Authors: Fangzhou Lin, Zilin Dai, Rigved Sanku, Songlin Hou, Kazunori D Yamada, Haichong K. Zhang, Ziming Zhang
Abstract: The single-view image guided point cloud completion (SVIPC) task aims to reconstruct a complete point cloud from a partial input with the help of a single-view image. While previous works have demonstrated the effectiveness of this multimodal approach, the fundamental necessity of image guidance remains largely unexamined. To explore this, we propose a strong baseline approach for SVIPC based on an attention-based multi-branch encoder-decoder network that only takes partial point clouds as input, view-free. Our hierarchical self-fusion mechanism, driven by cross-attention and self-attention layers, effectively integrates information across multiple streams, enriching feature representations and strengthening the networks ability to capture geometric structures. Extensive experiments and ablation studies on the ShapeNet-ViPC dataset demonstrate that our view-free framework performs superiorly to state-of-the-art SVIPC methods. We hope our findings provide new insights into the development of multimodal learning in SVIPC. Our demo code will be available at https://github.com/Zhang-VISLab.
Authors: Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei YE, Kuofeng Gao, Yi Huang, Yuan Yao
Abstract: Vision-Language Models (VLMs) have demonstrated great potential in real-world applications. While existing research primarily focuses on improving their accuracy, the efficiency remains underexplored. Given the real-time demands of many applications and the high inference overhead of VLMs, efficiency robustness is a critical issue. However, previous studies evaluate efficiency robustness under unrealistic assumptions, requiring access to the model architecture and parameters -- an impractical scenario in ML-as-a-service settings, where VLMs are deployed via inference APIs. To address this gap, we propose VLMInferSlow, a novel approach for evaluating VLM efficiency robustness in a realistic black-box setting. VLMInferSlow incorporates fine-grained efficiency modeling tailored to VLM inference and leverages zero-order optimization to search for adversarial examples. Experimental results show that VLMInferSlow generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%. We hope this research raises the community's awareness about the efficiency robustness of VLMs.
Authors: Ruoyu Wang, Tong Yu, Junda Wu, Yao Liu, Julian McAuley, Lina Yao
Abstract: Visual Language Navigation (VLN) is a fundamental task within the field of Embodied AI, focusing on the ability of agents to navigate complex environments based on natural language instructions. Despite the progress made by existing methods, these methods often present some common challenges. First, they rely on pre-trained backbone models for visual perception, which struggle with the dynamic viewpoints in VLN scenarios. Second, the performance is limited when using pre-trained LLMs or VLMs without fine-tuning, due to the absence of VLN domain knowledge. Third, while fine-tuning LLMs and VLMs can improve results, their computational costs are higher than those without fine-tuning. To address these limitations, we propose Weakly-supervised Partial Contrastive Learning (WPCL), a method that enhances an agent's ability to identify objects from dynamic viewpoints in VLN scenarios by effectively integrating pre-trained VLM knowledge into the perception process, without requiring VLM fine-tuning. Our method enhances the agent's ability to interpret and respond to environmental cues while ensuring computational efficiency. Experimental results have shown that our method outperforms the baseline methods on multiple benchmarks, which validate the effectiveness, robustness and generalizability of our method.
Authors: Akarshani Ramanayake, Nihal Kodikara
Abstract: In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene mapping of the surrounding objects is an essential task in addressing the above problem. Despite its importance in dense vehicle traffic conditions, 3D scene reconstruction of object shapes with higher boundary level accuracy is not yet entirely considered in current literature. The sign distance function represents any shape through parameters that calculate the distance from any point in space to the closest obstacle surface, making it more efficient in terms of storage. In recent studies, researchers have started to formulate problems with Implicit 3D reconstruction methods in the autonomous driving domain, highlighting the possibility of using sign distance function to map obstacles effectively. This research addresses this gap by developing a learning-based 3D scene reconstruction methodology that leverages LiDAR data and a deep neural network to build a the static Signed Distance Function (SDF) maps. Unlike traditional polygonal representations, this approach has the potential to map 3D obstacle shapes with more boundary-level details. Our preliminary results demonstrate that this method would significantly enhance collision detection performance, particularly in congested and dynamic environments.
Authors: Fatmah AlHindaassi, Mohammed Talha Alam, Fakhri Karray
Abstract: Adverse weather conditions, particularly fog, pose a significant challenge to autonomous vehicles, surveillance systems, and other safety-critical applications by severely degrading visual information. We introduce ADAM-Dehaze, an adaptive, density-aware dehazing framework that jointly optimizes image restoration and object detection under varying fog intensities. A lightweight Haze Density Estimation Network (HDEN) classifies each input as light, medium, or heavy fog. Based on this score, the system dynamically routes the image through one of three CORUN branches: Light, Medium, or Complex, each tailored to its haze regime. A novel adaptive loss balances physical-model coherence and perceptual fidelity, ensuring both accurate defogging and preservation of fine details. On Cityscapes and the real-world RTTS benchmark, ADAM-Dehaze improves PSNR by up to 2.1 dB, reduces FADE by 30 percent, and increases object detection mAP by up to 13 points, while cutting inference time by 20 percent. These results highlight the importance of intensity-specific processing and seamless integration with downstream vision tasks. Code available at: https://github.com/talha-alam/ADAM-Dehaze.
Authors: Jiahao Wang, Hualian Sheng, Sijia Cai, Weizhan Zhang, Caixia Yan, Yachuang Feng, Bing Deng, Jieping Ye
Abstract: Video diffusion models substantially boost the productivity of artistic workflows with high-quality portrait video generative capacity. However, prevailing pipelines are primarily constrained to single-shot creation, while real-world applications urge for multiple shots with identity consistency and flexible content controllability. In this work, we propose EchoShot, a native and scalable multi-shot framework for portrait customization built upon a foundation video diffusion model. To start with, we propose shot-aware position embedding mechanisms within video diffusion transformer architecture to model inter-shot variations and establish intricate correspondence between multi-shot visual content and their textual descriptions. This simple yet effective design enables direct training on multi-shot video data without introducing additional computational overhead. To facilitate model training within multi-shot scenario, we construct PortraitGala, a large-scale and high-fidelity human-centric video dataset featuring cross-shot identity consistency and fine-grained captions such as facial attributes, outfits, and dynamic motions. To further enhance applicability, we extend EchoShot to perform reference image-based personalized multi-shot generation and long video synthesis with infinite shot counts. Extensive evaluations demonstrate that EchoShot achieves superior identity consistency as well as attribute-level controllability in multi-shot portrait video generation. Notably, the proposed framework demonstrates potential as a foundational paradigm for general multi-shot video modeling.
Authors: Dominic Akt, Marco Peer, Florian Kleber
Abstract: This paper tackles the task of writer identification for Greek papyri. A common preprocessing step in writer identification pipelines is image binarization, which prevents the model from learning background features. This is challenging in historical documents, in our case Greek papyri, as background is often non-uniform, fragmented, and discolored with visible fiber structures. We compare traditional binarization methods to state-of-the-art Deep Learning (DL) models, evaluating the impact of binarization quality on subsequent writer identification performance. DL models are trained with and without a custom data augmentation technique, as well as different model selection criteria are applied. The performance of these binarization methods, is then systematically evaluated on the DIBCO 2019 dataset. The impact of binarization on writer identification is subsequently evaluated using a state-of-the-art approach for writer identification. The results of this analysis highlight the influence of data augmentation for DL methods. Furthermore, findings indicate a strong correlation between binarization effectiveness on papyri documents of DIBCO 2019 and downstream writer identification performance.
Authors: Abdolazim Rezaei, Mehdi Sookhak, Ahmad Patooghy
Abstract: Connected and Autonomous Vehicles (CAVs) rely on a range of devices that often process privacy-sensitive data. Among these, roadside units play a critical role particularly through the use of AI-equipped (AIE) cameras for applications such as violation detection. However, the privacy risks associated with captured imagery remain a major concern, as such data can be misused for identity theft, profiling, or unauthorized commercial purposes. While traditional techniques such as face blurring and obfuscation have been applied to mitigate privacy risks, individual privacy remains at risk, as individuals can still be tracked using other features such as their clothing. This paper introduces a novel privacy-preserving framework that leverages feedback-based reinforcement learning (RL) and vision-language models (VLMs) to protect sensitive visual information captured by AIE cameras. The main idea is to convert images into semantically equivalent textual descriptions, ensuring that scene-relevant information is retained while visual privacy is preserved. A hierarchical RL strategy is employed to iteratively refine the generated text, enhancing both semantic accuracy and privacy. Evaluation results demonstrate significant improvements in both privacy protection and textual quality, with the Unique Word Count increasing by approximately 77\% and Detail Density by around 50\% compared to existing approaches.
Authors: Rim Assouel, Declan Campbell, Taylor Webb
Abstract: To accurately process a visual scene, observers must bind features together to represent individual objects. This capacity is necessary, for instance, to distinguish an image containing a red square and a blue circle from an image containing a blue square and a red circle. Recent work has found that language models solve this 'binding problem' via a set of symbol-like, content-independent indices, but it is unclear whether similar mechanisms are employed by vision language models (VLMs). This question is especially relevant, given the persistent failures of VLMs on tasks that require binding. Here, we identify a set of emergent symbolic mechanisms that support binding in VLMs via a content-independent, spatial indexing scheme. Moreover, we find that binding errors can be traced directly to failures in these mechanisms. Taken together, these results shed light on the mechanisms that support symbol-like processing in VLMs, and suggest possible avenues for addressing the persistent binding failures exhibited by these models.
Authors: Elif Keles, Merve Yazol, Gorkem Durak, Ziliang Hong, Halil Ertugrul Aktas, Zheyuan Zhang, Linkai Peng, Onkar Susladkar, Necati Guzelyel, Oznur Leman Boyunaga, Cemal Yazici, Mark Lowe, Aliye Uc, Ulas Bagci
Abstract: Objective: Our study aimed to evaluate and validate PanSegNet, a deep learning (DL) algorithm for pediatric pancreas segmentation on MRI in children with acute pancreatitis (AP), chronic pancreatitis (CP), and healthy controls. Methods: With IRB approval, we retrospectively collected 84 MRI scans (1.5T/3T Siemens Aera/Verio) from children aged 2-19 years at Gazi University (2015-2024). The dataset includes healthy children as well as patients diagnosed with AP or CP based on clinical criteria. Pediatric and general radiologists manually segmented the pancreas, then confirmed by a senior pediatric radiologist. PanSegNet-generated segmentations were assessed using Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff distance (HD95). Cohen's kappa measured observer agreement. Results: Pancreas MRI T2W scans were obtained from 42 children with AP/CP (mean age: 11.73 +/- 3.9 years) and 42 healthy children (mean age: 11.19 +/- 4.88 years). PanSegNet achieved DSC scores of 88% (controls), 81% (AP), and 80% (CP), with HD95 values of 3.98 mm (controls), 9.85 mm (AP), and 15.67 mm (CP). Inter-observer kappa was 0.86 (controls), 0.82 (pancreatitis), and intra-observer agreement reached 0.88 and 0.81. Strong agreement was observed between automated and manual volumes (R^2 = 0.85 in controls, 0.77 in diseased), demonstrating clinical reliability. Conclusion: PanSegNet represents the first validated deep learning solution for pancreatic MRI segmentation, achieving expert-level performance across healthy and diseased states. This tool, algorithm, along with our annotated dataset, are freely available on GitHub and OSF, advancing accessible, radiation-free pediatric pancreatic imaging and fostering collaborative research in this underserved domain.
Authors: Liangyan Li, Yimo Ning, Kevin Le, Wei Dong, Yunzhe Li, Jun Chen, Xiaohong Liu
Abstract: This paper introduces a novel framework for image and video demoir\'eing by integrating Maximum A Posteriori (MAP) estimation with advanced deep learning techniques. Demoir\'eing addresses inherently nonlinear degradation processes, which pose significant challenges for existing methods. Traditional supervised learning approaches either fail to remove moir\'e patterns completely or produce overly smooth results. This stems from constrained model capacity and scarce training data, which inadequately represent the clean image distribution and hinder accurate reconstruction of ground-truth images. While generative models excel in image restoration for linear degradations, they struggle with nonlinear cases such as demoir\'eing and often introduce artifacts. To address these limitations, we propose a hybrid MAP-based framework that integrates two complementary components. The first is a supervised learning model enhanced with efficient linear attention Test-Time Training (TTT) modules, which directly learn nonlinear mappings for RAW-to-sRGB demoir\'eing. The second is a Truncated Flow Matching Prior (TFMP) that further refines the outputs by aligning them with the clean image distribution, effectively restoring high-frequency details and suppressing artifacts. These two components combine the computational efficiency of linear attention with the refinement abilities of generative models, resulting in improved restoration performance.
Authors: Yosub Shin, Igor Molybog
Abstract: Video synchronization-aligning multiple video streams capturing the same event from different angles-is crucial for applications such as reality TV show production, sports analysis, surveillance, and autonomous systems. Prior work has heavily relied on audio cues or specific visual events, limiting applicability in diverse settings where such signals may be unreliable or absent. Additionally, existing benchmarks for video synchronization lack generality and reproducibility, restricting progress in the field. In this work, we introduce VideoSync, a video synchronization framework that operates independently of specific feature extraction methods, such as human pose estimation, enabling broader applicability across different content types. We evaluate our system on newly composed datasets covering single-human, multi-human, and non-human scenarios, providing both the methodology and code for dataset creation to establish reproducible benchmarks. Our analysis reveals biases in prior SOTA work, particularly in SeSyn-Net's preprocessing pipeline, leading to inflated performance claims. We correct these biases and propose a more rigorous evaluation framework, demonstrating that VideoSync outperforms existing approaches, including SeSyn-Net, under fair experimental conditions. Additionally, we explore various synchronization offset prediction methods, identifying a convolutional neural network (CNN)-based model as the most effective. Our findings advance video synchronization beyond domain-specific constraints, making it more generalizable and robust for real-world applications.
Authors: Zhongchen Zhao, Chaodong Xiao, Hui Lin, Qi Xie, Lei Zhang, Deyu Meng
Abstract: Global dependency modeling and spatial position modeling are two core issues of the foundational architecture design in current deep learning frameworks. Recently, Vision Transformers (ViTs) have achieved remarkable success in computer vision, leveraging the powerful global dependency modeling capability of the self-attention mechanism. Furthermore, Mamba2 has demonstrated its significant potential in natural language processing tasks by explicitly modeling the spatial adjacency prior through the structured mask. In this paper, we propose Polyline Path Masked Attention (PPMA) that integrates the self-attention mechanism of ViTs with an enhanced structured mask of Mamba2, harnessing the complementary strengths of both architectures. Specifically, we first ameliorate the traditional structured mask of Mamba2 by introducing a 2D polyline path scanning strategy and derive its corresponding structured mask, polyline path mask, which better preserves the adjacency relationships among image tokens. Notably, we conduct a thorough theoretical analysis on the structural characteristics of the proposed polyline path mask and design an efficient algorithm for the computation of the polyline path mask. Next, we embed the polyline path mask into the self-attention mechanism of ViTs, enabling explicit modeling of spatial adjacency prior. Extensive experiments on standard benchmarks, including image classification, object detection, and segmentation, demonstrate that our model outperforms previous state-of-the-art approaches based on both state-space models and Transformers. For example, our proposed PPMA-T/S/B models achieve 48.7%/51.1%/52.3% mIoU on the ADE20K semantic segmentation task, surpassing RMT-T/S/B by 0.7%/1.3%/0.3%, respectively. Code is available at https://github.com/zhongchenzhao/PPMA.
Authors: Jiawen Yang, Shuhao Chen, Yucong Duan, Ke Tang, Yu Zhang
Abstract: Unsupervised domain adaptation (UDA) methods effectively bridge domain gaps but become struggled when the source and target domains belong to entirely distinct modalities. To address this limitation, we propose a novel setting called Heterogeneous-Modal Unsupervised Domain Adaptation (HMUDA), which enables knowledge transfer between completely different modalities by leveraging a bridge domain containing unlabeled samples from both modalities. To learn under the HMUDA setting, we propose Latent Space Bridging (LSB), a specialized framework designed for the semantic segmentation task. Specifically, LSB utilizes a dual-branch architecture, incorporating a feature consistency loss to align representations across modalities and a domain alignment loss to reduce discrepancies between class centroids across domains. Extensive experiments conducted on six benchmark datasets demonstrate that LSB achieves state-of-the-art performance.
Authors: Jingwei Zhang, Xi Han, Hong Qin, Mahdi S. Hosseini, Dimitris Samaras
Abstract: Mamba, a State Space Model (SSM) that accelerates training by recasting recurrence as a parallel selective scan, has recently emerged as a linearly-scaling, efficient alternative to self-attention. Because of its unidirectional nature, each state in Mamba only has information of its previous states and is blind to states after. Current Mamba-based computer-vision methods typically overcome this limitation by augmenting Mamba's global forward scan with a global backward scan, forming a bi-directional scan that restores a full receptive field. However, this operation doubles the computational load, eroding much of the efficiency advantage that originally Mamba have. To eliminate this extra scans, we introduce LBMamba, a locally bi-directional SSM block that embeds a lightweight locally backward scan inside the forward selective scan and executes it entirely in per-thread registers. Building on LBMamba, we present LBVim, a scalable vision backbone that alternates scan directions every two layers to recover a global receptive field without extra backward sweeps. We validate the versatility of our approach on both natural images and whole slide images (WSIs). We show that our LBVim constantly offers a superior performance-throughput trade-off. That is under the same throughput, LBVim achieves 0.8% to 1.6% higher top-1 accuracy on the ImageNet-1K classification dataset, 0.6% to 2.7% higher mIoU on the ADE20K semantic segmentation dataset, 0.9% higher APb and 1.1% higher APm on the COCO detection dataset. We also integrate LBMamba into the SOTA pathology multiple instance learning (MIL) approach, MambaMIL, which uses single directional scan. Experiments on 3 public WSI classification datasets for show that our method achieves a relative improvement of up to 3.06% better AUC, 3.39% better F1, 1.67% better accuracy.
Authors: Sungrae Hong, Hyeongmin Park, Youngsin Ko, Sol Lee, Bryan Wong, Mun Yong Yi
Abstract: As the frontline data for cancer diagnosis, microscopic pathology images are fundamental for providing patients with rapid and accurate treatment. However, despite their practical value, the deep learning community has largely overlooked their usage. This paper proposes a novel approach to classifying microscopy images as time series data, addressing the unique challenges posed by their manual acquisition and weakly labeled nature. The proposed method fits image sequences of varying lengths to a fixed-length target by leveraging Dynamic Time-series Warping (DTW). Attention-based pooling is employed to predict the class of the case simultaneously. We demonstrate the effectiveness of our approach by comparing performance with various baselines and showcasing the benefits of using various inference strategies in achieving stable and reliable results. Ablation studies further validate the contribution of each component. Our approach contributes to medical image analysis by not only embracing microscopic images but also lifting them to a trustworthy level of performance.
Authors: Cong Wang, Zexuan Deng, Zhiwei Jiang, Fei Shen, Yafeng Yin, Shiwei Gan, Zifeng Cheng, Shiping Ge, Qing Gu
Abstract: Sign Language Video Generation (SLVG) seeks to generate identity-preserving sign language videos from spoken language texts. Existing methods primarily rely on the single coarse condition (\eg, skeleton sequences) as the intermediary to bridge the translation model and the video generation model, which limits both the naturalness and expressiveness of the generated videos. To overcome these limitations, we propose SignViP, a novel SLVG framework that incorporates multiple fine-grained conditions for improved generation fidelity. Rather than directly translating error-prone high-dimensional conditions, SignViP adopts a discrete tokenization paradigm to integrate and represent fine-grained conditions (\ie, fine-grained poses and 3D hands). SignViP contains three core components. (1) Sign Video Diffusion Model is jointly trained with a multi-condition encoder to learn continuous embeddings that encapsulate fine-grained motion and appearance. (2) Finite Scalar Quantization (FSQ) Autoencoder is further trained to compress and quantize these embeddings into discrete tokens for compact representation of the conditions. (3) Multi-Condition Token Translator is trained to translate spoken language text to discrete multi-condition tokens. During inference, Multi-Condition Token Translator first translates the spoken language text into discrete multi-condition tokens. These tokens are then decoded to continuous embeddings by FSQ Autoencoder, which are subsequently injected into Sign Video Diffusion Model to guide video generation. Experimental results show that SignViP achieves state-of-the-art performance across metrics, including video quality, temporal coherence, and semantic fidelity. The code is available at https://github.com/umnooob/signvip/.
Authors: Connor Malone, Owen Claxton, Iman Shames, Michael Milford
Abstract: Stand-alone Visual Place Recognition (VPR) systems have little defence against a well-designed adversarial attack, which can lead to disastrous consequences when deployed for robot navigation. This paper extensively analyzes the effect of four adversarial attacks common in other perception tasks and four novel VPR-specific attacks on VPR localization performance. We then propose how to close the loop between VPR, an Adversarial Attack Detector (AAD), and active navigation decisions by demonstrating the performance benefit of simulated AADs in a novel experiment paradigm -- which we detail for the robotics community to use as a system framework. In the proposed experiment paradigm, we see the addition of AADs across a range of detection accuracies can improve performance over baseline; demonstrating a significant improvement -- such as a ~50% reduction in the mean along-track localization error -- can be achieved with True Positive and False Positive detection rates of only 75% and up to 25% respectively. We examine a variety of metrics including: Along-Track Error, Percentage of Time Attacked, Percentage of Time in an `Unsafe' State, and Longest Continuous Time Under Attack. Expanding further on these results, we provide the first investigation into the efficacy of the Fast Gradient Sign Method (FGSM) adversarial attack for VPR. The analysis in this work highlights the need for AADs in real-world systems for trustworthy navigation, and informs quantitative requirements for system design.
Authors: Weiwei Duan, Michael P. Gerlek, Steven N. Minton, Craig A. Knoblock, Fandel Lin, Theresa Chen, Leeje Jang, Sofia Kirsanova, Zekun Li, Yijun Lin, Yao-Yi Chiang
Abstract: Historical geologic maps contain rich geospatial information, such as rock units, faults, folds, and bedding planes, that is critical for assessing mineral resources essential to renewable energy, electric vehicles, and national security. However, digitizing maps remains a labor-intensive and time-consuming task. We present DIGMAPPER, a modular, scalable system developed in collaboration with the United States Geological Survey (USGS) to automate the digitization of geologic maps. DIGMAPPER features a fully dockerized, workflow-orchestrated architecture that integrates state-of-the-art deep learning models for map layout analysis, feature extraction, and georeferencing. To overcome challenges such as limited training data and complex visual content, our system employs innovative techniques, including in-context learning with large language models, synthetic data generation, and transformer-based models. Evaluations on over 100 annotated maps from the DARPA-USGS dataset demonstrate high accuracy across polygon, line, and point feature extraction, and reliable georeferencing performance. Deployed at USGS, DIGMAPPER significantly accelerates the creation of analysis-ready geospatial datasets, supporting national-scale critical mineral assessments and broader geoscientific applications.
Authors: Liangjing Shao, Linxin Bai, Chenkang Du, Xinrong Chen
Abstract: Monocular depth estimation and ego-motion estimation are significant tasks for scene perception and navigation in stable, accurate and efficient robot-assisted endoscopy. To tackle lighting variations and sparse textures in endoscopic scenes, multiple techniques including optical flow, appearance flow and intrinsic image decomposition have been introduced into the existing methods. However, the effective training strategy for multiple modules are still critical to deal with both illumination issues and information interference for self-supervised depth estimation in endoscopy. Therefore, a novel framework with multistep efficient finetuning is proposed in this work. In each epoch of end-to-end training, the process is divided into three steps, including optical flow registration, multiscale image decomposition and multiple transformation alignments. At each step, only the related networks are trained without interference of irrelevant information. Based on parameter-efficient finetuning on the foundation model, the proposed method achieves state-of-the-art performance on self-supervised depth estimation on SCARED dataset and zero-shot depth estimation on Hamlyn dataset, with 4\%$\sim$10\% lower error. The evaluation code of this work has been published on https://github.com/BaymaxShao/EndoMUST.
Authors: Tianchen Zhao, Ke Hong, Xinhao Yang, Xuefeng Xiao, Huixia Li, Feng Ling, Ruiqi Xie, Siqi Chen, Hongyu Zhu, Yichong Zhang, Yu Wang
Abstract: In visual generation, the quadratic complexity of attention mechanisms results in high memory and computational costs, especially for longer token sequences required in high-resolution image or multi-frame video generation. To address this, prior research has explored techniques such as sparsification and quantization. However, these techniques face significant challenges under low density and reduced bitwidths. Through systematic analysis, we identify that the core difficulty stems from the dispersed and irregular characteristics of visual attention patterns. Therefore, instead of introducing specialized sparsification and quantization design to accommodate such patterns, we propose an alternative strategy: *reorganizing* the attention pattern to alleviate the challenges. Inspired by the local aggregation nature of visual feature extraction, we design a novel **Pattern-Aware token ReOrdering (PARO)** technique, which unifies the diverse attention patterns into a hardware-friendly block-wise pattern. This unification substantially simplifies and enhances both sparsification and quantization. We evaluate the performance-efficiency trade-offs of various design choices and finalize a methodology tailored for the unified pattern. Our approach, **PAROAttention**, achieves video and image generation with lossless metrics, and nearly identical results from full-precision (FP) baselines, while operating at notably lower density (~20%-30%) and bitwidth (**INT8/INT4**), achieving a **1.9x** to **2.7x** end-to-end latency speedup.
Authors: Yong Liu, SongLi Wu, Sule Bai, Jiahao Wang, Yitong Wang, Yansong Tang
Abstract: Open-vocabulary segmentation aims to achieve segmentation of arbitrary categories given unlimited text inputs as guidance. To achieve this, recent works have focused on developing various technical routes to exploit the potential of large-scale pre-trained vision-language models and have made significant progress on existing benchmarks. However, we find that existing test sets are limited in measuring the models' comprehension of ``open-vocabulary" concepts, as their semantic space closely resembles the training space, even with many overlapping categories. To this end, we present a new benchmark named OpenBench that differs significantly from the training semantics. It is designed to better assess the model's ability to understand and segment a wide range of real-world concepts. When testing existing methods on OpenBench, we find that their performance diverges from the conclusions drawn on existing test sets. In addition, we propose a method named OVSNet to improve the segmentation performance for diverse and open scenarios. Through elaborate fusion of heterogeneous features and cost-free expansion of the training space, OVSNet achieves state-of-the-art results on both existing datasets and our proposed OpenBench. Corresponding analysis demonstrate the soundness and effectiveness of our proposed benchmark and method.
Authors: Yucheng Jin, Jinyan Chen, Ziyue He, Baojun Han, Furan An
Abstract: Human pose estimation in low-resolution videos presents a fundamental challenge in computer vision. Conventional methods either assume high-quality inputs or employ computationally expensive cascaded processing, which limits their deployment in resource-constrained environments. We propose STAR-Pose, a spatial-temporal adaptive super-resolution framework specifically designed for video-based human pose estimation. Our method features a novel spatial-temporal Transformer with LeakyReLU-modified linear attention, which efficiently captures long-range temporal dependencies. Moreover, it is complemented by an adaptive fusion module that integrates parallel CNN branch for local texture enhancement. We also design a pose-aware compound loss to achieve task-oriented super-resolution. This loss guides the network to reconstruct structural features that are most beneficial for keypoint localization, rather than optimizing purely for visual quality. Extensive experiments on several mainstream video HPE datasets demonstrate that STAR-Pose outperforms existing approaches. It achieves up to 5.2% mAP improvement under extremely low-resolution (64x48) conditions while delivering 2.8x to 4.4x faster inference than cascaded approaches.
Authors: Byung Hoon Lee, Wooseok Shin, Sung Won Han
Abstract: The word-level lipreading approach typically employs a two-stage framework with separate frontend and backend architectures to model dynamic lip movements. Each component has been extensively studied, and in the backend architecture, temporal convolutional networks (TCNs) have been widely adopted in state-of-the-art methods. Recently, dense skip connections have been introduced in TCNs to mitigate the limited density of the receptive field, thereby improving the modeling of complex temporal representations. However, their performance remains constrained owing to potential information loss regarding the continuous nature of lip movements, caused by blind spots in the receptive field. To address this limitation, we propose TD3Net, a temporal densely connected multi-dilated convolutional network that combines dense skip connections and multi-dilated temporal convolutions as the backend architecture. TD3Net covers a wide and dense receptive field without blind spots by applying different dilation factors to skip-connected features. Experimental results on a word-level lipreading task using two large publicly available datasets, Lip Reading in the Wild (LRW) and LRW-1000, indicate that the proposed method achieves performance comparable to state-of-the-art methods. It achieved higher accuracy with fewer parameters and lower floating-point operations compared to existing TCN-based backend architectures. Moreover, visualization results suggest that our approach effectively utilizes diverse temporal features while preserving temporal continuity, presenting notable advantages in lipreading systems. The code is available at our GitHub repository: https://github.com/Leebh-kor/TD3Net-A-Temporal-Densely-Connected-Multi-dilated-Convolutional-Network-for-Lipreading
Authors: Yizhe Li, Sanping Zhou, Zheng Qin, Le Wang
Abstract: Dense video captioning is a challenging task that aims to localize and caption multiple events in an untrimmed video. Recent studies mainly follow the transformer-based architecture to jointly perform the two sub-tasks, i.e., event localization and caption generation, in an end-to-end manner. Based on the general philosophy of detection transformer, these methods implicitly learn the event locations and event semantics, which requires a large amount of training data and limits the model's performance in practice. In this paper, we propose a novel dense video captioning framework, named PR-DETR, which injects the explicit position and relation prior into the detection transformer to improve the localization accuracy and caption quality, simultaneously. On the one hand, we first generate a set of position-anchored queries to provide the scene-specific position and semantic information about potential events as position prior, which serves as the initial event search regions to eliminate the implausible event proposals. On the other hand, we further design an event relation encoder to explicitly calculate the relationship between event boundaries as relation prior to guide the event interaction to improve the semantic coherence of the captions. Extensive ablation studies are conducted to verify the effectiveness of the position and relation prior. Experimental results also show the competitive performance of our method on ActivityNet Captions and YouCook2 datasets.
Authors: Yuan Zhang, Chun-Kai Fan, Tao Huang, Ming Lu, Sicheng Yu, Junwen Pan, Kuan Cheng, Qi She, Shanghang Zhang
Abstract: Inspired by text prompts in large language models (LLMs), visual prompts have been explored to enhance the reasoning capabilities of large vision-language models (LVLMs). Current methods design heuristic visual prompts, such as overlaying a text-query-guided attention heatmap on the original input image. However, designing effective prompts manually is challenging and time-consuming, and it often fails to explore the benefits of different visual prompts, leading to sub-optimal performance. To this end, we propose \textbf{AutoV} that learns to automatically select the optimal visual prompt from various candidates based on given textual queries and the input image. To train AutoV, we developed an automatic data collection and labeling pipeline that evaluates various visual prompts with a pre-trained LVLM. We input a set of visual prompts into the LVLM and rank them according to the prediction losses generated by the model. Using the ranking as a supervision signal, we train AutoV to automatically choose the optimal visual prompt from various visual prompts for LVLMs. Experimental results indicate that AutoV enhances the performance of various LVLMs across multiple popular image understanding tasks. For instance, LLaVA-OV with AutoV achieves $\textbf{1.7}\%$ accuracy gain on LLaVA$^{\text{Wild}}$, and AutoV boosts Qwen2.5-VL by $\textbf{1.9}\%$ on MMMU, highlighting its potential as an optimal visual prompting method for LVLMs.
Authors: Chengyu Bai, Yuming Li, Zhongyu Zhao, Jintao Chen, Peidong Jia, Qi She, Ming Lu, Shanghang Zhang
Abstract: Video generation has made significant strides with the development of diffusion models; however, achieving high temporal consistency remains a challenging task. Recently, FreeInit identified a training-inference gap and introduced a method to iteratively refine the initial noise during inference. However, iterative refinement significantly increases the computational cost associated with video generation. In this paper, we introduce FastInit, a fast noise initialization method that eliminates the need for iterative refinement. FastInit learns a Video Noise Prediction Network (VNPNet) that takes random noise and a text prompt as input, generating refined noise in a single forward pass. Therefore, FastInit greatly enhances the efficiency of video generation while achieving high temporal consistency across frames. To train the VNPNet, we create a large-scale dataset consisting of pairs of text prompts, random noise, and refined noise. Extensive experiments with various text-to-video models show that our method consistently improves the quality and temporal consistency of the generated videos. FastInit not only provides a substantial improvement in video generation but also offers a practical solution that can be applied directly during inference. The code and dataset will be released.
Authors: Stefano Colamonaco, David Debot, Giuseppe Marra
Abstract: Relational learning enables models to generalize across structured domains by reasoning over objects and their interactions. While recent advances in neurosymbolic reasoning and object-centric learning bring us closer to this goal, existing systems rely either on object-level supervision or on a predefined decomposition of the input into objects. In this work, we propose a neurosymbolic formulation for learning object-centric representations directly from raw unstructured perceptual data and using only distant supervision. We instantiate this approach in DeepObjectLog, a neurosymbolic model that integrates a perceptual module, which extracts relevant object representations, with a symbolic reasoning layer based on probabilistic logic programming. By enabling sound probabilistic logical inference, the symbolic component introduces a novel learning signal that further guides the discovery of meaningful objects in the input. We evaluate our model across a diverse range of generalization settings, including unseen object compositions, unseen tasks, and unseen number of objects. Experimental results show that our method outperforms neural and neurosymbolic baselines across the tested settings.
Authors: Yi Chen, Yuying Ge, Rui Wang, Yixiao Ge, Junhao Cheng, Ying Shan, Xihui Liu
Abstract: Recent reinforcement learning approaches, such as outcome-supervised GRPO, have advanced Chain-of-Thought reasoning in large language models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) is unexplored. To address the lack of rigorous evaluation for MLLM post-training methods, we introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning. It offers a large training set and evaluates generalization across three escalating challenges: in-distribution, cross-environment, and cross-environment-task scenarios. Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate. This stems from reward signals focusing solely on final answers, encouraging shortcuts, and strict KL penalties limiting exploration.To address this, we propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision. GRPO-CARE introduces a two-tiered reward: (1) a base reward for answer correctness, and (2) an adaptive consistency bonus, computed by comparing the model's reasoning-to-answer likelihood (via a slowly-evolving reference model) against group peers.This dual mechanism amplifies rewards for reasoning paths that are both correct and logically consistent. Replacing KL penalties with this adaptive bonus, GRPO-CARE outperforms standard GRPO on SEED-Bench-R1, achieving a 6.7% performance gain on the hardest evaluation level and a 24.5% improvement in consistency. It also shows strong transferability, improving model performance across diverse video understanding benchmarks. Our work contributes a systematically designed benchmark and a generalizable post-training framework, advancing the development of more interpretable and robust MLLMs.
Authors: Xingbai Chen, Tingchao Fu, Renyang Liu, Wei Zhou, Chao Yi
Abstract: Referring Expression Segmentation (RES) enables precise object segmentation in images based on natural language descriptions, offering high flexibility and broad applicability in real-world vision tasks. Despite its impressive performance, the robustness of RES models against adversarial examples remains largely unexplored. While prior adversarial attack methods have explored adversarial robustness on conventional segmentation models, they perform poorly when directly applied to RES, failing to expose vulnerabilities in its multimodal structure. Moreover, in practical open-world scenarios, users typically issue multiple, diverse referring expressions to interact with the same image, highlighting the need for adversarial examples that generalize across varied textual inputs. To address these multimodal challenges, we propose a novel adversarial attack strategy termed \textbf{Multimodal Bidirectional Attack}, tailored for RES models. Our method introduces learnable proxy textual embedding perturbation and jointly performs visual-aligned optimization on the image modality and textual-adversarial optimization on the textual modality during attack generation. This dual optimization framework encourages adversarial images to actively adapt to more challenging text embedding during optimization, thereby enhancing their cross-text transferability, which refers to the ability of adversarial examples to remain effective under a variety of unseen or semantically diverse textual inputs. Extensive experiments conducted on multiple RES models and benchmark datasets demonstrate the superior effectiveness of our method compared to existing methods.
Authors: Taisei Omine (Sony Group Corporation), Naoyuki Kawabata (Sony Group Corporation), Fuminori Homma (Sony Group Corporation)
Abstract: With the advancement of conversational AI, research on bodily expressions, including gestures and facial expressions, has also progressed. However, many existing studies focus on photorealistic avatars, making them unsuitable for non-photorealistic characters, such as those found in anime. This study proposes methods for expressing emotions, including exaggerated expressions unique to non-photorealistic characters, by utilizing expression data extracted from comics and dialogue-specific semantic gestures. A user study demonstrated significant improvements across multiple aspects when compared to existing research.
