh reconstruction component generates an accurate representation of the scene structure by combining geometric information extracted from the input RGB image and semantic information from its corresponding semantic labels. The relighting component integrates real-world nighttime light sources and material characteristics to simulate the complex interplay of light and object surfaces under low-light conditions. The scope of this thesis mainly focuses on the implementation and evaluation of the mesh reconstruction component. Through experiments, we demonstrate the effectiveness of the mesh reconstruction component in producing high-quality scene meshes and their generality across different autonomous driving datasets. We also propose a detailed experiment plan for evaluating the entire pipeline, including both quantitative metrics in training state-of-the-art supervised and unsupervised semantic segmentation approaches and human perceptual studies, aiming to indicate the capability of our approach to generate realistic nighttime images and the value of our dataset in steering future progress in the field.
Authors: Boxuan Zhu, Sicheng Yang, Zhuo Wang, Haining Liang, Junxiao Shen
Abstract: Gesture recognition in resource-constrained scenarios faces significant challenges in achieving high accuracy and low latency. The streaming gesture recognition framework, Duo Streamers, proposed in this paper, addresses these challenges through a three-stage sparse recognition mechanism, an RNN-lite model with an external hidden state, and specialized training and post-processing pipelines, thereby making innovative progress in real-time performance and lightweight design. Experimental results show that Duo Streamers matches mainstream methods in accuracy metrics, while reducing the real-time factor by approximately 92.3%, i.e., delivering a nearly 13-fold speedup. In addition, the framework shrinks parameter counts to 1/38 (idle state) and 1/9 (busy state) compared to mainstream models. In summary, Duo Streamers not only offers an efficient and practical solution for streaming gesture recognition in resource-constrained devices but also lays a solid foundation for extended applications in multimodal and diverse scenarios.
Authors: Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu
Abstract: As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific knowledge in training data, has been widely used in privacy protection. However, MU for safety in MLLM has yet to be fully explored. To address this issue, we propose SAFEERASER, a safety unlearning benchmark for MLLMs, consisting of 3,000 images and 28.8K VQA pairs. We comprehensively evaluate unlearning methods from two perspectives: forget quality and model utility. Our findings show that existing MU methods struggle to maintain model performance while implementing the forget operation and often suffer from over-forgetting. Hence, we introduce Prompt Decouple (PD) Loss to alleviate over-forgetting through decouple prompt during unlearning process. To quantitatively measure over-forgetting mitigated by PD Loss, we propose a new metric called Safe Answer Refusal Rate (SARR). Experimental results demonstrate that combining PD Loss with existing unlearning methods can effectively prevent over-forgetting and achieve a decrease of 79.5% in the SARR metric of LLaVA-7B and LLaVA-13B, while maintaining forget quality and model utility. Our code and dataset will be released upon acceptance. Warning: This paper contains examples of harmful language and images, and reader discretion is recommended.
Authors: Yucheng Shi, Quanzheng Li, Jin Sun, Xiang Li, Ninghao Liu
Abstract: Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific objectives and provide justifiable explanations for their predictions. To address the above challenge, we propose a novel visual rejection sampling framework to improve the cognition and explainability of LMMs using self-synthesized data. Specifically, visual fine-tuning requires images, queries, and target answers. Our approach begins by synthesizing interpretable answers that include human-verifiable visual features. These features are based on expert-defined concepts, and carefully selected based on their alignment with the image content. After each round of fine-tuning, we apply a reward model-free filtering mechanism to select the highest-quality interpretable answers for the next round of tuning. This iterative process of synthetic data generation and fine-tuning progressively improves the model's ability to generate accurate and reasonable explanations. Experimental results demonstrate the effectiveness of our method in improving both the accuracy and explainability of specialized visual classification tasks.
