Authors: Tongshun Zhang, Pingping Liu, Yubing Lu, Mengen Cai, Zijian Zhang, Zhe Zhang, Qiuzhan Zhou
Abstract: Traditional Low-Light Image Enhancement (LLIE) methods primarily focus on uniform brightness adjustment, often neglecting instance-level semantic information and the inherent characteristics of different features. To address these limitations, we propose CWNet (Causal Wavelet Network), a novel architecture that leverages wavelet transforms for causal reasoning. Specifically, our approach comprises two key components: 1) Inspired by the concept of intervention in causality, we adopt a causal reasoning perspective to reveal the underlying causal relationships in low-light enhancement. From a global perspective, we employ a metric learning strategy to ensure causal embeddings adhere to causal principles, separating them from non-causal confounding factors while focusing on the invariance of causal factors. At the local level, we introduce an instance-level CLIP semantic loss to precisely maintain causal factor consistency. 2) Based on our causal analysis, we present a wavelet transform-based backbone network that effectively optimizes the recovery of frequency information, ensuring precise enhancement tailored to the specific attributes of wavelet transforms. Extensive experiments demonstrate that CWNet significantly outperforms current state-of-the-art methods across multiple datasets, showcasing its robust performance across diverse scenes. Code is available at https://github.com/bywlzts/CWNet-Causal-Wavelet-Network.
URLs: https://github.com/bywlzts/CWNet-Causal-Wavelet-Network.
Authors: Jiayuan Chen, Thai-Hoang Pham, Yuanlong Wang, Ping Zhang
Abstract: High-throughput screening techniques, such as microscopy imaging of cellular responses to genetic and chemical perturbations, play a crucial role in drug discovery and biomedical research. However, robust perturbation screening for \textit{de novo} cell lines remains challenging due to the significant morphological and biological heterogeneity across cell lines. To address this, we propose a novel framework that integrates external biological knowledge into existing pretraining strategies to enhance microscopy image profiling models. Our approach explicitly disentangles perturbation-specific and cell line-specific representations using external biological information. Specifically, we construct a knowledge graph leveraging protein interaction data from STRING and Hetionet databases to guide models toward perturbation-specific features during pretraining. Additionally, we incorporate transcriptomic features from single-cell foundation models to capture cell line-specific representations. By learning these disentangled features, our method improves the generalization of imaging models to \textit{de novo} cell lines. We evaluate our framework on the RxRx database through one-shot fine-tuning on an RxRx1 cell line and few-shot fine-tuning on cell lines from the RxRx19a dataset. Experimental results demonstrate that our method enhances microscopy image profiling for \textit{de novo} cell lines, highlighting its effectiveness in real-world phenotype-based drug discovery applications.
Authors: Rina Khan, Catherine Stinson
Abstract: Facial expression recognition (FER) algorithms classify facial expressions into emotions such as happy, sad, or angry. An evaluative challenge facing FER algorithms is the fall in performance when detecting spontaneous expressions compared to posed expressions. An ethical (and evaluative) challenge facing FER algorithms is that they tend to perform poorly for people of some races and skin colors. These challenges are linked to the data collection practices employed in the creation of FER datasets. In this study, we audit two state-of-the-art FER datasets. We take random samples from each dataset and examine whether images are spontaneous or posed. In doing so, we propose a methodology for identifying spontaneous or posed images. We discover a significant number of images that were posed in the datasets purporting to consist of in-the-wild images. Since performance of FER models vary between spontaneous and posed images, the performance of models trained on these datasets will not represent the true performance if such models were to be deployed in in-the-wild applications. We also observe the skin color of individuals in the samples, and test three models trained on each of the datasets to predict facial expressions of people from various races and skin tones. We find that the FER models audited were more likely to predict people labeled as not white or determined to have dark skin as showing a negative emotion such as anger or sadness even when they were smiling. This bias makes such models prone to perpetuate harm in real life applications.
Authors: Ionu\c{t} Grigore, C\u{a}lin-Adrian Popa, Claudiu Leoveanu-Condrei
Abstract: The extraction and matching of interest points are fundamental to many geometric computer vision tasks. Traditionally, matching is performed by assigning descriptors to interest points and identifying correspondences based on descriptor similarity. This work introduces a technique where interest points are inherently associated during detection, eliminating the need for computing, storing, transmitting, or matching descriptors. Although the matching accuracy is marginally lower than that of conventional approaches, our method completely eliminates the need for descriptors, leading to a drastic reduction in memory usage for localization systems. We assess its effectiveness by comparing it against both classical handcrafted methods and modern learned approaches.
Authors: Jeffrey Joan Sam, Janhavi Sathe, Nikhil Chigali, Naman Gupta, Radhey Ruparel, Yicheng Jiang, Janmajay Singh, James W. Berck, Arko Barman
Abstract: Spacecraft deployed in outer space are routinely subjected to various forms of damage due to exposure to hazardous environments. In addition, there are significant risks to the subsequent process of in-space repairs through human extravehicular activity or robotic manipulation, incurring substantial operational costs. Recent developments in image segmentation could enable the development of reliable and cost-effective autonomous inspection systems. While these models often require large amounts of training data to achieve satisfactory results, publicly available annotated spacecraft segmentation data are very scarce. Here, we present a new dataset of nearly 64k annotated spacecraft images that was created using real spacecraft models, superimposed on a mixture of real and synthetic backgrounds generated using NASA's TTALOS pipeline. To mimic camera distortions and noise in real-world image acquisition, we also added different types of noise and distortion to the images. Finally, we finetuned YOLOv8 and YOLOv11 segmentation models to generate performance benchmarks for the dataset under well-defined hardware and inference time constraints to mimic real-world image segmentation challenges for real-time onboard applications in space on NASA's inspector spacecraft. The resulting models, when tested under these constraints, achieved a Dice score of 0.92, Hausdorff distance of 0.69, and an inference time of about 0.5 second. The dataset and models for performance benchmark are available at https://github.com/RiceD2KLab/SWiM.