Authors: Jiyao Wang, Xiao Yang, Hao Lu, Dengbo He, Kaishun Wu
Abstract: Multi-source synsemantic domain generalization (MSSDG) for multi-task remote physiological measurement seeks to enhance the generalizability of these metrics and attracts increasing attention. However, challenges like partial labeling and environmental noise may disrupt task-specific accuracy. Meanwhile, given that real-time adaptation is necessary for personalized products, the test-time personalized adaptation (TTPA) after MSSDG is also worth exploring, while the gap between previous generalization and personalization methods is significant and hard to fuse. Thus, we proposed a unified framework for MSSD\textbf{G} and TTP\textbf{A} employing \textbf{P}riors (\textbf{GAP}) in biometrics and remote photoplethysmography (rPPG). We first disentangled information from face videos into invariant semantics, individual bias, and noise. Then, multiple modules incorporating priors and our observations were applied in different stages and for different facial information. Then, based on the different principles of achieving generalization and personalization, our framework could simultaneously address MSSDG and TTPA under multi-task remote physiological estimation with minimal adjustments. We expanded the MSSDG benchmark to the TTPA protocol on six publicly available datasets and introduced a new real-world driving dataset with complete labeling. Extensive experiments that validated our approach, and the codes along with the new dataset will be released.
Authors: Zhenghao Xi, Xiang Liu, Yaqi Liu, Yitong Cai, Yangyu Zheng
Abstract: Accident detection using Closed Circuit Television (CCTV) footage is one of the most imperative features for enhancing transport safety and efficient traffic control. To this end, this research addresses the issues of supervised monitoring and data deficiency in accident detection systems by adapting excellent deep learning technologies. The motivation arises from rising statistics in the number of car accidents worldwide; this calls for innovation and the establishment of a smart, efficient and automated way of identifying accidents and calling for help to save lives. Addressing the problem of the scarcity of data, the presented framework joins Generative Adversarial Networks (GANs) for synthesizing data and Convolutional Neural Networks (CNN) for model training. Video frames for accidents and non-accidents are collected from YouTube videos, and we perform resizing, image enhancement and image normalisation pixel range adjustments. Three models are used: CNN, Fine-tuned Convolutional Neural Network (FTCNN) and Vision Transformer (VIT) worked best for detecting accidents from CCTV, obtaining an accuracy rate of 94% and 95%, while the CNN model obtained 88%. Such results show that the proposed framework suits traffic safety applications due to its high real-time accident detection capabilities and broad-scale applicability. This work lays the foundation for intelligent surveillance systems in the future for real-time traffic monitoring, smart city framework, and integration of intelligent surveillance systems into emergency management systems.
Authors: Annajoyce Mariani, Kira Maag, Hanno Gottschalk
Abstract: Being able to generate realistic trajectory options is at the core of increasing the degree of automation of road vehicles. While model-driven, rule-based, and classical learning-based methods are widely used to tackle these tasks at present, they can struggle to effectively capture the complex, multimodal distributions of future trajectories. In this paper we investigate whether a generative adversarial network (GAN) trained on videos of bird's-eye view (BEV) traffic scenarios can generate statistically accurate trajectories that correctly capture spatial relationships between the agents. To this end, we propose a pipeline that uses low-resolution BEV occupancy grid videos as training data for a video generative model. From the generated videos of traffic scenarios we extract abstract trajectory data using single-frame object detection and frame-to-frame object matching. We particularly choose a GAN architecture for the fast training and inference times with respect to diffusion models. We obtain our best results within 100 GPU hours of training, with inference times under 20\,ms. We demonstrate the physical realism of the proposed trajectories in terms of distribution alignment of spatial and dynamic parameters with respect to the ground truth videos from the Waymo Open Motion Dataset.
Authors: Xinting Liao, Weiming Liu, Jiaming Qian, Pengyang Zhou, Jiahe Xu, Wenjie Wang, Chaochao Chen, Xiaolin Zheng, Tat-Seng Chua
Abstract: Federated prompt learning (FPL) for vision-language models is a powerful approach to collaboratively adapt models across distributed clients while preserving data privacy. However, existing FPL approaches suffer from a trade-off between performance and robustness, particularly in out-of-distribution (OOD) shifts, limiting their reliability in real-world scenarios. The inherent in-distribution (ID) data heterogeneity among different clients makes it more challenging to maintain this trade-off. To fill this gap, we introduce a Federated OOD-aware Context Optimization (FOCoOp) framework, which captures diverse distributions among clients using ID global prompts, local prompts, and OOD prompts. Specifically, FOCoOp leverages three sets of prompts to create both class-level and distribution-level separations, which adapt to OOD shifts through bi-level distributionally robust optimization. Additionally, FOCoOp improves the discrimination consistency among clients, i.e., calibrating global prompts, seemingly OOD prompts, and OOD prompts by semi-unbalanced optimal transport. The extensive experiments on real-world datasets demonstrate that FOCoOp effectively captures decentralized heterogeneous distributions and enhances robustness of different OOD shifts. The project is available at GitHub.
Authors: Weeyoung Kwon, Jeahun Sung, Minkyu Jeon, Chanho Eom, Jihyong Oh
Abstract: Neural rendering methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have achieved significant progress in photorealistic 3D scene reconstruction and novel view synthesis. However, most existing models assume clean and high-resolution (HR) multi-view inputs, which limits their robustness under real-world degradations such as noise, blur, low-resolution (LR), and weather-induced artifacts. To address these limitations, the emerging field of 3D Low-Level Vision (3D LLV) extends classical 2D Low-Level Vision tasks including super-resolution (SR), deblurring, weather degradation removal, restoration, and enhancement into the 3D spatial domain. This survey, referred to as R\textsuperscript{3}eVision, provides a comprehensive overview of robust rendering, restoration, and enhancement for 3D LLV by formalizing the degradation-aware rendering problem and identifying key challenges related to spatio-temporal consistency and ill-posed optimization. Recent methods that integrate LLV into neural rendering frameworks are categorized to illustrate how they enable high-fidelity 3D reconstruction under adverse conditions. Application domains such as autonomous driving, AR/VR, and robotics are also discussed, where reliable 3D perception from degraded inputs is critical. By reviewing representative methods, datasets, and evaluation protocols, this work positions 3D LLV as a fundamental direction for robust 3D content generation and scene-level reconstruction in real-world environments.
Authors: Zhaoyi Wang, Jemil Avers Butt, Shengyu Huang, Tomislav Medic, Andreas Wieser
Abstract: Landslide monitoring is essential for understanding geohazards and mitigating associated risks. However, existing point cloud-based methods typically rely on either geometric or radiometric information and often yield sparse or non-3D displacement estimates. In this paper, we propose a hierarchical partition-based coarse-to-fine approach that fuses 3D point clouds and co-registered RGB images to estimate dense 3D displacement vector fields. We construct patch-level matches using both 3D geometry and 2D image features. These matches are refined via geometric consistency checks, followed by rigid transformation estimation per match. Experimental results on two real-world landslide datasets demonstrate that our method produces 3D displacement estimates with high spatial coverage (79% and 97%) and high accuracy. Deviations in displacement magnitude with respect to external measurements (total station or GNSS observations) are 0.15 m and 0.25 m on the two datasets, respectively, and only 0.07 m and 0.20 m compared to manually derived references. These values are below the average scan resolutions (0.08 m and 0.30 m). Our method outperforms the state-of-the-art method F2S3 in spatial coverage while maintaining comparable accuracy. Our approach offers a practical and adaptable solution for TLS-based landslide monitoring and is extensible to other types of point clouds and monitoring tasks. Our example data and source code are publicly available at https://github.com/zhaoyiww/fusion4landslide.
Authors: Xin Jiang, Meiqi Cao, Hao Tang, Fei Shen, Zechao Li
Abstract: Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR solutions typically follow two regimes: enforce pairwise similarity constraints in the semantic embedding space, or incorporate a localization sub-network to fine-tune the entire model. However, such two regimes tend to overfit the training data while forgetting the knowledge gained from large-scale pre-training, thus reducing their generalization ability. In this paper, we propose a Dual-Vision Adaptation (DVA) approach for FGIR, which guides the frozen pre-trained model to perform FGIR through collaborative sample and feature adaptation. Specifically, we design Object-Perceptual Adaptation, which modifies input samples to help the pre-trained model perceive critical objects and elements within objects that are helpful for category prediction. Meanwhile, we propose In-Context Adaptation, which introduces a small set of parameters for feature adaptation without modifying the pre-trained parameters. This makes the FGIR task using these adjusted features closer to the task solved during the pre-training. Additionally, to balance retrieval efficiency and performance, we propose Discrimination Perception Transfer to transfer the discriminative knowledge in the object-perceptual adaptation to the image encoder using the knowledge distillation mechanism. Extensive experiments show that DVA has fewer learnable parameters and performs well on three in-distribution and three out-of-distribution fine-grained datasets.
Authors: Heng Zhang, Zikang Wan, Danilo Vasconcellos Vargas
Abstract: Human vision excels at segmenting visual cues without the need for explicit training, and it remains remarkably robust even as noise severity increases. In contrast, existing AI algorithms struggle to maintain accuracy under similar conditions. Here, we present SyncMapV2, the first to solve unsupervised segmentation with state-of-the-art robustness. SyncMapV2 exhibits a minimal drop in mIoU, only 0.01%, under digital corruption, compared to a 23.8% drop observed in SOTA methods.This superior performance extends across various types of corruption: noise (7.3% vs. 37.7%), weather (7.5% vs. 33.8%), and blur (7.0% vs. 29.5%). Notably, SyncMapV2 accomplishes this without any robust training, supervision, or loss functions. It is based on a learning paradigm that uses self-organizing dynamical equations combined with concepts from random networks. Moreover,unlike conventional methods that require re-initialization for each new input, SyncMapV2 adapts online, mimicking the continuous adaptability of human vision. Thus, we go beyond the accurate and robust results, and present the first algorithm that can do all the above online, adapting to input rather than re-initializing. In adaptability tests, SyncMapV2 demonstrates near-zero performance degradation, which motivates and fosters a new generation of robust and adaptive intelligence in the near future.
Authors: Xu Zhao, Chen Zhao, Xiantao Hu, Hongliang Zhang, Ying Tai, Jian Yang
Abstract: Recent advancements in multi-scale architectures have demonstrated exceptional performance in image denoising tasks. However, existing architectures mainly depends on a fixed single-input single-output Unet architecture, ignoring the multi-scale representations of pixel level. In addition, previous methods treat the frequency domain uniformly, ignoring the different characteristics of high-frequency and low-frequency noise. In this paper, we propose a novel multi-scale adaptive dual-domain network (MADNet) for image denoising. We use image pyramid inputs to restore noise-free results from low-resolution images. In order to realize the interaction of high-frequency and low-frequency information, we design an adaptive spatial-frequency learning unit (ASFU), where a learnable mask is used to separate the information into high-frequency and low-frequency components. In the skip connections, we design a global feature fusion block to enhance the features at different scales. Extensive experiments on both synthetic and real noisy image datasets verify the effectiveness of MADNet compared with current state-of-the-art denoising approaches.
Authors: Carmelo Scribano, Elena Govi, Paolo bertellini, Simone Parisi, Giorgia Franchini, Marko Bertogna
Abstract: Accurate mapping of agricultural field boundaries is essential for the efficient operation of agriculture. Automatic extraction from high-resolution satellite imagery, supported by computer vision techniques, can avoid costly ground surveys. In this paper, we present a pipeline for field delineation based on the Segment Anything Model (SAM), introducing a fine-tuning strategy to adapt SAM to this task. In addition to using published datasets, we describe a method for acquiring a complementary regional dataset that covers areas beyond current sources. Extensive experiments assess segmentation accuracy and evaluate the generalization capabilities. Our approach provides a robust baseline for automated field delineation. The new regional dataset, known as ERAS, is now publicly available.
Authors: Arpit Jadon, Haoran Wang, Phillip Thomas, Michael Stanley, S. Nathaniel Cibik, Rachel Laurat, Omar Maher, Lukas Hoyer, Ozan Unal, Dengxin Dai
Abstract: As perception models continue to develop, the need for large-scale datasets increases. However, data annotation remains far too expensive to effectively scale and meet the demand. Synthetic datasets provide a solution to boost model performance with substantially reduced costs. However, current synthetic datasets remain limited in their scope, realism, and are designed for specific tasks and applications. In this work, we present RealDriveSim, a realistic multi-modal synthetic dataset for autonomous driving that not only supports popular 2D computer vision applications but also their LiDAR counterparts, providing fine-grained annotations for up to 64 classes. We extensively evaluate our dataset for a wide range of applications and domains, demonstrating state-of-the-art results compared to existing synthetic benchmarks. The dataset is publicly available at https://realdrivesim.github.io/.
Authors: Ji Zhang, Jingkuan Song, Lianli Gao, Nicu Sebe, Heng Tao Shen
Abstract: Recent advances in model pre-training give rise to task adaptation-based few-shot learning (FSL), where the goal is to adapt a pre-trained task-agnostic model for capturing task-specific knowledge with a few-labeled support samples of the target task.Nevertheless, existing approaches may still fail in the open world due to the inevitable in-distribution (ID) and out-of-distribution (OOD) noise from both support and query samples of the target task. With limited support samples available, i) the adverse effect of the dual noises can be severely amplified during task adaptation, and ii) the adapted model can produce unreliable predictions on query samples in the presence of the dual noises. In this work, we propose DEnoised Task Adaptation (DETA++) for reliable FSL. DETA++ uses a Contrastive Relevance Aggregation (CoRA) module to calculate image and region weights for support samples, based on which a clean prototype loss and a noise entropy maximization loss are proposed to achieve noise-robust task adaptation. Additionally,DETA++ employs a memory bank to store and refine clean regions for each inner-task class, based on which a Local Nearest Centroid Classifier (LocalNCC) is devised to yield noise-robust predictions on query samples. Moreover, DETA++ utilizes an Intra-class Region Swapping (IntraSwap) strategy to rectify ID class prototypes during task adaptation, enhancing the model's robustness to the dual noises. Extensive experiments demonstrate the effectiveness and flexibility of DETA++.
Authors: Viktoria Pundy, Marco Peer, Florian Kleber
Abstract: Neural Networks are the state of the art for many tasks in the computer vision domain, including Writer Identification (WI) and Writer Verification (WV). The transparency of these "black box" systems is important for improvements of performance and reliability. For this work, two transparency techniques are applied to neural networks trained on WI and WV for the first time in this domain. The first technique provides pixel-level saliency maps, while the point-specific saliency maps of the second technique provide information on similarities between two images. The transparency techniques are evaluated using deletion and insertion score metrics. The goal is to support forensic experts with information on similarities in handwritten text and to explore the characteristics selected by a neural network for the identification process. For the qualitative evaluation, the highlights of the maps are compared to the areas forensic experts consider during the identification process. The evaluation results show that the pixel-wise saliency maps outperform the point-specific saliency maps and are suitable for the support of forensic experts.
Authors: Chao He, Hongxi Wei
Abstract: Deep image hashing aims to enable effective large-scale image retrieval by mapping the input images into simple binary hash codes through deep neural networks. More recently, Vision Mamba with linear time complexity has attracted extensive attention from researchers by achieving outstanding performance on various computer tasks. Nevertheless, the suitability of Mamba for large-scale image retrieval tasks still needs to be explored. Towards this end, we propose a visual state space hashing model, called MambaHash. Concretely, we propose a backbone network with stage-wise architecture, in which grouped Mamba operation is introduced to model local and global information by utilizing Mamba to perform multi-directional scanning along different groups of the channel. Subsequently, the proposed channel interaction attention module is used to enhance information communication across channels. Finally, we meticulously design an adaptive feature enhancement module to increase feature diversity and enhance the visual representation capability of the model. We have conducted comprehensive experiments on three widely used datasets: CIFAR-10, NUS-WIDE and IMAGENET. The experimental results demonstrate that compared with the state-of-the-art deep hashing methods, our proposed MambaHash has well efficiency and superior performance to effectively accomplish large-scale image retrieval tasks. Source code is available https://github.com/shuaichaochao/MambaHash.git
Authors: Pallabi Dutta, Anubhab Maity, Sushmita Mitra
Abstract: The high computational demands of Vision Transformers (ViTs), in processing a huge number of tokens, often constrain their practical application in analyzing medical images. This research proposes an adaptive prompt-guided pruning method to selectively reduce the processing of irrelevant tokens in the segmentation pipeline. The prompt-based spatial prior helps to rank the tokens according to their relevance. Tokens with low-relevance scores are down-weighted, ensuring that only the relevant ones are propagated for processing across subsequent stages. This data-driven pruning strategy facilitates end-to-end training, maintains gradient flow, and improves segmentation accuracy by focusing computational resources on essential regions. The proposed framework is integrated with several state-of-the-art models to facilitate the elimination of irrelevant tokens; thereby, enhancing computational efficiency while preserving segmentation accuracy. The experimental results show a reduction of $\sim$ 35-55\% tokens; thus reducing the computational costs relative to the baselines. Cost-effective medical image processing, using our framework, facilitates real-time diagnosis by expanding its applicability in resource-constrained environments.
Authors: Yunhao Hou, Bochao Zou, Min Zhang, Ran Chen, Shangdong Yang, Yanmei Zhang, Junbao Zhuo, Siheng Chen, Jiansheng Chen, Huimin Ma
Abstract: By sharing information across multiple agents, collaborative perception helps autonomous vehicles mitigate occlusions and improve overall perception accuracy. While most previous work focus on vehicle-to-vehicle and vehicle-to-infrastructure collaboration, with limited attention to aerial perspectives provided by UAVs, which uniquely offer dynamic, top-down views to alleviate occlusions and monitor large-scale interactive environments. A major reason for this is the lack of high-quality datasets for aerial-ground collaborative scenarios. To bridge this gap, we present AGC-Drive, the first large-scale real-world dataset for Aerial-Ground Cooperative 3D perception. The data collection platform consists of two vehicles, each equipped with five cameras and one LiDAR sensor, and one UAV carrying a forward-facing camera and a LiDAR sensor, enabling comprehensive multi-view and multi-agent perception. Consisting of approximately 120K LiDAR frames and 440K images, the dataset covers 14 diverse real-world driving scenarios, including urban roundabouts, highway tunnels, and on/off ramps. Notably, 19.5% of the data comprises dynamic interaction events, including vehicle cut-ins, cut-outs, and frequent lane changes. AGC-Drive contains 400 scenes, each with approximately 100 frames and fully annotated 3D bounding boxes covering 13 object categories. We provide benchmarks for two 3D perception tasks: vehicle-to-vehicle collaborative perception and vehicle-to-UAV collaborative perception. Additionally, we release an open-source toolkit, including spatiotemporal alignment verification tools, multi-agent visualization systems, and collaborative annotation utilities. The dataset and code are available at https://github.com/PercepX/AGC-Drive.
Authors: Santosh Patapati, Trisanth Srinivasan, Amith Adiraju
Abstract: Micro-gesture recognition is a challenging task in affective computing due to the subtle, involuntary nature of the gestures and their low movement amplitude. In this paper, we introduce a Pose-Guided Semantics-Aware CLIP-based architecture, or CLIP for Micro-Gesture recognition (CLIP-MG), a modified CLIP model tailored for micro-gesture classification on the iMiGUE dataset. CLIP-MG integrates human pose (skeleton) information into the CLIP-based recognition pipeline through pose-guided semantic query generation and a gated multi-modal fusion mechanism. The proposed model achieves a Top-1 accuracy of 61.82%. These results demonstrate both the potential of our approach and the remaining difficulty in fully adapting vision-language models like CLIP for micro-gesture recognition.
Authors: Peixiang Huang, Yanyan Huang, Weiqin Zhao, Junjun He, Lequan Yu
Abstract: Pathology is essential for cancer diagnosis, with multiple instance learning (MIL) widely used for whole slide image (WSI) analysis. WSIs exhibit a natural hierarchy -- patches, regions, and slides -- with distinct semantic associations. While some methods attempt to leverage this hierarchy for improved representation, they predominantly rely on Euclidean embeddings, which struggle to fully capture semantic hierarchies. To address this limitation, we propose HyperPath, a novel method that integrates knowledge from textual descriptions to guide the modeling of semantic hierarchies of WSIs in hyperbolic space, thereby enhancing WSI classification. Our approach adapts both visual and textual features extracted by pathology vision-language foundation models to the hyperbolic space. We design an Angular Modality Alignment Loss to ensure robust cross-modal alignment, while a Semantic Hierarchy Consistency Loss further refines feature hierarchies through entailment and contradiction relationships and thus enhance semantic coherence. The classification is performed with geodesic distance, which measures the similarity between entities in the hyperbolic semantic hierarchy. This eliminates the need for linear classifiers and enables a geometry-aware approach to WSI analysis. Extensive experiments show that our method achieves superior performance across tasks compared to existing methods, highlighting the potential of hyperbolic embeddings for WSI analysis.
Authors: Dong Nguyen Tien, Dung D. Le
Abstract: Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains insufficiently explored. We introduce the first unified framework for generating and evaluating multi-modal adversarial attacks on OCR-based VDU models. Our method covers six gradient-based layout attack scenarios, incorporating manipulations of OCR bounding boxes, pixels, and texts across both word and line granularities, with constraints on layout perturbation budget (e.g., IoU >= 0.6) to preserve plausibility. Experimental results across four datasets (FUNSD, CORD, SROIE, DocVQA) and six model families demonstrate that line-level attacks and compound perturbations (BBox + Pixel + Text) yield the most severe performance degradation. Projected Gradient Descent (PGD)-based BBox perturbations outperform random-shift baselines in all investigated models. Ablation studies further validate the impact of layout budget, text modification, and adversarial transferability.
Authors: Berk Yilmaz, Daniel Fidel Harvey, Prajit Dhuri
Abstract: This study investigates the integration of signal processing transformations -- Fast Fourier Transform (FFT), Walsh-Hadamard Transform (WHT), and Discrete Cosine Transform (DCT) -- within the ResNet50 convolutional neural network (CNN) model for image classification. The primary objective is to assess the trade-offs between computational efficiency, energy consumption, and classification accuracy during training and inference. Using the CIFAR-100 dataset (100 classes, 60,000 images), experiments demonstrated that incorporating WHT significantly reduced energy consumption while improving accuracy. Specifically, a baseline ResNet50 model achieved a testing accuracy of 66%, consuming an average of 25,606 kJ per model. In contrast, a modified ResNet50 incorporating WHT in the early convolutional layers achieved 74% accuracy, and an enhanced version with WHT applied to both early and late layers achieved 79% accuracy, with an average energy consumption of only 39 kJ per model. These results demonstrate the potential of WHT as a highly efficient and effective approach for energy-constrained CNN applications.
Authors: Jan Skvrna, Lukas Neumann
Abstract: This paper presents the winning solution for the S23DR Challenge 2025, which involves predicting a house's 3D roof wireframe from a sparse point cloud and semantic segmentations. Our method operates directly in 3D, first identifying vertex candidates from the COLMAP point cloud using Gestalt segmentations. We then employ two PointNet-like models: one to refine and classify these candidates by analyzing local cubic patches, and a second to predict edges by processing the cylindrical regions connecting vertex pairs. This two-stage, 3D deep learning approach achieved a winning Hybrid Structure Score (HSS) of 0.43 on the private leaderboard.
Authors: Giuseppe Lando, Rosario Forte, Giovanni Maria Farinella, Antonino Furnari
Abstract: We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while being 10**4/10**5 times more memory-efficient. Extensive ablations provides insights into the role of each component and design choice, and highlight directions of improvement for future research.
Authors: Riccardo Ziglio, Cecilia Pasquini, Silvio Ranise
Abstract: Face swapping manipulations in video streams represents an increasing threat in remote video communications, due to advances in automated and real-time tools. Recent literature proposes to characterize and exploit visual artifacts introduced in video frames by swapping algorithms when dealing with challenging physical scenes, such as face occlusions. This paper investigates the effectiveness of this approach by benchmarking CNN-based data-driven models on two data corpora (including a newly collected one) and analyzing generalization capabilities with respect to different acquisition sources and swapping algorithms. The results confirm excellent performance of general-purpose CNN architectures when operating within the same data source, but a significant difficulty in robustly characterizing occlusion-based visual cues across datasets. This highlights the need for specialized detection strategies to deal with such artifacts.
Authors: Zeqiang Lai, Yunfei Zhao, Haolin Liu, Zibo Zhao, Qingxiang Lin, Huiwen Shi, Xianghui Yang, Mingxin Yang, Shuhui Yang, Yifei Feng, Sheng Zhang, Xin Huang, Di Luo, Fan Yang, Fang Yang, Lifu Wang, Sicong Liu, Yixuan Tang, Yulin Cai, Zebin He, Tian Liu, Yuhong Liu, Jie Jiang, Linus, Jingwei Huang, Chunchao Guo
Abstract: In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.
Authors: Mei Qi Tang, Sean Sedwards, Chengjie Huang, Krzysztof Czarnecki
Abstract: The impact of snowfall on 3D object detection performance remains underexplored. Conducting such an evaluation requires a dataset with sufficient labelled data from both weather conditions, ideally captured in the same driving environment. Current driving datasets with LiDAR point clouds either do not provide enough labelled data in both snowy and clear weather conditions, or rely on de-snowing methods to generate synthetic clear weather. Synthetic data often lacks realism and introduces an additional domain shift that confounds accurate evaluations. To address these challenges, we present CADC+, the first paired weather domain adaptation dataset for autonomous driving in winter conditions. CADC+ extends the Canadian Adverse Driving Conditions dataset (CADC) using clear weather data that was recorded on the same roads and in the same period as CADC. To create CADC+, we pair each CADC sequence with a clear weather sequence that matches the snowy sequence as closely as possible. CADC+ thus minimizes the domain shift resulting from factors unrelated to the presence of snow. We also present some preliminary results using CADC+ to evaluate the effect of snow on 3D object detection performance. We observe that snow introduces a combination of aleatoric and epistemic uncertainties, acting as both noise and a distinct data domain.
Authors: Keyhan Najafian, Farhad Maleki, Lingling Jin, Ian Stavness
Abstract: Instance segmentation is essential for applications such as automated monitoring of plant health, growth, and yield. However, extensive effort is required to create large-scale datasets with pixel-level annotations of each object instance for developing instance segmentation models that restrict the use of deep learning in these areas. This challenge is more significant in images with densely packed, self-occluded objects, which are common in agriculture. To address this challenge, we propose a semi-self-supervised learning approach that requires minimal manual annotation to develop a high-performing instance segmentation model. We design GLMask, an image-mask representation for the model to focus on shape, texture, and pattern while minimizing its dependence on color features. We develop a pipeline to generate semantic segmentation and then transform it into instance-level segmentation. The proposed approach substantially outperforms the conventional instance segmentation models, establishing a state-of-the-art wheat head instance segmentation model with mAP@50 of 98.5%. Additionally, we assessed the proposed methodology on the general-purpose Microsoft COCO dataset, achieving a significant performance improvement of over 12.6% mAP@50. This highlights that the utility of our proposed approach extends beyond precision agriculture and applies to other domains, specifically those with similar data characteristics.
Authors: Tongan Cai, Haomiao Ni, Wenchao Ma, Yuan Xue, Qian Ma, Rachel Leicht, Kelvin Wong, John Volpi, Stephen T. C. Wong, James Z. Wang, Sharon X. Huang
Abstract: Effective stroke triage in emergency settings often relies on clinicians' ability to identify subtle abnormalities in facial muscle coordination. While recent AI models have shown promise in detecting such patterns from patient facial videos, their reliance on real patient data raises significant ethical and privacy challenges -- especially when training robust and generalizable models across institutions. To address these concerns, we propose SafeTriage, a novel method designed to de-identify patient facial videos while preserving essential motion cues crucial for stroke diagnosis. SafeTriage leverages a pretrained video motion transfer (VMT) model to map the motion characteristics of real patient faces onto synthetic identities. This approach retains diagnostically relevant facial dynamics without revealing the patients' identities. To mitigate the distribution shift between normal population pre-training videos and patient population test videos, we introduce a conditional generative model for visual prompt tuning, which adapts the input space of the VMT model to ensure accurate motion transfer without needing to fine-tune the VMT model backbone. Comprehensive evaluation, including quantitative metrics and clinical expert assessments, demonstrates that SafeTriage-produced synthetic videos effectively preserve stroke-relevant facial patterns, enabling reliable AI-based triage. Our evaluations also show that SafeTriage provides robust privacy protection while maintaining diagnostic accuracy, offering a secure and ethically sound foundation for data sharing and AI-driven clinical analysis in neurological disorders.
Authors: Tal Zeevi, El\'eonore V. Lieffrig, Lawrence H. Staib, John A. Onofrey
Abstract: Uncertainty maps highlight unreliable regions in segmentation predictions. However, most uncertainty evaluation metrics treat voxels independently, ignoring spatial context and anatomical structure. As a result, they may assign identical scores to qualitatively distinct patterns (e.g., scattered vs. boundary-aligned uncertainty). We propose three spatially aware metrics that incorporate structural and boundary information and conduct a thorough validation on medical imaging data from the prostate zonal segmentation challenge within the Medical Segmentation Decathlon. Our results demonstrate improved alignment with clinically important factors and better discrimination between meaningful and spurious uncertainty patterns.
Authors: Muhammad Azeem Aslam, Muhammad Hamza, Nisar Ahmed, Gulshan Saleem, Zhu Shuangtong, Hu Hongfei, Xu Wei, Saba Aslam, Wang Jun
Abstract: Image Quality Assessment (IQA) is a critical task in a wide range of applications but remains challenging due to the subjective nature of human perception and the complexity of real-world image distortions. This study proposes MetaQAP, a novel no-reference IQA model designed to address these challenges by leveraging quality-aware pre-training and meta-learning. The model performs three key contributions: pre-training Convolutional Neural Networks (CNNs) on a quality-aware dataset, implementing a quality-aware loss function to optimize predictions, and integrating a meta-learner to form an ensemble model that effectively combines predictions from multiple base models. Experimental evaluations were conducted on three benchmark datasets: LiveCD, KonIQ-10K, and BIQ2021. The proposed MetaQAP model achieved exceptional performance with Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank Order Correlation Coefficient (SROCC) scores of 0.9885/0.9812 on LiveCD, 0.9702/0.9658 on KonIQ-10K, and 0.884/0.8765 on BIQ2021, outperforming existing IQA methods. Cross-dataset evaluations further demonstrated the generalizability of the model, with PLCC and SROCC scores ranging from 0.6721 to 0.8023 and 0.6515 to 0.7805, respectively, across diverse datasets. The ablation study confirmed the significance of each model component, revealing substantial performance degradation when critical elements such as the meta-learner or quality-aware loss function were omitted. MetaQAP not only addresses the complexities of authentic distortions but also establishes a robust and generalizable framework for practical IQA applications. By advancing the state-of-the-art in no-reference IQA, this research provides valuable insights and methodologies for future improvements and extensions in the field.
Authors: Ajesh Thangaraj Nadar, Gabriel Nixon Raj, Soham Chandane, Sushant Bhat
Abstract: The increasing proliferation of electronic devices in the modern era has led to a significant surge in electronic waste (e-waste). Improper disposal and insufficient recycling of e-waste pose serious environmental and health risks. This paper proposes an IoT-enabled system combined with a lightweight CNN-based classification pipeline to enhance the identification, categorization, and routing of e-waste materials. By integrating a camera system and a digital weighing scale, the framework automates the classification of electronic items based on visual and weight-based attributes. The system demonstrates how real-time detection of e-waste components such as circuit boards, sensors, and wires can facilitate smart recycling workflows and improve overall waste processing efficiency.
Authors: Michael Gyimadu, Gregory Bell
Abstract: High-dimensional image data often require dimensionality reduction before further analysis. This paper provides a purely analytical comparison of two linear techniques-Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). After the derivation of each algorithm from first principles, we assess their interpretability, numerical stability, and suitability for differing matrix shapes. building on classical and recent numerical literature, We synthesize rule-of-thumb guidelines for choosing one out of the two algorithms without empirical benchmarking, building on classical and recent numerical literature. Limitations and directions for future experimental work are outlined at the end.
Authors: Ruiming Chen, Junming Yang, Shiyu Xia, Xu Yang, Jing Wang, Xin Geng
Abstract: CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, the computational overhead of a large number of parameters and large-scale pre-training poses challenges of pre-training a different scale of CLIP. Learngene extracts the generalizable components termed as learngene from an ancestry model and initializes diverse descendant models with it. Previous Learngene paradigms fail to handle the generalizable knowledge in multimodal scenarios. In this paper, we put forward the idea of utilizing a multimodal block to extract the multimodal generalizable knowledge, which inspires us to propose MM-LG (Multimodal Learngene), a novel framework designed to extract and leverage generalizable components from CLIP. Specifically, we first establish multimodal and unimodal blocks to extract the multimodal and unimodal generalizable knowledge in a weighted-sum manner. Subsequently, we employ these components to numerically initialize descendant models of varying scales and modalities. Extensive experiments demonstrate MM-LG's effectiveness, which achieves performance gains over existing learngene approaches (e.g.,+3.1% on Oxford-IIIT PET and +4.13% on Flickr30k) and comparable or superior results to the pre-training and fine-tuning paradigm (e.g.,+1.9% on Oxford-IIIT PET and +3.65% on Flickr30k). Notably, MM-LG requires only around 25% of the parameter storage while reducing around 2.8 times pre-training costs for diverse model scales compared to the pre-training and fine-tuning paradigm, making it particularly suitable for efficient deployment across diverse downstream tasks.
Authors: Manuel Brack, Sudeep Katakol, Felix Friedrich, Patrick Schramowski, Hareesh Ravi, Kristian Kersting, Ajinkya Kale
Abstract: Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted towards synthetic training captions. While this setup is generally believed to produce more capable models, current literature does not provide any insights into its design choices. This study closes this gap by systematically investigating how different synthetic captioning strategies impact the downstream performance of text-to-image models. Our experiments demonstrate that dense, high-quality captions enhance text alignment but may introduce trade-offs in output aesthetics and diversity. Conversely, captions of randomized lengths yield balanced improvements across aesthetics and alignment without compromising sample diversity. We also demonstrate that varying caption distributions introduce significant shifts in the output bias of a trained model. Our findings underscore the importance of caption design in achieving optimal model performance and provide practical insights for more effective training data strategies in text-to-image generation.
Authors: Yun Xing, Yue Cao, Nhat Chung, Jie Zhang, Ivor Tsang, Ming-Ming Cheng, Yang Liu, Lei Ma, Qing Guo
Abstract: Stereo Depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help reveal vulnerabilities before deployment. Previous work has shown that repeating optimized textures can effectively mislead stereo depth estimation in digital settings. However, our research reveals that these naively repeated texture structures perform poorly in physical-world implementations, i.e., when deployed as patches, limiting their practical utility for testing stereo depth estimation systems. In this work, for the first time, we discover that introducing regular intervals between repeated textures, creating a striped structure, significantly enhances the patch attack effectiveness. Through extensive experimentation, we analyze how variations of this novel structure influence the performance. Based on these insights, we develop a novel stereo depth attack that jointly optimizes both the striped structure and texture elements. Our generated adversarial patches can be inserted into any scenes and successfully attack state-of-the-art stereo depth estimation methods, i.e., RAFT-Stereo and STTR. Most critically, our patch can also attack commercial RGB-D cameras (Intel RealSense) in real-world conditions, demonstrating their practical relevance for security assessment of stereo systems.
Authors: Tongtian Yue, Longteng Guo, Yepeng Tang, Zijia Zhao, Xinxin Zhu, Hua Huang, Jing Liu
Abstract: Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or introduce severe long-context computational burden, severely limiting scalability and efficiency. In this paper, we rethink multimodal integration and present LaVi, a novel LVLM that enables seamless and efficient vision-language fusion through internal feature modulation within the Large Language Models (LLMs). Unlike dominant LVLMs that rely on visual token concatenation, LaVi bypasses long-context expansion by introducing a lightweight and adaptive transformation, which incorporates visual context by injecting token-wise vision-conditioned deltas into the affine parameters of layer normalization. This mechanism directly modulates linguistic hidden states based on visual input, ensuring precise vision-language alignment while preserving the LLM's linguistic priors and drastically reducing computational costs. Extensive evaluations across 15 image and video benchmarks demonstrate that LaVi not only achieves state-of-the-art multimodal performance but also dramatically enhances efficiency. Compared to LLaVA-OV-7B, LaVi reduces FLOPs by 94.0%, improves inference speed by 3.1 times, and cuts memory usage in half - establishing LaVi as a scalable and practical solution for real-time multimodal reasoning. The code and models will be released soon.