Authors: Yishuo Wang, Feng Zhou
Abstract: Existing ocean front detection methods--including histogram-based variance analysis, Lyapunov exponent, gradient thresholding, and machine learning--suffer from critical limitations: discontinuous outputs, over-detection, reliance on single-threshold decisions, and lack of open-source implementations. To address these challenges, this paper proposes the Bayesian Front Detection and Tracking framework with Metric Space Analysis (BFDT-MSA). The framework introduces three innovations: (1) a Bayesian decision mechanism that integrates gradient priors and field operators to eliminate manual threshold sensitivity; (2) morphological refinement algorithms for merging fragmented fronts, deleting spurious rings, and thinning frontal zones to pixel-level accuracy; and (3) a novel metric space definition for temporal front tracking, enabling systematic analysis of front evolution. Validated on global SST data (2022--2024), BFDT-MSA reduces over-detection by $73\%$ compared to histogram-based methods while achieving superior intensity ($0.16^\circ$C/km), continuity, and spatiotemporal coherence. The open-source release bridges a critical gap in reproducible oceanographic research.
Authors: Xikai Tang, Ye Huang, Guangqiang Yin, Lixin Duan
Abstract: We present VPNeXt, a new and simple model for the Plain Vision Transformer (ViT). Unlike the many related studies that share the same homogeneous paradigms, VPNeXt offers a fresh perspective on dense representation based on ViT. In more detail, the proposed VPNeXt addressed two concerns about the existing paradigm: (1) Is it necessary to use a complex Transformer Mask Decoder architecture to obtain good representations? (2) Does the Plain ViT really need to depend on the mock pyramid feature for upsampling? For (1), we investigated the potential underlying reasons that contributed to the effectiveness of the Transformer Decoder and introduced the Visual Context Replay (VCR) to achieve similar effects efficiently. For (2), we introduced the ViTUp module. This module fully utilizes the previously overlooked ViT real pyramid feature to achieve better upsampling results compared to the earlier mock pyramid feature. This represents the first instance of such functionality in the field of semantic segmentation for Plain ViT. We performed ablation studies on related modules to verify their effectiveness gradually. We conducted relevant comparative experiments and visualizations to show that VPNeXt achieved state-of-the-art performance with a simple and effective design. Moreover, the proposed VPNeXt significantly exceeded the long-established mIoU wall/barrier of the VOC2012 dataset, setting a new state-of-the-art by a large margin, which also stands as the largest improvement since 2015.
Authors: Zhe Zhu, Honghua Chen, Xing He, Mingqiang Wei
Abstract: Point cloud completion is a fundamental yet not well-solved problem in 3D vision. Current approaches often rely on 3D coordinate information and/or additional data (e.g., images and scanning viewpoints) to fill in missing parts. Unlike these methods, we explore self-structure augmentation and propose PointSea for global-to-local point cloud completion. In the global stage, consider how we inspect a defective region of a physical object, we may observe it from various perspectives for a better understanding. Inspired by this, PointSea augments data representation by leveraging self-projected depth images from multiple views. To reconstruct a compact global shape from the cross-modal input, we incorporate a feature fusion module to fuse features at both intra-view and inter-view levels. In the local stage, to reveal highly detailed structures, we introduce a point generator called the self-structure dual-generator. This generator integrates both learned shape priors and geometric self-similarities for shape refinement. Unlike existing efforts that apply a unified strategy for all points, our dual-path design adapts refinement strategies conditioned on the structural type of each point, addressing the specific incompleteness of each point. Comprehensive experiments on widely-used benchmarks demonstrate that PointSea effectively understands global shapes and generates local details from incomplete input, showing clear improvements over existing methods.