Authors: Hsiang-Wei Huang, Jen-Hao Cheng, Kuang-Ming Chen, Cheng-Yen Yang, Bahaa Alattar, Yi-Ru Lin, Pyongkun Kim, Sangwon Kim, Kwangju Kim, Chung-I Huang, Jenq-Neng Hwang
Abstract: Spatial understanding has been a challenging task for existing Multi-modal Large Language Models~(MLLMs). Previous methods leverage large-scale MLLM finetuning to enhance MLLM's spatial understanding ability. In this paper, we present a data-efficient approach. We propose a LLM agent system with strong and advanced spatial reasoning ability, which can be used to solve the challenging spatial question answering task in complex indoor warehouse scenarios. Our system integrates multiple tools that allow the LLM agent to conduct spatial reasoning and API tools interaction to answer the given complicated spatial question. Extensive evaluations on the 2025 AI City Challenge Physical AI Spatial Intelligence Warehouse dataset demonstrate that our system achieves high accuracy and efficiency in tasks such as object retrieval, counting, and distance estimation. The code is available at: https://github.com/hsiangwei0903/SpatialAgent
Authors: Ali Hojjat, Janek Haberer, Soren Pirk, Olaf Landsiedel
Abstract: Vision Transformers deliver state-of-the-art performance, yet their fixed computational budget prevents scalable deployment across heterogeneous hardware. Recent nested Transformer architectures mitigate this by embedding nested subnetworks within a single model to enable scalable inference. However, these models allocate the same amount of compute to all inputs, regardless of their complexity, which leads to inefficiencies. To address this, we introduce ThinkingViT, a nested ViT architecture that employs progressive thinking stages to dynamically adjust inference computation based on input difficulty. ThinkingViT initiates inference by activating a small subset of the most important attention heads and terminates early if predictions reach sufficient certainty. Otherwise, it activates additional attention heads and re-evaluates the input. At the core of ThinkingViT is our Token Recycling mechanism, which conditions each subsequent inference stage on the embeddings from the previous stage, enabling progressive improvement. Due to its backbone-preserving design, ThinkingViT also serves as a plugin upgrade for vanilla ViT. Experiments show that ThinkingViT surpasses nested baselines by up to 2.0 percentage points (p.p.) in accuracy at the same throughput and by up to 2.9 p.p. at equal GMACs on ImageNet-1K. The source code is available at https://github.com/ds-kiel/ThinkingViT.
Authors: Furkan Mumcu, Michael J. Jones, Anoop Cherian, Yasin Yilmaz
Abstract: Object detection traditionally relies on fixed category sets, requiring costly re-training to handle novel objects. While Open-World and Open-Vocabulary Object Detection (OWOD and OVOD) improve flexibility, OWOD lacks semantic labels for unknowns, and OVOD depends on user prompts, limiting autonomy. We propose an LLM-guided agentic object detection (LAOD) framework that enables fully label-free, zero-shot detection by prompting a Large Language Model (LLM) to generate scene-specific object names. These are passed to an open-vocabulary detector for localization, allowing the system to adapt its goals dynamically. We introduce two new metrics, Class-Agnostic Average Precision (CAAP) and Semantic Naming Average Precision (SNAP), to separately evaluate localization and naming. Experiments on LVIS, COCO, and COCO-OOD validate our approach, showing strong performance in detecting and naming novel objects. Our method offers enhanced autonomy and adaptability for open-world understanding.
Authors: Casey Wall, Longwei Wang, Rodrigue Rizk, KC Santosh
Abstract: Interpreting the decision-making process of Convolutional Neural Networks (CNNs) is critical for deploying models in high-stakes domains. Gradient-weighted Class Activation Mapping (Grad-CAM) is a widely used method for visual explanations, yet it typically focuses on the final convolutional layer or na\"ively averages across layers, strategies that can obscure important semantic cues or amplify irrelevant noise. We propose Winsor-CAM, a novel, human-tunable extension of Grad-CAM that generates robust and coherent saliency maps by aggregating information across all convolutional layers. To mitigate the influence of noisy or extreme attribution values, Winsor-CAM applies Winsorization, a percentile-based outlier attenuation technique. A user-controllable threshold allows for semantic-level tuning, enabling flexible exploration of model behavior across representational hierarchies. Evaluations on standard architectures (ResNet50, DenseNet121, VGG16, InceptionV3) using the PASCAL VOC 2012 dataset demonstrate that Winsor-CAM produces more interpretable heatmaps and achieves superior performance in localization metrics, including intersection-over-union and center-of-mass alignment, when compared to Grad-CAM and uniform layer-averaging baselines. Winsor-CAM advances the goal of trustworthy AI by offering interpretable, multi-layer insights with human-in-the-loop control.
Authors: Wei Chen, Jingxi Yu, Zichen Miao, Qiang Qiu
Abstract: Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch. However, in existing fine-tuning methods, the updated representations are formed as a dense combination of modified parameters, making it challenging to interpret their contributions and understand how the model adapts to new tasks. In this work, we introduce a fine-tuning framework inspired by sparse coding, where fine-tuned features are represented as a sparse combination of basic elements, i.e., feature dictionary atoms. The feature dictionary atoms function as fundamental building blocks of the representation, and tuning atoms allows for seamless adaptation to downstream tasks. Sparse coefficients then serve as indicators of atom importance, identifying the contribution of each atom to the updated representation. Leveraging the atom selection capability of sparse coefficients, we first demonstrate that our method enhances image editing performance by improving text alignment through the removal of unimportant feature dictionary atoms. Additionally, we validate the effectiveness of our approach in the text-to-image concept customization task, where our method efficiently constructs the target concept using a sparse combination of feature dictionary atoms, outperforming various baseline fine-tuning methods.