Authors: Xiaodan Hu, Chuhang Zou, Suchen Wang, Jaechul Kim, Narendra Ahuja
Abstract: Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that humans use to constitute an understanding of objects, human-object interactions, and activities - that have not been fully exploited. In this paper, we introduce a framework incorporating language-driven common sense priors to identify cluttered video action sequences from monocular views that are often heavily occluded. We propose: (1) A video context summary component that generates candidate objects, activities, and the interactions between objects and activities; (2) A description generation module that describes the current scene given the context and infers subsequent activities, through auxiliary prompts and common sense reasoning; (3) A multi-modal activity recognition head that combines visual and textual cues to recognize video actions. We demonstrate the effectiveness of our approach on the challenging Action Genome and Charades datasets.
Authors: Yunhan Ren, Feng Luo, Siyu Huang
Abstract: While existing Generalized Category Discovery (GCD) models have achieved significant success, their performance with limited labeled samples and a small number of known categories remains largely unexplored. In this work, we introduce the task of Few-shot Generalized Category Discovery (FSGCD), aiming to achieve competitive performance in GCD tasks under conditions of known information scarcity. To tackle this challenge, we propose a decision boundary enhancement framework with affinity-based retrieval. Our framework is designed to learn the decision boundaries of known categories and transfer these boundaries to unknown categories. First, we use a decision boundary pre-training module to mitigate the overfitting of pre-trained information on known category boundaries and improve the learning of these decision boundaries using labeled samples. Second, we implement a two-stage retrieval-guided decision boundary optimization strategy. Specifically, this strategy further enhances the severely limited known boundaries by using affinity-retrieved pseudo-labeled samples. Then, these refined boundaries are applied to unknown clusters via guidance from affinity-based feature retrieval. Experimental results demonstrate that our proposed method outperforms existing methods on six public GCD benchmarks under the FSGCD setting. The codes are available at: https://github.com/Ryh1218/FSGCD
Authors: Mingrui Zhu, Xiru Chen, Xin Wei, Nannan Wang, Xinbo Gao
Abstract: Infrared and visible image fusion (IVF) aims to combine complementary information from both image modalities, producing more informative and comprehensive outputs. Recently, text-guided IVF has shown great potential due to its flexibility and versatility. However, the effective integration and utilization of textual semantic information remains insufficiently studied. To tackle these challenges, we introduce textual semantics at two levels: the mask semantic level and the text semantic level, both derived from textual descriptions extracted by large Vision-Language Models (VLMs). Building on this, we propose Textual Semantic Guidance for infrared and visible image fusion, termed TeSG, which guides the image synthesis process in a way that is optimized for downstream tasks such as detection and segmentation. Specifically, TeSG consists of three core components: a Semantic Information Generator (SIG), a Mask-Guided Cross-Attention (MGCA) module, and a Text-Driven Attentional Fusion (TDAF) module. The SIG generates mask and text semantics based on textual descriptions. The MGCA module performs initial attention-based fusion of visual features from both infrared and visible images, guided by mask semantics. Finally, the TDAF module refines the fusion process with gated attention driven by text semantics. Extensive experiments demonstrate the competitiveness of our approach, particularly in terms of performance on downstream tasks, compared to existing state-of-the-art methods.
Authors: Yunshan Li, Wenwu Gong, Qianqian Wang, Chao Wang, Lili Yang
Abstract: Recent approaches based on transform-based tensor nuclear norm (TNN) have demonstrated notable effectiveness in hyperspectral image (HSI) inpainting by leveraging low-rank structures in latent representations. Recent developments incorporate deep transforms to improve low-rank tensor representation; however, existing approaches typically restrict the transform to the spectral mode, neglecting low-rank properties along other tensor modes. In this paper, we propose a novel 3-directional deep low-rank tensor representation (3DeepRep) model, which performs deep nonlinear transforms along all three modes of the HSI tensor. To enforce low-rankness, the model minimizes the nuclear norms of mode-i frontal slices in the corresponding latent space for each direction (i=1,2,3), forming a 3-directional TNN regularization. The outputs from the three directional branches are subsequently fused via a learnable aggregation module to produce the final result. An efficient gradient-based optimization algorithm is developed to solve the model in a self-supervised manner. Extensive experiments on real-world HSI datasets demonstrate that the proposed method achieves superior inpainting performance compared to existing state-of-the-art techniques, both qualitatively and quantitatively.
Authors: Liu Zongzhen, Luo Hui, Wang Zhixing, Wei Yuxing, Zuo Haorui, Zhang Jianlin
Abstract: Unmanned aerial vehicle (UAV) object detection plays a vital role in applications such as environmental monitoring and urban security. To improve robustness, recent studies have explored multimodal detection by fusing visible (RGB) and infrared (IR) imagery. However, due to UAV platform motion and asynchronous imaging, spatial misalignment frequently occurs between modalities, leading to weak alignment. This introduces two major challenges: semantic inconsistency at corresponding spatial locations and modality conflict during feature fusion. Existing methods often address these issues in isolation, limiting their effectiveness. In this paper, we propose Cross-modal Offset-guided Dynamic Alignment and Fusion (CoDAF), a unified framework that jointly tackles both challenges in weakly aligned UAV-based object detection. CoDAF comprises two novel modules: the Offset-guided Semantic Alignment (OSA), which estimates attention-based spatial offsets and uses deformable convolution guided by a shared semantic space to align features more precisely; and the Dynamic Attention-guided Fusion Module (DAFM), which adaptively balances modality contributions through gating and refines fused features via spatial-channel dual attention. By integrating alignment and fusion in a unified design, CoDAF enables robust UAV object detection. Experiments on standard benchmarks validate the effectiveness of our approach, with CoDAF achieving a mAP of 78.6% on the DroneVehicle dataset.
Authors: Md Nahiduzzaman, Ruwan Tennakoon, Steven Korevaar, Zongyuan Ge, Alireza Bab-Hadiashar
Abstract: In medical imaging, AI decision-support systems must balance accuracy and interpretability to build user trust and support effective clinical decision-making. Recently, Variational Information Pursuit (V-IP) and its variants have emerged as interpretable-by-design modeling techniques, aiming to explain AI decisions in terms of human-understandable, clinically relevant concepts. However, existing V-IP methods overlook instance-level uncertainties in query-answer generation, which can arise from model limitations (epistemic uncertainty) or variability in expert responses (aleatoric uncertainty). This paper introduces Uncertainty-Aware V-IP (UAV-IP), a novel framework that integrates uncertainty quantification into the V-IP process. We evaluate UAV-IP across four medical imaging datasets, PH2, Derm7pt, BrEaST, and SkinCon, demonstrating an average AUC improvement of approximately 3.2% while generating 20% more concise explanations compared to baseline V-IP, without sacrificing informativeness. These findings highlight the importance of uncertainty-aware reasoning in interpretable by design models for robust and reliable medical decision-making.
Authors: Weinan Guan, Wei Wang, Bo Peng, Ziwen He, Jing Dong, Haonan Cheng
Abstract: With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure.However, a key challenge for forgery detection is generalising to diffusion models not seen during training. In this paper, we address this problem by focusing on image noise. We observe that images from different diffusion models share similar noise patterns, distinct from genuine images. Building upon this insight, we introduce a novel Noise-Aware Self-Attention (NASA) module that focuses on noise regions to capture anomalous patterns. To implement a SOTA detection model, we incorporate NASA into Swin Transformer, forming an novel detection architecture NASA-Swin. Additionally, we employ a cross-modality fusion embedding to combine RGB and noise images, along with a channel mask strategy to enhance feature learning from both modalities. Extensive experiments demonstrate the effectiveness of our approach in enhancing detection capabilities for diffusion-generated images. When encountering unseen generation methods, our approach achieves the state-of-the-art performance.Our code is available at https://github.com/WeinanGuan/NASA-Swin.
Authors: Qi-Ying Sun, Wan-Lei Zhao, Yi-Bo Miao, Chong-Wah Ngo
Abstract: Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance level feature representation. Supervised or weakly supervised object detection methods are not among the options due to their poor performance on the unknown object categories. In this paper, based on the feature set output from self-supervised ViT, the instance level region discovery is modeled as detecting the compact feature subsets in a hierarchical fashion. The hierarchical decomposition results in a hierarchy of feature subsets. The non-leaf nodes and leaf nodes on the hierarchy correspond to the various instance regions in an image of different semantic scales. The hierarchical decomposition well addresses the problem of object embedding and occlusions, which are widely observed in the real scenarios. The features derived from the nodes on the hierarchy make up a comprehensive representation for the latent instances in the image. Our instance-level descriptor remains effective on both the known and unknown object categories. Empirical studies on three instance search benchmarks show that it outperforms state-of-the-art methods considerably.
Authors: Shuchen Sun, Ligen Shi, Chang Liu, Lina Wu, Jun Qiu
Abstract: Infrared and visible light image fusion aims to combine the strengths of both modalities to generate images that are rich in information and fulfill visual or computational requirements. This paper proposes an image fusion method based on Implicit Neural Representations (INR), referred to as INRFuse. This method parameterizes a continuous function through a neural network to implicitly represent the multimodal information of the image, breaking through the traditional reliance on discrete pixels or explicit features. The normalized spatial coordinates of the infrared and visible light images serve as inputs, and multi-layer perceptrons is utilized to adaptively fuse the features of both modalities, resulting in the output of the fused image. By designing multiple loss functions, the method jointly optimizes the similarity between the fused image and the original images, effectively preserving the thermal radiation information of the infrared image while maintaining the texture details of the visible light image. Furthermore, the resolution-independent characteristic of INR allows for the direct fusion of images with varying resolutions and achieves super-resolution reconstruction through high-density coordinate queries. Experimental results indicate that INRFuse outperforms existing methods in both subjective visual quality and objective evaluation metrics, producing fused images with clear structures, natural details, and rich information without the necessity for a training dataset.
Authors: Beomseok Ko, Hyeryung Jang
Abstract: Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques. In this paper, we propose PQCAD-DM, a novel hybrid compression framework combining Progressive Quantization (PQ) and Calibration-Assisted Distillation (CAD) to address these challenges. PQ employs a two-stage quantization with adaptive bit-width transitions guided by a momentum-based mechanism, reducing excessive weight perturbations in low-precision. CAD leverages full-precision calibration datasets during distillation, enabling the student to match full-precision performance even with a quantized teacher. As a result, PQCAD-DM achieves a balance between computational efficiency and generative quality, halving inference time while maintaining competitive performance. Extensive experiments validate PQCAD-DM's superior generative capabilities and efficiency across diverse datasets, outperforming fixed-bit quantization methods.
Authors: Xiaoyu Shi, Rahul Kumar Jain, Yinhao Li, Ruibo Hou, Jingliang Cheng, Jie Bai, Guohua Zhao, Lanfen Lin, Rui Xu, Yen-wei Chen
Abstract: Deep learning has demonstrated remarkable success in medical image segmentation and computer-aided diagnosis. In particular, numerous advanced methods have achieved state-of-the-art performance in brain tumor segmentation from MRI scans. While recent studies in other medical imaging domains have revealed that integrating textual reports with visual data can enhance segmentation accuracy, the field of brain tumor analysis lacks a comprehensive dataset that combines radiological images with corresponding textual annotations. This limitation has hindered the exploration of multimodal approaches that leverage both imaging and textual data. To bridge this critical gap, we introduce the TextBraTS dataset, the first publicly available volume-level multimodal dataset that contains paired MRI volumes and rich textual annotations, derived from the widely adopted BraTS2020 benchmark. Building upon this novel dataset, we propose a novel baseline framework and sequential cross-attention method for text-guided volumetric medical image segmentation. Through extensive experiments with various text-image fusion strategies and templated text formulations, our approach demonstrates significant improvements in brain tumor segmentation accuracy, offering valuable insights into effective multimodal integration techniques. Our dataset, implementation code, and pre-trained models are publicly available at https://github.com/Jupitern52/TextBraTS.
Authors: Junbo Qiao, Miaomiao Cai, Wei Li, Yutong Liu, Xudong Huang, Gaoqi He, Jiao Xie, Jie Hu, Xinghao Chen, Shaohui Lin
Abstract: Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both low-fidelity and unnatural. We present RealSR-R1 in this work, which empowers the RealSR models with understanding and reasoning capabilities. Inspired by the success of Chain of Thought (CoT) in large language models (LLMs), we simulate the human process of handling degraded images and propose the VLCoT framework, which integrates vision and language reasoning. The framework aims to precisely restore image details by progressively generating more comprehensive text and higher-resolution images. To overcome the challenge of traditional supervised learning CoT failing to generalize to real-world scenarios, we introduce, for the first time, Group Relative Policy Optimization (GRPO) into the Real-World Image Super-Resolution task. We propose VLCoT-GRPO as a solution, which designs four reward functions: (1) Format reward, used to standardize the CoT process; (2) Degradation reward, to incentivize accurate degradation estimation; (3) Understanding reward, to ensure the accuracy of the generated content; and (4) Generation reward, where we propose using a visual expert model to evaluate the quality of generated images, encouraging the model to generate more realistic images. Extensive experiments demonstrate that our proposed RealSR-R1 can generate realistic details and accurately understand image content, particularly in semantically rich scenes or images with severe degradation.
Authors: Riccardo Corvi, Davide Cozzolino, Ekta Prashnani, Shalini De Mello, Koki Nagano, Luisa Verdoliva
Abstract: Synthetic video generation is progressing very rapidly. The latest models can produce very realistic high-resolution videos that are virtually indistinguishable from real ones. Although several video forensic detectors have been recently proposed, they often exhibit poor generalization, which limits their applicability in a real-world scenario. Our key insight to overcome this issue is to guide the detector towards seeing what really matters. In fact, a well-designed forensic classifier should focus on identifying intrinsic low-level artifacts introduced by a generative architecture rather than relying on high-level semantic flaws that characterize a specific model. In this work, first, we study different generative architectures, searching and identifying discriminative features that are unbiased, robust to impairments, and shared across models. Then, we introduce a novel forensic-oriented data augmentation strategy based on the wavelet decomposition and replace specific frequency-related bands to drive the model to exploit more relevant forensic cues. Our novel training paradigm improves the generalizability of AI-generated video detectors, without the need for complex algorithms and large datasets that include multiple synthetic generators. To evaluate our approach, we train the detector using data from a single generative model and test it against videos produced by a wide range of other models. Despite its simplicity, our method achieves a significant accuracy improvement over state-of-the-art detectors and obtains excellent results even on very recent generative models, such as NOVA and FLUX. Code and data will be made publicly available.
Authors: Chao Chen, Nobel Dang, Juexiao Zhang, Wenkai Sun, Pengfei Zheng, Xuhang He, Yimeng Ye, Taarun Srinivas, Chen Feng
Abstract: Humans exhibit a remarkable ability to recognize co-visibility-the overlapping regions visible in multiple images-even when these images are sparsely distributed across a complex scene. This capability is foundational in 3D vision and robotic perception. Despite significant progress in vision learning, it remains unclear whether current vision models have reached human-level proficiency in co-visibility analysis. In this work, we introduce the Co-Visibility reasONing (Co-VisiON) benchmark, designed to directly evaluate co-visibility reasoning on sparse image sets across over 1000 indoor scenarios. Our experiments reveal that while co-visibility is typically treated as a low-level feature matching task, it poses a significant challenge for existing vision models under sparse conditions. Notably, a proprietary vision-language model outperforms all purely vision-based approaches, with all models lagging substantially behind human performance. This gap underscores the need for more than basic pairwise vision processing-it calls for a comprehensive spatial understanding through high-level reasoning across multiple views. Inspired by human visual cognition, we propose a novel multi-view baseline, Covis, which achieves top performance among pure vision models and narrows the gap to the proprietary VLM. We hope our benchmark and findings will spur further advancements in developing vision models capable of robust, high-level reasoning in challenging, sparse environments. Our dataset and source code can be found at: https://ai4ce.github.io/CoVISION
Authors: Fan Yang, Yousong Zhu, Xin Li, Yufei Zhan, Hongyin Zhao, Shurong Zheng, Yaowei Wang, Ming Tang, Jinqiao Wang
Abstract: Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling, enabling both accurate content understanding and flexible editing. However, current approaches treat "what to see" and "how to edit" separately: they either perform isolated object segmentation or utilize segmentation masks merely as conditional prompts for local edit generation tasks, often relying on multiple disjointed models. To bridge these gaps, we introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework. FOCUS employs a dual-branch visual encoder to simultaneously capture global semantic context and fine-grained spatial details. In addition, we leverage a MoVQGAN-based visual tokenizer to produce discrete visual tokens that enhance generation quality. To enable accurate and controllable image editing, we propose a progressive multi-stage training pipeline, where segmentation masks are jointly optimized and used as spatial condition prompts to guide the diffusion decoder. This strategy aligns visual encoding, segmentation, and generation modules, effectively bridging segmentation-aware perception with fine-grained visual synthesis. Extensive experiments across three core tasks, including multimodal understanding, referring segmentation accuracy, and controllable image generation, demonstrate that FOCUS achieves strong performance by jointly optimizing visual perception and generative capabilities.
Authors: Yuchu Jiang, Jiaming Chu, Jian Zhao, Xin Zhang, Xu Yang, Lei Jin, Chi Zhang, Xuelong Li
Abstract: The proliferation of generative models has raised serious concerns about visual content forgery. Existing deepfake detection methods primarily target either image-level classification or pixel-wise localization. While some achieve high accuracy, they often suffer from limited generalization across manipulation types or rely on complex architectures. In this paper, we propose Loupe, a lightweight yet effective framework for joint deepfake detection and localization. Loupe integrates a patch-aware classifier and a segmentation module with conditional queries, allowing simultaneous global authenticity classification and fine-grained mask prediction. To enhance robustness against distribution shifts of test set, Loupe introduces a pseudo-label-guided test-time adaptation mechanism by leveraging patch-level predictions to supervise the segmentation head. Extensive experiments on the DDL dataset demonstrate that Loupe achieves state-of-the-art performance, securing the first place in the IJCAI 2025 Deepfake Detection and Localization Challenge with an overall score of 0.846. Our results validate the effectiveness of the proposed patch-level fusion and conditional query design in improving both classification accuracy and spatial localization under diverse forgery patterns. The code is available at https://github.com/Kamichanw/Loupe.
Authors: Can Lin, Daniele Affinita, Marco E. P. Zimmatore, Daniele Nardi, Domenico D. Bloisi, Vincenzo Suriani
Abstract: Robust and accurate ball detection is a critical component for autonomous humanoid soccer robots, particularly in dynamic and challenging environments such as RoboCup outdoor fields. However, traditional supervised approaches require extensive manual annotation, which is costly and time-intensive. To overcome this problem, we present a self-supervised learning framework for domain-adaptive feature extraction to enhance ball detection performance. The proposed approach leverages a general-purpose pretrained model to generate pseudo-labels, which are then used in a suite of self-supervised pretext tasks -- including colorization, edge detection, and triplet loss -- to learn robust visual features without relying on manual annotations. Additionally, a model-agnostic meta-learning (MAML) strategy is incorporated to ensure rapid adaptation to new deployment scenarios with minimal supervision. A new dataset comprising 10,000 labeled images from outdoor RoboCup SPL matches is introduced, used to validate the method, and made available to the community. Experimental results demonstrate that the proposed pipeline outperforms baseline models in terms of accuracy, F1 score, and IoU, while also exhibiting faster convergence.
Authors: Sattwik Sahu, Agamdeep Singh, Karthik Nambiar, Srikanth Saripalli, P. B. Sujit
Abstract: Off-road traversability segmentation enables autonomous navigation with applications in search-and-rescue, military operations, wildlife exploration, and agriculture. Current frameworks struggle due to significant variations in unstructured environments and uncertain scene changes, and are not adaptive to be used for different robot types. We present AnyTraverse, a framework combining natural language-based prompts with human-operator assistance to determine navigable regions for diverse robotic vehicles. The system segments scenes for a given set of prompts and calls the operator only when encountering previously unexplored scenery or unknown class not part of the prompt in its region-of-interest, thus reducing active supervision load while adapting to varying outdoor scenes. Our zero-shot learning approach eliminates the need for extensive data collection or retraining. Our experimental validation includes testing on RELLIS-3D, Freiburg Forest, and RUGD datasets and demonstrate real-world deployment on multiple robot platforms. The results show that AnyTraverse performs better than GA-NAV and Off-seg while offering a vehicle-agnostic approach to off-road traversability that balances automation with targeted human supervision.
Authors: Chaehyeon Song, Dongjae Lee, Jongwoo Lim, Ayoung Kim
Abstract: Camera calibration using planar targets has been widely favored, and two types of control points have been mainly considered as measurements: the corners of the checkerboard and the centroid of circles. Since a centroid is derived from numerous pixels, the circular pattern provides more precise measurements than the checkerboard. However, the existing projection model of circle centroids is biased under lens distortion, resulting in low performance. To surmount this limitation, we propose an unbiased projection model of the circular pattern and demonstrate its superior accuracy compared to the checkerboard. Complementing this, we introduce uncertainty into circular patterns to enhance calibration robustness and completeness. Defining centroid uncertainty improves the performance of calibration components, including pattern detection, optimization, and evaluation metrics. We also provide guidelines for performing good camera calibration based on the evaluation metric. The core concept of this approach is to model the boundary points of a two-dimensional shape as a Markov random field, considering its connectivity. The shape distribution is propagated to the centroid uncertainty through an appropriate shape representation based on the Green theorem. Consequently, the resulting framework achieves marked gains in calibration accuracy and robustness. The complete source code and demonstration video are available at https://github.com/chaehyeonsong/discocal.
Authors: Chaonan Ji, Jinwei Qi, Peng Zhang, Bang Zhang, Liefeng Bo
Abstract: In this paper, we propose a novel diffusion-based multi-condition controllable framework for video head swapping, which seamlessly transplant a human head from a static image into a dynamic video, while preserving the original body and background of target video, and further allowing to tweak head expressions and movements during swapping as needed. Existing face-swapping methods mainly focus on localized facial replacement neglecting holistic head morphology, while head-swapping approaches struggling with hairstyle diversity and complex backgrounds, and none of these methods allow users to modify the transplanted head expressions after swapping. To tackle these challenges, our method incorporates several innovative strategies through a unified latent diffusion paradigm. 1) Identity-preserving context fusion: We propose a shape-agnostic mask strategy to explicitly disentangle foreground head identity features from background/body contexts, combining hair enhancement strategy to achieve robust holistic head identity preservation across diverse hair types and complex backgrounds. 2) Expression-aware landmark retargeting and editing: We propose a disentangled 3DMM-driven retargeting module that decouples identity, expression, and head poses, minimizing the impact of original expressions in input images and supporting expression editing. While a scale-aware retargeting strategy is further employed to minimize cross-identity expression distortion for higher transfer precision. Experimental results demonstrate that our method excels in seamless background integration while preserving the identity of the source portrait, as well as showcasing superior expression transfer capabilities applicable to both real and virtual characters.
Authors: Jun Fu, Bin Tian, Haonan Chen, Shi Meng, Tingting Yao
Abstract: Autonomous parking plays a vital role in intelligent vehicle systems, particularly in constrained urban environments where high-precision control is required. While traditional rule-based parking systems struggle with environmental uncertainties and lack adaptability in crowded or dynamic scenes, human drivers demonstrate the ability to park intuitively without explicit modeling. Inspired by this observation, we propose a Transformer-based end-to-end framework for autonomous parking that learns from expert demonstrations. The network takes as input surround-view camera images, goal-point representations, ego vehicle motion, and pedestrian trajectories. It outputs discrete control sequences including throttle, braking, steering, and gear selection. A novel cross-attention module integrates BEV features with target points, and a GRU-based pedestrian predictor enhances safety by modeling dynamic obstacles. We validate our method on the CARLA 0.9.14 simulator in both vertical and parallel parking scenarios. Experiments show our model achieves a high success rate of 96.57\%, with average positional and orientation errors of 0.21 meters and 0.41 degrees, respectively. The ablation studies further demonstrate the effectiveness of key modules such as pedestrian prediction and goal-point attention fusion. The code and dataset will be released at: https://github.com/little-snail-f/ParkFormer.
Authors: Fabian Gr\"oger, Shuo Wen, Huyen Le, Maria Brbi\'c
Abstract: Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment including zero-shot classification and cross-modal retrieval. However, existing models typically rely on millions of paired multimodal samples, which are prohibitively expensive or infeasible to obtain in many domains. In this work, we explore the feasibility of building multimodal models with limited amount of paired data by aligning pretrained unimodal foundation models. We show that high-quality alignment is possible with as few as tens of thousands of paired samples$\unicode{x2013}$less than $1\%$ of the data typically used in the field. To achieve this, we introduce STRUCTURE, an effective regularization technique that preserves the neighborhood geometry of the latent space of unimodal encoders. Additionally, we show that aligning last layers is often suboptimal and demonstrate the benefits of aligning the layers with the highest representational similarity across modalities. These two components can be readily incorporated into existing alignment methods, yielding substantial gains across 24 zero-shot image classification and retrieval benchmarks, with average relative improvement of $51.6\%$ in classification and $91.8\%$ in retrieval tasks. Our results highlight the effectiveness and broad applicability of our framework for limited-sample multimodal learning and offer a promising path forward for resource-constrained domains.
Authors: Annika Thomas, Robaire Galliath, Aleksander Garbuz, Luke Anger, Cormac O'Neill, Trevor Johst, Dami Thomas, George Lordos, Jonathan P. How
Abstract: Global localization is necessary for autonomous operations on the lunar surface where traditional Earth-based navigation infrastructure, such as GPS, is unavailable. As NASA advances toward sustained lunar presence under the Artemis program, autonomous operations will be an essential component of tasks such as robotic exploration and infrastructure deployment. Tasks such as excavation and transport of regolith require precise pose estimation, but proposed approaches such as visual-inertial odometry (VIO) accumulate odometry drift over long traverses. Precise pose estimation is particularly important for upcoming missions such as the ISRU Pilot Excavator (IPEx) that rely on autonomous agents to operate over extended timescales and varied terrain. To help overcome odometry drift over long traverses, we propose LunarLoc, an approach to global localization that leverages instance segmentation for zero-shot extraction of boulder landmarks from onboard stereo imagery. Segment detections are used to construct a graph-based representation of the terrain, which is then aligned with a reference map of the environment captured during a previous session using graph-theoretic data association. This method enables accurate and drift-free global localization in visually ambiguous settings. LunarLoc achieves sub-cm level accuracy in multi-session global localization experiments, significantly outperforming the state of the art in lunar global localization. To encourage the development of further methods for global localization on the Moon, we release our datasets publicly with a playback module: https://github.com/mit-acl/lunarloc-data.
Authors: Fanfei Li, Thomas Klein, Wieland Brendel, Robert Geirhos, Roland S. Zimmermann
Abstract: Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from robustness benchmarks to quantify progress. While various benchmark datasets such as ImageNet-C were proposed in the ImageNet era, most ImageNet-C corruption types are no longer OOD relative to today's large, web-scraped datasets, which already contain common corruptions such as blur or JPEG compression artifacts. Consequently, these benchmarks are no longer well-suited for evaluating OOD robustness in the era of web-scale datasets. Indeed, recent models show saturating scores on ImageNet-era OOD benchmarks, indicating that it is unclear whether models trained on web-scale datasets truly become better at OOD generalization or whether they have simply been exposed to the test distortions during training. To address this, we introduce LAION-C as a benchmark alternative for ImageNet-C. LAION-C consists of six novel distortion types specifically designed to be OOD, even for web-scale datasets such as LAION. In a comprehensive evaluation of state-of-the-art models, we find that the LAION-C dataset poses significant challenges to contemporary models, including MLLMs such as Gemini and GPT-4o. We additionally conducted a psychophysical experiment to evaluate the difficulty of our corruptions for human observers, enabling a comparison of models to lab-quality human robustness data. We observe a paradigm shift in OOD generalization: from humans outperforming models, to the best models now matching or outperforming the best human observers.
Authors: Wenyang Luo, Haina Qin, Zewen Chen, Libin Wang, Dandan Zheng, Yuming Li, Yufan Liu, Bing Li, Weiming Hu
Abstract: Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose \textbf{Defusion}, a novel all-in-one image restoration framework that utilizes visual instruction-guided degradation diffusion. Unlike existing methods that rely on task-specific models or ambiguous text-based priors, Defusion constructs explicit \textbf{visual instructions} that align with the visual degradation patterns. These instructions are grounded by applying degradations to standardized visual elements, capturing intrinsic degradation features while agnostic to image semantics. Defusion then uses these visual instructions to guide a diffusion-based model that operates directly in the degradation space, where it reconstructs high-quality images by denoising the degradation effects with enhanced stability and generalizability. Comprehensive experiments demonstrate that Defusion outperforms state-of-the-art methods across diverse image restoration tasks, including complex and real-world degradations.
Authors: Haina Qin, Wenyang Luo, Libin Wang, Dandan Zheng, Jingdong Chen, Ming Yang, Bing Li, Weiming Hu
Abstract: Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restoration, including diffusion and score-based models, often treat the degradation process as a stochastic transformation, which introduces inefficiency and complexity. In this work, we propose ResFlow, a novel image restoration framework that models the degradation process as a deterministic path using continuous normalizing flows. ResFlow augments the degradation process with an auxiliary process that disambiguates the uncertainty in HQ prediction to enable reversible modeling of the degradation process. ResFlow adopts entropy-preserving flow paths and learns the augmented degradation flow by matching the velocity field. ResFlow significantly improves the performance and speed of image restoration, completing the task in fewer than four sampling steps. Extensive experiments demonstrate that ResFlow achieves state-of-the-art results across various image restoration benchmarks, offering a practical and efficient solution for real-world applications.
Authors: Haoran Sun, Yankai Jiang, Wenjie Lou, Yujie Zhang, Wenjie Li, Lilong Wang, Mianxin Liu, Lei Liu, Xiaosong Wang
Abstract: Multimodal large language models (MLLMs) have begun to demonstrate robust reasoning capabilities on general tasks, yet their application in the medical domain remains in its early stages. Constructing chain-of-thought (CoT) training data is essential for bolstering the reasoning abilities of medical MLLMs. However, existing approaches exhibit a deficiency in offering a comprehensive framework for searching and evaluating effective reasoning paths towards critical diagnosis. To address this challenge, we propose Mentor-Intern Collaborative Search (MICS), a novel reasoning-path searching scheme to generate rigorous and effective medical CoT data. MICS first leverages mentor models to initialize the reasoning, one step at a time, then prompts each intern model to continue the thinking along those initiated paths, and finally selects the optimal reasoning path according to the overall reasoning performance of multiple intern models. The reasoning performance is determined by an MICS-Score, which assesses the quality of generated reasoning paths. Eventually, we construct MMRP, a multi-task medical reasoning dataset with ranked difficulty, and Chiron-o1, a new medical MLLM devised via a curriculum learning strategy, with robust visual question-answering and generalizable reasoning capabilities. Extensive experiments demonstrate that Chiron-o1, trained on our CoT dataset constructed using MICS, achieves state-of-the-art performance across a list of medical visual question answering and reasoning benchmarks. Codes are available at GitHub - manglu097/Chiron-o1: Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs
Authors: Binbin Xiang, Maciej Wielgosz, Stefano Puliti, Kamil Kr\'al, Martin Kr\r{u}\v{c}ek, Azim Missarov, Rasmus Astrup
Abstract: The segmentation of forest LiDAR 3D point clouds, including both individual tree and semantic segmentation, is fundamental for advancing forest management and ecological research. However, current approaches often struggle with the complexity and variability of natural forest environments. We present ForestFormer3D, a new unified and end-to-end framework designed for precise individual tree and semantic segmentation. ForestFormer3D incorporates ISA-guided query point selection, a score-based block merging strategy during inference, and a one-to-many association mechanism for effective training. By combining these new components, our model achieves state-of-the-art performance for individual tree segmentation on the newly introduced FOR-instanceV2 dataset, which spans diverse forest types and regions. Additionally, ForestFormer3D generalizes well to unseen test sets (Wytham woods and LAUTx), showcasing its robustness across different forest conditions and sensor modalities. The FOR-instanceV2 dataset and the ForestFormer3D code will be released soon.
Authors: Yasir Ali Farrukh, Syed Wali, Irfan Khan, Nathaniel D. Bastian
Abstract: Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA methods typically rely on large vision-language models and require full access to source-domain data during adaptation, limiting their applicability. In this work, we propose Prmpt2Adpt, a lightweight and efficient zero-shot domain adaptation framework built around a teacher-student paradigm guided by prompt-based feature alignment. At the core of our method is a distilled and fine-tuned CLIP model, used as the frozen backbone of a Faster R-CNN teacher. A small set of low-level source features is aligned to the target domain semantics-specified only through a natural language prompt-via Prompt-driven Instance Normalization (PIN). These semantically steered features are used to briefly fine-tune the detection head of the teacher model. The adapted teacher then generates high-quality pseudo-labels, which guide the on-the-fly adaptation of a compact student model. Experiments on the MDS-A dataset demonstrate that Prmpt2Adpt achieves competitive detection performance compared to state-of-the-art methods, while delivering up to 7x faster adaptation and 5x faster inference speed using few source images-making it a practical and scalable solution for real-time adaptation in low-resource domains.
Authors: Hanlin Wu, Pengfei Lin, Ehsan Javanmardi, Naren Bao, Bo Qian, Hao Si, Manabu Tsukada
Abstract: 3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, the perception capability of a single vehicle is inherently constrained by occlusion, restricted sensor range, and narrow viewpoints. To address these limitations, collaborative perception enables the exchange of complementary information, thereby enhancing the completeness and accuracy. In the absence of a dedicated dataset for collaborative 3D semantic occupancy prediction, we augment an existing collaborative perception dataset by replaying it in CARLA with a high-resolution semantic voxel sensor to provide dense and comprehensive occupancy annotations. In addition, we establish benchmarks with varying prediction ranges designed to systematically assess the impact of spatial extent on collaborative prediction. We further develop a baseline model that performs inter-agent feature fusion via spatial alignment and attention aggregation. Experimental results demonstrate that our baseline model consistently outperforms single-agent models, with increasing gains observed as the prediction range expands.
Authors: Yiyang Tie, Hong Zhu, Yunyun Luo, Jing Shi
Abstract: The training of real-world super-resolution reconstruction models heavily relies on datasets that reflect real-world degradation patterns. Extracting and modeling degradation patterns for super-resolution reconstruction using only real-world low-resolution (LR) images remains a challenging task. When synthesizing datasets to simulate real-world degradation, relying solely on degradation extraction methods fails to capture both blur and diverse noise characteristics across varying LR distributions, as well as more implicit degradations such as color gamut shifts. Conversely, domain translation alone cannot accurately approximate real-world blur characteristics due to the significant degradation domain gap between synthetic and real data. To address these challenges, we propose a novel TripleGAN framework comprising two strategically designed components: The FirstGAN primarily focuses on narrowing the domain gap in blur characteristics, while the SecondGAN performs domain-specific translation to approximate target-domain blur properties and learn additional degradation patterns. The ThirdGAN is trained on pseudo-real data generated by the FirstGAN and SecondGAN to reconstruct real-world LR images. Extensive experiments on the RealSR and DRealSR datasets demonstrate that our method exhibits clear advantages in quantitative metrics while maintaining sharp reconstructions without over-smoothing artifacts. The proposed framework effectively learns real-world degradation patterns from LR observations and synthesizes aligned datasets with corresponding degradation characteristics, thereby enabling the trained network to achieve superior performance in reconstructing high-quality SR images from real-world LR inputs.
Authors: Lorenzo Tausani, Paolo Muratore, Morgan B. Talbot, Giacomo Amerio, Gabriel Kreiman, Davide Zoccolan
Abstract: Uncovering which features' combinations high-level visual units encode is critical to understand how images are transformed into representations that support recognition. While existing feature visualization approaches typically infer a unit's most exciting images, this is insufficient to reveal the manifold of transformations under which responses remain invariant, which is key to generalization in vision. Here we introduce Stretch-and-Squeeze (SnS), an unbiased, model-agnostic, and gradient-free framework to systematically characterize a unit's invariance landscape and its vulnerability to adversarial perturbations in both biological and artificial visual systems. SnS frames these transformations as bi-objective optimization problems. To probe invariance, SnS seeks image perturbations that maximally alter the representation of a reference stimulus in a given processing stage while preserving unit activation. To probe adversarial sensitivity, SnS seeks perturbations that minimally alter the stimulus while suppressing unit activation. Applied to convolutional neural networks (CNNs), SnS revealed image variations that were further from a reference image in pixel-space than those produced by affine transformations, while more strongly preserving the target unit's response. The discovered invariant images differed dramatically depending on the choice of image representation used for optimization: pixel-level changes primarily affected luminance and contrast, while stretching mid- and late-layer CNN representations altered texture and pose respectively. Notably, the invariant images from robust networks were more recognizable by human subjects than those from standard networks, supporting the higher fidelity of robust CNNs as models of the visual system.