Authors: Canyu Zhao, Mingyu Liu, Huanyi Zheng, Muzhi Zhu, Zhiyue Zhao, Hao Chen, Tong He, Chunhua Shen
Abstract: Our primary goal here is to create a good, generalist perception model that can tackle multiple tasks, within limits on computational resources and training data. To achieve this, we resort to text-to-image diffusion models pre-trained on billions of images. Our exhaustive evaluation metrics demonstrate that DICEPTION effectively tackles multiple perception tasks, achieving performance on par with state-of-the-art models. We achieve results on par with SAM-vit-h using only 0.06% of their data (e.g., 600K vs. 1B pixel-level annotated images). Inspired by Wang et al., DICEPTION formulates the outputs of various perception tasks using color encoding; and we show that the strategy of assigning random colors to different instances is highly effective in both entity segmentation and semantic segmentation. Unifying various perception tasks as conditional image generation enables us to fully leverage pre-trained text-to-image models. Thus, DICEPTION can be efficiently trained at a cost of orders of magnitude lower, compared to conventional models that were trained from scratch. When adapting our model to other tasks, it only requires fine-tuning on as few as 50 images and 1% of its parameters. DICEPTION provides valuable insights and a more promising solution for visual generalist models. Homepage: https://aim-uofa.github.io/Diception, Huggingface Demo: https://huggingface.co/spaces/Canyu/Diception-Demo.
URLs: https://aim-uofa.github.io/Diception,, https://huggingface.co/spaces/Canyu/Diception-Demo.
Authors: Gabriele Berton, Carlo Masone
Abstract: Retrieving images from the same location as a given query is an important component of multiple computer vision tasks, like Visual Place Recognition, Landmark Retrieval, Visual Localization, 3D reconstruction, and SLAM. However, existing solutions are built to specifically work for one of these tasks, and are known to fail when the requirements slightly change or when they meet out-of-distribution data. In this paper we combine a variety of existing methods, training techniques, and datasets to train a retrieval model, called MegaLoc, that is performant on multiple tasks. We find that MegaLoc (1) achieves state of the art on a large number of Visual Place Recognition datasets, (2) impressive results on common Landmark Retrieval datasets, and (3) sets a new state of the art for Visual Localization on the LaMAR datasets, where we only changed the retrieval method to the existing localization pipeline. The code for MegaLoc is available at https://github.com/gmberton/MegaLoc
Authors: Simon Boeder, Fabian Gigengack, Benjamin Risse
Abstract: Occupancy estimation has become a prominent task in 3D computer vision, particularly within the autonomous driving community. In this paper, we present a novel approach to occupancy estimation, termed GaussianFlowOcc, which is inspired by Gaussian Splatting and replaces traditional dense voxel grids with a sparse 3D Gaussian representation. Our efficient model architecture based on a Gaussian Transformer significantly reduces computational and memory requirements by eliminating the need for expensive 3D convolutions used with inefficient voxel-based representations that predominantly represent empty 3D spaces. GaussianFlowOcc effectively captures scene dynamics by estimating temporal flow for each Gaussian during the overall network training process, offering a straightforward solution to a complex problem that is often neglected by existing methods. Moreover, GaussianFlowOcc is designed for scalability, as it employs weak supervision and does not require costly dense 3D voxel annotations based on additional data (e.g., LiDAR). Through extensive experimentation, we demonstrate that GaussianFlowOcc significantly outperforms all previous methods for weakly supervised occupancy estimation on the nuScenes dataset while featuring an inference speed that is 50 times faster than current SOTA.