Authors: Saadat Behzadi, Danial Sharifrazi, Bita Mesbahzadeh, Javad Hassannataj Joloudarid, Roohallah Alizadehsani
Abstract: Objectives: Timely and accurate detection of colorectal polyps plays a crucial role in diagnosing and preventing colorectal cancer, a major cause of mortality worldwide. This study introduces a new, lightweight, and efficient framework for polyp detection that combines the Local Outlier Factor (LOF) algorithm for filtering noisy data with the YOLO-v11n deep learning model. Study design: An experimental study leveraging deep learning and outlier removal techniques across multiple public datasets. Methods: The proposed approach was tested on five diverse and publicly available datasets: CVC-ColonDB, CVC-ClinicDB, Kvasir-SEG, ETIS, and EndoScene. Since these datasets originally lacked bounding box annotations, we converted their segmentation masks into suitable detection labels. To enhance the robustness and generalizability of our model, we apply 5-fold cross-validation and remove anomalous samples using the LOF method configured with 30 neighbors and a contamination ratio of 5%. Cleaned data are then fed into YOLO-v11n, a fast and resource-efficient object detection architecture optimized for real-time applications. We train the model using a combination of modern augmentation strategies to improve detection accuracy under diverse conditions. Results: Our approach significantly improves polyp localization performance, achieving a precision of 95.83%, recall of 91.85%, F1-score of 93.48%, mAP@0.5 of 96.48%, and mAP@0.5:0.95 of 77.75%. Compared to previous YOLO-based methods, our model demonstrates enhanced accuracy and efficiency. Conclusions: These results suggest that the proposed method is well-suited for real-time colonoscopy support in clinical settings. Overall, the study underscores how crucial data preprocessing and model efficiency are when designing effective AI systems for medical imaging.
Authors: Roman Naeem, David Hagerman, Jennifer Alv\'en, Lennart Svensson, Fredrik Kahl
Abstract: Tubular tree structures, such as blood vessels and airways, are essential in human anatomy and accurately tracking them while preserving their topology is crucial for various downstream tasks. Trexplorer is a recurrent model designed for centerline tracking in 3D medical images but it struggles with predicting duplicate branches and terminating tracking prematurely. To address these issues, we present Trexplorer Super, an enhanced version that notably improves performance through novel advancements. However, evaluating centerline tracking models is challenging due to the lack of public datasets. To enable thorough evaluation, we develop three centerline datasets, one synthetic and two real, each with increasing difficulty. Using these datasets, we conduct a comprehensive evaluation of existing state-of-the-art (SOTA) models and compare them with our approach. Trexplorer Super outperforms previous SOTA models on every dataset. Our results also highlight that strong performance on synthetic data does not necessarily translate to real datasets. The code and datasets are available at https://github.com/RomStriker/Trexplorer-Super.
Authors: Minjong Cheon, Eunhan Goo, Su-Hyeon Shin, Muhammad Ahmed, Hyungjun Kim
Abstract: Recently, AI-based weather forecast models have achieved impressive advances. These models have reached accuracy levels comparable to traditional NWP systems, marking a significant milestone in data-driven weather prediction. However, they mostly leverage Transformer-based architectures, which often leads to high training complexity and resource demands due to the massive parameter sizes. In this study, we introduce a modernized CNN-based model for global weather forecasting that delivers competitive accuracy while significantly reducing computational requirements. To present a systematic modernization roadmap, we highlight key architectural enhancements across multiple design scales from an earlier CNN-based approach. KAI-a incorporates a scale-invariant architecture and InceptionNeXt-based blocks within a geophysically-aware design, tailored to the structure of Earth system data. Trained on the ERA5 daily dataset with 67 atmospheric variables, the model contains about 7 million parameters and completes training in just 12 hours on a single NVIDIA L40s GPU. Our evaluation shows that KAI-a matches the performance of state-of-the-art models in medium-range weather forecasting, while offering a significantly lightweight design. Furthermore, case studies on the 2018 European heatwave and the East Asian summer monsoon demonstrate KAI-a's robust skill in capturing extreme events, reinforcing its practical utility.
Authors: Xiaocong Zeng, Craig Michoski, Yan Pang, Dongyang Kuang
Abstract: In this work, we address the often-overlooked issue of Timescale Dependent Label Inconsistency (TsDLI) in training neural network models for EEG-based human emotion recognition. To mitigate TsDLI and enhance model generalization and explainability, we propose two novel regularization strategies: Local Variation Loss (LVL) and Local-Global Consistency Loss (LGCL). Both methods incorporate classical mathematical principles--specifically, functions of bounded variation and commute-time distances--within a graph theoretic framework. Complementing our regularizers, we introduce a suite of new evaluation metrics that better capture the alignment between temporally local predictions and their associated global emotion labels. We validate our approach through comprehensive experiments on two widely used EEG emotion datasets, DREAMER and DEAP, across a range of neural architectures including LSTM and transformer-based models. Performance is assessed using five distinct metrics encompassing both quantitative accuracy and qualitative consistency. Results consistently show that our proposed methods outperform state-of-the-art baselines, delivering superior aggregate performance and offering a principled trade-off between interpretability and predictive power under label inconsistency. Notably, LVL achieves the best aggregate rank across all benchmarked backbones and metrics, while LGCL frequently ranks the second, highlighting the effectiveness of our framework.
Authors: Shaowen Tong, Zimin Xia, Alexandre Alahi, Xuming He, Yujiao Shi
Abstract: Cross-view localization, the task of estimating a camera's 3-degrees-of-freedom (3-DoF) pose by aligning ground-level images with satellite images, is crucial for large-scale outdoor applications like autonomous navigation and augmented reality. Existing methods often rely on fully supervised learning, which requires costly ground-truth pose annotations. In this work, we propose GeoDistill, a Geometry guided weakly supervised self distillation framework that uses teacher-student learning with Field-of-View (FoV)-based masking to enhance local feature learning for robust cross-view localization. In GeoDistill, the teacher model localizes a panoramic image, while the student model predicts locations from a limited FoV counterpart created by FoV-based masking. By aligning the student's predictions with those of the teacher, the student focuses on key features like lane lines and ignores textureless regions, such as roads. This results in more accurate predictions and reduced uncertainty, regardless of whether the query images are panoramas or limited FoV images. Our experiments show that GeoDistill significantly improves localization performance across different frameworks. Additionally, we introduce a novel orientation estimation network that predicts relative orientation without requiring precise planar position ground truth. GeoDistill provides a scalable and efficient solution for real-world cross-view localization challenges. Code and model can be found at https://github.com/tongshw/GeoDistill.