Authors: Florent Meyer, Laurent Guichard, Denis Coquenet, Guillaume Gravier, Yann Soullard, Bertrand Co\"uasnon
Abstract: Effective license plate recognition systems are required to be resilient to constant change, as new license plates are released into traffic daily. While Transformer-based networks excel in their recognition at first sight, we observe significant performance drop over time which proves them unsuitable for tense production environments. Indeed, such systems obtain state-of-the-art results on plates whose syntax is seen during training. Yet, we show they perform similarly to random guessing on future plates where legible characters are wrongly recognized due to a shift in their syntax. After highlighting the flows of positional and contextual information in Transformer encoder-decoders, we identify several causes for their over-reliance on past syntax. Following, we devise architectural cut-offs and replacements which we integrate into SaLT, an attempt at a Syntax-Less Transformer for syntax-agnostic modeling of license plate representations. Experiments on both real and synthetic datasets show that our approach reaches top accuracy on past syntax and most importantly nearly maintains performance on future license plates. We further demonstrate the robustness of our architecture enhancements by way of various ablations.
Authors: Wang Zhao, Yan-Pei Cao, Jiale Xu, Yuejiang Dong, Ying Shan
Abstract: We present Assembler, a scalable and generalizable framework for 3D part assembly that reconstructs complete objects from input part meshes and a reference image. Unlike prior approaches that mostly rely on deterministic part pose prediction and category-specific training, Assembler is designed to handle diverse, in-the-wild objects with varying part counts, geometries, and structures. It addresses the core challenges of scaling to general 3D part assembly through innovations in task formulation, representation, and data. First, Assembler casts part assembly as a generative problem and employs diffusion models to sample plausible configurations, effectively capturing ambiguities arising from symmetry, repeated parts, and multiple valid assemblies. Second, we introduce a novel shape-centric representation based on sparse anchor point clouds, enabling scalable generation in Euclidean space rather than SE(3) pose prediction. Third, we construct a large-scale dataset of over 320K diverse part-object assemblies using a synthesis and filtering pipeline built on existing 3D shape repositories. Assembler achieves state-of-the-art performance on PartNet and is the first to demonstrate high-quality assembly for complex, real-world objects. Based on Assembler, we further introduce an interesting part-aware 3D modeling system that generates high-resolution, editable objects from images, demonstrating potential for interactive and compositional design. Project page: https://assembler3d.github.io
Authors: Ke Li, Chenyu Zhang, Yuxin Ding, Xianbiao Hu, Ruwen Qin
Abstract: Driving scene identification, which assigns multiple non-exclusive class labels to a scene, provides the contextual awareness necessary for enhancing autonomous vehicles' ability to understand, reason about, and interact with the complex driving environment. As a multi-label classification problem, it is better tackled via multitasking learning. However, directly training a multi-label classification model for driving scene identification through multitask learning presents two main challenges: acquiring a balanced, comprehensively annotated multi-label dataset and balancing learning across different tasks. This paper introduces a novel learning system that synergizes knowledge acquisition and accumulation (KAA) with consistency-based active learning (CAL) to address those challenges. KAA acquires and accumulates knowledge about scene identification from various single-label datasets via monotask learning. Subsequently, CAL effectively resolves the knowledge gap caused by the discrepancy between the marginal distributions of individual attributes and their joint distribution. An ablation study on our Driving Scene Identification (DSI) dataset demonstrates a 56.1% performance increase over the baseline model pretrained on ImageNet. Of this, KAA accounts for 31.3% of the gain, and CAL contributes 24.8%. Moreover, KAA-CAL stands out as the best performer when compared to state-of-the-art (SOTA) multi-label models on two public datasets, BDD100K and HSD, achieving this while using 85% less data. The DSI dataset and the implementation code for KAA-CAL are available at https://github.com/KELISBU/KAA-CAL .
Authors: Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal
Abstract: Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance, medical diagnosis requires precise reasoning over structured clinical tables, while financial forecasting depends on interpreting plot-based data to make informed predictions. To tackle this challenge, we introduce MEXA, a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse and distinct domains. MEXA dynamically selects expert models based on the input modality and the task-specific reasoning demands (i.e., skills). Each expert model, specialized in a modality task pair, generates interpretable textual reasoning outputs. MEXA then aggregates and reasons over these outputs using a Large Reasoning Model (LRM) to produce the final answer. This modular design allows flexible and transparent multimodal reasoning across diverse domains without additional training overhead. We extensively evaluate our approach on diverse multimodal benchmarks, including Video Reasoning, Audio Reasoning, 3D Understanding, and Medical QA. MEXA consistently delivers performance improvements over strong multimodal baselines, highlighting the effectiveness and broad applicability of our expert-driven selection and aggregation in diverse multimodal reasoning tasks.
Authors: Teng Guo, Jingjin Yu
Abstract: We introduce a robust framework, RGBTrack, for real-time 6D pose estimation and tracking that operates solely on RGB data, thereby eliminating the need for depth input for such dynamic and precise object pose tracking tasks. Building on the FoundationPose architecture, we devise a novel binary search strategy combined with a render-and-compare mechanism to efficiently infer depth and generate robust pose hypotheses from true-scale CAD models. To maintain stable tracking in dynamic scenarios, including rapid movements and occlusions, RGBTrack integrates state-of-the-art 2D object tracking (XMem) with a Kalman filter and a state machine for proactive object pose recovery. In addition, RGBTrack's scale recovery module dynamically adapts CAD models of unknown scale using an initial depth estimate, enabling seamless integration with modern generative reconstruction techniques. Extensive evaluations on benchmark datasets demonstrate that RGBTrack's novel depth-free approach achieves competitive accuracy and real-time performance, making it a promising practical solution candidate for application areas including robotics, augmented reality, and computer vision. The source code for our implementation will be made publicly available at https://github.com/GreatenAnoymous/RGBTrack.git.
Authors: Md Sakibur Sajal, Marc Dandin
Abstract: Digital image watermarks as a security feature can be derived from the imager's physically unclonable functions (PUFs) by utilizing the manufacturing variations, i.e., the dark signal non-uniformity (DSNU). While a few demonstrations focused on the CMOS image sensors (CIS) and active pixel sensors (APS), single photon avalanche diode (SPAD) imagers have never been investigated for this purpose. In this work, we have proposed a novel watermarking technique using perimeter gated SPAD (pgSPAD) imagers. We utilized the DSNU of three 64 x 64 pgSPAD imager chips, fabricated in a 0.35 {\mu}m standard CMOS process and analyzed the simulated watermarks for standard test images from publicly available database. Our observation shows that both source identification and tamper detection can be achieved using the proposed source-scene-specific dynamic watermarks with a controllable sensitivity-robustness trade-off.
Authors: Dongdong Meng, Sheng Li, Hao Wu, Guoping Wang, Xueqing Yan
Abstract: Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve the accuracy of medical image segmentation by providing complementary information. However, they face challenges in achieving significant improvements under semi-supervised conditions due to the challenge of effectively leveraging unlabeled data. There is a significant need to create an effective and reliable multi-modal learning strategy for leveraging unlabeled data in semi-supervised segmentation. To address these issues, we propose a novel semi-supervised multi-modal medical image segmentation approach, which leverages complementary multi-modal information to enhance performance with limited labeled data. Our approach employs a multi-stage multi-modal fusion and enhancement strategy to fully utilize complementary multi-modal information, while reducing feature discrepancies and enhancing feature sharing and alignment. Furthermore, we effectively introduce contrastive mutual learning to constrain prediction consistency across modalities, thereby facilitating the robustness of segmentation results in semi-supervised tasks. Experimental results on two multi-modal datasets demonstrate the superior performance and robustness of the proposed framework, establishing its valuable potential for solving medical image segmentation tasks in complex scenarios.
Authors: Zhuonan Liang, Dongnan Liu, Jianan Fan, Yaxuan Song, Qiang Qu, Yu Yao, Peng Fu, Weidong Cai
Abstract: Object counting models suffer when deployed across domains with differing density variety, since density shifts are inherently task-relevant and violate standard domain adaptation assumptions. To address this, we propose a theoretical framework of conditional feature alignment. We first formalize the notion of conditional divergence by partitioning each domain into subsets (e.g., object vs. background) and measuring divergences per condition. We then derive a joint error bound showing that, under discrete label spaces treated as condition sets, aligning distributions conditionally leads to tighter bounds on the combined source-target decision error than unconditional alignment. These insights motivate a general conditional adaptation principle: by preserving task-relevant variations while filtering out nuisance shifts, one can achieve superior cross-domain generalization for counting. We provide both defining conditional divergence then proving its benefit in lowering joint error and a practical adaptation strategy that preserves task-relevant information in unsupervised domain-adaptive counting. We demonstrate the effectiveness of our approach through extensive experiments on multiple counting datasets with varying density distributions. The results show that our method outperforms existing unsupervised domain adaptation methods, empirically validating the theoretical insights on conditional feature alignment.
Authors: Ritabrata Chakraborty, Rajatsubhra Chakraborty, Avijit Dasgupta, Sandeep Chaurasia
Abstract: Traditional video-based tasks like soccer action spotting rely heavily on visual inputs, often requiring complex and computationally expensive models to process dense video data. In this work, we propose a shift from this video-centric approach to a text-based task, making it lightweight and scalable by utilizing Large Language Models (LLMs) instead of Vision-Language Models (VLMs). We posit that expert commentary, which provides rich, fine-grained descriptions and contextual cues such as excitement and tactical insights, contains enough information to reliably spot key actions in a match. To demonstrate this, we use the SoccerNet Echoes dataset, which provides timestamped commentary, and employ a system of three LLMs acting as judges specializing in outcome, excitement, and tactics. Each LLM evaluates sliding windows of commentary to identify actions like goals, cards, and substitutions, generating accurate timestamps for these events. Our experiments show that this language-centric approach performs effectively in detecting critical match events, providing a lightweight and training-free alternative to traditional video-based methods for action spotting.
Authors: Qing Xu, Yuxiang Luo, Wenting Duan, Zhen Chen
Abstract: Medical image analysis is critical yet challenged by the need of jointly segmenting organs or tissues, and numerous instances for anatomical structures and tumor microenvironment analysis. Existing studies typically formulated different segmentation tasks in isolation, which overlooks the fundamental interdependencies between these tasks, leading to suboptimal segmentation performance and insufficient medical image understanding. To address this issue, we propose a Co-Seg++ framework for versatile medical segmentation. Specifically, we introduce a novel co-segmentation paradigm, allowing semantic and instance segmentation tasks to mutually enhance each other. We first devise a spatio-temporal prompt encoder (STP-Encoder) to capture long-range spatial and temporal relationships between segmentation regions and image embeddings as prior spatial constraints. Moreover, we devise a multi-task collaborative decoder (MTC-Decoder) that leverages cross-guidance to strengthen the contextual consistency of both tasks, jointly computing semantic and instance segmentation masks. Extensive experiments on diverse CT and histopathology datasets demonstrate that the proposed Co-Seg++ outperforms state-of-the-arts in the semantic, instance, and panoptic segmentation of dental anatomical structures, histopathology tissues, and nuclei instances. The source code is available at https://github.com/xq141839/Co-Seg-Plus.
Authors: Ketil Malde
Abstract: There now exists many popular object detectors based on deep learning that can analyze images and extract locations and class labels for occurrences of objects. For image time series (i.e., video or sequences of stills), tracking objects over time and preserving object identity can help to improve object detection performance, and is necessary for many downstream tasks, including classifying and predicting behaviors, and estimating total abundances. Here we present yasmot, a lightweight and flexible object tracker that can process the output from popular object detectors and track objects over time from either monoscopic or stereoscopic camera configurations. In addition, it includes functionality to generate consensus detections from ensembles of object detectors.
Authors: Israel Ju\'arez-Jim\'enez, Tiffany Guadalupe Mart\'inez Paredes, Jes\'us Garc\'ia-Ram\'irez, Eric Ramos Aguilar
Abstract: Emotion recognition from facial images is a crucial task in human-computer interaction, enabling machines to learn human emotions through facial expressions. Previous studies have shown that facial images can be used to train deep learning models; however, most of these studies do not include a through dataset analysis. Visualizing facial landmarks can be challenging when extracting meaningful dataset insights; to address this issue, we propose facial landmark box plots, a visualization technique designed to identify outliers in facial datasets. Additionally, we compare two sets of facial landmark features: (i) the landmarks' absolute positions and (ii) their displacements from a neutral expression to the peak of an emotional expression. Our results indicate that a neural network achieves better performance than a random forest classifier.
Authors: Jiaqi Li, Junshu Tang, Zhiyong Xu, Longhuang Wu, Yuan Zhou, Shuai Shao, Tianbao Yu, Zhiguo Cao, Qinglin Lu
Abstract: Recent advances in diffusion-based and controllable video generation have enabled high-quality and temporally coherent video synthesis, laying the groundwork for immersive interactive gaming experiences. However, current methods face limitations in dynamics, generality, long-term consistency, and efficiency, which limit the ability to create various gameplay videos. To address these gaps, we introduce Hunyuan-GameCraft, a novel framework for high-dynamic interactive video generation in game environments. To achieve fine-grained action control, we unify standard keyboard and mouse inputs into a shared camera representation space, facilitating smooth interpolation between various camera and movement operations. Then we propose a hybrid history-conditioned training strategy that extends video sequences autoregressively while preserving game scene information. Additionally, to enhance inference efficiency and playability, we achieve model distillation to reduce computational overhead while maintaining consistency across long temporal sequences, making it suitable for real-time deployment in complex interactive environments. The model is trained on a large-scale dataset comprising over one million gameplay recordings across over 100 AAA games, ensuring broad coverage and diversity, then fine-tuned on a carefully annotated synthetic dataset to enhance precision and control. The curated game scene data significantly improves the visual fidelity, realism and action controllability. Extensive experiments demonstrate that Hunyuan-GameCraft significantly outperforms existing models, advancing the realism and playability of interactive game video generation.
Authors: Teng Li, Quanfeng Lu, Lirui Zhao, Hao Li, Xizhou Zhu, Yu Qiao, Jun Zhang, Wenqi Shao
Abstract: Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work, we start by analyzing the modality alignment behaviors of task-specific expert models for understanding and generation, as well as current unified models. Our analysis reveals a crucial observation: understanding tasks benefit from a progressively increasing modality alignment across network depth, which helps build up semantic information for better comprehension; In contrast, generation tasks follow a different trend: modality alignment increases in the early layers but decreases in the deep layers to recover spatial details. These divergent alignment patterns create a fundamental conflict in fully shared Transformer backbones, where a uniform representational flow often leads to performance compromises across two tasks. Motivated by this finding, we introduce UniFork, a novel Y-shaped architecture that shares the shallow layers for cross-task representation learning, while employing task-specific branches in deeper layers to avoid task interference. This design effectively balances shared learning and task specialization. Through extensive ablation experiments, we demonstrate that Unifork consistently outperforms conventional fully shared Transformer architectures, and achieves performance on par with or better than task-specific models.
Authors: Tianjiao Yu, Vedant Shah, Muntasir Wahed, Ying Shen, Kiet A. Nguyen, Ismini Lourentzou
Abstract: Articulated objects are common in the real world, yet modeling their structure and motion remains a challenging task for 3D reconstruction methods. In this work, we introduce Part$^{2}$GS, a novel framework for modeling articulated digital twins of multi-part objects with high-fidelity geometry and physically consistent articulation. Part$^{2}$GS leverages a part-aware 3D Gaussian representation that encodes articulated components with learnable attributes, enabling structured, disentangled transformations that preserve high-fidelity geometry. To ensure physically consistent motion, we propose a motion-aware canonical representation guided by physics-based constraints, including contact enforcement, velocity consistency, and vector-field alignment. Furthermore, we introduce a field of repel points to prevent part collisions and maintain stable articulation paths, significantly improving motion coherence over baselines. Extensive evaluations on both synthetic and real-world datasets show that Part$^{2}$GS consistently outperforms state-of-the-art methods by up to 10$\times$ in Chamfer Distance for movable parts.
Authors: Xiuyu Yang, Shuhan Tan, Philipp Kr\"ahenb\"uhl
Abstract: An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. The code and model of InfGen will be released at https://orangesodahub.github.io/InfGen
Authors: Zeyuan Yang, Xueyang Yu, Delin Chen, Maohao Shen, Chuang Gan
Abstract: Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render explicit images, but the heavy image-generation pre-training often hinders the reasoning ability. Inspired by the way humans reason with mental imagery-the internal construction and manipulation of visual cues-we investigate whether VLMs can reason through interleaved multimodal trajectories without producing explicit images. To this end, we present a Machine Mental Imagery framework, dubbed as Mirage, which augments VLM decoding with latent visual tokens alongside ordinary text. Concretely, whenever the model chooses to ``think visually'', it recasts its hidden states as next tokens, thereby continuing a multimodal trajectory without generating pixel-level images. Begin by supervising the latent tokens through distillation from ground-truth image embeddings, we then switch to text-only supervision to make the latent trajectory align tightly with the task objective. A subsequent reinforcement learning stage further enhances the multimodal reasoning capability. Experiments on diverse benchmarks demonstrate that Mirage unlocks stronger multimodal reasoning without explicit image generation.
Authors: Jisu Nam, Soowon Son, Dahyun Chung, Jiyoung Kim, Siyoon Jin, Junhwa Hur, Seungryong Kim
Abstract: Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental question persists: how do these models internally establish and represent temporal correspondences across frames? We introduce DiffTrack, the first quantitative analysis framework designed to answer this question. DiffTrack constructs a dataset of prompt-generated video with pseudo ground-truth tracking annotations and proposes novel evaluation metrics to systematically analyze how each component within the full 3D attention mechanism of DiTs (e.g., representations, layers, and timesteps) contributes to establishing temporal correspondences. Our analysis reveals that query-key similarities in specific, but not all, layers play a critical role in temporal matching, and that this matching becomes increasingly prominent during the denoising process. We demonstrate practical applications of DiffTrack in zero-shot point tracking, where it achieves state-of-the-art performance compared to existing vision foundation and self-supervised video models. Further, we extend our findings to motion-enhanced video generation with a novel guidance method that improves temporal consistency of generated videos without additional training. We believe our work offers crucial insights into the inner workings of video DiTs and establishes a foundation for further research and applications leveraging their temporal understanding.
Authors: Zhangyang Qi, Zhixiong Zhang, Yizhou Yu, Jiaqi Wang, Hengshuang Zhao
Abstract: Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions. Current language model-based navigation systems operate on discrete topological graphs, limiting path planning to predefined node connections. We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions, adopting GRPO-based training inspired by DeepSeek-R1. To enable effective training, we first construct the VLN-Ego dataset using a 3D simulator, Habitat, and propose Long-Short Memory Sampling to balance historical and current observations. While large language models can supervise complete textual instructions, they lack fine-grained action-level control. Our framework employs a two-stage training approach: a) Supervised fine-tuning (SFT) to align the model's action sequence text predictions with expert demonstrations, followed by b) Reinforcement fine-tuning (RFT) enhanced with a Time-Decayed Reward (TDR) mechanism that strategically weights multi-step future actions. Experimental results show VLN-R1 achieves strong performance on VLN-CE benchmark. VLN-R1 proves LVLMs can drive embodied navigation and enhance task-specific reasoning through data-efficient, reward-driven post-training.
Authors: Ho Yin 'Sam' Ng, Ting-Yao Hsu, Aashish Anantha Ramakrishnan, Branislav Kveton, Nedim Lipka, Franck Dernoncourt, Dongwon Lee, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ting-Hao 'Kenneth' Huang
Abstract: Figure captions are crucial for helping readers understand and remember a figure's key message. Many models have been developed to generate these captions, helping authors compose better quality captions more easily. Yet, authors almost always need to revise generic AI-generated captions to match their writing style and the domain's style, highlighting the need for personalization. Despite language models' personalization (LaMP) advances, these technologies often focus on text-only settings and rarely address scenarios where both inputs and profiles are multimodal. This paper introduces LaMP-Cap, a dataset for personalized figure caption generation with multimodal figure profiles. For each target figure, LaMP-Cap provides not only the needed inputs, such as figure images, but also up to three other figures from the same document--each with its image, caption, and figure-mentioning paragraphs--as a profile to characterize the context. Experiments with four LLMs show that using profile information consistently helps generate captions closer to the original author-written ones. Ablation studies reveal that images in the profile are more helpful than figure-mentioning paragraphs, highlighting the advantage of using multimodal profiles over text-only ones.
Authors: Yunhak Oh, Junseok Lee, Yeongmin Kim, Sangwoo Seo, Namkyeong Lee, Chanyoung Park
Abstract: Spatially Resolved Transcriptomics (SRT) is a cutting-edge technique that captures the spatial context of cells within tissues, enabling the study of complex biological networks. Recent graph-based methods leverage both gene expression and spatial information to identify relevant spatial domains. However, these approaches fall short in obtaining meaningful spot representations, especially for spots near spatial domain boundaries, as they heavily emphasize adjacent spots that have minimal feature differences from an anchor node. To address this, we propose Spotscape, a novel framework that introduces the Similarity Telescope module to capture global relationships between multiple spots. Additionally, we propose a similarity scaling strategy to regulate the distances between intra- and inter-slice spots, facilitating effective multi-slice integration. Extensive experiments demonstrate the superiority of Spotscape in various downstream tasks, including single-slice and multi-slice scenarios. Our code is available at the following link: https: //github.com/yunhak0/Spotscape.
Authors: Le Jiang, Liyan Ma, Guang Yang
Abstract: Federated learning (FL) has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in sensitive fields like healthcare, where protecting patient data is paramount. However, privacy leakage remains a critical challenge, as the communication of model updates can be exploited by potential adversaries. Gradient inversion attacks (GIAs), for instance, allow adversaries to approximate the gradients used for training and reconstruct training images, thus stealing patient privacy. Existing defense mechanisms obscure gradients, yet lack a nuanced understanding of which gradients or types of image information are most vulnerable to such attacks. These indiscriminate calibrated perturbations result in either excessive privacy protection degrading model accuracy, or insufficient one failing to safeguard sensitive information. Therefore, we introduce a framework that addresses these challenges by leveraging a shadow model with interpretability for identifying sensitive areas. This enables a more targeted and sample-specific noise injection. Specially, our defensive strategy achieves discrepancies of 3.73 in PSNR and 0.2 in SSIM compared to the circumstance without defense on the ChestXRay dataset, and 2.78 in PSNR and 0.166 in the EyePACS dataset. Moreover, it minimizes adverse effects on model performance, with less than 1\% F1 reduction compared to SOTA methods. Our extensive experiments, conducted across diverse types of medical images, validate the generalization of the proposed framework. The stable defense improvements for FedAvg are consistently over 1.5\% times in LPIPS and SSIM. It also offers a universal defense against various GIA types, especially for these sensitive areas in images.
Authors: Juntae Lee, Munawar Hayat, Sungrack Yun
Abstract: Few-shot class incremental learning (FSCIL) enables the continual learning of new concepts with only a few training examples. In FSCIL, the model undergoes substantial updates, making it prone to forgetting previous concepts and overfitting to the limited new examples. Most recent trend is typically to disentangle the learning of the representation from the classification head of the model. A well-generalized feature extractor on the base classes (many examples and many classes) is learned, and then fixed during incremental learning. Arguing that the fixed feature extractor restricts the model's adaptability to new classes, we introduce a novel FSCIL method to effectively address catastrophic forgetting and overfitting issues. Our method enables to seamlessly update the entire model with a few examples. We mainly propose a tripartite weight-space ensemble (Tri-WE). Tri-WE interpolates the base, immediately previous, and current models in weight-space, especially for the classification heads of the models. Then, it collaboratively maintains knowledge from the base and previous models. In addition, we recognize the challenges of distilling generalized representations from the previous model from scarce data. Hence, we suggest a regularization loss term using amplified data knowledge distillation. Simply intermixing the few-shot data, we can produce richer data enabling the distillation of critical knowledge from the previous model. Consequently, we attain state-of-the-art results on the miniImageNet, CUB200, and CIFAR100 datasets.
Authors: Jiangnan Zhao (Key Laboratory of Smart Agriculture Systems, Ministry of Education, China Agricultural University, Beijing, PR China, Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs of China, China Agricultural University, Beijing, PR China), Hanbo Xu (Key Laboratory of Smart Agriculture Systems, Ministry of Education, China Agricultural University, Beijing, PR China, Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs of China, China Agricultural University, Beijing, PR China), Cifu Xu (Key Laboratory of Smart Agriculture Systems, Ministry of Education, China Agricultural University, Beijing, PR China, Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs of China, China Agricultural University, Beijing, PR China), Wenlong Yin (Key Laboratory of Smart Agriculture Systems, Ministry of Education, China Agricultural University, Beijing, PR China, Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs of China, China Agricultural University, Beijing, PR China), Laixin Luo (Department of Plant Pathology, China Agricultural University, Beijing Key Laboratory of Seed Disease Testing and Control, Beijing, PR China), Gang Liu (Key Laboratory of Smart Agriculture Systems, Ministry of Education, China Agricultural University, Beijing, PR China, Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs of China, China Agricultural University, Beijing, PR China), Yan Wang (Key Laboratory of Smart Agriculture Systems, Ministry of Education, China Agricultural University, Beijing, PR China, Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs of China, China Agricultural University, Beijing, PR China)
Abstract: Potato late blight, caused by the oomycete pathogen Phytophthora infestans, is one of the most devastating diseases affecting potato crops in the history. Although conventional detection methods of plant diseases such as PCR and LAMP are highly sensitive and specific, they rely on bulky and expensive laboratory equipment and involve complex operations, making them impracticable for point-of care diagnosis in the field. Here in this study, we report a portable RPA-CRISPR based diagnosis system for plant disease, integrating smartphone for acquisition and analysis of fluorescent images. A polyvinyl alcohol (PVA) microneedle patch was employed for sample extraction on the plant leaves within one minute, the DNA extraction efficiency achieved 56 ug/mg, which is approximately 3 times to the traditional CTAB methods (18 ug/mg). The system of RPA-CRISPR-Cas12a isothermal assay was established to specifically target P. infestans with no cross-reactivity observed against closely-related species (P. sojae, P. capsici). The system demonstrated a detection limit of 2 pg/uL for P. infestans genomic DNA, offering sensitivity comparable to that of benchtop laboratory equipment. The system demonstrates the early-stage diagnosis capability by achieving a approximately 80% and 100% detection rate on the third and fourth day post-inoculation respectively, before visible symptoms observed on the leaves. The smartphone-based "sample-to-result" system decouples the limitations of traditional methods that rely heavily on specialized equipment, offering a promising way for early-stage plant disease detection and control in the field.
Authors: Peiyuan Tang, Haojie Xin, Xiaodong Zhang, Jun Sun, Qin Xia, Zijiang Yang
Abstract: As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs), VLMs face unique vulnerabilities due to their multimodal nature, allowing adversaries to modify visual or textual inputs to bypass safety guardrails and trigger the generation of harmful content. Through systematic analysis of VLM behavior under attack, we identify a novel phenomenon termed ``delayed safety awareness''. Specifically, we observe that safety-aligned VLMs may initially be compromised to produce harmful content, but eventually recognize the associated risks and attempt to self-correct. This pattern suggests that VLMs retain their underlying safety awareness but experience a temporal delay in their activation. Building on this insight, we hypothesize that VLMs' safety awareness can be proactively reactivated through carefully designed prompts. To this end, we introduce ``The Safety Reminder'', a soft prompt tuning approach that optimizes learnable prompt tokens, which are periodically injected during the text generation process to enhance safety awareness, effectively preventing harmful content generation. Additionally, our safety reminder only activates when harmful content is detected, leaving normal conversations unaffected and preserving the model's performance on benign tasks. Through comprehensive evaluation across three established safety benchmarks and one adversarial attacks, we demonstrate that our approach significantly reduces attack success rates while maintaining model utility, offering a practical solution for deploying safer VLMs in real-world applications.
Authors: Seyed Mohsen Hosseini
Abstract: Class imbalance and the difficulty imbalance are the two types of data imbalance that affect the performance of neural networks in medical segmentation tasks. In class imbalance the loss is dominated by the majority classes and in difficulty imbalance the loss is dominated by easy to classify pixels. This leads to an ineffective training. Dice loss, which is based on a geometrical metric, is very effective in addressing the class imbalance compared to the cross entropy (CE) loss, which is adopted directly from classification tasks. To address the difficulty imbalance, the common approach is employing a re-weighted CE loss or a modified Dice loss to focus the training on difficult to classify areas. The existing modification methods are computationally costly and with limited success. In this study we propose a simple modification to the Dice loss with minimal computational cost. With a pixel level modulating term, we take advantage of the effectiveness of Dice loss in handling the class imbalance to also handle the difficulty imbalance. Results on three commonly used medical segmentation tasks show that the proposed Pixel-wise Modulated Dice loss (PM Dice loss) outperforms other methods, which are designed to tackle the difficulty imbalance problem.
Authors: Zhe Wang, Yuhua Ru, Aladine Chetouani, Tina Shiang, Fang Chen, Fabian Bauer, Liping Zhang, Didier Hans, Rachid Jennane, William Ewing Palmer, Mohamed Jarraya, Yung Hsin Chen
Abstract: Automated grading of Knee Osteoarthritis (KOA) from radiographs is challenged by significant inter-observer variability and the limited robustness of deep learning models, particularly near critical decision boundaries. To address these limitations, this paper proposes a novel framework, Diffusion-based Counterfactual Augmentation (DCA), which enhances model robustness and interpretability by generating targeted counterfactual examples. The method navigates the latent space of a diffusion model using a Stochastic Differential Equation (SDE), governed by balancing a classifier-informed boundary drive with a manifold constraint. The resulting counterfactuals are then used within a self-corrective learning strategy to improve the classifier by focusing on its specific areas of uncertainty. Extensive experiments on the public Osteoarthritis Initiative (OAI) and Multicenter Osteoarthritis Study (MOST) datasets demonstrate that this approach significantly improves classification accuracy across multiple model architectures. Furthermore, the method provides interpretability by visualizing minimal pathological changes and revealing that the learned latent space topology aligns with clinical knowledge of KOA progression. The DCA framework effectively converts model uncertainty into a robust training signal, offering a promising pathway to developing more accurate and trustworthy automated diagnostic systems. Our code is available at https://github.com/ZWang78/DCA.
Authors: Narayan Kandel, Daljit Singh J. S. Dhillon
Abstract: Structural coloration is commonly modeled using wave optics for reliable and photorealistic rendering of natural, quasi-periodic and complex nanostructures. Such models often rely on dense, preliminary or preprocessed data to accurately capture the nuanced variations in diffractive surface reflectances. This heavy data dependency warrants implicit neural representation which has not been addressed comprehensively in the current literature. In this paper, we present a multi-layer perceptron (MLP) based method for data-driven rendering of diffractive surfaces with high accuracy and efficiency. We primarily approach this problem from a data compression perspective to devise a nuanced training and modeling method which is attuned to the domain and range characteristics of diffractive reflectance datasets. Importantly, our approach avoids over-fitting and has robust resampling behavior. Using Peak-Signal-to-Noise (PSNR), Structural Similarity Index Measure (SSIM) and a flipping difference evaluator (FLIP) as evaluation metrics, we demonstrate the high-quality reconstruction of the ground-truth. In comparison to a recent state-of-the-art offline, wave-optical, forward modeling approach, our method reproduces subjectively similar results with significant performance gains. We reduce the memory footprint of the raw datasets by two orders of magnitude in general. Lastly, we depict the working of our method with actual surface renderings.
Authors: Pham Khai Nguyen Do, Bao Nguyen Tran, Nam Nguyen, Duc Dung Nguyen
Abstract: Recent advances in Novel View Synthesis (NVS) and 3D generation have significantly improved editing tasks, with a primary emphasis on maintaining cross-view consistency throughout the generative process. Contemporary methods typically address this challenge using a dual-strategy framework: performing consistent 2D inpainting across all views guided by embedded priors either explicitly in pixel space or implicitly in latent space; and conducting 3D reconstruction with additional consistency guidance. Previous strategies, in particular, often require an initial 3D reconstruction phase to establish geometric structure, introducing considerable computational overhead. Even with the added cost, the resulting reconstruction quality often remains suboptimal. In this paper, we present VEIGAR, a computationally efficient framework that outperforms existing methods without relying on an initial reconstruction phase. VEIGAR leverages a lightweight foundation model to reliably align priors explicitly in the pixel space. In addition, we introduce a novel supervision strategy based on scale-invariant depth loss, which removes the need for traditional scale-and-shift operations in monocular depth regularization. Through extensive experimentation, VEIGAR establishes a new state-of-the-art benchmark in reconstruction quality and cross-view consistency, while achieving a threefold reduction in training time compared to the fastest existing method, highlighting its superior balance of efficiency and effectiveness.
Authors: Mingyuan Luo, Xin Yang, Zhongnuo Yan, Yan Cao, Yuanji Zhang, Xindi Hu, Jin Wang, Haoxuan Ding, Wei Han, Litao Sun, Dong Ni
Abstract: Three-dimensional (3D) ultrasound (US) aims to provide sonographers with the spatial relationships of anatomical structures, playing a crucial role in clinical diagnosis. Recently, deep-learning-based freehand 3D US has made significant advancements. It reconstructs volumes by estimating transformations between images without external tracking. However, image-only reconstruction poses difficulties in reducing cumulative drift and further improving reconstruction accuracy, particularly in scenarios involving complex motion trajectories. In this context, we propose an enhanced motion network (MoNetV2) to enhance the accuracy and generalizability of reconstruction under diverse scanning velocities and tactics. First, we propose a sensor-based temporal and multi-branch structure that fuses image and motion information from a velocity perspective to improve image-only reconstruction accuracy. Second, we devise an online multi-level consistency constraint that exploits the inherent consistency of scans to handle various scanning velocities and tactics. This constraint exploits both scan-level velocity consistency, path-level appearance consistency, and patch-level motion consistency to supervise inter-frame transformation estimation. Third, we distill an online multi-modal self-supervised strategy that leverages the correlation between network estimation and motion information to further reduce cumulative errors. Extensive experiments clearly demonstrate that MoNetV2 surpasses existing methods in both reconstruction quality and generalizability performance across three large datasets.
Authors: Kirill Muravyev, Vasily Yuryev, Oleg Bulichev, Dmitry Yudin, Konstantin Yakovlev
Abstract: Localization in the environment is one of the crucial tasks of navigation of a mobile robot or a self-driving vehicle. For long-range routes, performing localization within a dense global lidar map in real time may be difficult, and the creation of such a map may require much memory. To this end, leveraging topological maps may be useful. In this work, we propose PRISM-Loc -- a topological map-based approach for localization in large environments. The proposed approach leverages a twofold localization pipeline, which consists of global place recognition and estimation of the local pose inside the found location. For local pose estimation, we introduce an original lidar scan matching algorithm, which is based on 2D features and point-based optimization. We evaluate the proposed method on the ITLP-Campus dataset on a 3 km route, and compare it against the state-of-the-art metric map-based and place recognition-based competitors. The results of the experiments show that the proposed method outperforms its competitors both quality-wise and computationally-wise.
Authors: Qiyuan Wu, Mark Campbell
Abstract: The uncertainty quantification of sensor measurements coupled with deep learning networks is crucial for many robotics systems, especially for safety-critical applications such as self-driving cars. This paper develops an uncertainty quantification approach in the context of visual localization for autonomous driving, where locations are selected based on images. Key to our approach is to learn the measurement uncertainty using light-weight sensor error model, which maps both image feature and semantic information to 2-dimensional error distribution. Our approach enables uncertainty estimation conditioned on the specific context of the matched image pair, implicitly capturing other critical, unannotated factors (e.g., city vs highway, dynamic vs static scenes, winter vs summer) in a latent manner. We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting and weather (sunny, night, snowy). Both the uncertainty quantification of the sensor+network is evaluated, along with Bayesian localization filters using unique sensor gating method. Results show that the measurement error does not follow a Gaussian distribution with poor weather and lighting conditions, and is better predicted by our Gaussian Mixture model.