Authors: Andr\'e V. Duarte, Xuandong Zhao, Arlindo L. Oliveira, Lei Li
Abstract: How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data? Motivated by the hypothesis that a VLM is able to recognize images from its training corpus, we propose DIS-CO, a novel approach to infer the inclusion of copyrighted content during the model's development. By repeatedly querying a VLM with specific frames from targeted copyrighted material, DIS-CO extracts the content's identity through free-form text completions. To assess its effectiveness, we introduce MovieTection, a benchmark comprising 14,000 frames paired with detailed captions, drawn from films released both before and after a model's training cutoff. Our results show that DIS-CO significantly improves detection performance, nearly doubling the average AUC of the best prior method on models with logits available. Our findings also highlight a broader concern: all tested models appear to have been exposed to some extent to copyrighted content. Our code and data are available at https://github.com/avduarte333/DIS-CO
Authors: Tianrui Zhu, Shiyi Zhang, Jiawei Shao, Yansong Tang
Abstract: Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to $O(1)$ using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit
Authors: Tresor Y. Koffi, Youssef Mourchid, Mohammed Hindawi, Yohan Dupuis
Abstract: Falls among individuals, especially the elderly population, can lead to serious injuries and complications. Detecting impact moments within a fall event is crucial for providing timely assistance and minimizing the negative consequences. In this work, we aim to address this challenge by applying thorough preprocessing techniques to the multisensor dataset, the goal is to eliminate noise and improve data quality. Furthermore, we employ a feature selection process to identify the most relevant features derived from the multisensor UP-FALL dataset, which in turn will enhance the performance and efficiency of machine learning models. We then evaluate the efficiency of various machine learning models in detecting the impact moment using the resulting data information from multiple sensors. Through extensive experimentation, we assess the accuracy of our approach using various evaluation metrics. Our results achieve high accuracy rates in impact detection, showcasing the power of leveraging multisensor data for fall detection tasks. This highlights the potential of our approach to enhance fall detection systems and improve the overall safety and well-being of individuals at risk of falls.
Authors: Youssef Mourchid, Rim Slama
Abstract: This paper tackles the challenge of automatically assessing physical rehabilitation exercises for patients who perform the exercises without clinician supervision. The objective is to provide a quality score to ensure correct performance and achieve desired results. To achieve this goal, a new graph-based model, the Dense Spatio-Temporal Graph Conv-GRU Network with Transformer, is introduced. This model combines a modified version of STGCN and transformer architectures for efficient handling of spatio-temporal data. The key idea is to consider skeleton data respecting its non-linear structure as a graph and detecting joints playing the main role in each rehabilitation exercise. Dense connections and GRU mechanisms are used to rapidly process large 3D skeleton inputs and effectively model temporal dynamics. The transformer encoder's attention mechanism focuses on relevant parts of the input sequence, making it useful for evaluating rehabilitation exercises. The evaluation of our proposed approach on the KIMORE and UI-PRMD datasets highlighted its potential, surpassing state-of-the-art methods in terms of accuracy and computational time. This resulted in faster and more accurate learning and assessment of rehabilitation exercises. Additionally, our model provides valuable feedback through qualitative illustrations, effectively highlighting the significance of joints in specific exercises.
Authors: Luca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli, Lamberto Ballan, Fabio Galasso
Abstract: The success of collaboration between humans and robots in shared environments relies on the robot's real-time adaptation to human motion. Specifically, in Social Navigation, the agent should be close enough to assist but ready to back up to let the human move freely, avoiding collisions. Human trajectories emerge as crucial cues in Social Navigation, but they are partially observable from the robot's egocentric view and computationally complex to process. We present the first Social Dynamics Adaptation model (SDA) based on the robot's state-action history to infer the social dynamics. We propose a two-stage Reinforcement Learning framework: the first learns to encode the human trajectories into social dynamics and learns a motion policy conditioned on this encoded information, the current status, and the previous action. Here, the trajectories are fully visible, i.e., assumed as privileged information. In the second stage, the trained policy operates without direct access to trajectories. Instead, the model infers the social dynamics solely from the history of previous actions and statuses in real-time. Tested on the novel Habitat 3.0 platform, SDA sets a novel state-of-the-art (SotA) performance in finding and following humans. The code can be found at https://github.com/L-Scofano/SDA.