Authors: Zhengyi Xu, Haoran Wu, Wen Jiang, Jie Geng
Abstract: Semantic change detection (SCD) extends the binary change detection task to provide not only the change locations but also the detailed "from-to" categories in multi-temporal remote sensing data. Such detailed semantic insights into changes offer considerable advantages for a wide array of applications. However, since SCD involves the simultaneous optimization of multiple tasks, the model is prone to negative transfer due to task-specific learning difficulties and conflicting gradient flows. To address this issue, we propose Graph Aggregation Prototype Learning for Semantic Change Detection in remote sensing(GAPL-SCD). In this framework, a multi-task joint optimization method is designed to optimize the primary task of semantic segmentation and change detection, along with the auxiliary task of graph aggregation prototype learning. Adaptive weight allocation and gradient rotation methods are used to alleviate the conflict between training tasks and improve multi-task learning capabilities. Specifically, the graph aggregation prototype learning module constructs an interaction graph using high-level features. Prototypes serve as class proxies, enabling category-level domain alignment across time points and reducing interference from irrelevant changes. Additionally, the proposed self-query multi-level feature interaction and bi-temporal feature fusion modules further enhance multi-scale feature representation, improving performance in complex scenes. Experimental results on the SECOND and Landsat-SCD datasets demonstrate that our method achieves state-of-the-art performance, with significant improvements in accuracy and robustness for SCD task.
Authors: Yushun Fang, Lu Liu, Xiang Gao, Qiang Hu, Ning Cao, Jianghe Cui, Gang Chen, Xiaoyun Zhang
Abstract: The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs and stochastic generative processes remains unresolved. To address this challenge, we present Robust ID-Specific Face Restoration (RIDFR), a novel ID-specific face restoration framework based on diffusion models. Specifically, RIDFR leverages a pre-trained diffusion model in conjunction with two parallel conditioning modules. The Content Injection Module inputs the severely degraded image, while the Identity Injection Module integrates the specific identity from a given image. Subsequently, RIDFR incorporates Alignment Learning, which aligns the restoration results from multiple references with the same identity in order to suppress the interference of ID-irrelevant face semantics (e.g. pose, expression, make-up, hair style). Experiments demonstrate that our framework outperforms the state-of-the-art methods, reconstructing high-quality ID-specific results with high identity fidelity and demonstrating strong robustness.
Authors: Palash Ray, Mahuya Sasmal, Asish Bera
Abstract: Sports action classification representing complex body postures and player-object interactions is an emerging area in image-based sports analysis. Some works have contributed to automated sports action recognition using machine learning techniques over the past decades. However, sufficient image datasets representing women sports actions with enough intra- and inter-class variations are not available to the researchers. To overcome this limitation, this work presents a new dataset named WomenSports for women sports classification using small-scale training data. This dataset includes a variety of sports activities, covering wide variations in movements, environments, and interactions among players. In addition, this study proposes a convolutional neural network (CNN) for deep feature extraction. A channel attention scheme upon local contextual regions is applied to refine and enhance feature representation. The experiments are carried out on three different sports datasets and one dance dataset for generalizing the proposed algorithm, and the performances on these datasets are noteworthy. The deep learning method achieves 89.15% top-1 classification accuracy using ResNet-50 on the proposed WomenSports dataset, which is publicly available for research at Mendeley Data.
Authors: Quan Bi Pay, Vishnu Monn Baskaran, Junn Yong Loo, KokSheik Wong, Simon See
Abstract: Human-object interaction (HOI) detection is essential for accurately localizing and characterizing interactions between humans and objects, providing a comprehensive understanding of complex visual scenes across various domains. However, existing HOI detectors often struggle to deliver reliable predictions efficiently, relying on resource-intensive training methods and inefficient architectures. To address these challenges, we conceptualize a wavelet attention-like backbone and a novel ray-based encoder architecture tailored for HOI detection. Our wavelet backbone addresses the limitations of expressing middle-order interactions by aggregating discriminative features from the low- and high-order interactions extracted from diverse convolutional filters. Concurrently, the ray-based encoder facilitates multi-scale attention by optimizing the focus of the decoder on relevant regions of interest and mitigating computational overhead. As a result of harnessing the attenuated intensity of learnable ray origins, our decoder aligns query embeddings with emphasized regions of interest for accurate predictions. Experimental results on benchmark datasets, including ImageNet and HICO-DET, showcase the potential of our proposed architecture. The code is publicly available at [https://github.com/henry-pay/RayEncoder].
Authors: Ayush Gupta, Siyuan Huang, Rama Chellappa
Abstract: Gait is becoming popular as a method of person re-identification because of its ability to identify people at a distance. However, most current works in gait recognition do not address the practical problem of occlusions. Among those which do, some require paired tuples of occluded and holistic sequences, which are impractical to collect in the real world. Further, these approaches work on occlusions but fail to retain performance on holistic inputs. To address these challenges, we propose RG-Gait, a method for residual correction for occluded gait recognition with holistic retention. We model the problem as a residual learning task, conceptualizing the occluded gait signature as a residual deviation from the holistic gait representation. Our proposed network adaptively integrates the learned residual, significantly improving performance on occluded gait sequences without compromising the holistic recognition accuracy. We evaluate our approach on the challenging Gait3D, GREW and BRIAR datasets and show that learning the residual can be an effective technique to tackle occluded gait recognition with holistic retention.