Authors: Amit Das, Naofumi Tomita, Kyle J. Syme, Weijie Ma, Paige O'Connor, Kristin N. Corbett, Bing Ren, Xiaoying Liu, Saeed Hassanpour
Abstract: Hematoxylin and Eosin (H&E) staining is a cornerstone of pathological analysis, offering reliable visualization of cellular morphology and tissue architecture for cancer diagnosis, subtyping, and grading. Immunohistochemistry (IHC) staining provides molecular insights by detecting specific proteins within tissues, enhancing diagnostic accuracy, and improving treatment planning. However, IHC staining is costly, time-consuming, and resource-intensive, requiring specialized expertise. To address these limitations, this study proposes HistoStainAlign, a novel deep learning framework that predicts IHC staining patterns directly from H&E whole-slide images (WSIs) by learning joint representations of morphological and molecular features. The framework integrates paired H&E and IHC embeddings through a contrastive training strategy, capturing complementary features across staining modalities without patch-level annotations or tissue registration. The model was evaluated on gastrointestinal and lung tissue WSIs with three commonly used IHC stains: P53, PD-L1, and Ki-67. HistoStainAlign achieved weighted F1 scores of 0.735 [95% Confidence Interval (CI): 0.670-0.799], 0.830 [95% CI: 0.772-0.886], and 0.723 [95% CI: 0.607-0.836], respectively for these three IHC stains. Embedding analyses demonstrated the robustness of the contrastive alignment in capturing meaningful cross-stain relationships. Comparisons with a baseline model further highlight the advantage of incorporating contrastive learning for improved stain pattern prediction. This study demonstrates the potential of computational approaches to serve as a pre-screening tool, helping prioritize cases for IHC staining and improving workflow efficiency.
Authors: Md Sakibur Sajal, Hunter Guthrie, Marc Dandin
Abstract: Random number generators that utilize arrays of entropy source elements suffer from bias variation (BV). Despite the availability of efficient debiasing algorithms, optimized implementations of hardware friendly options depend on the bit bias in the raw bit streams and cannot accommodate a wide BV. In this work, we present a 64 x 64 array of perimeter gated single photon avalanche diodes (pgSPADs), fabricated in a 0.35 {\mu}m standard CMOS technology, as a source of entropy to generate random binary strings with a BV compensation technique. By applying proper gate voltages based on the devices' native dark count rates, we demonstrate less than 1% BV for a raw-bit generation rate of 2 kHz/pixel at room temperature. The raw bits were debiased using the classical iterative Von Neumann's algorithm and the debiased bits were found to pass all of the 16 tests from NIST's Statistical Test Suite.
Authors: Jiawen Yu, Jieji Ren, Yang Chang, Qiaojun Yu, Xuan Tong, Boyang Wang, Yan Song, You Li, Xinji Mai, Wenqiang Zhang
Abstract: Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging environments. However, accurately detecting workpiece defects in complex and unstructured industrial environments with varying views, poses and illumination remains challenging. We propose a novel anomaly detection and localization method specifically designed to handle inputs with perturbative patterns. Our approach introduces a new framework based on a collaborative distillation heterogeneous teacher network (HetNet), an adaptive local-global feature fusion module, and a local multivariate Gaussian noise generation module. HetNet can learn to model the complex feature distribution of normal patterns using limited information about local disruptive changes. We conducted extensive experiments on mainstream benchmarks. HetNet demonstrates superior performance with approximately 10% improvement across all evaluation metrics on MSC-AD under industrial conditions, while achieving state-of-the-art results on other datasets, validating its resilience to environmental fluctuations and its capability to enhance the reliability of industrial anomaly detection systems across diverse scenarios. Tests in real-world environments further confirm that HetNet can be effectively integrated into production lines to achieve robust and real-time anomaly detection. Codes, images and videos are published on the project website at: https://zihuatanejoyu.github.io/HetNet/
Authors: Ziran Zhu, Tongda Xu, Minye Huang, Dailan He, Xingtong Ge, Xinjie Zhang, Ling Li, Yan Wang
Abstract: Training-free perceptual image codec adopt pre-trained unconditional generative model during decoding to avoid training new conditional generative model. However, they heavily rely on diffusion inversion or sample communication, which take 1 min to intractable amount of time to decode a single image. In this paper, we propose a training-free algorithm that improves the perceptual quality of any existing codec with theoretical guarantee. We further propose different implementations for optimal perceptual quality when decoding time budget is $\approx 0.1$s, $0.1-10$s and $\ge 10$s. Our approach: 1). improves the decoding time of training-free codec from 1 min to $0.1-10$s with comparable perceptual quality. 2). can be applied to non-differentiable codec such as VTM. 3). can be used to improve previous perceptual codecs, such as MS-ILLM. 4). can easily achieve perception-distortion trade-off. Empirically, we show that our approach successfully improves the perceptual quality of ELIC, VTM and MS-ILLM with fast decoding. Our approach achieves comparable FID to previous training-free codec with significantly less decoding time. And our approach still outperforms previous conditional generative model based codecs such as HiFiC and MS-ILLM in terms of FID. The source code is provided in the supplementary material.
Authors: Ignacio Hern\'andez Montilla, Alfonso Medela, Paola Pasquali, Andy Aguilar, Taig Mac Carthy, Gerardo Fern\'andez, Antonio Martorell, Enrique Onieva
Abstract: Teledermatology has become a widely accepted communication method in daily clinical practice, enabling remote care while showing strong agreement with in-person visits. Poor image quality remains an unsolved problem in teledermatology and is a major concern to practitioners, as bad-quality images reduce the usefulness of the remote consultation process. However, research on Image Quality Assessment (IQA) in dermatology is sparse, and does not leverage the latest advances in non-dermatology IQA, such as using larger image databases with ratings from large groups of human observers. In this work, we propose cross-domain training of IQA models, combining dermatology and non-dermatology IQA datasets. For this purpose, we created a novel dermatology IQA database, Legit.Health-DIQA-Artificial, using dermatology images from several sources and having them annotated by a group of human observers. We demonstrate that cross-domain training yields optimal performance across domains and overcomes one of the biggest limitations in dermatology IQA, which is the small scale of data, and leads to models trained on a larger pool of image distortions, resulting in a better management of image quality in the teledermatology process.
Authors: Sen Wang, Le Wang, Sanping Zhou, Jingyi Tian, Jiayi Li, Haowen Sun, Wei Tang
Abstract: Robotic manipulation in high-precision tasks is essential for numerous industrial and real-world applications where accuracy and speed are required. Yet current diffusion-based policy learning methods generally suffer from low computational efficiency due to the iterative denoising process during inference. Moreover, these methods do not fully explore the potential of generative models for enhancing information exploration in 3D environments. In response, we propose FlowRAM, a novel framework that leverages generative models to achieve region-aware perception, enabling efficient multimodal information processing. Specifically, we devise a Dynamic Radius Schedule, which allows adaptive perception, facilitating transitions from global scene comprehension to fine-grained geometric details. Furthermore, we integrate state space models to integrate multimodal information, while preserving linear computational complexity. In addition, we employ conditional flow matching to learn action poses by regressing deterministic vector fields, simplifying the learning process while maintaining performance. We verify the effectiveness of the FlowRAM in the RLBench, an established manipulation benchmark, and achieve state-of-the-art performance. The results demonstrate that FlowRAM achieves a remarkable improvement, particularly in high-precision tasks, where it outperforms previous methods by 12.0% in average success rate. Additionally, FlowRAM is able to generate physically plausible actions for a variety of real-world tasks in less than 4 time steps, significantly increasing inference speed.
Authors: Zhenxuan Zhang, Lipei Zhang, Yanqi Cheng, Zi Wang, Fanwen Wang, Haosen Zhang, Yue Yang, Yinzhe Wu, Jiahao Huang, Angelica I Aviles-Rivero, Zhifan Gao, Guang Yang, Peter J. Lally
Abstract: In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially under accelerated acquisitions or patient motion. However, this task remains challenging due to hierarchical structural disruptions. It includes local detail loss from k-space undersampling, global structural aliasing caused by motion, and volumetric anisotropy. Therefore, we propose a progressive refinement implicit neural representation (PR-INR) framework. Our PR-INR unifies motion correction, structural refinement, and volumetric synthesis within a geometry-aware coordinate space. Specifically, a motion-aware diffusion module is first employed to generate coarse volumetric reconstructions that suppress motion artifacts and preserve global anatomical structures. Then, we introduce an implicit detail restoration module that performs residual refinement by aligning spatial coordinates with visual features. It corrects local structures and enhances boundary precision. Further, a voxel continuous-aware representation module represents the image as a continuous function over 3D coordinates. It enables accurate inter-slice completion and high-frequency detail recovery. We evaluate PR-INR on five public MRI datasets under various motion conditions (3% and 5% displacement), undersampling rates (4x and 8x) and slice resolutions (scale = 5). Experimental results demonstrate that PR-INR outperforms state-of-the-art methods in both quantitative reconstruction metrics and visual quality. It further shows generalization and robustness across diverse unseen domains.
Authors: Raghav Mehta, Fabio De Sousa Ribeiro, Tian Xia, Melanie Roschewitz, Ainkaran Santhirasekaram, Dominic C. Marshall, Ben Glocker
Abstract: Segmenting anatomical structures in medical images plays an important role in the quantitative assessment of various diseases. However, accurate segmentation becomes significantly more challenging in the presence of disease. Disease patterns can alter the appearance of surrounding healthy tissues, introduce ambiguous boundaries, or even obscure critical anatomical structures. As such, segmentation models trained on real-world datasets may struggle to provide good anatomical segmentation, leading to potential misdiagnosis. In this paper, we generate counterfactual (CF) images to simulate how the same anatomy would appear in the absence of disease without altering the underlying structure. We then use these CF images to segment structures of interest, without requiring any changes to the underlying segmentation model. Our experiments on two real-world clinical chest X-ray datasets show that the use of counterfactual images improves anatomical segmentation, thereby aiding downstream clinical decision-making.
Authors: C\'esar D\'iaz-Parga, Marta Nu\~nez-Garcia, Maria J. Carreira, Gabriel Bernardino, Nicol\'as Vila-Blanco
Abstract: Being born small carries significant health risks, including increased neonatal mortality and a higher likelihood of future cardiac diseases. Accurate estimation of gestational age is critical for monitoring fetal growth, but traditional methods, such as estimation based on the last menstrual period, are in some situations difficult to obtain. While ultrasound-based approaches offer greater reliability, they rely on manual measurements that introduce variability. This study presents an interpretable deep learning-based method for automated gestational age calculation, leveraging a novel segmentation architecture and distance maps to overcome dataset limitations and the scarcity of segmentation masks. Our approach achieves performance comparable to state-of-the-art models while reducing complexity, making it particularly suitable for resource-constrained settings and with limited annotated data. Furthermore, our results demonstrate that the use of distance maps is particularly suitable for estimating femur endpoints.
Authors: Yueji Ma, Yanzun Meng, Dong Xiao, Zuoqiang Shi, Bin Wang
Abstract: Unoriented surface reconstruction is an important task in computer graphics and has extensive applications. Based on the compact support of wavelet and orthogonality properties, classic wavelet surface reconstruction achieves good and fast reconstruction. However, this method can only handle oriented points. Despite some improved attempts for unoriented points, such as iWSR, these methods perform poorly on sparse point clouds. To address these shortcomings, we propose a wavelet-based method to represent the mollified indicator function and complete both the orientation and surface reconstruction tasks. We use the modifying kernel function to smoothen out discontinuities on the surface, aligning with the continuity of the wavelet basis function. During the calculation of coefficient, we fully utilize the properties of the convolutional kernel function to shift the modifying computation onto wavelet basis to accelerate. In addition, we propose a novel method for constructing the divergence-free function field and using them to construct the additional homogeneous constraints to improve the effectiveness and stability. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both orientation and reconstruction for sparse models. We align the matrix construction with the compact support property of wavelet basis functions to further accelerate our method, resulting in efficient performance on CPU. Our source codes will be released on GitHub.
Authors: Nikola Jovanovi\'c, Ismail Labiad, Tom\'a\v{s} Sou\v{c}ek, Martin Vechev, Pierre Fernandez
Abstract: Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to watermark their outputs at the token level. In this work, we present the first such approach by adapting language model watermarking techniques to this setting. We identify a key challenge: the lack of reverse cycle-consistency (RCC), wherein re-tokenizing generated image tokens significantly alters the token sequence, effectively erasing the watermark. To address this and to make our method robust to common image transformations, neural compression, and removal attacks, we introduce (i) a custom tokenizer-detokenizer finetuning procedure that improves RCC, and (ii) a complementary watermark synchronization layer. As our experiments demonstrate, our approach enables reliable and robust watermark detection with theoretically grounded p-values.
Authors: Chunhou Ji, Qiumeng Li
Abstract: GPS trajectory data reveals valuable patterns of human mobility and urban dynamics, supporting a variety of spatial applications. However, traditional methods often struggle to extract deep semantic representations and incorporate contextual map information. We propose TrajSceneLLM, a multimodal perspective for enhancing semantic understanding of GPS trajectories. The framework integrates visualized map images (encoding spatial context) and textual descriptions generated through LLM reasoning (capturing temporal sequences and movement dynamics). Separate embeddings are generated for each modality and then concatenated to produce trajectory scene embeddings with rich semantic content which are further paired with a simple MLP classifier. We validate the proposed framework on Travel Mode Identification (TMI), a critical task for analyzing travel choices and understanding mobility behavior. Our experiments show that these embeddings achieve significant performance improvement, highlighting the advantage of our LLM-driven method in capturing deep spatio-temporal dependencies and reducing reliance on handcrafted features. This semantic enhancement promises significant potential for diverse downstream applications and future research in geospatial artificial intelligence. The source code and dataset are publicly available at: https://github.com/februarysea/TrajSceneLLM.
Authors: Xiaoya Lu, Zeren Chen, Xuhao Hu, Yijin Zhou, Weichen Zhang, Dongrui Liu, Lu Sheng, Jing Shao
Abstract: Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks within these interactive environments, since they cannot simulate dynamic risks that emerge from an agent's actions and rely on unreliable post-hoc evaluations that ignore unsafe intermediate steps. To bridge this critical gap, we propose evaluating an agent's interactive safety: its ability to perceive emergent risks and execute mitigation steps in the correct procedural order. We thus present IS-Bench, the first multi-modal benchmark designed for interactive safety, featuring 161 challenging scenarios with 388 unique safety risks instantiated in a high-fidelity simulator. Crucially, it facilitates a novel process-oriented evaluation that verifies whether risk mitigation actions are performed before/after specific risk-prone steps. Extensive experiments on leading VLMs, including the GPT-4o and Gemini-2.5 series, reveal that current agents lack interactive safety awareness, and that while safety-aware Chain-of-Thought can improve performance, it often compromises task completion. By highlighting these critical limitations, IS-Bench provides a foundation for developing safer and more reliable embodied AI systems.
Authors: Changsheng Gao, Zijie Liu, Li Li, Dong Liu, Xiaoyan Sun, Weisi Lin
Abstract: Like image coding in visual data transmission, feature coding is essential for the distributed deployment of large models by significantly reducing transmission and storage overhead. However, prior studies have mostly targeted task- or model-specific scenarios, leaving the challenge of universal feature coding across diverse large models largely unaddressed. In this paper, we present the first systematic study on universal feature coding for large models. The key challenge lies in the inherently diverse and distributionally incompatible nature of features extracted from different models. For example, features from DINOv2 exhibit highly peaky, concentrated distributions, while those from Stable Diffusion 3 (SD3) are more dispersed and uniform. This distributional heterogeneity severely hampers both compression efficiency and cross-model generalization. To address this, we propose a learned peaky-to-balanced distribution transformation, which reshapes highly skewed feature distributions into a common, balanced target space. This transformation is non-uniform, data-driven, and plug-and-play, enabling effective alignment of heterogeneous distributions without modifying downstream codecs. With this alignment, a universal codec trained on the balanced target distribution can effectively generalize to features from different models and tasks. We validate our approach on three representative large models-LLaMA3, DINOv2, and SD3-across multiple tasks and modalities. Extensive experiments show that our method achieves notable improvements in both compression efficiency and cross-model generalization over task-specific baselines. All source code will be released for future research.
Authors: Ronald Skorobogat, Karsten Roth, Mariana-Iuliana Georgescu, Zeynep Akata
Abstract: Model merging enables the combination of multiple specialized expert models into a single model capable of performing multiple tasks. However, the benefits of merging an increasing amount of specialized experts generally lead to diminishing returns and reduced overall performance gains. In this work, we offer an explanation and analysis from a task arithmetic perspective; revealing that as the merging process (across numerous existing merging methods) continues for more and more experts, the associated task vector space experiences rank collapse. To mitigate this issue, we introduce Subspace Boosting, which operates on the singular value decomposed task vector space and maintains task vector ranks. Subspace Boosting raises merging efficacy for up to 20 expert models by large margins of more than 10% when evaluated on vision benchmarks. Moreover, we propose employing Higher-Order Generalized Singular Value Decomposition to further quantify task similarity, offering a new interpretable perspective on model merging.
Authors: Salvatore Esposito, Daniel Rebain, Arno Onken, Changjian Li, Oisin Mac Aodha
Abstract: Accurate segmentation of vascular networks from sparse CT scan slices remains a significant challenge in medical imaging, particularly due to the thin, branching nature of vessels and the inherent sparsity between imaging planes. Existing deep learning approaches, based on binary voxel classification, often struggle with structural continuity and geometric fidelity. To address this challenge, we present VesselSDF, a novel framework that leverages signed distance fields (SDFs) for robust vessel reconstruction. Our method reformulates vessel segmentation as a continuous SDF regression problem, where each point in the volume is represented by its signed distance to the nearest vessel surface. This continuous representation inherently captures the smooth, tubular geometry of blood vessels and their branching patterns. We obtain accurate vessel reconstructions while eliminating common SDF artifacts such as floating segments, thanks to our adaptive Gaussian regularizer which ensures smoothness in regions far from vessel surfaces while producing precise geometry near the surface boundaries. Our experimental results demonstrate that VesselSDF significantly outperforms existing methods and preserves vessel geometry and connectivity, enabling more reliable vascular analysis in clinical settings.
Authors: Yuxin Chen, Jianglan Wei, Chenfeng Xu, Boyi Li, Masayoshi Tomizuka, Andrea Bajcsy, Ran Tian
Abstract: World models enable robots to "imagine" future observations given current observations and planned actions, and have been increasingly adopted as generalized dynamics models to facilitate robot learning. Despite their promise, these models remain brittle when encountering novel visual distractors such as objects and background elements rarely seen during training. Specifically, novel distractors can corrupt action outcome predictions, causing downstream failures when robots rely on the world model imaginations for planning or action verification. In this work, we propose Reimagination with Observation Intervention (ReOI), a simple yet effective test-time strategy that enables world models to predict more reliable action outcomes in open-world scenarios where novel and unanticipated visual distractors are inevitable. Given the current robot observation, ReOI first detects visual distractors by identifying which elements of the scene degrade in physically implausible ways during world model prediction. Then, it modifies the current observation to remove these distractors and bring the observation closer to the training distribution. Finally, ReOI "reimagines" future outcomes with the modified observation and reintroduces the distractors post-hoc to preserve visual consistency for downstream planning and verification. We validate our approach on a suite of robotic manipulation tasks in the context of action verification, where the verifier needs to select desired action plans based on predictions from a world model. Our results show that ReOI is robust to both in-distribution and out-of-distribution visual distractors. Notably, it improves task success rates by up to 3x in the presence of novel distractors, significantly outperforming action verification that relies on world model predictions without imagination interventions.
Authors: Chanung Park, Joo Chan Lee, Jong Hwan Ko
Abstract: Although image compression is fundamental to visual data processing and has inspired numerous standard and learned codecs, these methods still suffer severe quality degradation at extremely low bits per pixel. While recent diffusion based models provided enhanced generative performance at low bitrates, they still yields limited perceptual quality and prohibitive decoding latency due to multiple denoising steps. In this paper, we propose the first single step diffusion model for image compression (DiffO) that delivers high perceptual quality and fast decoding at ultra low bitrates. DiffO achieves these goals by coupling two key innovations: (i) VQ Residual training, which factorizes a structural base code and a learned residual in latent space, capturing both global geometry and high frequency details; and (ii) rate adaptive noise modulation, which tunes denoising strength on the fly to match the desired bitrate. Extensive experiments show that DiffO surpasses state of the art compression performance while improving decoding speed by about 50x compared to prior diffusion-based methods, greatly improving the practicality of generative codecs. The code will be available at https://github.com/Freemasti/DiffO.
Authors: Muhammad Azeem Aslam, Asim Naveed, Nisar Ahmed
Abstract: Breast ultrasound imaging is a valuable tool for early breast cancer detection, but automated tumor segmentation is challenging due to inherent noise, variations in scale of lesions, and fuzzy boundaries. To address these challenges, we propose a novel hybrid attention-based network for lesion segmentation. Our proposed architecture integrates a pre-trained DenseNet121 in the encoder part for robust feature extraction with a multi-branch attention-enhanced decoder tailored for breast ultrasound images. The bottleneck incorporates Global Spatial Attention (GSA), Position Encoding (PE), and Scaled Dot-Product Attention (SDPA) to learn global context, spatial relationships, and relative positional features. The Spatial Feature Enhancement Block (SFEB) is embedded at skip connections to refine and enhance spatial features, enabling the network to focus more effectively on tumor regions. A hybrid loss function combining Binary Cross-Entropy (BCE) and Jaccard Index loss optimizes both pixel-level accuracy and region-level overlap metrics, enhancing robustness to class imbalance and irregular tumor shapes. Experiments on public datasets demonstrate that our method outperforms existing approaches, highlighting its potential to assist radiologists in early and accurate breast cancer diagnosis.
Authors: Anupma Choudhary, Sohith Bandari, B. S. Kushvah, C. Swastik
Abstract: The classification of exoplanets has been a longstanding challenge in astronomy, requiring significant computational and observational resources. Traditional methods demand substantial effort, time, and cost, highlighting the need for advanced machine learning techniques to enhance classification efficiency. In this study, we propose a methodology that transforms raw light curve data from NASA's Kepler mission into Gramian Angular Fields (GAFs) and Recurrence Plots (RPs) using the Gramian Angular Difference Field and recurrence plot techniques. These transformed images serve as inputs to the Vision Transformer (ViT) model, leveraging its ability to capture intricate temporal dependencies. We assess the performance of the model through recall, precision, and F1 score metrics, using a 5-fold cross-validation approach to obtain a robust estimate of the model's performance and reduce evaluation bias. Our comparative analysis reveals that RPs outperform GAFs, with the ViT model achieving an 89.46$\%$ recall and an 85.09$\%$ precision rate, demonstrating its significant capability in accurately identifying exoplanetary transits. Despite using under-sampling techniques to address class imbalance, dataset size reduction remains a limitation. This study underscores the importance of further research into optimizing model architectures to enhance automation, performance, and generalization of the model.
Authors: Haotian Yin, Aleksander Plocharski, Michal Jan Wlodarczyk, Mikolaj Kida, Przemyslaw Musialski
Abstract: Neural signed-distance fields (SDFs) have become a versatile backbone for geometric learning, yet enforcing developable, CAD-style behavior still hinges on Gaussian curvature penalties that require full Hessian evaluation and second-order automatic differentiation, both of which are costly in memory and runtime. We present a curvature proxy that regularizes only the mixed second-order term (Weingarten term), allowing the two principal curvatures to adapt freely to data while suppressing unwanted warp. Two complementary instantiations realize this idea: (i) a finite-difference proxy that replaces each Hessian entry with four forward SDF evaluations and a single first-order gradient, and (ii) an autodiff proxy that computes the same mixed derivative via one Hessian-vector product, sidestepping explicit full Hessian assembly and remaining faster in practice. Both variants converge to the exact mixed second derivative, thus preserving the intended geometric bias without incurring full second-order graphs. On the ABC benchmarks, the proxies match or exceed the reconstruction fidelity of Hessian-based baselines while reducing GPU memory use and wall-clock time by a factor of two. Because the method is drop-in and framework-agnostic, it opens a practical path toward scalable, curvature-aware SDF learning for engineering-grade shape reconstruction.
Authors: Saghir Alfasly, Ghazal Alabtah, H. R. Tizhoosh
Abstract: This study investigates the critical problem of overfitting in deep learning models applied to histopathology image analysis. We show that simply adopting and fine-tuning large-scale models designed for natural image analysis often leads to suboptimal performance and significant overfitting when applied to histopathology tasks. Through extensive experiments with various model architectures, including ResNet variants and Vision Transformers (ViT), we show that increasing model capacity does not necessarily improve performance on histopathology datasets. Our findings emphasize the need for customized architectures specifically designed for histopathology image analysis, particularly when working with limited datasets. Using Oesophageal Adenocarcinomas public dataset, we demonstrate that simpler, domain-specific architectures can achieve comparable or better performance while minimizing overfitting.
Authors: Guang Yin, Yitong Li, Yixuan Wang, Dale McConachie, Paarth Shah, Kunimatsu Hashimoto, Huan Zhang, Katherine Liu, Yunzhu Li
Abstract: Natural language instructions for robotic manipulation tasks often exhibit ambiguity and vagueness. For instance, the instruction "Hang a mug on the mug tree" may involve multiple valid actions if there are several mugs and branches to choose from. Existing language-conditioned policies typically rely on end-to-end models that jointly handle high-level semantic understanding and low-level action generation, which can result in suboptimal performance due to their lack of modularity and interpretability. To address these challenges, we introduce a novel robotic manipulation framework that can accomplish tasks specified by potentially ambiguous natural language. This framework employs a Vision-Language Model (VLM) to interpret abstract concepts in natural language instructions and generates task-specific code - an interpretable and executable intermediate representation. The generated code interfaces with the perception module to produce 3D attention maps that highlight task-relevant regions by integrating spatial and semantic information, effectively resolving ambiguities in instructions. Through extensive experiments, we identify key limitations of current imitation learning methods, such as poor adaptation to language and environmental variations. We show that our approach excels across challenging manipulation tasks involving language ambiguity, contact-rich manipulation, and multi-object interactions.
Authors: Fang Chen, Weifeng Zhang, Xingyu Ai, BingXuan Li, An Li, Qiegen Liu
Abstract: Positron emission tomography (PET) is widely used to assess metabolic activity, but its application is limited by the availability of radiotracers. 18F-labeled fluorodeoxyglucose (18F-FDG) is the most commonly used tracer but shows limited effectiveness for certain tumors. In contrast, 6-18F-fluoro-3,4-dihydroxy-L-phenylalanine (18F-DOPA) offers higher specificity for neuroendocrine tumors and neurological disorders. However, its complex synthesis and limitations in transportation and clinical use hinder widespread adoption. During PET imaging, the sinogram represents a form of raw data acquired by the scanner. Therefore, modeling in projection domain enables more direct utilization of the original information, potentially reducing the accumulation of errors introduced during the image reconstruction process. Inspired by these factors, this study proposes a prior-guided joint diffusion model (PJDM) for transforming 18F-FDG PET images into 18F-DOPA PET images in projection domain. Specifically, a coarse estimation model and a prior refinement model are trained independently. During inference, an initial synthetic 18F-DOPA PET sinogram is generated using a higher-order hybrid sampler. This sinogram is then degraded and serves as an additional condition to guide the iterative refinement process using learned prior. Experimental results demonstrated that PJDM effectively improved both sinogram quality and synthetic outcomes. The code is available at: https://github.com/yqx7150/PJDM.
Authors: Lei Jiang, Zixun Zhang, Zizhou Wang, Xiaobing Sun, Zhen Li, Liangli Zhen, Xiaohua Xu
Abstract: Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box jailbreak methods primarily rely on adversarial textual prompts or image perturbations, yet these approaches are highly detectable by standard content filtering systems and exhibit low query and computational efficiency. In this work, we present Cross-modal Adversarial Multimodal Obfuscation (CAMO), a novel black-box jailbreak attack framework that decomposes malicious prompts into semantically benign visual and textual fragments. By leveraging LVLMs' cross-modal reasoning abilities, CAMO covertly reconstructs harmful instructions through multi-step reasoning, evading conventional detection mechanisms. Our approach supports adjustable reasoning complexity and requires significantly fewer queries than prior attacks, enabling both stealth and efficiency. Comprehensive evaluations conducted on leading LVLMs validate CAMO's effectiveness, showcasing robust performance and strong cross-model transferability. These results underscore significant vulnerabilities in current built-in safety mechanisms, emphasizing an urgent need for advanced, alignment-aware security and safety solutions in vision-language systems.
Authors: Ning Chu, Siya Zheng, Shanqing Zhang, Li Li, Caifang Cai, Ali Mohammad-Djafari, Feng Zhao, Yuanbo Song
Abstract: Infrared thermography faces persistent challenges in temperature accuracy due to material emissivity variations, where existing methods often neglect the joint optimization of radiometric calibration and image degradation. This study introduces a physically guided neural framework that unifies temperature correction and image enhancement through a symmetric skip-CNN architecture and an emissivity-aware attention module. The pre-processing stage segments the ROIs of the image and and initially corrected the firing rate. A novel dual-constrained loss function strengthens the statistical consistency between the target and reference regions through mean-variance alignment and histogram matching based on Kullback-Leibler dispersion. The method works by dynamically fusing thermal radiation features and spatial context, and the model suppresses emissivity artifacts while recovering structural details. After validating the industrial blower system under different conditions, the improved network realizes the dynamic fusion of thermal radiation characteristics and spatial background, with accurate calibration results in various industrial conditions.
Authors: Grzegorz Gruszczynski, Michal Jan Wlodarczyk, Jakub J Meixner, Przemyslaw Musialski
Abstract: We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward pass formulates image corruption via a physically motivated PDE that couples directional advection with isotropic diffusion and Gaussian noise, controlled by dimensionless numbers (Peclet, Fourier). We implement this PDE numerically through a GPU-accelerated custom Lattice Boltzmann solver for fast evaluation. To induce realistic turbulence, we generate stochastic velocity fields that introduce coherent motion and capture multi-scale mixing. In the generative process, a neural network learns to reverse the advection-diffusion operator thus constituting a novel generative model. We discuss how previous methods emerge as specific cases of our operator, demonstrating that our framework generalizes prior PDE-based corruption techniques. We illustrate how advection improves the diversity and quality of the generated images while keeping the overall color palette unaffected. This work bridges fluid dynamics, dimensionless PDE theory, and deep generative modeling, offering a fresh perspective on physically informed image corruption processes for diffusion-based synthesis.
Authors: Sebastian H\"onel, Jonas Nordqvist
Abstract: The detection and localization of quality-related problems in industrially mass-produced products has historically relied on manual inspection, which is costly and error-prone. Machine learning has the potential to replace manual handling. As such, the desire is to facilitate an unsupervised (or self-supervised) approach, as it is often impossible to specify all conceivable defects ahead of time. A plethora of prior works have demonstrated the aptitude of common reconstruction-, embedding-, and synthesis-based methods in laboratory settings. However, in practice, we observe that most methods do not handle low data quality well or exude low robustness in unfavorable, but typical real-world settings. For practitioners it may be very difficult to identify the actual underlying problem when such methods underperform. Worse, often-reported metrics (e.g., AUROC) are rarely suitable in practice and may give misleading results. In our setting, we attempt to identify subtle anomalies on the surface of blasted forged metal parts, using rather low-quality RGB imagery only, which is a common industrial setting. We specifically evaluate two types of state-of-the-art models that allow us to identify and improve quality issues in production data, without having to obtain new data. Our contribution is to provide guardrails for practitioners that allow them to identify problems related to, e.g., (lack of) robustness or invariance, in either the chosen model or the data reliably in similar scenarios. Furthermore, we exemplify common pitfalls in and shortcomings of likelihood-based approaches and outline a framework for proper empirical risk estimation that is more suitable for real-world scenarios.
Authors: Ciro Beneduce, Massimiliano Luca, Bruno Lepri
Abstract: Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fr\'echet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon.
Authors: Bin Huang, Feihong Xu, Xinchong Shi, Shan Huang, Binxuan Li, Fei Li, Qiegen Liu
Abstract: In clinical practice, single-radiotracer positron emission tomography (PET) is commonly used for imaging. Although multi-tracer PET imaging can provide supplementary information of radiotracers that are sensitive to physiological function changes, enabling a more comprehensive characterization of physiological and pathological states, the gamma-photon pairs generated by positron annihilation reactions of different tracers in PET imaging have the same energy, making it difficult to distinguish the tracer signals. In this study, a multi-latent space guided texture conditional diffusion transformer model (MS-CDT) is proposed for PET tracer separation. To the best of our knowledge, this is the first attempt to use texture condition and multi-latent space for tracer separation in PET imaging. The proposed model integrates diffusion and transformer architectures into a unified optimization framework, with the novel addition of texture masks as conditional inputs to enhance image details. By leveraging multi-latent space prior derived from different tracers, the model captures multi-level feature representations, aiming to balance computational efficiency and detail preservation. The texture masks, serving as conditional guidance, help the model focus on salient structural patterns, thereby improving the extraction and utilization of fine-grained image textures. When combined with the diffusion transformer backbone, this conditioning mechanism contributes to more accurate and robust tracer separation. To evaluate its effectiveness, the proposed MS-CDT is compared with several advanced methods on two types of 3D PET datasets: brain and chest scans. Experimental results indicate that MS-CDT achieved competitive performance in terms of image quality and preservation of clinically relevant information. Code is available at: https://github.com/yqx7150/MS-CDT.
Authors: Teng Guo, Baichuan Huang, Jingjin Yu
Abstract: Accurate 6D object pose estimation is a prerequisite for successfully completing robotic prehensile and non-prehensile manipulation tasks. At present, 6D pose estimation for robotic manipulation generally relies on depth sensors based on, e.g., structured light, time-of-flight, and stereo-vision, which can be expensive, produce noisy output (as compared with RGB cameras), and fail to handle transparent objects. On the other hand, state-of-the-art monocular depth estimation models (MDEMs) provide only affine-invariant depths up to an unknown scale and shift. Metric MDEMs achieve some successful zero-shot results on public datasets, but fail to generalize. We propose a novel framework, Monocular One-shot Metric-depth Alignment (MOMA), to recover metric depth from a single RGB image, through a one-shot adaptation building on MDEM techniques. MOMA performs scale-rotation-shift alignments during camera calibration, guided by sparse ground-truth depth points, enabling accurate depth estimation without additional data collection or model retraining on the testing setup. MOMA supports fine-tuning the MDEM on transparent objects, demonstrating strong generalization capabilities. Real-world experiments on tabletop 2-finger grasping and suction-based bin-picking applications show MOMA achieves high success rates in diverse tasks, confirming its effectiveness.
Authors: Josu\'e Mart\'inez-Mart\'inez, Olivia Brown, Mostafa Karami, Sheida Nabavi
Abstract: Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.
Authors: David Jacob Drexlin, Jonas Dippel, Julius Hense, Niklas Preni{\ss}l, Gr\'egoire Montavon, Frederick Klauschen, Klaus-Robert M\"uller
Abstract: Deep learning models have made significant advances in histological prediction tasks in recent years. However, for adaptation in clinical practice, their lack of robustness to varying conditions such as staining, scanner, hospital, and demographics is still a limiting factor: if trained on overrepresented subpopulations, models regularly struggle with less frequent patterns, leading to shortcut learning and biased predictions. Large-scale foundation models have not fully eliminated this issue. Therefore, we propose a novel approach explicitly modeling such metadata into a Metadata-guided generative Diffusion model framework (MeDi). MeDi allows for a targeted augmentation of underrepresented subpopulations with synthetic data, which balances limited training data and mitigates biases in downstream models. We experimentally show that MeDi generates high-quality histopathology images for unseen subpopulations in TCGA, boosts the overall fidelity of the generated images, and enables improvements in performance for downstream classifiers on datasets with subpopulation shifts. Our work is a proof-of-concept towards better mitigating data biases with generative models.
Authors: Mahin Montasir Afif, Abdullah Al Noman, K. M. Tahsin Kabir, Md. Mortuza Ahmmed, Md. Mostafizur Rahman, Mufti Mahmud, Md. Ashraful Babu
Abstract: Generative Adversarial Networks (GAN) have shown potential in expanding limited medical imaging datasets. This study explores how different ratios of GAN-generated and real brain tumor MRI images impact the performance of a CNN in classifying healthy vs. tumorous scans. A DCGAN was used to create synthetic images which were mixed with real ones at various ratios to train a custom CNN. The CNN was then evaluated on a separate real-world test set. Our results indicate that the model maintains high sensitivity and precision in tumor classification, even when trained predominantly on synthetic data. When only a small portion of GAN data was added, such as 900 real images and 100 GAN images, the model achieved excellent performance, with test accuracy reaching 95.2%, and precision, recall, and F1-score all exceeding 95%. However, as the proportion of GAN images increased further, performance gradually declined. This study suggests that while GANs are useful for augmenting limited datasets especially when real data is scarce, too much synthetic data can introduce artifacts that affect the model's ability to generalize to real world cases.