Authors: Qijun Gan, Song Wang, Shengtao Wu, Jianke Zhu
Abstract: Recently, artificial intelligence techniques for education have been received increasing attentions, while it still remains an open problem to design the effective music instrument instructing systems. Although key presses can be directly derived from sheet music, the transitional movements among key presses require more extensive guidance in piano performance. In this work, we construct a piano-hand motion generation benchmark to guide hand movements and fingerings for piano playing. To this end, we collect an annotated dataset, PianoMotion10M, consisting of 116 hours of piano playing videos from a bird's-eye view with 10 million annotated hand poses. We also introduce a powerful baseline model that generates hand motions from piano audios through a position predictor and a position-guided gesture generator. Furthermore, a series of evaluation metrics are designed to assess the performance of the baseline model, including motion similarity, smoothness, positional accuracy of left and right hands, and overall fidelity of movement distribution. Despite that piano key presses with respect to music scores or audios are already accessible, PianoMotion10M aims to provide guidance on piano fingering for instruction purposes. The source code and dataset can be accessed at https://github.com/agnJason/PianoMotion10M.
Authors: Alireza Aghelan, Ali Amiryan, Abolfazl Zarghani, Modjtaba Rouhani
Abstract: In the field of single image super-resolution (SISR), transformer-based models, have demonstrated significant advancements. However, the potential and efficiency of these models in applied fields such as real-world image super-resolution have been less noticed and there are substantial opportunities for improvement. Recently, composite fusion attention transformer (CFAT), outperformed previous state-of-the-art (SOTA) models in classic image super-resolution. In this paper, we propose a novel GAN-based framework by incorporating the CFAT model to effectively exploit the performance of transformers in real-world image super-resolution. In our proposed approach, we integrate a semantic-aware discriminator to reconstruct fine details more accurately and employ an adaptive degradation model to better simulate real-world degradations. Moreover, we introduce a new combination of loss functions by adding wavelet loss to loss functions of GAN-based models to better recover high-frequency details. Empirical results demonstrate that IG-CFAT significantly outperforms existing SOTA models in both quantitative and qualitative metrics. Our proposed model revolutionizes the field of real-world image super-resolution and demonstrates substantially better performance in recovering fine details and generating realistic textures. The introduction of IG-CFAT offers a robust and adaptable solution for real-world image super-resolution tasks.
Authors: Lei Li, Hannah Smith, Yilin Lyu, Julia Camps, Shuang Qian, Blanca Rodriguez, Abhirup Banerjee, Vicente Grau
Abstract: Cardiac digital twins (CDTs) offer personalized in-silico cardiac representations for the inference of multi-scale properties tied to cardiac mechanisms. The creation of CDTs requires precise information about the electrode position on the torso, especially for the personalized electrocardiogram (ECG) calibration. However, current studies commonly rely on additional acquisition of torso imaging and manual/semi-automatic methods for ECG electrode localization. In this study, we propose a novel and efficient topology-informed model to fully automatically extract personalized ECG standard electrode locations from 2D clinically standard cardiac MRIs. Specifically, we obtain the sparse torso contours from the cardiac MRIs and then localize the standard electrodes of 12-lead ECG from the contours. Cardiac MRIs aim at imaging of the heart instead of the torso, leading to incomplete torso geometry within the imaging. To tackle the missing topology, we incorporate the electrodes as a subset of the keypoints, which can be explicitly aligned with the 3D torso topology. The experimental results demonstrate that the proposed model outperforms the time-consuming conventional model projection-based method in terms of accuracy (Euclidean distance: $1.24 \pm 0.293$ cm vs. $1.48 \pm 0.362$ cm) and efficiency ($2$~s vs. $30$-$35$~min). We further demonstrate the effectiveness of using the detected electrodes for in-silico ECG simulation, highlighting their potential for creating accurate and efficient CDT models. The code is available at https://github.com/lileitech/12lead_ECG_electrode_localizer.
URLs: https://github.com/lileitech/12lead_ECG_electrode_localizer.
Authors: Md Awsafur Rahman, Zaber Ibn Abdul Hakim, Najibul Haque Sarker, Bishmoy Paul, Shaikh Anowarul Fattah
Abstract: The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. For long songs, our top-performing variant outperforms ViT by 8% in F1 score, is 38% faster, and uses 26% less memory, while also surpassing ConvNeXt with a 1% F1 score gain, 20% speed boost, and 67% memory reduction.