Authors: Quan Bi Pay, Vishnu Monn Baskaran, Junn Yong Loo, KokSheik Wong, Simon See
Abstract: The resurgence of convolutional neural networks (CNNs) in visual recognition tasks, exemplified by ConvNeXt, has demonstrated their capability to rival transformer-based architectures through advanced training methodologies and ViT-inspired design principles. However, both CNNs and transformers exhibit a simplicity bias, favoring straightforward features over complex structural representations. Furthermore, modern CNNs often integrate MLP-like blocks akin to those in transformers, but these blocks suffer from significant information redundancies, necessitating high expansion ratios to sustain competitive performance. To address these limitations, we propose SpaRTAN, a lightweight architectural design that enhances spatial and channel-wise information processing. SpaRTAN employs kernels with varying receptive fields, controlled by kernel size and dilation factor, to capture discriminative multi-order spatial features effectively. A wave-based channel aggregation module further modulates and reinforces pixel interactions, mitigating channel-wise redundancies. Combining the two modules, the proposed network can efficiently gather and dynamically contextualize discriminative features. Experimental results in ImageNet and COCO demonstrate that SpaRTAN achieves remarkable parameter efficiency while maintaining competitive performance. In particular, on the ImageNet-1k benchmark, SpaRTAN achieves 77. 7% accuracy with only 3.8M parameters and approximately 1.0 GFLOPs, demonstrating its ability to deliver strong performance through an efficient design. On the COCO benchmark, it achieves 50.0% AP, surpassing the previous benchmark by 1.2% with only 21.5M parameters. The code is publicly available at [https://github.com/henry-pay/SpaRTAN].
Authors: Yuhu Bai, Jiangning Zhang, Yunkang Cao, Guangyuan Lu, Qingdong He, Xiangtai Li, Guanzhong Tian
Abstract: With the advent of vision-language models (e.g., CLIP) in zero- and few-shot settings, CLIP has been widely applied to zero-shot anomaly detection (ZSAD) in recent research, where the rare classes are essential and expected in many applications. This study introduces \textbf{FiSeCLIP} for ZSAD with training-free \textbf{CLIP}, combining the feature matching with the cross-modal alignment. Testing with the entire dataset is impractical, while batch-based testing better aligns with real industrial needs, and images within a batch can serve as mutual reference points. Accordingly, FiSeCLIP utilizes other images in the same batch as reference information for the current image. However, the lack of labels for these references can introduce ambiguity, we apply text information to \textbf{fi}lter out noisy features. In addition, we further explore CLIP's inherent potential to restore its local \textbf{se}mantic correlation, adapting it for fine-grained anomaly detection tasks to enable a more accurate filtering process. Our approach exhibits superior performance for both anomaly classification and segmentation on anomaly detection benchmarks, building a stronger baseline for the direction, e.g., on MVTec-AD, FiSeCLIP outperforms the SOTA AdaCLIP by +4.6\%$\uparrow$/+5.7\%$\uparrow$ in segmentation metrics AU-ROC/$F_1$-max.
Authors: Zeyi Hou, Zeqiang Wei, Ruixin Yan, Ning Lang, Xiuzhuang Zhou
Abstract: Recent advances in automated radiology report generation from chest X-rays using deep learning algorithms have the potential to significantly reduce the arduous workload of radiologists. However, due to the inherent massive data bias in radiology images, where abnormalities are typically subtle and sparsely distributed, existing methods often produce fluent yet medically inaccurate reports, limiting their applicability in clinical practice. To address this issue effectively, we propose a Semantically Informed Salient Regions-guided (SISRNet) report generation method. Specifically, our approach explicitly identifies salient regions with medically critical characteristics using fine-grained cross-modal semantics. Then, SISRNet systematically focuses on these high-information regions during both image modeling and report generation, effectively capturing subtle abnormal findings, mitigating the negative impact of data bias, and ultimately generating clinically accurate reports. Compared to its peers, SISRNet demonstrates superior performance on widely used IU-Xray and MIMIC-CXR datasets.
Authors: Sung Ho Kang, Hyun-Cheol Park
Abstract: We present a novel framework for CBCT-to-MDCT translation, grounded in the Schrodinger Bridge (SB) formulation, which integrates GAN-derived priors with human-guided conditional diffusion. Unlike conventional GANs or diffusion models, our approach explicitly enforces boundary consistency between CBCT inputs and pseudo targets, ensuring both anatomical fidelity and perceptual controllability. Binary human feedback is incorporated via classifier-free guidance (CFG), effectively steering the generative process toward clinically preferred outcomes. Through iterative refinement and tournament-based preference selection, the model internalizes human preferences without relying on a reward model. Subtraction image visualizations reveal that the proposed method selectively attenuates shade artifacts in key anatomical regions while preserving fine structural detail. Quantitative evaluations further demonstrate superior performance across RMSE, SSIM, LPIPS, and Dice metrics on clinical datasets -- outperforming prior GAN- and fine-tuning-based feedback methods -- while requiring only 10 sampling steps. These findings underscore the effectiveness and efficiency of our framework for real-time, preference-aligned medical image translation.
Authors: Sunghyun Park, Jungsoo Lee, Shubhankar Borse, Munawar Hayat, Sungha Choi, Kyuwoong Hwang, Fatih Porikli
Abstract: While open-vocabulary semantic segmentation (OVSS) can segment an image into semantic regions based on arbitrarily given text descriptions even for classes unseen during training, it fails to understand personal texts (e.g., `my mug cup') for segmenting regions of specific interest to users. This paper addresses challenges like recognizing `my mug cup' among `multiple mug cups'. To overcome this challenge, we introduce a novel task termed \textit{personalized open-vocabulary semantic segmentation} and propose a text prompt tuning-based plug-in method designed to recognize personal visual concepts using a few pairs of images and masks, while maintaining the performance of the original OVSS. Based on the observation that reducing false predictions is essential when applying text prompt tuning to this task, our proposed method employs `negative mask proposal' that captures visual concepts other than the personalized concept. We further improve the performance by enriching the representation of text prompts by injecting visual embeddings of the personal concept into them. This approach enhances personalized OVSS without compromising the original OVSS performance. We demonstrate the superiority of our method on our newly established benchmarks for this task, including FSS$^\text{per}$, CUB$^\text{per}$, and ADE$^\text{per}$.