Authors: Jianglong Ye, Keyi Wang, Chengjing Yuan, Ruihan Yang, Yiquan Li, Jiyue Zhu, Yuzhe Qin, Xueyan Zou, Xiaolong Wang
Abstract: Generating large-scale demonstrations for dexterous hand manipulation remains challenging, and several approaches have been proposed in recent years to address this. Among them, generative models have emerged as a promising paradigm, enabling the efficient creation of diverse and physically plausible demonstrations. In this paper, we introduce Dex1B, a large-scale, diverse, and high-quality demonstration dataset produced with generative models. The dataset contains one billion demonstrations for two fundamental tasks: grasping and articulation. To construct it, we propose a generative model that integrates geometric constraints to improve feasibility and applies additional conditions to enhance diversity. We validate the model on both established and newly introduced simulation benchmarks, where it significantly outperforms prior state-of-the-art methods. Furthermore, we demonstrate its effectiveness and robustness through real-world robot experiments. Our project page is at https://jianglongye.com/dex1b
Authors: Yukun Huang, Yanning Zhou, Jianan Wang, Kaiyi Huang, Xihui Liu
Abstract: 3D panorama synthesis is a promising yet challenging task that demands high-quality and diverse visual appearance and geometry of the generated omnidirectional content. Existing methods leverage rich image priors from pre-trained 2D foundation models to circumvent the scarcity of 3D panoramic data, but the incompatibility between 3D panoramas and 2D single views limits their effectiveness. In this work, we demonstrate that by applying multi-plane synchronization to the operators from 2D foundation models, their capabilities can be seamlessly extended to the omnidirectional domain. Based on this design, we further introduce DreamCube, a multi-plane RGB-D diffusion model for 3D panorama generation, which maximizes the reuse of 2D foundation model priors to achieve diverse appearances and accurate geometry while maintaining multi-view consistency. Extensive experiments demonstrate the effectiveness of our approach in panoramic image generation, panoramic depth estimation, and 3D scene generation.
Authors: Patrick Wenzel, Rui Wang, Nan Yang, Qing Cheng, Qadeer Khan, Lukas von Stumberg, Niclas Zeller, Daniel Cremers
Abstract: We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking. The data was collected in different scenarios and under a wide variety of weather conditions and illuminations, including day and night. This resulted in more than 350 km of recordings in nine different environments ranging from multi-level parking garage over urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up-to centimeter accuracy obtained from the fusion of direct stereo visual-inertial odometry with RTK-GNSS. The full dataset is available at https://go.vision.in.tum.de/4seasons.
Authors: Xiaowei Hu, Min Shi, Weiyun Wang, Sitong Wu, Linjie Xing, Wenhai Wang, Xizhou Zhu, Lewei Lu, Jie Zhou, Xiaogang Wang, Yu Qiao, Jifeng Dai
Abstract: Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these advancements are not solely attributable to novel feature transformation designs; certain benefits also arise from advanced network-level and block-level architectures. This paper aims to identify the real gains of popular convolution and attention operators through a detailed study. We find that the key difference among these feature transformation modules, such as attention or convolution, lies in their spatial feature aggregation approach, known as the "spatial token mixer" (STM). To facilitate an impartial comparison, we introduce a unified architecture to neutralize the impact of divergent network-level and block-level designs. Subsequently, various STMs are integrated into this unified framework for comprehensive comparative analysis. Our experiments on various tasks and an analysis of inductive bias show a significant performance boost due to advanced network-level and block-level designs, but performance differences persist among different STMs. Our detailed analysis also reveals various findings about different STMs, including effective receptive fields, invariance, and adversarial robustness tests.
Authors: Patrick Wenzel, Nan Yang, Rui Wang, Niclas Zeller, Daniel Cremers
Abstract: In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions. While significant progress has been made in advancing visual SLAM on small-scale datasets with similar conditions, there is still a lack of unified benchmarks representative of real-world scenarios for autonomous driving. We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance which is crucial to successfully enable autonomous driving in any condition. The data has been collected for more than one year, resulting in more than 300 km of recordings in nine different environments ranging from a multi-level parking garage to urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up to centimeter-level accuracy obtained from the fusion of direct stereo-inertial odometry with RTK GNSS. We evaluate the performance of several state-of-the-art visual odometry and visual localization baseline approaches on the benchmark and analyze their properties. The experimental results provide new insights into current approaches and show promising potential for future research. Our benchmark and evaluation protocols will be available at https://go.vision.in.tum.de/4seasons.
Authors: Shaobo Xia, Jun Yue, Kacper Kania, Leyuan Fang, Andrea Tagliasacchi, Kwang Moo Yi, Weiwei Sun
Abstract: We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations. The key challenge here is the discrepancy between the target of dense per-point semantic prediction and training losses derived from only scene-level labels. To address this, in addition to the typical weakly-supervised setup that supervises all points with the scene label, we propose to conservatively propagate the scene-level labels to points selectively. Specifically, we over-segment point cloud features via unsupervised clustering in the entire dataset and form primitives. We then associate scene-level labels with primitives through bipartite matching. Then, we allow labels to pass through this primitive-label relationship, while further encouraging features to form narrow clusters around the primitives. Importantly, through bipartite matching, this additional pathway through which labels flow, only propagates scene labels to the most relevant points, reducing the potential negative impact caused by the global approach that existing methods take. We evaluate our method on ScanNet and S3DIS datasets, outperforming the state of the art by a large margin.
Authors: Soikat Hasan Ahmed, Jan Finkbeiner, Emre Neftci
Abstract: Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for robust object detection. While Spiking Neural Networks (SNNs) on neuromorphic hardware are often considered for energy-efficient and low latency event-based data processing, they often fall short of Artificial Neural Networks (ANNs) in accuracy and flexibility. Here, we introduce Attention-based Hybrid SNN-ANN backbones for event-based object detection to leverage the strengths of both SNN and ANN architectures. A novel Attention-based SNN-ANN bridge module captures sparse spatial and temporal relations from the SNN layer and converts them into dense feature maps for the ANN part of the backbone. Additionally, we present a variant that integrates DWConvL-STMs to the ANN blocks to capture slower dynamics. This multi-timescale network combines fast SNN processing for short timesteps with long-term dense RNN processing, effectively capturing both fast and slow dynamics. Experimental results demonstrate that our proposed method surpasses SNN-based approaches by significant margins, with results comparable to existing ANN and RNN-based methods. Unlike ANN-only networks, the hybrid setup allows us to implement the SNN blocks on digital neuromorphic hardware to investigate the feasibility of our approach. Extensive ablation studies and implementation on neuromorphic hardware confirm the effectiveness of our proposed modules and architectural choices. Our hybrid SNN-ANN architectures pave the way for ANN-like performance at a drastically reduced parameter, latency, and power budget.
Authors: Yinzhe Xu, Huajian Huang, Yingshu Chen, Sai-Kit Yeung
Abstract: Visual object tracking and segmentation in omnidirectional videos are challenging due to the wide field-of-view and large spherical distortion brought by 360{\deg} images. To alleviate these problems, we introduce a novel representation, extended bounding field-of-view (eBFoV), for target localization and use it as the foundation of a general 360 tracking framework which is applicable for both omnidirectional visual object tracking and segmentation tasks. Building upon our previous work on omnidirectional visual object tracking (360VOT), we propose a comprehensive dataset and benchmark that incorporates a new component called omnidirectional video object segmentation (360VOS). The 360VOS dataset includes 290 sequences accompanied by dense pixel-wise masks and covers a broader range of target categories. To support both the development and evaluation of algorithms in this domain, we divide the dataset into a training subset with 170 sequences and a testing subset with 120 sequences. Furthermore, we tailor evaluation metrics for both omnidirectional tracking and segmentation to ensure rigorous assessment. Through extensive experiments, we benchmark state-of-the-art approaches and demonstrate the effectiveness of our proposed 360 tracking framework and training dataset. Homepage: https://360vots.hkustvgd.com/
Authors: Guanhua Zhao, Yu Gu, Xuhan Sheng, Yujie Hu, Jian Zhang
Abstract: With the popularity of social media platforms and retouching tools, more people are beautifying their facial photos, posing challenges for fields requiring photo authenticity. To address this issue, some work has proposed makeup removal methods, but they cannot revert images involving geometric deformations caused by retouching. To tackle the problem of facial retouching reversion, we propose a framework, dubbed Re-Face, which consists of three components: a facial retouching detector, an image reversion model named FaceR, and a color correction module called Hierarchical Adaptive Instance Normalization (H-AdaIN). FaceR can utilize labels generated by the facial retouching detector as guidance to revert the retouched facial images. Then, color correction is performed using H-AdaIN to address the issue of color shift. Extensive experiments demonstrate the effectiveness of our framework and each module.
Authors: Jun Huang, Yan Liu
Abstract: This paper proposes a new gradient-based XAI method called Guided AbsoluteGrad for saliency map explanations. We utilize both positive and negative gradient magnitudes and employ gradient variance to distinguish the important areas for noise deduction. We also introduce a novel evaluation metric named ReCover And Predict (RCAP), which considers the Localization and Visual Noise Level objectives of the explanations. We propose two propositions for these two objectives and prove the necessity of evaluating them. We evaluate Guided AbsoluteGrad with seven gradient-based XAI methods using the RCAP metric and other SOTA metrics in three case studies: (1) ImageNet dataset with ResNet50 model; (2) International Skin Imaging Collaboration (ISIC) dataset with EfficientNet model; (3) the Places365 dataset with DenseNet161 model. Our method surpasses other gradient-based approaches, showcasing the quality of enhanced saliency map explanations through gradient magnitude.
Authors: Thomas Manzini, Priyankari Perali, Raisa Karnik, Mihir Godbole, Hasnat Abdullah, Robin Murphy
Abstract: This work presents the first quantitative study of alignment errors between small uncrewed aerial systems (sUAS) georectified imagery and a priori building polygons and finds that alignment errors are non-uniform and irregular, which negatively impacts field robotics systems and human-robot interfaces that rely on geospatial information. There are no efforts that have considered the alignment of a priori spatial data with georectified sUAS imagery, possibly because straight-forward linear transformations often remedy any misalignment in satellite imagery. However, an attempt to develop machine learning models for an sUAS field robotics system for disaster response from nine wide-area disasters using the CRASAR-U-DROIDs dataset uncovered serious translational alignment errors. The analysis considered 21,608 building polygons in 51 orthomosaic images, covering 16787.2 Acres (26.23 square miles), and 7,880 adjustment annotations, averaging 75.36 pixels and an average intersection over union of 0.65. Further analysis found no uniformity among the angle and distance metrics of the building polygon alignments, presenting an average circular variance of 0.28 and an average distance variance of 0.45 pixels2, making it impossible to use the linear transform used to align satellite imagery. The study's primary contribution is alerting field robotics and human-robot interaction (HRI) communities to the problem of spatial alignment and that a new method will be needed to automate and communicate the alignment of spatial data in sUAS georectified imagery. This paper also contributes a description of the updated CRASAR-U-DROIDs dataset of sUAS imagery, which contains building polygons and human-curated corrections to spatial misalignment for further research in field robotics and HRI.
Authors: Kailas Dayanandan, Nikhil Kumar, Anand Sinha, Brejesh Lall
Abstract: The dual thinking framework considers fast, intuitive, and slower logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ, and the latter is under-explored in current studies. We introduce a novel adversarial dataset to provide evidence for the dual thinking framework in human vision, which also facilitates the study of the qualitative behavior of deep learning models. Our psychophysical studies show the presence of multiple inferences in rapid succession, and analysis of errors shows that the early stopping of visual processing can result in missing relevant information. MLLMs (Multi-modal Large Language Models) and VLMs (Vision Language Models) have made significant progress in correcting errors in intuitive processing in human vision and showed enhanced performance on images requiring logical processing. However, their improvements in logical processing have not kept pace with their advancements in intuitive processing. In contrast, segmentation models exhibit errors similar to those seen in intuitive human processing and lack understanding of sub-structures, as indicated by errors related to sub-components in identified instances. As AI (Artificial Intelligence)-based systems find increasing applications in safety-critical domains like autonomous driving, the integration of logical processing capabilities becomes essential. This not only enhances performance but also addresses the limitations of scaling-based approaches while ensuring robustness and reliability in real-world environments.
Authors: Sheng Miao, Jiaxin Huang, Dongfeng Bai, Weichao Qiu, Bingbing Liu, Andreas Geiger, Yiyi Liao
Abstract: Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images and extensive computation resources. To mitigate this shortcoming, we introduce a new method called Efficient Depth-Guided Urban View Synthesis (EDUS) for fast feed-forward inference and efficient per-scene fine-tuning. Different from prior generalizable methods that infer geometry based on feature matching, EDUS leverages noisy predicted geometric priors as guidance to enable generalizable urban view synthesis from sparse input images. The geometric priors allow us to apply our generalizable model directly in the 3D space, gaining robustness across various sparsity levels. Through comprehensive experiments on the KITTI-360 and Waymo datasets, we demonstrate promising generalization abilities on novel street scenes. Moreover, our results indicate that EDUS achieves state-of-the-art performance in sparse view settings when combined with fast test-time optimization.
Authors: Lianwei Yang, Haisong Gong, Haokun Lin, Yichen Wu, Zhenan Sun, Qingyi Gu
Abstract: Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training quantization (PTQ) reduces model size and speeds up inference, it often degrades performance, especially in low-bit settings. We identify two key reasons for the performance degradation: 1) existing quantization methods fail to align with the power-law distribution of post-Softmax activations, and 2) reparameterizing post-LayerNorm activations leads to a performance drop due to the significant influence of outliers in the scaling factors. To address these challenges, we propose DopQ-ViT, a Distribution-friendly and Outlier-aware Post-training Quantization method for ViTs. First, DopQ-ViT introduces the Tan Quantizer (TanQ), which better preserves the power-law distribution of post-Softmax activations by focusing more on values near 1. Second, DopQ-ViT presents the MAD-guided Optimal Scaling Factor (MOSF), which selects the optimal scaling factor without introducing additional calculations. Extensive experiments across various ViT models and quantization settings demonstrate that DopQ-ViT, with the help of TanQ and MOSF, outperforms previous PTQ methods on both classification and detection tasks.
Authors: Le Xue, Manli Shu, Anas Awadalla, Jun Wang, An Yan, Senthil Purushwalkam, Honglu Zhou, Viraj Prabhu, Yutong Dai, Michael S Ryoo, Shrikant Kendre, Jieyu Zhang, Shaoyen Tseng, Gustavo A Lujan-Moreno, Matthew L Olson, Musashi Hinck, David Cobbley, Vasudev Lal, Can Qin, Shu Zhang, Chia-Chih Chen, Ning Yu, Juntao Tan, Tulika Manoj Awalgaonkar, Shelby Heinecke, Huan Wang, Yejin Choi, Ludwig Schmidt, Zeyuan Chen, Silvio Savarese, Juan Carlos Niebles, Caiming Xiong, Ran Xu
Abstract: This paper introduces BLIP-3, an open framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. We release 4B and 14B models, including both the pre-trained base model and the instruction fine-tuned ones. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our models demonstrate competitive performance among open-source LMMs with similar model sizes. Our resulting LMMs demonstrate competitive performance among open-source LMMs with similar model sizes, with the ability to comprehend interleaved image-text inputs. Our training code, models, and all datasets used in this work, including the three largescale datasets we create and the preprocessed ones, will be open-sourced to better support the research community.
Authors: Ting Liu, Zunnan Xu, Yue Hu, Liangtao Shi, Zhiqiang Wang, Quanjun Yin
Abstract: Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer visual/linguistic knowledge by full fine-tuning. However, full fine-tuning the entire backbone not only breaks the rich prior knowledge embedded in the pre-training, but also incurs significant computational costs. Motivated by the recent emergence of Parameter-Efficient Transfer Learning (PETL) methods, we aim to solve the REC task in an effective and efficient manner. Directly applying these PETL methods to the REC task is inappropriate, as they lack the specific-domain abilities for precise local visual perception and visual-language alignment. Therefore, we propose a novel framework of Multimodal Prior-guided Parameter Efficient Tuning, namely MaPPER. Specifically, MaPPER comprises Dynamic Prior Adapters guided by an aligned prior, and Local Convolution Adapters to extract precise local semantics for better visual perception. Moreover, the Prior-Guided Text module is proposed to further utilize the prior for facilitating the cross-modal alignment. Experimental results on three widely-used benchmarks demonstrate that MaPPER achieves the best accuracy compared to the full fine-tuning and other PETL methods with only 1.41% tunable backbone parameters. Our code is available at https://github.com/liuting20/MaPPER.
Authors: Suorong Yang, Peng Ye, Wanli Ouyang, Dongzhan Zhou, Furao Shen
Abstract: Large-scale datasets have been pivotal to the advancements of deep learning models in recent years, but training on such large datasets invariably incurs substantial storage and computational overhead. Meanwhile, real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance. Data selection has shown promise in identifying the most representative samples from the entire dataset, which aims to minimize the performance gap with reduced training costs. Existing works typically rely on single-modality information to assign importance scores for individual samples, which may lead to inaccurate assessments, especially when dealing with noisy or corrupted samples. To address this limitation, we propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection. Specifically, our framework consists of three key modules-dataset adaptation, sample scoring, and selection optimization-that together harness extensive pre-trained multimodal knowledge to comprehensively assess sample influence and optimize the selection results through multi-objective optimization. Extensive experiments demonstrate that our approach consistently outperforms existing state-of-the-art baselines on various benchmark datasets. Notably, our method effectively removes noisy or damaged samples from the dataset, enabling it to achieve even higher performance with less data. This indicates that it is not only a way to accelerate training but can also improve overall data quality.
Authors: Jiyao Wang, Xiao Yang, Zhenyu Wang, Ximeng Wei, Ange Wang, Dengbo He, Kaishun Wu
Abstract: Road safety remains a critical challenge worldwide, with approximately 1.35 million fatalities annually attributed to traffic accidents, often due to human errors. As we advance towards higher levels of vehicle automation, challenges still exist, as driving with automation can cognitively over-demand drivers if they engage in non-driving-related tasks (NDRTs), or lead to drowsiness if driving was the sole task. This calls for the urgent need for an effective Driver Monitoring System (DMS) that can evaluate cognitive load and drowsiness in SAE Level-2/3 autonomous driving contexts. In this study, we propose a novel multi-task DMS, termed VDMoE, which leverages RGB video input to monitor driver states non-invasively. By utilizing key facial features to minimize computational load and integrating remote Photoplethysmography (rPPG) for physiological insights, our approach enhances detection accuracy while maintaining efficiency. Additionally, we optimize the Mixture-of-Experts (MoE) framework to accommodate multi-modal inputs and improve performance across different tasks. A novel prior-inclusive regularization method is introduced to align model outputs with statistical priors, thus accelerating convergence and mitigating overfitting risks. We validate our method with the creation of a new dataset (MCDD), which comprises RGB video and physiological indicators from 42 participants, and two public datasets. Our findings demonstrate the effectiveness of VDMoE in monitoring driver states, contributing to safer autonomous driving systems. The code and data will be released.
Authors: Xiufeng Song, Xiao Guo, Jiache Zhang, Qirui Li, Lei Bai, Xiaoming Liu, Guangtao Zhai, Xiaohong Liu
Abstract: Large numbers of synthesized videos from diffusion models pose threats to information security and authenticity, leading to an increasing demand for generated content detection. However, existing video-level detection algorithms primarily focus on detecting facial forgeries and often fail to identify diffusion-generated content with a diverse range of semantics. To advance the field of video forensics, we propose an innovative algorithm named Multi-Modal Detection(MM-Det) for detecting diffusion-generated videos. MM-Det utilizes the profound perceptual and comprehensive abilities of Large Multi-modal Models (LMMs) by generating a Multi-Modal Forgery Representation (MMFR) from LMM's multi-modal space, enhancing its ability to detect unseen forgery content. Besides, MM-Det leverages an In-and-Across Frame Attention (IAFA) mechanism for feature augmentation in the spatio-temporal domain. A dynamic fusion strategy helps refine forgery representations for the fusion. Moreover, we construct a comprehensive diffusion video dataset, called Diffusion Video Forensics (DVF), across a wide range of forgery videos. MM-Det achieves state-of-the-art performance in DVF, demonstrating the effectiveness of our algorithm. Both source code and DVF are available at https://github.com/SparkleXFantasy/MM-Det.
Authors: Yingying Fang, Zihao Jin, Shaojie Guo, Jinda Liu, Zhiling Yue, Yijian Gao, Junzhi Ning, Zhi Li, Simon Walsh, Guang Yang
Abstract: Despite significant advancements in automated report generation, the opaqueness of text interpretability continues to cast doubt on the reliability of the content produced. This paper introduces a novel approach to identify specific image features in X-ray images that influence the outputs of report generation models. Specifically, we propose Cyclic Vision-Language Manipulator CVLM, a module to generate a manipulated X-ray from an original X-ray and its report from a designated report generator. The essence of CVLM is that cycling manipulated X-rays to the report generator produces altered reports aligned with the alterations pre-injected into the reports for X-ray generation, achieving the term "cyclic manipulation". This process allows direct comparison between original and manipulated X-rays, clarifying the critical image features driving changes in reports and enabling model users to assess the reliability of the generated texts. Empirical evaluations demonstrate that CVLM can identify more precise and reliable features compared to existing explanation methods, significantly enhancing the transparency and applicability of AI-generated reports.
Authors: Leonidas Gee, Wing Yan Li, Viktoriia Sharmanska, Novi Quadrianto
Abstract: The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to runtime, making them ill-suited for online (real-time) inference, where a prediction is made on any new input as it comes in. We introduce the $\textbf{Visual Word Tokenizer}$ (VWT), a training-free method for reducing energy costs while retaining performance and runtime. The VWT groups visual subwords (image patches) that are frequently used into visual words while infrequent ones remain intact. To do so, $\textit{intra}$-image or $\textit{inter}$-image statistics are leveraged to identify similar visual concepts for sequence compression. Experimentally, we demonstrate a reduction in wattage of up to 25% with only a 20% increase in runtime at most. Comparative approaches of 8-bit quantization and token merging achieve a lower or similar energy efficiency but exact a higher toll on runtime (up to 100% or more). Our results indicate that VWTs are well-suited for efficient online inference with a marginal compromise on performance.
Authors: Shrisha Bharadwaj, Haiwen Feng, Giorgio Becherini, Victoria Fernandez Abrevaya, Michael J. Black
Abstract: Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics. This problem has traditionally been addressed using inverse rendering techniques, which involve explicit 3D asset reconstruction and costly ray-tracing simulations. Meanwhile, recent advancements in visual foundation models suggest that a new paradigm could soon be possible -- one that replaces explicit physical models with networks that are trained on large amounts of image and video data. In this paper, we exploit the physical world understanding of a video diffusion model, particularly Stable Video Diffusion, to relight a single image. We introduce GenLit, a framework that distills the ability of a graphics engine to perform light manipulation into a video-generation model, enabling users to directly insert and manipulate a point light in the 3D world within a given image, and generate results directly as a video sequence. We find that a model fine-tuned on only a small synthetic dataset generalizes to real-world scenes, enabling single-image relighting with plausible and convincing shadows. Our results highlight the ability of video foundation models to capture rich information about lighting, material, and, shape and our findings indicate that such models, with minimal training, can be used to perform relighting without explicit asset reconstruction or complex ray tracing. Project page: https://genlit.is.tue.mpg.de/.
Authors: Guoxing Sun, Rishabh Dabral, Heming Zhu, Pascal Fua, Christian Theobalt, Marc Habermann
Abstract: Real-time free-view human rendering from sparse-view RGB inputs is a challenging task due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods leverage 2D CNNs operating in texture space to learn rendering primitives. However, they either jointly learn geometry and appearance, or completely ignore sparse image information for geometry estimation, significantly harming visual quality and robustness to unseen body poses. To address these issues, we present Double Unprojected Textures, which at the core disentangles coarse geometric deformation estimation from appearance synthesis, enabling robust and photorealistic 4K rendering in real-time. Specifically, we first introduce a novel image-conditioned template deformation network, which estimates the coarse deformation of the human template from a first unprojected texture. This updated geometry is then used to apply a second and more accurate texture unprojection. The resulting texture map has fewer artifacts and better alignment with input views, which benefits our learning of finer-level geometry and appearance represented by Gaussian splats. We validate the effectiveness and efficiency of the proposed method in quantitative and qualitative experiments, which significantly surpasses other state-of-the-art methods. Project page: https://vcai.mpi-inf.mpg.de/projects/DUT/
Authors: Yiming Zhang, Zicheng Zhang, Xinyi Wei, Xiaohong Liu, Guangtao Zhai, Xiongkuo Min
Abstract: Current Visual Language Models (VLMs) show impressive image understanding but struggle with visual illusions, especially in real-world scenarios. Existing benchmarks focus on classical cognitive illusions, which have been learned by state-of-the-art (SOTA) VLMs, revealing issues such as hallucinations and limited perceptual abilities. To address this gap, we introduce IllusionBench, a comprehensive visual illusion dataset that encompasses not only classic cognitive illusions but also real-world scene illusions. This dataset features 1,051 images, 5,548 question-answer pairs, and 1,051 golden text descriptions that address the presence, causes, and content of the illusions. We evaluate ten SOTA VLMs on this dataset using true-or-false, multiple-choice, and open-ended tasks. In addition to real-world illusions, we design trap illusions that resemble classical patterns but differ in reality, highlighting hallucination issues in SOTA models. The top-performing model, GPT-4o, achieves 80.59% accuracy on true-or-false tasks and 76.75% on multiple-choice questions, but still lags behind human performance. In the semantic description task, GPT-4o's hallucinations on classical illusions result in low scores for trap illusions, even falling behind some open-source models. IllusionBench is, to the best of our knowledge, the largest and most comprehensive benchmark for visual illusions in VLMs to date.
Authors: Jiaxin Ge, Zora Zhiruo Wang, Xuhui Zhou, Yi-Hao Peng, Sanjay Subramanian, Qinyue Tan, Maarten Sap, Alane Suhr, Daniel Fried, Graham Neubig, Trevor Darrell
Abstract: Designing structured visuals such as presentation slides is essential for communicative needs, necessitating both content creation and visual planning skills. In this work, we tackle the challenge of automated slide generation, where models produce slide presentations from natural language (NL) instructions. We first introduce the SlidesBench benchmark, the first benchmark for slide generation with 7k training and 585 testing examples derived from 310 slide decks across 10 domains. SlidesBench supports evaluations that are (i)reference-based to measure similarity to a target slide, and (ii)reference-free to measure the design quality of generated slides alone. We benchmark end-to-end image generation and program generation methods with a variety of models, and find that programmatic methods produce higher-quality slides in user-interactable formats. Built on the success of program generation, we create AutoPresent, an 8B Llama-based model trained on 7k pairs of instructions paired with code for slide generation, and achieve results comparable to the closed-source model GPT-4o. We further explore iterative design refinement where the model is tasked to self-refine its own output, and we found that this process improves the slide's quality. We hope that our work will provide a basis for future work on generating structured visuals.
Authors: Tongxu Zhang, Bei Wang
Abstract: In recent years, point cloud upsampling has been widely applied in tasks such as 3D reconstruction and object recognition. This study proposed a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both global and local structural features of point clouds. Specifically, we extracted global features from uniformly segmented inputs (Average Segments) and local features from patch-based inputs of the same point cloud. These two types of features were processed through parallel autoencoders, fused, and then fed into a shared decoder for upsampling. This dual-input design improved feature completeness and cross-scale consistency, especially in sparse and noisy regions. Our framework was applied to several state-of-the-art autoencoder-based networks and validated on standard datasets. Experimental results demonstrated consistent improvements in geometric fidelity and robustness. In addition, saliency maps confirmed that parallel global-local learning significantly enhanced the interpretability and performance of point cloud upsampling.
Authors: Benoit Brummer, Christophe De Vleeschouwer
Abstract: This paper introduces the Raw Natural Image Noise Dataset (RawNIND), a diverse collection of paired raw images designed to support the development of denoising models that generalize across sensors, image development workflows, and styles. Two denoising methods are proposed: one operates directly on raw Bayer data, leveraging computational efficiency, while the other processes linear RGB images for improved generalization to different sensors, with both preserving flexibility for subsequent development. Both methods outperform traditional approaches which rely on developed images. Additionally, the integration of denoising and compression at the raw data level significantly enhances rate-distortion performance and computational efficiency. These findings suggest a paradigm shift toward raw data workflows for efficient and flexible image processing.
Authors: Jan Skvrna, Lukas Neumann
Abstract: Inferring object 3D position and orientation from a single RGB camera is a foundational task in computer vision with many important applications. Traditionally, 3D object detection methods are trained in a fully-supervised setup, requiring LiDAR and vast amounts of human annotations, which are laborious, costly, and do not scale well with the ever-increasing amounts of data being captured. We present a novel method to train a 3D object detector from a single RGB camera without domain-specific human annotations, making orders of magnitude more data available for training. The method uses newly proposed Local Object Motion Model to disentangle object movement source between subsequent frames, is approximately 700 times faster than previous work and compensates camera focal length differences to aggregate multiple datasets. The method is evaluated on three public datasets, where despite using no human labels, it outperforms prior work by a significant margin. It also shows its versatility as a pre-training tool for fully-supervised training and shows that combining pseudo-labels from multiple datasets can achieve comparable accuracy to using human labels from a single dataset. The source code and model are available at https://github.com/jskvrna/MonoSOWA.
Authors: Kavitha Viswanathan, Shashwat Pathak, Piyush Bharambe, Harsh Choudhary, Amit Sethi
Abstract: The tradeoff between reconstruction quality and compute required for video super-resolution (VSR) remains a formidable challenge in its adoption for deployment on resource-constrained edge devices. While transformer-based VSR models have set new benchmarks for reconstruction quality in recent years, these require substantial computational resources. On the other hand, lightweight models that have been introduced even recently struggle to deliver state-of-the-art reconstruction. We propose a novel lightweight and parameter-efficient neural architecture for VSR that achieves state-of-the-art reconstruction accuracy with just 2.3 million parameters. Our model enhances information utilization based on several architectural attributes. Firstly, it uses 2D wavelet decompositions strategically interlayered with learnable convolutional layers to utilize the inductive prior of spatial sparsity of edges in visual data. Secondly, it uses a single memory tensor to capture inter-frame temporal information while avoiding the computational cost of previous memory-based schemes. Thirdly, it uses residual deformable convolutions for implicit inter-frame object alignment that improve upon deformable convolutions by enhancing spatial information in inter-frame feature differences. Architectural insights from our model can pave the way for real-time VSR on the edge, such as display devices for streaming data.
Authors: R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie
Abstract: We present ShapeLib, the first method that leverages the priors of LLMs to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of design intent: text descriptions of functions to include in the library and a seed set of exemplar shapes. We discover abstractions that match this design intent with a guided LLM workflow that first proposes, and then validates, different ways of applying and implementing functions. We learn recognition networks that map shapes to programs with these newly discovered abstractions by training on data produced by LLM authored synthetic data generation procedures. Across modeling domains (split by shape category), we find that LLMs, when thoughtfully combined with geometric reasoning, can be guided to author a library of abstraction functions that generalize to shapes outside of the seed set. This framework addresses a long-standing shape analysis problem of how to discover reusable abstraction functions while exposing interpretable, semantically aligned interfaces. We find that ShapeLib provides distinct advantages over prior alternative abstraction discovery works in terms of generalization, usability, and maintaining plausibility under manipulation. Finally, we demonstrate that ShapeLib's abstraction functions unlock a number of downstream applications, combining LLM reasoning over shape programs with geometry processing to support shape editing and generation.
Authors: Huaying Yuan, Zheng Liu, Minghao Qin, Hongjin Qian, Yan Shu, Zhicheng Dou, Ji-Rong Wen, Nicu Sebe
Abstract: Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to compression and brute-force downsampling. While retrieval-augmented generation (RAG) methods mitigate this issue, their applicability is limited due to explicit query dependency. To overcome this challenge, we introduce a novel memory-enhanced RAG-based approach called MemVid, which is inspired by the cognitive memory of human beings. Our approach operates in four basic steps: 1) memorizing holistic video information, 2) reasoning about the task's information needs based on memory, 3) retrieving critical moments based on the information needs, and 4) focusing on the retrieved moments to produce the final answer. To enhance the system's memory-grounded reasoning capabilities while achieving optimal end-to-end performance, we propose a curriculum learning strategy. This approach begins with supervised learning on well-annotated reasoning results, then progressively explores and reinforces more plausible reasoning outcomes through reinforcement learning. We perform extensive evaluations on popular LVU benchmarks, including MLVU, VideoMME and LVBench. In our experiments, MemVid demonstrates superior efficiency and effectiveness compared to both LVLMs and RAG methods.
Authors: Qi Mao, Haobo Hu, Yujie He, Difei Gao, Haokun Chen, Libiao Jin
Abstract: Affective Image Manipulation (AIM) aims to alter visual elements within an image to evoke specific emotional responses from viewers. However, existing AIM approaches rely on rigid \emph{one-to-one} mappings between emotions and visual cues, making them ill-suited for the inherently subjective and diverse ways in which humans perceive and express emotion.To address this, we introduce a novel task setting termed \emph{Diverse AIM (D-AIM)}, aiming to generate multiple visually distinct yet emotionally consistent image edits from a single source image and target emotion. We propose \emph{EmoAgent}, the first multi-agent framework tailored specifically for D-AIM. EmoAgent explicitly decomposes the manipulation process into three specialized phases executed by collaborative agents: a Planning Agent that generates diverse emotional editing strategies, an Editing Agent that precisely executes these strategies, and a Critic Agent that iteratively refines the results to ensure emotional accuracy. This collaborative design empowers EmoAgent to model \emph{one-to-many} emotion-to-visual mappings, enabling semantically diverse and emotionally faithful edits.Extensive quantitative and qualitative evaluations demonstrate that EmoAgent substantially outperforms state-of-the-art approaches in both emotional fidelity and semantic diversity, effectively generating multiple distinct visual edits that convey the same target emotion.
Authors: Xiaojin Lu, Taoran yue, Jiaxi cai, Yuanping Chen, Cuihong Lv, Shibing Chu
Abstract: In complex environments, detecting tiny infrared targets has always been challenging because of the low contrast and high noise levels inherent in infrared images. These factors often lead to the loss of crucial details during feature extraction. Moreover, existing detection methods have limitations in adequately integrating global and local information, which constrains the efficiency and accuracy of infrared small target detection. To address these challenges, this paper proposes a network architecture named MSCA-Net, which integrates three key components: Multi-Scale Enhanced Dilated Attention mechanism (MSEDA), Positional Convolutional Block Attention Module (PCBAM), and Channel Aggregation Feature Fusion Block (CAB). Specifically, MSEDA employs a multi-scale feature fusion attention mechanism to adaptively aggregate information across different scales, enriching feature representation. PCBAM captures the correlation between global and local features through a correlation matrix-based strategy, enabling deep feature interaction. Moreover, CAB enhances the representation of critical features by assigning greater weights to them, integrating both low-level and high-level information, and thereby improving the models detection performance in complex backgrounds. The experimental results demonstrate that MSCA-Net achieves strong small target detection performance in complex backgrounds. Specifically, it attains mIoU scores of 78.43%, 94.56%, and 67.08% on the NUAA-SIRST, NUDT-SIRST, and IRTSD-1K datasets, respectively, underscoring its effectiveness and strong potential for real-world applications.
Authors: Chengan Che, Chao Wang, Tom Vercauteren, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera
Abstract: Advancements in computer-assisted surgical procedures heavily rely on accurate visual data interpretation from camera systems used during surgeries. Traditional open-access datasets focusing on surgical procedures are often limited by their small size, typically consisting of fewer than 100 videos with less than 100K images. To address these constraints, a new dataset called Surg-3M has been compiled using a novel aggregation pipeline that collects high-resolution videos from online sources. Featuring an extensive collection of over 4K surgical videos totaling 938 hours of high-quality footage across multiple procedure types, Surg-3M offers a comprehensive resource surpassing existing alternatives in size and scope, including two novel tasks. To demonstrate the effectiveness of this dataset, we present SurgFM, a self-supervised foundation model pretrained on Surg-3M that achieves impressive results in downstream tasks such as surgical phase recognition, action recognition, and tool presence detection. Combining key components from ConvNeXt, DINO, and an innovative augmented distillation method, SurgFM exhibits exceptional performance compared to specialist architectures across various benchmarks. Our experimental results show that SurgFM outperforms state-of-the-art models in multiple downstream tasks, including significant gains in surgical phase recognition (+8.9pp, +4.7pp, and +3.9pp of Jaccard in AutoLaparo, M2CAI16, and Cholec80), action recognition (+3.1pp of mAP in CholecT50) and tool presence detection (+4.6pp of mAP in Cholec80). Moreover, even when using only half of the data, SurgFM outperforms state-of-the-art models in AutoLaparo and achieves state-of-the-art performance in Cholec80. Both Surg-3M and SurgFM have significant potential to accelerate progress towards developing autonomous robotic surgery systems.