Authors: Yuxin Liu, Rongjun Ge, Yuting He, Zhan Wu, Shangwen Yang, Yuan Gao, Chenyu You, Ge Wang, Yang Chen, Shuo Li
Abstract: Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We propose the multi-scale integrated Transformer AMPlifier (TAMP), the first imaging foundation model for universal NICT enhancement. Pre-trained on 10.8 million physics-driven simulated NICT images, TAMP generalizes effectively across various NICT settings, defect degrees, and body regions. Moreover, a parameter-efficient fine-tuning strategy enables TAMP to adapt to specific clinical scenarios using only few slices. Extensive experiments, including radiologists and real-world validations, demonstrate that TAMP consistently improves image quality and clinical acceptability, underscoring its significant potential to advance CT imaging and broaden NICT applications in clinical practice.
Authors: Deqing Fu, Tong Xiao, Rui Wang, Wang Zhu, Pengchuan Zhang, Guan Pang, Robin Jia, Lawrence Chen
Abstract: Although reward models have been successful in improving multimodal large language models, the reward models themselves remain brutal and contain minimal information. Notably, existing reward models only mimic human annotations by assigning only one binary feedback to any text, no matter how long the text is. In the realm of multimodal language models, where models are required to process both images and texts, a naive reward model may learn implicit biases toward texts and become less grounded in images. In this paper, we propose a $\textbf{T}$oken-$\textbf{L}$evel $\textbf{D}$etective $\textbf{R}$eward Model ($\textbf{TLDR}$) to provide fine-grained annotations to each text token. We first introduce a perturbation-based method to generate synthetic hard negatives and their token-level labels to train TLDR models. Then we show the rich usefulness of TLDR models both in assisting off-the-shelf models to self-correct their generations, and in serving as a hallucination evaluation tool. We show that TLDR automatically trains a token-level likelihood optimization, and can improve the base model's performance significantly. Finally, we show that TLDR models can significantly speed up human annotation by 3 times to acquire a broader range of high-quality vision language data.
Authors: Peiwen Sun, Sitong Cheng, Xiangtai Li, Zhen Ye, Huadai Liu, Honggang Zhang, Wei Xue, Yike Guo
Abstract: Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple sources. Beyond text modality, we have also acquired a set of images and rationally paired stereo audios through retrieval to advance multimodal generation. Existing audio generation models tend to generate rather random and indistinct spatial audio. To provide accurate guidance for Latent Diffusion Models, we introduce the SpatialSonic model utilizing spatial-aware encoders and azimuth state matrices to reveal reasonable spatial guidance. By leveraging spatial guidance, our model not only achieves the objective of generating immersive and controllable spatial audio from text but also extends to other modalities as the pioneer attempt. Finally, under fair settings, we conduct subjective and objective evaluations on simulated and real-world data to compare our approach with prevailing methods. The results demonstrate the effectiveness of our method, highlighting its capability to generate spatial audio that adheres to physical rules.
Authors: Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui Zhang, Xuyang Liu, Weiya Li, Xuming Hu, Linfeng Zhang
Abstract: The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, AutoGnothi, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. AutoGnothi enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that AutoGnothi offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability.