Authors: Lirong Zheng, Yanshan Li, Rui Yu, Kaihao Zhang
Abstract: Transformer-based models exhibit strong global modeling capabilities in single-image dehazing, but their high computational cost limits real-time applicability. Existing methods predominantly rely on spatial-domain features to capture long-range dependencies, which are computationally expensive and often inadequate under complex haze conditions. While some approaches introduce frequency-domain cues, the weak coupling between spatial and frequency branches limits the overall performance. To overcome these limitations, we propose the Dark Channel Guided Frequency-aware Dehazing Network (DGFDNet), a novel dual-domain framework that performs physically guided degradation alignment across spatial and frequency domains. At its core, the DGFDBlock comprises two key modules: 1) the Haze-Aware Frequency Modulator (HAFM), which generates a pixel-level haze confidence map from dark channel priors to adaptively enhance haze-relevant frequency components, thereby achieving global degradation-aware spectral modulation; 2) the Multi-level Gating Aggregation Module (MGAM), which fuses multi-scale features through diverse convolutional kernels and hybrid gating mechanisms to recover fine structural details. Additionally, a Prior Correction Guidance Branch (PCGB) incorporates a closed-loop feedback mechanism, enabling iterative refinement of the prior by intermediate dehazed features and significantly improving haze localization accuracy, especially in challenging outdoor scenes. Extensive experiments on four benchmark haze datasets demonstrate that DGFDNet achieves state-of-the-art performance with superior robustness and real-time efficiency. Code is available at: https://github.com/Dilizlr/DGFDNet.
Authors: Jie-Wen Li, Zi-Han Ye, Qingyuan Zhou, Jiayi Song, Ying He, Ben Fei, Wen-Ming Chen
Abstract: The kinematics analysis of foot-ankle complex during gait is essential for advancing biomechanical research and clinical assessment. Collecting accurate surface geometry data from the foot and ankle during dynamic gait conditions is inherently challenging due to swing foot occlusions and viewing limitations. Thus, this paper introduces FootGait3D, a novel multi-view dataset of high-resolution ankle-foot surface point clouds captured during natural gait. Different from existing gait datasets that typically target whole-body or lower-limb motion, FootGait3D focuses specifically on the detailed modeling of the ankle-foot region, offering a finer granularity of motion data. To address this, FootGait3D consists of 8,403 point cloud frames collected from 46 subjects using a custom five-camera depth sensing system. Each frame includes a complete 5-view reconstruction of the foot and ankle (serving as ground truth) along with partial point clouds obtained from only four, three, or two views. This structured variation enables rigorous evaluation of 3D point cloud completion methods under varying occlusion levels and viewpoints. Our dataset is designed for shape completion tasks, facilitating the benchmarking of state-of-the-art single-modal (e.g., PointTr, SnowflakeNet, Anchorformer) and multi-modal (e.g., SVDFormer, PointSea, CSDN) completion networks on the challenge of recovering the full foot geometry from occluded inputs. FootGait3D has significant potential to advance research in biomechanics and multi-segment foot modeling, offering a valuable testbed for clinical gait analysis, prosthetic design, and robotics applications requiring detailed 3D models of the foot during motion. The dataset is now available at https://huggingface.co/datasets/ljw285/FootGait3D.
Authors: Nicolas Drapier, Aladine Chetouani, Aur\'elien Chateigner
Abstract: We present GLOD, a transformer-first architecture for object detection in high-resolution satellite imagery. GLOD replaces CNN backbones with a Swin Transformer for end-to-end feature extraction, combined with novel UpConvMixer blocks for robust upsampling and Fusion Blocks for multi-scale feature integration. Our approach achieves 32.95\% on xView, outperforming SOTA methods by 11.46\%. Key innovations include asymmetric fusion with CBAM attention and a multi-path head design capturing objects across scales. The architecture is optimized for satellite imagery challenges, leveraging spatial priors while maintaining computational efficiency.
Authors: Shuchang Ye, Usman Naseem, Mingyuan Meng, Jinman Kim
Abstract: Medical language-guided segmentation, integrating textual clinical reports as auxiliary guidance to enhance image segmentation, has demonstrated significant improvements over unimodal approaches. However, its inherent reliance on paired image-text input, which we refer to as ``textual reliance", presents two fundamental limitations: 1) many medical segmentation datasets lack paired reports, leaving a substantial portion of image-only data underutilized for training; and 2) inference is limited to retrospective analysis of cases with paired reports, limiting its applicability in most clinical scenarios where segmentation typically precedes reporting. To address these limitations, we propose ProLearn, the first Prototype-driven Learning framework for language-guided segmentation that fundamentally alleviates textual reliance. At its core, we introduce a novel Prototype-driven Semantic Approximation (PSA) module to enable approximation of semantic guidance from textual input. PSA initializes a discrete and compact prototype space by distilling segmentation-relevant semantics from textual reports. Once initialized, it supports a query-and-respond mechanism which approximates semantic guidance for images without textual input, thereby alleviating textual reliance. Extensive experiments on QaTa-COV19, MosMedData+ and Kvasir-SEG demonstrate that ProLearn outperforms state-of-the-art language-guided methods when limited text is available.
Authors: Hayeon Kim, Ji Ha Jang, Se Young Chun
Abstract: Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D edits remains challenging, especially for Gaussian Splatting, due to inconsistent multi-view 2D part segmentations and inherently ambiguous nature of Score Distillation Sampling (SDS) loss. To address these limitations, we propose RoMaP, a novel local 3D Gaussian editing framework that enables precise and drastic part-level modifications. First, we introduce a robust 3D mask generation module with our 3D-Geometry Aware Label Prediction (3D-GALP), which uses spherical harmonics (SH) coefficients to model view-dependent label variations and soft-label property, yielding accurate and consistent part segmentations across viewpoints. Second, we propose a regularized SDS loss that combines the standard SDS loss with additional regularizers. In particular, an L1 anchor loss is introduced via our Scheduled Latent Mixing and Part (SLaMP) editing method, which generates high-quality part-edited 2D images and confines modifications only to the target region while preserving contextual coherence. Additional regularizers, such as Gaussian prior removal, further improve flexibility by allowing changes beyond the existing context, and robust 3D masking prevents unintended edits. Experimental results demonstrate that our RoMaP achieves state-of-the-art local 3D editing on both reconstructed and generated Gaussian scenes and objects qualitatively and quantitatively, making it possible for more robust and flexible part-level 3D Gaussian editing.