Authors: Ben Lonnqvist, Elsa Scialom, Abdulkadir Gokce, Zehra Merchant, Michael H. Herzog, Martin Schrimpf
Abstract: Despite the tremendous success of deep learning in computer vision, models still fall behind humans in generalizing to new input distributions. Existing benchmarks do not investigate the specific failure points of models by analyzing performance under many controlled conditions. Our study systematically dissects where and why models struggle with contour integration -- a hallmark of human vision -- by designing an experiment that tests object recognition under various levels of object fragmentation. Humans (n=50) perform at high accuracy, even with few object contours present. This is in contrast to models which exhibit substantially lower sensitivity to increasing object contours, with most of the over 1,000 models we tested barely performing above chance. Only at very large scales ($\sim5B$ training dataset size) do models begin to approach human performance. Importantly, humans exhibit an integration bias -- a preference towards recognizing objects made up of directional fragments over directionless fragments. We find that not only do models that share this property perform better at our task, but that this bias also increases with model training dataset size, and training models to exhibit contour integration leads to high shape bias. Taken together, our results suggest that contour integration is a hallmark of object vision that underlies object recognition performance, and may be a mechanism learned from data at scale.
Authors: Junli Liu, Qizhi Chen, Zhigang Wang, Yiwen Tang, Yiting Zhang, Chi Yan, Dong Wang, Bin Zhao, Xuelong Li
Abstract: Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual grounding from aerial views. Compared to traditional VG, AerialVG poses new challenges, \emph{e.g.}, appearance-based grounding is insufficient to distinguish among multiple visually similar objects, and positional relations should be emphasized. Besides, existing VG models struggle when applied to aerial imagery, where high-resolution images cause significant difficulties. To address these challenges, we introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects. Particularly, each annotation in AerialVG dataset contains multiple target objects annotated with relative spatial relations, requiring models to perform comprehensive spatial reasoning. Furthermore, we propose an innovative model especially for the AerialVG task, where a Hierarchical Cross-Attention is devised to focus on target regions, and a Relation-Aware Grounding module is designed to infer positional relations. Experimental results validate the effectiveness of our dataset and method, highlighting the importance of spatial reasoning in aerial visual grounding. The code and dataset will be released.
Authors: Mahshad Lotfinia, Arash Tayebiarasteh, Samaneh Samiei, Mehdi Joodaki, Soroosh Tayebi Arasteh
Abstract: Reliable artificial intelligence (AI) models for medical image analysis often depend on large and diverse labeled datasets. Federated learning (FL) offers a decentralized and privacy-preserving approach to training but struggles in highly non-independent and identically distributed (non-IID) settings, where institutions with more representative data may experience degraded performance. Moreover, existing large-scale FL studies have been limited to adult datasets, neglecting the unique challenges posed by pediatric data, which introduces additional non-IID variability. To address these limitations, we analyzed n=398,523 adult chest radiographs from diverse institutions across multiple countries and n=9,125 pediatric images, leveraging transfer learning from general-purpose self-supervised image representations to classify pneumonia and cases with no abnormality. Using state-of-the-art vision transformers, we found that FL improved performance only for smaller adult datasets (P<0.001) but degraded performance for larger datasets (P<0.064) and pediatric cases (P=0.242). However, equipping FL with self-supervised weights significantly enhanced outcomes across pediatric cases (P=0.031) and most adult datasets (P<0.008), except the largest dataset (P=0.052). These findings underscore the potential of easily deployable general-purpose self-supervised image representations to address non-IID challenges in clinical FL applications and highlight their promise for enhancing patient outcomes and advancing pediatric healthcare, where data scarcity and variability remain persistent obstacles.
Authors: Naibang Wang, Deyong Shang, Yan Gong, Xiaoxi Hu, Ziying Song, Lei Yang, Yuhan Huang, Xiaoyu Wang, Jianli Lu
Abstract: Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://github.com/frankwnb/Collaborative-Perception-Datasets-for-Autonomous-Driving.
URLs: https://github.com/frankwnb/Collaborative-Perception-Datasets-for-Autonomous-Driving.
Authors: Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi, Triantafyllos Afouras, Tushar Nagarajan, Muhammad Maaz, Yale Song, Tengyu Ma, Shuming Hu, Suyog Jain, Miguel Martin, Huiyu Wang, Hanoona Rasheed, Peize Sun, Po-Yao Huang, Daniel Bolya, Nikhila Ravi, Shashank Jain, Tammy Stark, Shane Moon, Babak Damavandi, Vivian Lee, Andrew Westbury, Salman Khan, Philipp Kr\"ahenb\"uhl, Piotr Doll\'ar, Lorenzo Torresani, Kristen Grauman, Christoph Feichtenhofer
Abstract: Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about "what", "where", "when", and "how" of a video. We make our work fully reproducible by providing data, training recipes, code & models. https://github.com/facebookresearch/perception_models
Authors: Hao Xu, Arbind Agrahari Baniya, Sam Well, Mohamed Reda Bouadjenek, Richard Dazeley, Sunil Aryal
Abstract: Video event detection is central to modern sports analytics, enabling automated understanding of key moments for performance evaluation, content creation, and tactical feedback. While deep learning has significantly advanced tasks like Temporal Action Localization (TAL), Action Spotting (AS), and Precise Event Spotting (PES), existing surveys often overlook the fine-grained temporal demands and domain-specific challenges posed by sports. This survey first provides a clear conceptual distinction between TAL, AS, and PES, then introduces a methods-based taxonomy covering recent deep learning approaches for AS and PES, including feature-based pipelines, end-to-end architectures, and multimodal strategies. We further review benchmark datasets and evaluation protocols, identifying critical limitations such as reliance on broadcast-quality footage and lenient multi-label metrics that hinder real-world deployment. Finally, we outline open challenges and future directions toward more temporally precise, generalizable, and practical event spotting in sports video analysis.
Authors: Gonglin Chen, Tianwen Fu, Haiwei Chen, Wenbin Teng, Hanyuan Xiao, Yajie Zhao
Abstract: As a core step in structure-from-motion and SLAM, robust feature detection and description under challenging scenarios such as significant viewpoint changes remain unresolved despite their ubiquity. While recent works have identified the importance of local features in modeling geometric transformations, these methods fail to learn the visual cues present in long-range relationships. We present Robust Deformable Detector (RDD), a novel and robust keypoint detector/descriptor leveraging the deformable transformer, which captures global context and geometric invariance through deformable self-attention mechanisms. Specifically, we observed that deformable attention focuses on key locations, effectively reducing the search space complexity and modeling the geometric invariance. Furthermore, we collected an Air-to-Ground dataset for training in addition to the standard MegaDepth dataset. Our proposed method outperforms all state-of-the-art keypoint detection/description methods in sparse matching tasks and is also capable of semi-dense matching. To ensure comprehensive evaluation, we introduce two challenging benchmarks: one emphasizing large viewpoint and scale variations, and the other being an Air-to-Ground benchmark -- an evaluation setting that has recently gaining popularity for 3D reconstruction across different altitudes.
Authors: Yukiyasu Kamitani, Misato Tanaka, Ken Shirakawa
Abstract: Visual image reconstruction, the decoding of perceptual content from brain activity into images, has advanced significantly with the integration of deep neural networks (DNNs) and generative models. This review traces the field's evolution from early classification approaches to sophisticated reconstructions that capture detailed, subjective visual experiences, emphasizing the roles of hierarchical latent representations, compositional strategies, and modular architectures. Despite notable progress, challenges remain, such as achieving true zero-shot generalization for unseen images and accurately modeling the complex, subjective aspects of perception. We discuss the need for diverse datasets, refined evaluation metrics aligned with human perceptual judgments, and compositional representations that strengthen model robustness and generalizability. Ethical issues, including privacy, consent, and potential misuse, are underscored as critical considerations for responsible development. Visual image reconstruction offers promising insights into neural coding and enables new psychological measurements of visual experiences, with applications spanning clinical diagnostics and brain-machine interfaces.
Authors: Faika Fairuj Preotee, Shuvashis Sarker, Shamim Rahim Refat, Tashreef Muhammad, Shifat Islam
Abstract: Leaf diseases are harmful conditions that affect the health, appearance and productivity of plants, leading to significant plant loss and negatively impacting farmers' livelihoods. These diseases cause visible symptoms such as lesions, color changes, and texture variations, making it difficult for farmers to manage plant health, especially in large or remote farms where expert knowledge is limited. The main motivation of this study is to provide an efficient and accessible solution for identifying plant leaf diseases in Bangladesh, where agriculture plays a critical role in food security. The objective of our research is to classify 21 distinct leaf diseases across six plants using deep learning models, improving disease detection accuracy while reducing the need for expert involvement. Deep Learning (DL) techniques, including CNN and Transfer Learning (TL) models like VGG16, VGG19, MobileNetV2, InceptionV3, ResNet50V2 and Xception are used. VGG19 and Xception achieve the highest accuracies, with 98.90% and 98.66% respectively. Additionally, Explainable AI (XAI) techniques such as GradCAM, GradCAM++, LayerCAM, ScoreCAM and FasterScoreCAM are used to enhance transparency by highlighting the regions of the models focused on during disease classification. This transparency ensures that farmers can understand the model's predictions and take necessary action. This approach not only improves disease management but also supports farmers in making informed decisions, leading to better plant protection and increased agricultural productivity.
Authors: Shuvashis Sarker, Shamim Rahim Refat, Faika Fairuj Preotee, Shifat Islam, Tashreef Muhammad, Mohammad Ashraful Hoque
Abstract: The brain is a highly complex organ that manages many important tasks, including movement, memory and thinking. Brain-related conditions, like tumors and degenerative disorders, can be hard to diagnose and treat. Magnetic Resonance Imaging (MRI) serves as a key tool for identifying these conditions, offering high-resolution images of brain structures. Despite this, interpreting MRI scans can be complicated. This study tackles this challenge by conducting a comparative analysis of Vision Transformer (ViT) and Transfer Learning (TL) models such as VGG16, VGG19, Resnet50V2, MobilenetV2 for classifying brain diseases using MRI data from Bangladesh based dataset. ViT, known for their ability to capture global relationships in images, are particularly effective for medical imaging tasks. Transfer learning helps to mitigate data constraints by fine-tuning pre-trained models. Furthermore, Explainable AI (XAI) methods such as GradCAM, GradCAM++, LayerCAM, ScoreCAM, and Faster-ScoreCAM are employed to interpret model predictions. The results demonstrate that ViT surpasses transfer learning models, achieving a classification accuracy of 94.39%. The integration of XAI methods enhances model transparency, offering crucial insights to aid medical professionals in diagnosing brain diseases with greater precision.
Authors: Jiquan Shan, Junxiao Wang, Lifeng Zhao, Liang Cai, Hongyuan Zhang, Ioannis Liritzis
Abstract: Recently, vision transformers (ViTs) have achieved excellent performance on vision tasks by measuring the global self-attention among the image patches. Given $n$ patches, they will have quadratic complexity such as $\mathcal{O}(n^2)$ and the time cost is high when splitting the input image with a small granularity. Meanwhile, the pivotal information is often randomly gathered in a few regions of an input image, some tokens may not be helpful for the downstream tasks. To handle this problem, we introduce an anchor-based efficient vision transformer (AnchorFormer), which employs the anchor tokens to learn the pivotal information and accelerate the inference. Firstly, by estimating the bipartite attention between the anchors and tokens, the complexity will be reduced from $\mathcal{O}(n^2)$ to $\mathcal{O}(mn)$, where $m$ is an anchor number and $m < n$. Notably, by representing the anchors with the neurons in a neural layer, we can differentiably learn these anchors and approximate global self-attention through the Markov process. It avoids the burden caused by non-differentiable operations and further speeds up the approximate attention. Moreover, we extend the proposed model to three downstream tasks including classification, detection, and segmentation. Extensive experiments show the effectiveness of our AnchorFormer, e.g., achieving up to a 9.0% higher accuracy or 46.7% FLOPs reduction on ImageNet classification, 81.3% higher mAP on COCO detection under comparable FLOPs, as compared to the current baselines.
Authors: Cainan Davidson, Deva Ramanan, Neehar Peri
Abstract: Autonomous Vehicles (AVs) collect and pseudo-label terabytes of multi-modal data localized to HD maps during normal fleet testing. However, identifying interesting and safety-critical scenarios from uncurated driving logs remains a significant challenge. Traditional scenario mining techniques are error-prone and prohibitively time-consuming, often relying on hand-crafted structured queries. In this work, we revisit spatio-temporal scenario mining through the lens of recent vision-language models (VLMs) to detect whether a described scenario occurs in a driving log and, if so, precisely localize it in both time and space. To address this problem, we introduce RefAV, a large-scale dataset of 10,000 diverse natural language queries that describe complex multi-agent interactions relevant to motion planning derived from 1000 driving logs in the Argoverse 2 Sensor dataset. We evaluate several referential multi-object trackers and present an empirical analysis of our baselines. Notably, we find that naively repurposing off-the-shelf VLMs yields poor performance, suggesting that scenario mining presents unique challenges. Lastly, we discuss our recent CVPR 2025 competition and share insights from the community. Our code and dataset are available at https://github.com/CainanD/RefAV/ and https://argoverse.github.io/user-guide/tasks/scenario_mining.html
URLs: https://github.com/CainanD/RefAV/, https://argoverse.github.io/user-guide/tasks/scenario_mining.html
Authors: Runmin Jiang, Genpei Zhang, Yuntian Yang, Siqi Wu, Yuheng Zhang, Wanyue Feng, Yizhou Zhao, Xi Xiao, Xiao Wang, Tianyang Wang, Xingjian Li, Min Xu
Abstract: Cryo-electron microscopy (cryo-EM) offers near-atomic resolution imaging of macromolecules, but developing robust models for downstream analysis is hindered by the scarcity of high-quality annotated data. While synthetic data generation has emerged as a potential solution, existing methods often fail to capture both the structural diversity of biological specimens and the complex, spatially varying noise inherent in cryo-EM imaging. To overcome these limitations, we propose CryoCCD, a synthesis framework that integrates biophysical modeling with generative techniques. Specifically, CryoCCD produces multi-scale cryo-EM micrographs that reflect realistic biophysical variability through compositional heterogeneity, cellular context, and physics-informed imaging. To generate realistic noise, we employ a conditional diffusion model, enhanced by cycle consistency to preserve structural fidelity and mask-aware contrastive learning to capture spatially adaptive noise patterns. Extensive experiments show that CryoCCD generates structurally accurate micrographs and enhances performance in downstream tasks, outperforming state-of-the-art baselines in both particle picking and reconstruction.
Authors: Bin Lin, Zongjian Li, Xinhua Cheng, Yuwei Niu, Yang Ye, Xianyi He, Shenghai Yuan, Wangbo Yu, Shaodong Wang, Yunyang Ge, Yatian Pang, Li Yuan
Abstract: Although existing unified models achieve strong performance in vision-language understanding and text-to-image generation, they remain limited in addressing image perception and manipulation -- capabilities increasingly demanded in practical applications. Recently, OpenAI introduced the powerful GPT-4o-Image model, which showcases advanced capabilities in comprehensive image perception and manipulation, sparking widespread interest. Through carefully designed experiments, we observe that GPT-4o-Image likely relies on semantic encoders rather than VAEs for feature extraction, despite VAEs being commonly regarded as crucial for image manipulation tasks. Inspired by this insight, we propose UniWorld-V1, a unified generative framework built upon semantic features extracted from powerful multimodal large language models and contrastive semantic encoders. Using only 2.7M training data, UniWorld-V1 achieves impressive performance across diverse tasks, including image understanding, generation, manipulation, and perception. We fully open-source the UniWorld-V1 framework, including model weights, training and evaluation scripts, and datasets to promote reproducibility and further research.
Authors: Massimo Rizzoli, Simone Alghisi, Olha Khomyn, Gabriel Roccabruna, Seyed Mahed Mousavi, Giuseppe Riccardi
Abstract: While Vision-Language Models (VLMs) have achieved competitive performance in various tasks, their comprehension of the underlying structure and semantics of a scene remains understudied. To investigate the understanding of VLMs, we study their capability regarding object properties and relations in a controlled and interpretable manner. To this scope, we introduce CIVET, a novel and extensible framework for systematiC evaluatIon Via controllEd sTimuli. CIVET addresses the lack of standardized systematic evaluation for assessing VLMs' understanding, enabling researchers to test hypotheses with statistical rigor. With CIVET, we evaluate five state-of-the-art VLMs on exhaustive sets of stimuli, free from annotation noise, dataset-specific biases, and uncontrolled scene complexity. Our findings reveal that 1) current VLMs can accurately recognize only a limited set of basic object properties; 2) their performance heavily depends on the position of the object in the scene; 3) they struggle to understand basic relations among objects. Furthermore, a comparative evaluation with human annotators reveals that VLMs still fall short of achieving human-level accuracy.
Authors: Xing Hu, Siyuan Chen, Xuming Huang, Qianqian Duan, LingKun Luo, Ruijiao Li, Huiliang Shang, Linhua Jiang, Jianping Yang, Hamid Reza Karimi, Dawei Zhang
Abstract: With the growing application of computer vision in agriculture, image analysis has become essential for tasks such as crop health monitoring and pest detection. However, significant domain shifts caused by environmental variations, different crop types, and diverse data acquisition methods hinder model generalization across regions, seasons, and complex agricultural settings. This paper investigates how Domain Adaptation (DA) techniques can address these challenges by improving cross-domain transferability in agricultural image analysis. Given the limited availability of labeled data, weak model adaptability, and dynamic field conditions, DA has emerged as a promising solution. The review systematically summarizes recent advances in DA for agricultural imagery, focusing on applications such as crop health monitoring, pest detection, and fruit recognition, where DA methods have enhanced performance across diverse domains. DA approaches are categorized into shallow and deep learning methods, including supervised, semi-supervised, and unsupervised strategies, with particular attention to adversarial learning-based techniques that have demonstrated strong potential in complex scenarios. In addition, the paper reviews key public agricultural image datasets, evaluating their strengths and limitations in DA research. Overall, this work offers a comprehensive framework and critical insights to guide future research and development of domain adaptation in agricultural vision tasks.
Authors: Xiangyu Guo, Zhanqian Wu, Kaixin Xiong, Ziyang Xu, Lijun Zhou, Gangwei Xu, Shaoqing Xu, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Xinggang Wang
Abstract: We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a two-stage architecture that integrates a DiT-based video diffusion model with 3D-VAE encoding, and a BEV-aware LiDAR generator with NeRF-based rendering and adaptive sampling. Both modalities are directly coupled through a shared latent space, enabling coherent evolution across visual and geometric domains. To guide the generation with structured semantics, we introduce DataCrafter, a captioning module built on vision-language models that provides scene-level and instance-level supervision. Extensive experiments on the nuScenes benchmark demonstrate that Genesis achieves state-of-the-art performance across video and LiDAR metrics (FVD 16.95, FID 4.24, Chamfer 0.611), and benefits downstream tasks including segmentation and 3D detection, validating the semantic fidelity and practical utility of the generated data.
Authors: Kaiyu Guo, Zijian Wang, Tan Pan, Brian C. Lovell, Mahsa Baktashmotlagh
Abstract: Out-of-Distribution (OOD) detection is essential for the trustworthiness of AI systems. Methods using prior information (i.e., subspace-based methods) have shown effective performance by extracting information geometry to detect OOD data with a more appropriate distance metric. However, these methods fail to address the geometry distorted by ill-distributed samples, due to the limitation of statically extracting information geometry from the training distribution. In this paper, we argue that the influence of ill-distributed samples can be corrected by dynamically adjusting the prior geometry in response to new data. Based on this insight, we propose a novel approach that dynamically updates the prior covariance matrix using real-time input features, refining its information. Specifically, we reduce the covariance along the direction of real-time input features and constrain adjustments to the residual space, thus preserving essential data characteristics and avoiding effects on unintended directions in the principal space. We evaluate our method on two pre-trained models for the CIFAR dataset and five pre-trained models for ImageNet-1k, including the self-supervised DINO model. Extensive experiments demonstrate that our approach significantly enhances OOD detection across various models. The code is released at https://github.com/workerbcd/ooddcc.
Authors: Junfei Wu, Jian Guan, Kaituo Feng, Qiang Liu, Shu Wu, Liang Wang, Wei Wu, Tieniu Tan
Abstract: As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods primarily approach multimodal reasoning in a straightforward, text-centric manner, where both reasoning and answer derivation are conducted purely through text, with the only difference being the presence of multimodal input. As a result, these methods often encounter fundamental limitations in spatial reasoning tasks that demand precise geometric understanding and continuous spatial tracking-capabilities that humans achieve through mental visualization and manipulation. To address the limitations, we propose drawing to reason in space, a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space. By equipping models with basic drawing operations, including annotating bounding boxes and drawing auxiliary lines, we empower them to express and analyze spatial relationships through direct visual manipulation, meanwhile avoiding the performance ceiling imposed by specialized perception tools in previous tool-integrated reasoning approaches. To cultivate this capability, we develop a three-stage training framework: cold-start training with synthetic data to establish basic drawing abilities, reflective rejection sampling to enhance self-reflection behaviors, and reinforcement learning to directly optimize for target rewards. Extensive experiments demonstrate that our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks, involving maze navigation, static spatial reasoning, video-based reasoning, and multi-view-based reasoning tasks, with an average improvement of 18.4%.
Authors: Chenjian Gao, Lihe Ding, Xin Cai, Zhanpeng Huang, Zibin Wang, Tianfan Xue
Abstract: Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, limiting flexibility for specific edits. First-frame-guided editing provides control over the first frame, but lacks flexibility over subsequent frames. To address this, we propose a mask-based LoRA (Low-Rank Adaptation) tuning method that adapts pretrained Image-to-Video (I2V) models for flexible video editing. Our approach preserves background regions while enabling controllable edits propagation. This solution offers efficient and adaptable video editing without altering the model architecture. To better steer this process, we incorporate additional references, such as alternate viewpoints or representative scene states, which serve as visual anchors for how content should unfold. We address the control challenge using a mask-driven LoRA tuning strategy that adapts a pre-trained image-to-video model to the editing context. The model must learn from two distinct sources: the input video provides spatial structure and motion cues, while reference images offer appearance guidance. A spatial mask enables region-specific learning by dynamically modulating what the model attends to, ensuring that each area draws from the appropriate source. Experimental results show our method achieves superior video editing performance compared to state-of-the-art methods. Project Page: https://cjeen.github.io/LoraEditPaper
Authors: Hong Huang, Weixiang Sun, Zhijian Wu, Jingwen Niu, Donghuan Lu, Xian Wu, Yefeng Zheng
Abstract: Recently, the rapid advancements of vision-language models, such as CLIP, leads to significant progress in zero-/few-shot anomaly detection (ZFSAD) tasks. However, most existing CLIP-based ZFSAD methods commonly assume prior knowledge of categories and rely on carefully crafted prompts tailored to specific scenarios. While such meticulously designed text prompts effectively capture semantic information in the textual space, they fall short of distinguishing normal and anomalous instances within the joint embedding space. Moreover, these ZFSAD methods are predominantly explored in industrial scenarios, with few efforts conducted to medical tasks. To this end, we propose an innovative framework for ZFSAD tasks in medical domain, denoted as IQE-CLIP. We reveal that query embeddings, which incorporate both textual and instance-aware visual information, are better indicators for abnormalities. Specifically, we first introduce class-based prompting tokens and learnable prompting tokens for better adaptation of CLIP to the medical domain. Then, we design an instance-aware query module (IQM) to extract region-level contextual information from both text prompts and visual features, enabling the generation of query embeddings that are more sensitive to anomalies. Extensive experiments conducted on six medical datasets demonstrate that IQE-CLIP achieves state-of-the-art performance on both zero-shot and few-shot tasks. We release our code and data at https://github.com/hongh0/IQE-CLIP/.
Authors: Jin Kim, Muhammad Wahi-Anwa, Sangyun Park, Shawn Shin, John M. Hoffman, Matthew S. Brown
Abstract: Agentic Artificial Intelligence (AI) systems leveraging Large Language Models (LLMs) exhibit significant potential for complex reasoning, planning, and tool utilization. We demonstrate that a specialized computer vision system can be built autonomously from a natural language prompt using Agentic AI methods. This involved extending SimpleMind (SM), an open-source Cognitive AI environment with configurable tools for medical image analysis, with an LLM-based agent, implemented using OpenManus, to automate the planning (tool configuration) for a particular computer vision task. We provide a proof-of-concept demonstration that an agentic system can interpret a computer vision task prompt, plan a corresponding SimpleMind workflow by decomposing the task and configuring appropriate tools. From the user input prompt, "provide sm (SimpleMind) config for lungs, heart, and ribs segmentation for cxr (chest x-ray)"), the agent LLM was able to generate the plan (tool configuration file in YAML format), and execute SM-Learn (training) and SM-Think (inference) scripts autonomously. The computer vision agent automatically configured, trained, and tested itself on 50 chest x-ray images, achieving mean dice scores of 0.96, 0.82, 0.83, for lungs, heart, and ribs, respectively. This work shows the potential for autonomous planning and tool configuration that has traditionally been performed by a data scientist in the development of computer vision applications.
Authors: H\'ector Carri\'on, Yutong Bai, V\'ictor A. Hern\'andez Castro, Kishan Panaganti, Ayush Zenith, Matthew Trang, Tony Zhang, Pietro Perona, Jitendra Malik
Abstract: World models aim to simulate environments and enable effective agent behavior. However, modeling real-world environments presents unique challenges as they dynamically change across both space and, crucially, time. To capture these composed dynamics, we introduce a Spatio-Temporal Road Image Dataset for Exploration (STRIDE) permuting 360-degree panoramic imagery into rich interconnected observation, state and action nodes. Leveraging this structure, we can simultaneously model the relationship between egocentric views, positional coordinates, and movement commands across both space and time. We benchmark this dataset via TARDIS, a transformer-based generative world model that integrates spatial and temporal dynamics through a unified autoregressive framework trained on STRIDE. We demonstrate robust performance across a range of agentic tasks such as controllable photorealistic image synthesis, instruction following, autonomous self-control, and state-of-the-art georeferencing. These results suggest a promising direction towards sophisticated generalist agents--capable of understanding and manipulating the spatial and temporal aspects of their material environments--with enhanced embodied reasoning capabilities. Training code, datasets, and model checkpoints are made available at https://huggingface.co/datasets/Tera-AI/STRIDE.
Authors: Hanxue Gu, Yaqian Chen, Jisoo Lee, Diego Schaps, Regina Woody, Roy Colglazier, Maciej A. Mazurowski, Christopher Mantyh
Abstract: Objective: To evaluate whether preoperative body composition metrics automatically extracted from CT scans can predict postoperative outcomes after colectomy, either alone or combined with clinical variables or existing risk predictors. Main outcomes and measures: The primary outcome was the predictive performance for 1-year all-cause mortality following colectomy. A Cox proportional hazards model with 1-year follow-up was used, and performance was evaluated using the concordance index (C-index) and Integrated Brier Score (IBS). Secondary outcomes included postoperative complications, unplanned readmission, blood transfusion, and severe infection, assessed using AUC and Brier Score from logistic regression. Odds ratios (OR) described associations between individual CT-derived body composition metrics and outcomes. Over 300 features were extracted from preoperative CTs across multiple vertebral levels, including skeletal muscle area, density, fat areas, and inter-tissue metrics. NSQIP scores were available for all surgeries after 2012.
Authors: Naomi Fridman, Bubby Solway, Tomer Fridman, Itamar Barnea, Anat Goldstein
Abstract: Breast cancer remains a leading cause of cancer-related mortality worldwide, making early detection and accurate treatment response monitoring critical priorities. We present BreastDCEDL, a curated, deep learning-ready dataset comprising pre-treatment 3D Dynamic Contrast-Enhanced MRI (DCE-MRI) scans from 2,070 breast cancer patients drawn from the I-SPY1, I-SPY2, and Duke cohorts, all sourced from The Cancer Imaging Archive. The raw DICOM imaging data were rigorously converted into standardized 3D NIfTI volumes with preserved signal integrity, accompanied by unified tumor annotations and harmonized clinical metadata including pathologic complete response (pCR), hormone receptor (HR), and HER2 status. Although DCE-MRI provides essential diagnostic information and deep learning offers tremendous potential for analyzing such complex data, progress has been limited by lack of accessible, public, multicenter datasets. BreastDCEDL addresses this gap by enabling development of advanced models, including state-of-the-art transformer architectures that require substantial training data. To demonstrate its capacity for robust modeling, we developed the first transformer-based model for breast DCE-MRI, leveraging Vision Transformer (ViT) architecture trained on RGB-fused images from three contrast phases (pre-contrast, early post-contrast, and late post-contrast). Our ViT model achieved state-of-the-art pCR prediction performance in HR+/HER2- patients (AUC 0.94, accuracy 0.93). BreastDCEDL includes predefined benchmark splits, offering a framework for reproducible research and enabling clinically meaningful modeling in breast cancer imaging.
Authors: Hongbi Zhou, Zhangkai Ni
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian primitives based on scene characteristics, making it challenging to balance reconstruction quality and efficiency. Inspired by human perception, we propose scene-adaptive perceptual densification for Gaussian Splatting (Perceptual-GS), a novel framework that integrates perceptual sensitivity into the 3DGS training process to address this challenge. We first introduce a perception-aware representation that models human visual sensitivity while constraining the number of Gaussian primitives. Building on this foundation, we develop a perceptual sensitivity-adaptive distribution to allocate finer Gaussian granularity to visually critical regions, enhancing reconstruction quality and robustness. Extensive evaluations on multiple datasets, including BungeeNeRF for large-scale scenes, demonstrate that Perceptual-GS achieves state-of-the-art performance in reconstruction quality, efficiency, and robustness. The code is publicly available at: https://github.com/eezkni/Perceptual-GS
Authors: Eugene Kofi Okrah Denteh, Andrews Danyo, Joshua Kofi Asamoah, Blessing Agyei Kyem, Armstrong Aboah
Abstract: This study presents a novel demographics informed deep learning framework designed to forecast urban spatial transformations by jointly modeling geographic satellite imagery, socio-demographics, and travel behavior dynamics. The proposed model employs an encoder-decoder architecture with temporal gated residual connections, integrating satellite imagery and demographic data to accurately forecast future spatial transformations. The study also introduces a demographics prediction component which ensures that predicted satellite imagery are consistent with demographic features, significantly enhancing physiological realism and socioeconomic accuracy. The framework is enhanced by a proposed multi-objective loss function complemented by a semantic loss function that balances visual realism with temporal coherence. The experimental results from this study demonstrate the superior performance of the proposed model compared to state-of-the-art models, achieving higher structural similarity (SSIM: 0.8342) and significantly improved demographic consistency (Demo-loss: 0.14 versus 0.95 and 0.96 for baseline models). Additionally, the study validates co-evolutionary theories of urban development, demonstrating quantifiable bidirectional influences between built environment characteristics and population patterns. The study also contributes a comprehensive multimodal dataset pairing satellite imagery sequences (2012-2023) with corresponding demographic and travel behavior attributes, addressing existing gaps in urban and transportation planning resources by explicitly connecting physical landscape evolution with socio-demographic patterns.
Authors: Bingchen Zhao, Kai Han
Abstract: This paper addresses the problem of Generalized Category Discovery (GCD) under a long-tailed distribution, which involves discovering novel categories in an unlabelled dataset using knowledge from a set of labelled categories. Existing works assume a uniform distribution for both datasets, but real-world data often exhibits a long-tailed distribution, where a few categories contain most examples, while others have only a few. While the long-tailed distribution is well-studied in supervised and semi-supervised settings, it remains unexplored in the GCD context. We identify two challenges in this setting - balancing classifier learning and estimating category numbers - and propose a framework based on confident sample selection and density-based clustering to tackle them. Our experiments on both long-tailed and conventional GCD datasets demonstrate the effectiveness of our method.
Authors: Ye Li, Yuan Meng, Zewen Sun, Kangye Ji, Chen Tang, Jiajun Fan, Xinzhu Ma, Shutao Xia, Zhi Wang, Wenwu Zhu
Abstract: Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities. However, their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation. Existing VLA acceleration methods primarily focus on structural optimization, overlooking the fact that these models operate in sequential decision-making environments. As a result, temporal redundancy in sequential action generation and spatial redundancy in visual input remain unaddressed. To this end, we propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens. Specifically, we design an action-aware model scheduling mechanism that reduces temporal redundancy by dynamically switching between VLA model and a lightweight generator. Inspired by the human motion pattern of focusing on key decision points while relying on intuition for other actions, we categorize VLA actions into deliberative and intuitive, assigning the former to the VLA model and the latter to the lightweight generator, enabling frequency-adaptive execution through collaborative model scheduling. To address spatial redundancy, we further develop a spatio-semantic dual-aware token pruning method. Tokens are classified into spatial and semantic types and pruned based on their dual-aware importance to accelerate VLA inference. These two mechanisms work jointly to guide the VLA in focusing on critical actions and salient visual information, achieving effective acceleration while maintaining high accuracy. Experimental results demonstrate that our method achieves up to 1.5$\times$ acceleration with less than 3% drop in accuracy, outperforming existing approaches in multiple tasks.
Authors: Kshitij Kavimandan, Angelos Nalmpantis, Emma Beauxis-Aussalet, Robert-Jan Sips
Abstract: Patent images are technical drawings that convey information about a patent's innovation. Patent image retrieval systems aim to search in vast collections and retrieve the most relevant images. Despite recent advances in information retrieval, patent images still pose significant challenges due to their technical intricacies and complex semantic information, requiring efficient fine-tuning for domain adaptation. Current methods neglect patents' hierarchical relationships, such as those defined by the Locarno International Classification (LIC) system, which groups broad categories (e.g., "furnishing") into subclasses (e.g., "seats" and "beds") and further into specific patent designs. In this work, we introduce a hierarchical multi-positive contrastive loss that leverages the LIC's taxonomy to induce such relations in the retrieval process. Our approach assigns multiple positive pairs to each patent image within a batch, with varying similarity scores based on the hierarchical taxonomy. Our experimental analysis with various vision and multimodal models on the DeepPatent2 dataset shows that the proposed method enhances the retrieval results. Notably, our method is effective with low-parameter models, which require fewer computational resources and can be deployed on environments with limited hardware.
Authors: Thomas Kreutz, Max M\"uhlh\"auser, Alejandro Sanchez Guinea
Abstract: Despite LiDAR (Light Detection and Ranging) being an effective privacy-preserving alternative to RGB cameras to perceive human activities, it remains largely underexplored in the context of multi-modal contrastive pre-training for human activity understanding (e.g., human activity recognition (HAR), retrieval, or person re-identification (RE-ID)). To close this gap, our work explores learning the correspondence between LiDAR point clouds, human skeleton poses, IMU data, and text in a joint embedding space. More specifically, we present DeSPITE, a Deep Skeleton-Pointcloud-IMU-Text Embedding model, which effectively learns a joint embedding space across these four modalities. At the heart of our empirical exploration, we have combined the existing LIPD and Babel datasets, which enabled us to synchronize data of all four modalities, allowing us to explore the learning of a new joint embedding space. Our experiments demonstrate novel human activity understanding tasks for point cloud sequences enabled through DeSPITE, including Skeleton<->Pointcloud<->IMU matching, retrieval, and temporal moment retrieval. Furthermore, we show that DeSPITE is an effective pre-training strategy for point cloud HAR through experiments in MSR-Action3D and HMPEAR.