Authors: Jiuhong Xiao, Giuseppe Loianno
Abstract: Geo-localization is an essential component of Unmanned Aerial Vehicle (UAV) navigation systems to ensure precise absolute self-localization in outdoor environments. To address the challenges of GPS signal interruptions or low illumination, Thermal Geo-localization (TG) employs aerial thermal imagery to align with reference satellite maps to accurately determine the UAV's location. However, existing TG methods lack uncertainty measurement in their outputs, compromising system robustness in the presence of textureless or corrupted thermal images, self-similar or outdated satellite maps, geometric noises, or thermal images exceeding satellite maps. To overcome these limitations, this paper presents UASTHN, a novel approach for Uncertainty Estimation (UE) in Deep Homography Estimation (DHE) tasks for TG applications. Specifically, we introduce a novel Crop-based Test-Time Augmentation (CropTTA) strategy, which leverages the homography consensus of cropped image views to effectively measure data uncertainty. This approach is complemented by Deep Ensembles (DE) employed for model uncertainty, offering comparable performance with improved efficiency and seamless integration with any DHE model. Extensive experiments across multiple DHE models demonstrate the effectiveness and efficiency of CropTTA in TG applications. Analysis of detected failure cases underscores the improved reliability of CropTTA under challenging conditions. Finally, we demonstrate the capability of combining CropTTA and DE for a comprehensive assessment of both data and model uncertainty. Our research provides profound insights into the broader intersection of localization and uncertainty estimation. The code and models are publicly available.
Authors: Xinyu Zhang, Zewei Zhou, Zhaoyi Wang, Yangjie Ji, Yanjun Huang, Hong Chen
Abstract: Vehicle-to-everything technologies (V2X) have become an ideal paradigm to extend the perception range and see through the occlusion. Exiting efforts focus on single-frame cooperative perception, however, how to capture the temporal cue between frames with V2X to facilitate the prediction task even the planning task is still underexplored. In this paper, we introduce the Co-MTP, a general cooperative trajectory prediction framework with multi-temporal fusion for autonomous driving, which leverages the V2X system to fully capture the interaction among agents in both history and future domains to benefit the planning. In the history domain, V2X can complement the incomplete history trajectory in single-vehicle perception, and we design a heterogeneous graph transformer to learn the fusion of the history feature from multiple agents and capture the history interaction. Moreover, the goal of prediction is to support future planning. Thus, in the future domain, V2X can provide the prediction results of surrounding objects, and we further extend the graph transformer to capture the future interaction among the ego planning and the other vehicles' intentions and obtain the final future scenario state under a certain planning action. We evaluate the Co-MTP framework on the real-world dataset V2X-Seq, and the results show that Co-MTP achieves state-of-the-art performance and that both history and future fusion can greatly benefit prediction.
Authors: Junyang Wang, Haiyang Xu, Xi Zhang, Ming Yan, Ji Zhang, Fei Huang, Jitao Sang
Abstract: The rapid increase in mobile device usage necessitates improved automation for seamless task management. However, many AI-driven frameworks struggle due to insufficient operational knowledge. Manually written knowledge helps but is labor-intensive and inefficient. To address these challenges, we introduce Mobile-Agent-V, a framework that leverages video guidance to provide rich and cost-effective operational knowledge for mobile automation. Mobile-Agent-V enhances task execution capabilities by leveraging video inputs without requiring specialized sampling or preprocessing. Mobile-Agent-V integrates a sliding window strategy and incorporates a video agent and deep-reflection agent to ensure that actions align with user instructions. Through this innovative approach, users can record task processes with guidance, enabling the system to autonomously learn and execute tasks efficiently. Experimental results show that Mobile-Agent-V achieves a 30% performance improvement compared to existing frameworks. The code will be open-sourced at https://github.com/X-PLUG/MobileAgent.
Authors: Tianhong Li, Qinyi Sun, Lijie Fan, Kaiming He
Abstract: Modularization is a cornerstone of computer science, abstracting complex functions into atomic building blocks. In this paper, we introduce a new level of modularization by abstracting generative models into atomic generative modules. Analogous to fractals in mathematics, our method constructs a new type of generative model by recursively invoking atomic generative modules, resulting in self-similar fractal architectures that we call fractal generative models. As a running example, we instantiate our fractal framework using autoregressive models as the atomic generative modules and examine it on the challenging task of pixel-by-pixel image generation, demonstrating strong performance in both likelihood estimation and generation quality. We hope this work could open a new paradigm in generative modeling and provide a fertile ground for future research. Code is available at https://github.com/LTH14/fractalgen.