Authors: Chang Peng, Yifei Zhou, Huifeng Xi, Shiqing Huang, Chuangye Chen, Jianming Yang, Bao Yang, Zhenyu Jiang
Abstract: Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human poses. The performance of existing deep learning-based models for HPE refinement is considerably limited by inaccurate training datasets in which the keypoints are manually annotated. This paper proposed a novel method to overcome the difficulty through joint angle-based modeling. The key techniques include: (i) A joint angle-based model of human pose, which is robust to describe kinematic human poses; (ii) Approximating temporal variation of joint angles through high order Fourier series to get reliable "ground truth"; (iii) A bidirectional recurrent network is designed as a post-processing module to refine the estimation of well-established HRNet. Trained with the high-quality dataset constructed using our method, the network demonstrates outstanding performance to correct wrongly recognized joints and smooth their spatiotemporal trajectories. Tests show that joint angle-based refinement (JAR) outperforms the state-of-the-art HPE refinement network in challenging cases like figure skating and breaking.
Authors: Weizhao Ma, Dong Zhou, Yuhui Hu, Zipeng He
Abstract: Monocular pose estimation of non-cooperative spacecraft is significant for on-orbit service (OOS) tasks, such as satellite maintenance, space debris removal, and station assembly. Considering the high demands on pose estimation accuracy, mainstream monocular pose estimation methods typically consist of keypoint detectors and PnP solver. However, current keypoint detectors remain vulnerable to structural symmetry and partial occlusion of non-cooperative spacecraft. To this end, we propose a graph-based keypoints network for the monocular pose estimation of non-cooperative spacecraft, GKNet, which leverages the geometric constraint of keypoints graph. In order to better validate keypoint detectors, we present a moderate-scale dataset for the spacecraft keypoint detection, named SKD, which consists of 3 spacecraft targets, 90,000 simulated images, and corresponding high-precise keypoint annotations. Extensive experiments and an ablation study have demonstrated the high accuracy and effectiveness of our GKNet, compared to the state-of-the-art spacecraft keypoint detectors. The code for GKNet and the SKD dataset is available at https://github.com/Dongzhou-1996/GKNet.
Authors: Chang Peng, Bao Yang, Meiqi Li, Ge Zhang, Hui Sun, Zhenyu Jiang
Abstract: Ground penetrating radar (GPR) has become a rapid and non-destructive solution for road subsurface distress (RSD) detection. However, RSD recognition from GPR images is labor-intensive and heavily relies on inspectors' expertise. Deep learning offers the possibility for automatic RSD recognition, but its current performance is limited by two factors: Scarcity of high-quality dataset for network training and insufficient capability of network to distinguish RSD. In this study, a rigorously validated 3D GPR dataset containing 2134 samples of diverse types was constructed through field scanning. Based on the finding that the YOLO model trained with one of the three scans of GPR images exhibits varying sensitivity to specific type of RSD, we proposed a novel cross-verification strategy with outstanding accuracy in RSD recognition, achieving recall over 98.6% in field tests. The approach, integrated into an online RSD detection system, can reduce the labor of inspection by around 90%.
Authors: Tianchi Xu
Abstract: Atmospheric structure, represented by backscatter coefficients (BC) recovered from satellite LiDAR attenuated backscatter (ATB), provides a volumetric view of clouds, aerosols, and molecules, playing a critical role in human activities, climate understanding, and extreme weather forecasting. Existing methods often rely on auxiliary inputs and simplified physics-based approximations, and lack a standardized 3D benchmark for fair evaluation. However, such approaches may introduce additional uncertainties and insufficiently capture realistic radiative transfer and atmospheric scattering-absorption effects. To bridge these gaps, we present Atmos-Bench: the first 3D atmospheric benchmark, along with a novel FourCastX: Frequency-enhanced Spatio-Temporal Mixture-of-Experts Network that (a) generates 921,600 image slices from 3D scattering volumes simulated at 532 nm and 355 nm by coupling WRF with an enhanced COSP simulator over 384 land-ocean time steps, yielding high-quality voxel-wise references; (b) embeds ATB-BC physical constraints into the model architecture, promoting energy consistency during restoration; (c) achieves consistent improvements on the Atmos-Bench dataset across both 355 nm and 532 nm bands, outperforming state-of-the-art baseline models without relying on auxiliary inputs. Atmos-Bench establishes a new standard for satellite-based 3D atmospheric structure recovery and paves the way for deeper climate insight.
Authors: Qiyang Wan, Chengzhi Gao, Ruiping Wang, Xilin Chen
Abstract: In recent years, visual recognition methods have advanced significantly, finding applications across diverse fields. While researchers seek to understand the mechanisms behind the success of these models, there is also a growing impetus to deploy them in critical areas like autonomous driving and medical diagnostics to better diagnose failures, which promotes the development of interpretability research. This paper systematically reviews existing research on the interpretability of visual recognition models and proposes a taxonomy of methods from a human-centered perspective. The proposed taxonomy categorizes interpretable recognition methods based on Intent, Object, Presentation, and Methodology, thereby establishing a systematic and coherent set of grouping criteria for these XAI methods. Additionally, we summarize the requirements for evaluation metrics and explore new opportunities enabled by recent technologies, such as large multimodal models. We aim to organize existing research in this domain and inspire future investigations into the interpretability of visual recognition models.