Authors: Xiaohui Jiang, Haijiang Zhu, Chade Li, Fulin Tang, Ning An
Abstract: LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent point cloud density, induced by ego-motion dynamics and environmental disturbances during repeated traversals, leads to descriptor instability, and (2) Representation fragility stems from reliance on single-level geometric abstractions that lack discriminative power in structurally complex scenarios. To address these limitations, we propose a novel framework that redefines 3D place recognition through density-agnostic geometric reasoning. Specifically, we introduce an implicit 3D representation based on elastic points, which is immune to the interference of original scene point cloud density and achieves the characteristic of uniform distribution. Subsequently, we derive the occupancy grid and normal vector information of the scene from this implicit representation. Finally, with the aid of these two types of information, we obtain descriptors that fuse geometric information from both bird's-eye view (capturing macro-level spatial layouts) and 3D segment (encoding micro-scale surface geometries) perspectives. We conducted extensive experiments on numerous datasets (KITTI, KITTI-360, MulRan, NCLT) across diverse environments. The experimental results demonstrate that our method achieves state-of-the-art performance. Moreover, our approach strikes an optimal balance between accuracy, runtime, and memory optimization for historical maps, showcasing excellent Resilient and scalability. Our code will be open-sourced in the future.
Authors: Tian Xia, Fabio De Sousa Ribeiro, Rajat R Rasal, Avinash Kori, Raghav Mehta, Ben Glocker
Abstract: Counterfactual image generation aims to simulate realistic visual outcomes under specific causal interventions. Diffusion models have recently emerged as a powerful tool for this task, combining DDIM inversion with conditional generation via classifier-free guidance (CFG). However, standard CFG applies a single global weight across all conditioning variables, which can lead to poor identity preservation and spurious attribute changes - a phenomenon known as attribute amplification. To address this, we propose Decoupled Classifier-Free Guidance (DCFG), a flexible and model-agnostic framework that introduces group-wise conditioning control. DCFG builds on an attribute-split embedding strategy that disentangles semantic inputs, enabling selective guidance on user-defined attribute groups. For counterfactual generation, we partition attributes into intervened and invariant sets based on a causal graph and apply distinct guidance to each. Experiments on CelebA-HQ, MIMIC-CXR, and EMBED show that DCFG improves intervention fidelity, mitigates unintended changes, and enhances reversibility, enabling more faithful and interpretable counterfactual image generation.
Authors: Varun Mannam, Zhenyu Shi
Abstract: Accurate video annotation plays a vital role in modern retail applications, including customer behavior analysis, product interaction detection, and in-store activity recognition. However, conventional annotation methods heavily rely on time-consuming manual labeling by human annotators, introducing non-robust frame selection and increasing operational costs. To address these challenges in the retail domain, we propose a deep learning-based approach that automates key-frame identification in retail videos and provides automatic annotations of products and customers. Our method leverages deep neural networks to learn discriminative features by embedding video frames and incorporating object detection-based techniques tailored for retail environments. Experimental results showcase the superiority of our approach over traditional methods, achieving accuracy comparable to human annotator labeling while enhancing the overall efficiency of retail video annotation. Remarkably, our approach leads to an average of 2 times cost savings in video annotation. By allowing human annotators to verify/adjust less than 5% of detected frames in the video dataset, while automating the annotation process for the remaining frames without reducing annotation quality, retailers can significantly reduce operational costs. The automation of key-frame detection enables substantial time and effort savings in retail video labeling tasks, proving highly valuable for diverse retail applications such as shopper journey analysis, product interaction detection, and in-store security monitoring.
Authors: Yufei Liu, Haoke Xiao, Jiaxing Chai, Yongcun Zhang, Rong Wang, Zijie Meng, Zhiming Luo
Abstract: The advent of Large Vision Models (LVMs) offers new opportunities for few-shot medical image segmentation. However, existing training-free methods based on LVMs fail to effectively utilize negative prompts, leading to poor performance on low-contrast medical images. To address this issue, we propose SynPo, a training-free few-shot method based on LVMs (e.g., SAM), with the core insight: improving the quality of negative prompts. To select point prompts in a more reliable confidence map, we design a novel Confidence Map Synergy Module by combining the strengths of DINOv2 and SAM. Based on the confidence map, we select the top-k pixels as the positive points set and choose the negative points set using a Gaussian distribution, followed by independent K-means clustering for both sets. Then, these selected points are leveraged as high-quality prompts for SAM to get the segmentation results. Extensive experiments demonstrate that SynPo achieves performance comparable to state-of-the-art training-based few-shot methods.
Authors: Lanfeng Zhong, Xin Liao, Shichuan Zhang, Shaoting Zhang, Guotai Wang
Abstract: Pathology image classification plays a crucial role in accurate medical diagnosis and treatment planning. Training high-performance models for this task typically requires large-scale annotated datasets, which are both expensive and time-consuming to acquire. Active Learning (AL) offers a solution by iteratively selecting the most informative samples for annotation, thereby reducing the labeling effort. However, most AL methods are designed under the assumption of a closed-set scenario, where all the unannotated images belong to target classes. In real-world clinical environments, the unlabeled pool often contains a substantial amount of Out-Of-Distribution (OOD) data, leading to low efficiency of annotation in traditional AL methods. Furthermore, most existing AL methods start with random selection in the first query round, leading to a significant waste of labeling costs in open-set scenarios. To address these challenges, we propose OpenPath, a novel open-set active learning approach for pathological image classification leveraging a pre-trained Vision-Language Model (VLM). In the first query, we propose task-specific prompts that combine target and relevant non-target class prompts to effectively select In-Distribution (ID) and informative samples from the unlabeled pool. In subsequent queries, Diverse Informative ID Sampling (DIS) that includes Prototype-based ID candidate Selection (PIS) and Entropy-Guided Stochastic Sampling (EGSS) is proposed to ensure both purity and informativeness in a query, avoiding the selection of OOD samples. Experiments on two public pathology image datasets show that OpenPath significantly enhances the model's performance due to its high purity of selected samples, and outperforms several state-of-the-art open-set AL methods. The code is available at \href{https://github.com/HiLab-git/OpenPath}{https://github.com/HiLab-git/OpenPath}..
URLs: https://github.com/HiLab-git/OpenPath, https://github.com/HiLab-git/OpenPath
Authors: Jinheng Xie, Zhenheng Yang, Mike Zheng Shou
Abstract: This paper presents improved native unified multimodal models, \emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at https://github.com/showlab/Show-o.
Authors: Yujing Sun, Lingchen Sun, Shuaizheng Liu, Rongyuan Wu, Zhengqiang Zhang, Lei Zhang
Abstract: It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL.
Authors: Zhen Li, Chuanhao Li, Xiaofeng Mao, Shaoheng Lin, Ming Li, Shitian Zhao, Zhaopan Xu, Xinyue Li, Yukang Feng, Jianwen Sun, Zizhen Li, Fanrui Zhang, Jiaxin Ai, Zhixiang Wang, Yuwei Wu, Tong He, Jiangmiao Pang, Yu Qiao, Yunde Jia, Kaipeng Zhang
Abstract: Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well-suited for world exploration training as they suffer from some limitations: limited locations, short duration, static scenes, and a lack of annotations about exploration and the world. In this paper, we introduce Sekai (meaning ``world'' in Japanese), a high-quality first-person view worldwide video dataset with rich annotations for world exploration. It consists of over 5,000 hours of walking or drone view (FPV and UVA) videos from over 100 countries and regions across 750 cities. We develop an efficient and effective toolbox to collect, pre-process and annotate videos with location, scene, weather, crowd density, captions, and camera trajectories. Experiments demonstrate the quality of the dataset. And, we use a subset to train an interactive video world exploration model, named YUME (meaning ``dream'' in Japanese). We believe Sekai will benefit the area of video generation and world exploration, and motivate valuable applications. The project page is https://lixsp11.github.io/sekai-project/.
Authors: Moran Yanuka, Morris Alper, Hadar Averbuch-Elor, Raja Giryes
Abstract: Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard data filtering approaches succeed in removing mismatched text-image pairs, but permit semantically related but highly abstract or subjective text. These approaches lack the fine-grained ability to isolate the most concrete samples that provide the strongest signal for learning in a noisy dataset. In this work, we propose a new metric, image caption concreteness, that evaluates caption text without an image reference to measure its concreteness and relevancy for use in multimodal learning. Our approach leverages strong foundation models for measuring visual-semantic information loss in multimodal representations. We demonstrate that this strongly correlates with human evaluation of concreteness in both single-word and sentence-level texts. Moreover, we show that curation using ICC complements existing approaches: It succeeds in selecting the highest quality samples from multimodal web-scale datasets to allow for efficient training in resource-constrained settings.
Authors: Runmin Jiang, Zhaoxin Fan, Junhao Wu, Lenghan Zhu, Xin Huang, Tianyang Wang, Heng Huang, Min Xu
Abstract: 3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation. However, this approach heavily relies on labor-intensive and time-consuming fully annotated ground-truth labels, particularly for 3D volumes. To overcome this limitation, we propose a novel probabilistic-aware weakly supervised learning pipeline, specifically designed for 3D medical imaging. Our pipeline integrates three innovative components: a Probability-based Pseudo Label Generation technique for synthesizing dense segmentation masks from sparse annotations, a Probabilistic Multi-head Self-Attention network for robust feature extraction within our Probabilistic Transformer Network, and a Probability-informed Segmentation Loss Function to enhance training with annotation confidence. Demonstrating significant advances, our approach not only rivals the performance of fully supervised methods but also surpasses existing weakly supervised methods in CT and MRI datasets, achieving up to 18.1% improvement in Dice scores for certain organs. The code is available at https://github.com/runminjiang/PW4MedSeg.
Authors: Shijing Hu, Zhihui Lu, Xin Xu, Ruijun Deng, Xin Du, Qiang Duan
Abstract: Embodied intelligence (EI) enables manufacturing systems to flexibly perceive, reason, adapt, and operate within dynamic shop floor environments. In smart manufacturing, a representative EI scenario is robotic visual inspection, where industrial robots must accurately inspect components on rapidly changing, heterogeneous production lines. This task requires both high inference accuracy especially for uncommon defects and low latency to match production speeds, despite evolving lighting, part geometries, and surface conditions. To meet these needs, we propose LAECIPS, a large vision model-assisted adaptive edge-cloud collaboration framework for IoT-based embodied intelligence systems. LAECIPS decouples large vision models in the cloud from lightweight models on the edge, enabling plug-and-play model adaptation and continual learning. Through a hard input mining-based inference strategy, LAECIPS routes complex and uncertain inspection cases to the cloud while handling routine tasks at the edge, achieving both high accuracy and low latency. Experiments conducted on a real-world robotic semantic segmentation system for visual inspection demonstrate significant improvements in accuracy, processing latency, and communication overhead compared to state-of-the-art methods. LAECIPS provides a practical and scalable foundation for embodied intelligence in smart manufacturing, especially in adaptive robotic inspection and quality control scenarios.
Authors: Manasi Muglikar, Siddharth Somasundaram, Akshat Dave, Edoardo Charbon, Ramesh Raskar, Davide Scaramuzza
Abstract: Traditional cameras face a trade-off between low-light performance and high-speed imaging: longer exposure times to capture sufficient light results in motion blur, whereas shorter exposures result in Poisson-corrupted noisy images. While burst photography techniques help mitigate this tradeoff, conventional cameras are fundamentally limited in their sensor noise characteristics. Event cameras and single-photon avalanche diode (SPAD) sensors have emerged as promising alternatives to conventional cameras due to their desirable properties. SPADs are capable of single-photon sensitivity with microsecond temporal resolution, and event cameras can measure brightness changes up to 1 MHz with low bandwidth requirements. We show that these properties are complementary, and can help achieve low-light, high-speed image reconstruction with low bandwidth requirements. We introduce a sensor fusion framework to combine SPADs with event cameras to improves the reconstruction of high-speed, low-light scenes while reducing the high bandwidth cost associated with using every SPAD frame. Our evaluation, on both synthetic and real sensor data, demonstrates significant enhancements ( > 5 dB PSNR) in reconstructing low-light scenes at high temporal resolution (100 kHz) compared to conventional cameras. Event-SPAD fusion shows great promise for real-world applications, such as robotics or medical imaging.
Authors: Yunpeng Jiang, Yutong Ban, Paul Weng
Abstract: Data augmentation is widely applied and has shown its benefits in different machine learning tasks. However, as recently observed, it may have an unfair effect in multi-class classification. While data augmentation generally improves the overall performance (and therefore is beneficial for many classes), it can actually be detrimental for other classes, which can be problematic in some application domains. In this paper, to counteract this phenomenon, we propose CLAM, a CLAss-dependent Multiplicative-weights method. To derive it, we first formulate the training of a classifier as a non-linear optimization problem that aims at simultaneously maximizing the individual class performances and balancing them. By rewriting this optimization problem as an adversarial two-player game, we propose a novel multiplicative weight algorithm, for which we prove the convergence. Interestingly, our formulation also reveals that the class-dependent effects of data augmentation is not due to data augmentation only, but is in fact a general phenomenon. Our empirical results over six datasets demonstrate that the performance of learned classifiers is indeed more fairly distributed over classes, with only limited impact on the average accuracy.
Authors: Kaitao Chen, Mianxin Liu, Fang Yan, Lei Ma, Xiaoming Shi, Lilong Wang, Xiaosong Wang, Lifeng Zhu, Zhe Wang, Mu Zhou, Shaoting Zhang
Abstract: The advent of vision-language models fosters the interactive conversations between AI-enabled models and humans. Yet applying these models into clinics must deal with daunting challenges around large-scale training data, financial, and computational resources. Here we propose a cost-effective instruction learning framework for conversational pathology named as CLOVER. CLOVER only trains a lightweight module and uses instruction tuning while freezing the parameters of the large language model. Instead of using costly GPT-4, we propose well-designed prompts on GPT-3.5 for building generation-based instructions, emphasizing the utility of pathological knowledge derived from the Internet source. To augment the use of instructions, we construct a high-quality set of template-based instructions in the context of digital pathology. From two benchmark datasets, our findings reveal the strength of hybrid-form instructions in the visual question-answer in pathology. Extensive results show the cost-effectiveness of CLOVER in answering both open-ended and closed-ended questions, where CLOVER outperforms strong baselines that possess 37 times more training parameters and use instruction data generated from GPT-4. Through the instruction tuning, CLOVER exhibits robustness of few-shot learning in the external clinical dataset. These findings demonstrate that cost-effective modeling of CLOVER could accelerate the adoption of rapid conversational applications in the landscape of digital pathology.
Authors: Yihao Ding, Soyeon Caren Han, Jean Lee, Eduard Hovy
Abstract: Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting information from VRDs rely heavily on expert knowledge and manual annotation, making them labor-intensive and inefficient. Recent advances in deep learning have transformed this landscape by enabling multimodal models that integrate vision, language, and layout features through pretraining, significantly improving information extraction performance. This survey presents a comprehensive overview of deep learning-based frameworks for VRD Content Understanding (VRD-CU). We categorize existing methods based on their modeling strategies and downstream tasks, and provide a comparative analysis of key components, including feature representation, fusion techniques, model architectures, and pretraining objectives. Additionally, we highlight the strengths and limitations of each approach and discuss their suitability for different applications. The paper concludes with a discussion of current challenges and emerging trends, offering guidance for future research and practical deployment in real-world scenarios.
Authors: Yijiang Li, Qingying Gao, Tianwei Zhao, Bingyang Wang, Haoran Sun, Haiyun Lyu, Robert D. Hawkins, Nuno Vasconcelos, Tal Golan, Dezhi Luo, Hokin Deng
Abstract: While Multi-modal Large Language Models (MLLMs) demonstrate impressive abilities over high-level perception and reasoning, their robustness in the wild remains limited, often falling short on tasks that are intuitive and effortless for humans. We examine the hypothesis that these deficiencies stem from the absence of core knowledge--rudimentary cognitive abilities innate to humans from early childhood. To explore the core knowledge representation in MLLMs, we introduce CoreCognition, a large-scale benchmark encompassing 12 core knowledge concepts grounded in developmental cognitive science. We evaluate 230 models with 11 different prompts, leading to a total of 2,530 data points for analysis. Our experiments uncover four key findings, collectively demonstrating core knowledge deficits in MLLMs: they consistently underperform and show reduced, or even absent, scalability on low-level abilities relative to high-level ones. Finally, we propose Concept Hacking, a novel controlled evaluation method that reveals MLLMs fail to progress toward genuine core knowledge understanding, but instead rely on shortcut learning as they scale.
Authors: Syed Abdul Gaffar Shakhadri, Kruthika KR, Rakshit Aralimatti
Abstract: We introduce Shakti, a 2.5 billion parameter language model specifically optimized for resource-constrained environments such as edge devices, including smartphones, wearables, and IoT systems. Shakti combines high-performance NLP with optimized efficiency and precision, making it ideal for real-time AI applications where computational resources and memory are limited. With support for vernacular languages and domain-specific tasks, Shakti excels in industries such as healthcare, finance, and customer service. Benchmark evaluations demonstrate that Shakti performs competitively against larger models while maintaining low latency and on-device efficiency, positioning it as a leading solution for edge AI.
Authors: Guohui Cai, Ying Cai, Zeyu Zhang, Yuanzhouhan Cao, Lin Wu, Daji Ergu, Zhinbin Liao, Yang Zhao
Abstract: Lung cancer remains one of the leading causes of morbidity and mortality worldwide, making early diagnosis critical for improving therapeutic outcomes and patient prognosis. Computer-aided diagnosis systems, which analyze computed tomography images, have proven effective in detecting and classifying pulmonary nodules, significantly enhancing the detection rate of early-stage lung cancer. Although traditional machine learning algorithms have been valuable, they exhibit limitations in handling complex sample data. The recent emergence of deep learning has revolutionized medical image analysis, driving substantial advancements in this field. This review focuses on recent progress in deep learning for pulmonary nodule detection, segmentation, and classification. Traditional machine learning methods, such as support vector machines and k-nearest neighbors, have shown limitations, paving the way for advanced approaches like Convolutional Neural Networks, Recurrent Neural Networks, and Generative Adversarial Networks. The integration of ensemble models and novel techniques is also discussed, emphasizing the latest developments in lung cancer diagnosis. Deep learning algorithms, combined with various analytical techniques, have markedly improved the accuracy and efficiency of pulmonary nodule analysis, surpassing traditional methods, particularly in nodule classification. Although challenges remain, continuous technological advancements are expected to further strengthen the role of deep learning in medical diagnostics, especially for early lung cancer detection and diagnosis. A comprehensive list of lung cancer detection models reviewed in this work is available at https://github.com/CaiGuoHui123/Awesome-Lung-Cancer-Detection.
URLs: https://github.com/CaiGuoHui123/Awesome-Lung-Cancer-Detection.
Authors: Saketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong, Nael Abu-Ghazaleh, Amit K. Roy-Chowdhury
Abstract: Vision-language models (VLMs) have improved significantly in their capabilities, but their complex architecture makes their safety alignment challenging. In this paper, we reveal an uneven distribution of harmful information across the intermediate layers of the image encoder and show that skipping a certain set of layers and exiting early can increase the chance of the VLM generating harmful responses. We call it as "Image enCoder Early-exiT" based vulnerability (ICET). Our experiments across three VLMs: LLaVA-1.5, LLaVA-NeXT, and Llama 3.2, show that performing early exits from the image encoder significantly increases the likelihood of generating harmful outputs. To tackle this, we propose a simple yet effective modification of the Clipped-Proximal Policy Optimization (Clip-PPO) algorithm for performing layer-wise multi-modal RLHF for VLMs. We term this as Layer-Wise PPO (L-PPO). We evaluate our L-PPO algorithm across three multimodal datasets and show that it consistently reduces the harmfulness caused by early exits.
Authors: M\'elanie Roschewitz, Raghav Mehta, Charles Jones, Ben Glocker
Abstract: Shifts in data distribution can substantially harm the performance of clinical AI models and lead to misdiagnosis. Hence, various methods have been developed to detect the presence of such shifts at deployment time. However, the root causes of dataset shifts are diverse, and the choice of shift mitigation strategies is highly dependent on the precise type of shift encountered at test time. As such, detecting test-time dataset shift is not sufficient: precisely identifying which type of shift has occurred is critical. In this work, we propose the first unsupervised dataset shift identification framework for imaging datasets, effectively distinguishing between prevalence shift (caused by a change in the label distribution), covariate shift (caused by a change in input characteristics) and mixed shifts (simultaneous prevalence and covariate shifts). We discuss the importance of self-supervised encoders for detecting subtle covariate shifts and propose a novel shift detector leveraging both self-supervised encoders and task model outputs for improved shift detection. We show the effectiveness of the proposed shift identification framework across three different imaging modalities (chest radiography, digital mammography, and retinal fundus images) on five types of real-world dataset shifts using five large publicly available datasets.
Authors: Daixuan Cheng, Shaohan Huang, Ziyu Zhu, Xintong Zhang, Wayne Xin Zhao, Zhongzhi Luan, Bo Dai, Zhenliang Zhang
Abstract: Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applications. This paper systematically investigates domain adaptation of MLLMs via post-training, focusing on data synthesis, training pipeline, and task evaluation. (1) Data Synthesis: Using only open-source models, we develop a generate-then-filter pipeline that curates diverse visual instruction tasks based on domain-specific image-caption pairs. The resulting data surpass the data synthesized by manual rules or strong closed-source models in enhancing domain-specific performance. (2) Training Pipeline: Unlike general MLLMs that typically adopt a two-stage training paradigm, we find that a single-stage approach is more effective for domain adaptation. (3) Task Evaluation: We conduct extensive experiments in high-impact domains such as biomedicine, food, and remote sensing, by post-training a variety of MLLMs and then evaluating MLLM performance on various domain-specific tasks. Finally, we fully open-source our models, code, and data to encourage future research in this area.
Authors: Luca Colombo, Fabrizio Pittorino, Manuel Roveri
Abstract: Binary Neural Networks (BNNs) significantly reduce computational complexity and memory usage in machine and deep learning by representing weights and activations with just one bit. However, most existing training algorithms for BNNs rely on quantization-aware floating-point Stochastic Gradient Descent (SGD), limiting the full exploitation of binary operations to the inference phase only. In this work, we propose, for the first time, a fully binary and gradient-free training algorithm for multi-layer BNNs, eliminating the need for back-propagated floating-point gradients. Specifically, the proposed algorithm relies on local binary error signals and binary weight updates, employing integer-valued hidden weights that serve as a synaptic metaplasticity mechanism, thereby enhancing its neurobiological plausibility. Our proposed solution enables the training of binary multi-layer perceptrons by using exclusively XNOR, Popcount, and increment/decrement operations. Experimental results on multi-class classification benchmarks show test accuracy improvements of up to +35.47% over the only existing fully binary single-layer state-of-the-art solution. Compared to full-precision SGD, our solution improves test accuracy by up to +35.30% under the same total memory demand, while also reducing computational cost by two to three orders of magnitude in terms of the total number of Boolean gates. The proposed algorithm is made available to the scientific community as a public repository.
Authors: Roberto Daza, Alvaro Becerra, Ruth Cobos, Julian Fierrez, Aythami Morales
Abstract: This work presents the IMPROVE dataset, a multimodal resource designed to evaluate the effects of mobile phone usage on learners during online education. It includes behavioral, biometric, physiological, and academic performance data collected from 120 learners divided into three groups with different levels of phone interaction, enabling the analysis of the impact of mobile phone usage and related phenomena such as nomophobia. A setup involving 16 synchronized sensors -- including EEG, eye tracking, video cameras, smartwatches, and keystroke dynamics -- was used to monitor learner activity during 30-minute sessions involving educational videos, document reading, and multiple-choice tests. Mobile phone usage events, including both controlled interventions and uncontrolled interactions, were labeled by supervisors and refined through a semi-supervised re-labeling process. Technical validation confirmed signal quality, and statistical analyses revealed biometric changes associated with phone usage. The dataset is publicly available for research through GitHub and Science Data Bank, with synchronized recordings from three platforms (edBB, edX, and LOGGE), provided in standard formats (.csv, .mp4, .wav, and .tsv), and accompanied by a detailed guide.
Authors: Tuo Feng, Wenguan Wang, Yi Yang
Abstract: Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin technology, offering high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics. This paper systematically reviews recent advances in world models for autonomous driving, proposing a three-tiered taxonomy: (i) Generation of Future Physical World, covering Image-, BEV-, OG-, and PC-based generation methods that enhance scene evolution modeling through diffusion models and 4D occupancy forecasting; (ii) Behavior Planning for Intelligent Agents, combining rule-driven and learning-based paradigms with cost map optimization and reinforcement learning for trajectory generation in complex traffic conditions; (ii) Interaction between Prediction and Planning, achieving multi-agent collaborative decision-making through latent space diffusion and memory-augmented architectures. The study further analyzes training paradigms, including self-supervised learning, multimodal pretraining, and generative data augmentation, while evaluating world models' performance in scene understanding and motion prediction tasks. Future research must address key challenges in self-supervised representation learning, long-tail scenario generation, and multimodal fusion to advance the practical deployment of world models in complex urban environments. Overall, the comprehensive analysis provides a technical roadmap for harnessing the transformative potential of world models in advancing safe and reliable autonomous driving solutions.
Authors: Hitvarth Diwanji, Jing-Yan Liao, Akshar Tumu, Henrik I. Christensen, Marcell Vazquez-Chanlatte, Chikao Tsuchiya
Abstract: High-definition maps (HD maps) are detailed and informative maps capturing lane centerlines and road elements. Although very useful for autonomous driving, HD maps are costly to build and maintain. Furthermore, access to these high-quality maps is usually limited to the firms that build them. On the other hand, standard definition (SD) maps provide road centerlines with an accuracy of a few meters. In this paper, we explore the possibility of enhancing SD maps by incorporating information from road manuals using LLMs. We develop SD++, an end-to-end pipeline to enhance SD maps with location-dependent road information obtained from a road manual. We suggest and compare several ways of using LLMs for such a task. Furthermore, we show the generalization ability of SD++ by showing results from both California and Japan.
Authors: Zefan Yang, Xuanang Xu, Jiajin Zhang, Ge Wang, Mannudeep K. Kalra, Pingkun Yan
Abstract: Chest X-ray (CXR) is the most frequently ordered imaging test, supporting diverse clinical tasks from thoracic disease detection to postoperative monitoring. However, task-specific classification models are limited in scope, require costly labeled data, and lack generalizability to out-of-distribution datasets. To address these challenges, we introduce CheXFound, a self-supervised vision foundation model that learns robust CXR representations and generalizes effectively across a wide range of downstream tasks. We pretrain CheXFound on a curated CXR-1M dataset, comprising over one million unique CXRs from publicly available sources. We propose a Global and Local Representations Integration (GLoRI) module for downstream adaptations, by incorporating disease-specific local features with global image features for enhanced performance in multilabel classification. Our experimental results show that CheXFound outperforms state-of-the-art models in classifying 40 disease findings across different prevalence levels on the CXR-LT 24 dataset and exhibits superior label efficiency on downstream tasks with limited training data. Additionally, CheXFound achieved significant improvements on new tasks with out-of-distribution datasets, including opportunistic cardiovascular disease risk estimation and mortality prediction. These results highlight CheXFound's strong generalization capabilities, enabling diverse adaptations with improved label efficiency. The project source code is publicly available at https://github.com/RPIDIAL/CheXFound.
Authors: Elias Kempf, Simon Schrodi, Max Argus, Thomas Brox
Abstract: The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely unseen domain when trained on a diverse mixture of domains (domain generalization)? Can it generalize to unseen classes within partially seen domains (compositional generalization)? What factors affect such generalization? To answer these questions, we trained CLIP models on systematically constructed training distributions with controlled domain diversity and object class exposure. Our experiments show that domain diversity is essential for both domain and compositional generalization, yet compositional generalization can be surprisingly weaker than domain generalization when the training distribution contains a suboptimal subset of the test domain. Through data-centric and mechanistic analyses, we find that successful generalization requires the learning of sufficiently shared representations in intermediate layers and circuits.
Authors: Anita Srbinovska, Angela Srbinovska, Vivek Senthil, Adrian Martin, John McCluskey, Jonathan Bateman, Ernest Fokou\'e
Abstract: This paper proposes a novel interdisciplinary framework for analyzing police body-worn camera (BWC) footage from the Rochester Police Department (RPD) using advanced artificial intelligence (AI) and statistical machine learning (ML) techniques. Our goal is to detect, classify, and analyze patterns of interaction between police officers and civilians to identify key behavioral dynamics, such as respect, disrespect, escalation, and de-escalation. We apply multimodal data analysis by integrating image, audio, and natural language processing (NLP) techniques to extract meaningful insights from BWC footage. The framework incorporates speaker separation, transcription, and large language models (LLMs) to produce structured, interpretable summaries of police-civilian encounters. We also employ a custom evaluation pipeline to assess transcription quality and behavior detection accuracy in high-stakes, real-world policing scenarios. Our methodology, computational techniques, and findings outline a practical approach for law enforcement review, training, and accountability processes while advancing the frontiers of knowledge discovery from complex police BWC data.
Authors: Xiaohui Wang, Peng Ye, Chenyu Huang, Shenghe Zheng, Bo Zhang, Lei Bai, Wanli Ouyang, Tao Chen
Abstract: With the rise of the fine-tuned--pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information. (2) Distribution-Aware Compression applies uniform quantization and then groups parameters by value, followed by group-wise pruning, to better preserve intra-layer distribution. (3) Trace-Norm-Guided Rescaling uses the trace norm of delta weights to estimate a global rescaling factor, improving model stability under higher compression. Extensive experiments across (a) large language models (fine-tuned on LLaMA-2 7B and 13B) with up to 133x, (b) general NLP models (RoBERTa-base, T5-base) with up to 800x, (c) vision models (ViT-B/32, ViT-L/14) with up to 400x, and (d) multi-modal models (BEiT-3) with 40x compression ratio, demonstrate that UltraDelta consistently outperforms existing methods, especially under ultra-high compression.
Authors: Shuvashis Sarker, Shamim Rahim Refat, Faika Fairuj Preotee, Tanvir Rouf Shawon, Raihan Tanvir
Abstract: Advanced diagnostic instruments are crucial for the accurate detection and treatment of lung diseases, which affect millions of individuals globally. This study examines the effectiveness of deep learning and transfer learning models using a hybrid dataset, created by merging four individual datasets from Bangladesh and global sources. The hybrid dataset significantly enhances model accuracy and generalizability, particularly in detecting COVID-19, pneumonia, lung opacity, and normal lung conditions from chest X-ray images. A range of models, including CNN, VGG16, VGG19, InceptionV3, Xception, ResNet50V2, InceptionResNetV2, MobileNetV2, and DenseNet121, were applied to both individual and hybrid datasets. The results showed superior performance on the hybrid dataset, with VGG16, Xception, ResNet50V2, and DenseNet121 each achieving an accuracy of 99%. This consistent performance across the hybrid dataset highlights the robustness of these models in handling diverse data while maintaining high accuracy. To understand the models implicit behavior, explainable AI techniques were employed to illuminate their black-box nature. Specifically, LIME was used to enhance the interpretability of model predictions, especially in cases of misclassification, contributing to the development of reliable and interpretable AI-driven solutions for medical imaging.
Authors: Chengzhi Liu, Zhongxing Xu, Qingyue Wei, Juncheng Wu, James Zou, Xin Eric Wang, Yuyin Zhou, Sheng Liu
Abstract: Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability often comes with increased hallucination: as generations become longer, models tend to drift away from image-grounded content and rely more heavily on language priors. Attention analysis shows that longer reasoning chains lead to reduced focus on visual inputs, which contributes to hallucination. To systematically study this phenomenon, we introduce RH-AUC, a metric that quantifies how a model's perception accuracy changes with reasoning length, allowing us to evaluate whether the model preserves visual grounding during reasoning. We also release RH-Bench, a diagnostic benchmark that spans a variety of multimodal tasks, designed to assess the trade-off between reasoning ability and hallucination. Our analysis reveals that (i) larger models typically achieve a better balance between reasoning and perception, and (ii) this balance is influenced more by the types and domains of training data than by its overall volume. These findings underscore the importance of evaluation frameworks that jointly consider both reasoning quality and perceptual fidelity.
Authors: Mingxu Zhang, Xiaoqi Li, Jiahui Xu, Kaichen Zhou, Hojin Bae, Yan Shen, Chuyan Xiong, Hao Dong
Abstract: Recent advancements in 3D robotic manipulation have improved grasping of everyday objects, but transparent and specular materials remain challenging due to depth sensing limitations. While several 3D reconstruction and depth completion approaches address these challenges, they suffer from setup complexity or limited observation information utilization. To address this, leveraging the power of single view 3D object reconstruction approaches, we propose a training free framework SR3D that enables robotic grasping of transparent and specular objects from a single view observation. Specifically, given single view RGB and depth images, SR3D first uses the external visual models to generate 3D reconstructed object mesh based on RGB image. Then, the key idea is to determine the 3D object's pose and scale to accurately localize the reconstructed object back into its original depth corrupted 3D scene. Therefore, we propose view matching and keypoint matching mechanisms,which leverage both the 2D and 3D's inherent semantic and geometric information in the observation to determine the object's 3D state within the scene, thereby reconstructing an accurate 3D depth map for effective grasp detection. Experiments in both simulation and real world show the reconstruction effectiveness of SR3D.
Authors: Sujeevan Aseervatham, Achraf Kerzazi, Youn\`es Bennani
Abstract: Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a specific trigger into the input. This attack is performed during the training phase, where the adversary corrupts a small subset of the training data by embedding a pattern and modifying the labels to a chosen target. The objective is to make the model associate the pattern with the target label while maintaining normal performance on unaltered data. Several defense mechanisms have been proposed to sanitize training data-sets. However, these methods often rely on the availability of a clean dataset to compute statistical anomalies, which may not always be feasible in real-world scenarios where datasets can be unavailable or compromised. To address this limitation, we propose a novel defense method that trains a model on the given dataset, detects poisoned classes, and extracts the critical part of the attack trigger before identifying the poisoned instances. This approach enhances explainability by explicitly revealing the harmful part of the trigger. The effectiveness of our method is demonstrated through experimental evaluations on well-known image datasets and comparative analysis against three state-of-the-art algorithms: SCAn, ABL, and AGPD.
Authors: Haiyang Guo, Fanhu Zeng, Fei Zhu, Jiayi Wang, Xukai Wang, Jingang Zhou, Hongbo Zhao, Wenzhuo Liu, Shijie Ma, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu
Abstract: The rapid advancement of generative models has enabled modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specific domains. However, these models remain fundamentally constrained by catastrophic forgetting - a persistent challenge where adapting to new tasks typically leads to significant degradation in performance on previously learned tasks. To address this practical limitation, numerous approaches have been proposed to enhance the adaptability and scalability of generative models in real-world applications. In this work, we present a comprehensive survey of continual learning methods for mainstream generative models, including large language models, multimodal large language models, vision language action models, and diffusion models. Drawing inspiration from the memory mechanisms of the human brain, we systematically categorize these approaches into three paradigms: architecture-based, regularization-based, and replay-based methods, while elucidating their underlying methodologies and motivations. We further analyze continual learning setups for different generative models, including training objectives, benchmarks, and core backbones, offering deeper insights into the field. The project page of this paper is available at https://github.com/Ghy0501/Awesome-Continual-Learning-in-Generative-Models.
URLs: https://github.com/Ghy0501/Awesome-Continual-Learning-in-Generative-Models.
Authors: Jonghun Kim, Gyeongdeok Jo, Sinyoung Ra, Hyunjin Park
Abstract: Medical imaging data contain sensitive patient information requiring strong privacy protection. Many analytical setups require data to be sent to a server for inference purposes. Homomorphic encryption (HE) provides a solution by allowing computations to be performed on encrypted data without revealing the original information. However, HE inference is computationally expensive, particularly for large images (e.g., chest X-rays). In this study, we propose an HE inference framework for medical images that uses VQGAN to compress images into latent representations, thereby significantly reducing the computational burden while preserving image quality. We approximate the activation functions with lower-degree polynomials to balance the accuracy and efficiency in compliance with HE requirements. We observed that a downsampling factor of eight for compression achieved an optimal balance between performance and computational cost. We further adapted the squeeze and excitation module, which is known to improve traditional CNNs, to enhance the HE framework. Our method was tested on two chest X-ray datasets for multi-label classification tasks using vanilla CNN backbones. Although HE inference remains relatively slow and introduces minor performance differences compared with unencrypted inference, our approach shows strong potential for practical use in medical images
Authors: Yining Hong, Rui Sun, Bingxuan Li, Xingcheng Yao, Maxine Wu, Alexander Chien, Da Yin, Ying Nian Wu, Zhecan James Wang, Kai-Wei Chang
Abstract: AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the Embodied Web Agents task environments, a unified simulation platform that tightly integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the Embodied Web Agents Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation - all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access. All datasets, codes and websites are publicly available at our project page https://embodied-web-agent.github.io/.