Authors: Jie Yang, Wang Zeng, Sheng Jin, Lumin Xu, Wentao Liu, Chen Qian, Zhen Li, Ruimao Zhang
Abstract: The emergence of Multimodal Large Language Models (MLLMs) has revolutionized image understanding by bridging textual and visual modalities. However, these models often struggle with capturing fine-grained semantic information, such as the precise identification and analysis of object keypoints. Keypoints, as structure-aware, pixel-level, and compact representations of objects, particularly articulated ones, play a crucial role in applications such as fine-grained image analysis, object retrieval, and behavior recognition. In this paper, we propose KptLLM++, a novel multimodal large language model that specifically designed for generic keypoint comprehension through the integration of diverse input modalities guided by user-defined instructions. By unifying keypoint detection across varied contexts, KptLLM++ establishes itself as an advanced interface, fostering more effective human-AI collaboration. The model is built upon a novel identify-then-detect paradigm, which first interprets keypoint semantics and subsequently localizes their precise positions through a structured chain-of-thought reasoning mechanism. To push the boundaries of performance, we have scaled up the training dataset to over 500K samples, encompassing diverse objects, keypoint categories, image styles, and scenarios with complex occlusions. This extensive scaling enables KptLLM++ to unlock its potential, achieving remarkable accuracy and generalization. Comprehensive experiments on multiple keypoint detection benchmarks demonstrate its state-of-the-art performance, underscoring its potential as a unified solution for fine-grained image understanding and its transformative implications for human-AI interaction.
Authors: Md. Sabbir Hossen, Md. Saiduzzaman, Pabon Shaha, Mostofa Kamal Nasir
Abstract: Jellyfish, a diverse group of gelatinous marine organisms, play a crucial role in maintaining marine ecosystems but pose significant challenges for biodiversity and conservation due to their rapid proliferation and ecological impact. Accurate identification of jellyfish species is essential for ecological monitoring and management. In this study, we proposed a deep learning framework for jellyfish species detection and classification using an underwater image dataset. The framework integrates advanced feature extraction techniques, including MobileNetV3, ResNet50, EfficientNetV2-B0, and VGG16, combined with seven traditional machine learning classifiers and three Feedforward Neural Network classifiers for precise species identification. Additionally, we activated the softmax function to directly classify jellyfish species using the convolutional neural network models. The combination of the Artificial Neural Network with MobileNetV3 is our best-performing model, achieving an exceptional accuracy of 98%, significantly outperforming other feature extractor-classifier combinations. This study demonstrates the efficacy of deep learning and hybrid frameworks in addressing biodiversity challenges and advancing species detection in marine environments.
Authors: Hankun Liu, Yujian Zhao, Guanglin Niu
Abstract: Hard samples pose a significant challenge in person re-identification (ReID) tasks, particularly in clothing-changing person Re-ID (CC-ReID). Their inherent ambiguity or similarity, coupled with the lack of explicit definitions, makes them a fundamental bottleneck. These issues not only limit the design of targeted learning strategies but also diminish the model's robustness under clothing or viewpoint changes. In this paper, we propose a novel multimodal-guided Hard Sample Generation and Learning (HSGL) framework, which is the first effort to unify textual and visual modalities to explicitly define, generate, and optimize hard samples within a unified paradigm. HSGL comprises two core components: (1) Dual-Granularity Hard Sample Generation (DGHSG), which leverages multimodal cues to synthesize semantically consistent samples, including both coarse- and fine-grained hard positives and negatives for effectively increasing the hardness and diversity of the training data. (2) Hard Sample Adaptive Learning (HSAL), which introduces a hardness-aware optimization strategy that adjusts feature distances based on textual semantic labels, encouraging the separation of hard positives and drawing hard negatives closer in the embedding space to enhance the model's discriminative capability and robustness to hard samples. Extensive experiments on multiple CC-ReID benchmarks demonstrate the effectiveness of our approach and highlight the potential of multimodal-guided hard sample generation and learning for robust CC-ReID. Notably, HSAL significantly accelerates the convergence of the targeted learning procedure and achieves state-of-the-art performance on both PRCC and LTCC datasets. The code is available at https://github.com/undooo/TryHarder-ACMMM25.
Authors: Zhifeng Gu, Bing Wang
Abstract: Humans perceive the world through multimodal cues to understand and interact with the environment. Learning a scene representation for multiple modalities enhances comprehension of the physical world. However, modality conflicts, arising from inherent distinctions among different modalities, present two critical challenges: property disparity and granularity disparity. To address these challenges, we propose a general framework, MMOne, to represent multiple modalities in one scene, which can be readily extended to additional modalities. Specifically, a modality modeling module with a novel modality indicator is proposed to capture the unique properties of each modality. Additionally, we design a multimodal decomposition mechanism to separate multi-modal Gaussians into single-modal Gaussians based on modality differences. We address the essential distinctions among modalities by disentangling multimodal information into shared and modality-specific components, resulting in a more compact and efficient multimodal scene representation. Extensive experiments demonstrate that our method consistently enhances the representation capability for each modality and is scalable to additional modalities. The code is available at https://github.com/Neal2020GitHub/MMOne.
Authors: Lam Pham, Cam Le, Hieu Tang, Khang Truong, Truong Nguyen, Jasmin Lampert, Alexander Schindler, Martin Boyer, Son Phan
Abstract: In recent years, landslide disasters have reported frequently due to the extreme weather events of droughts, floods , storms, or the consequence of human activities such as deforestation, excessive exploitation of natural resources. However, automatically observing landslide is challenging due to the extremely large observing area and the rugged topography such as mountain or highland. This motivates us to propose an end-to-end deep-learning-based model which explores the remote sensing images for automatically observing landslide events. By considering remote sensing images as the input data, we can obtain free resource, observe large and rough terrains by time. To explore the remote sensing images, we proposed a novel neural network architecture which is for two tasks of landslide detection and landslide segmentation. We evaluated our proposed model on three different benchmark datasets of LandSlide4Sense, Bijie, and Nepal. By conducting extensive experiments, we achieve F1 scores of 98.23, 93.83 for the landslide detection task on LandSlide4Sense, Bijie datasets; mIoU scores of 63.74, 76.88 on the segmentation tasks regarding LandSlide4Sense, Nepal datasets. These experimental results prove potential to integrate our proposed model into real-life landslide observation systems.
Authors: Hongfei Ye, Bin Chen, Wenxi Liu, Yu Zhang, Zhao Li, Dandan Ni, Hongyang Chen
Abstract: With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset \footnote{Anonymous Github Showing some of the data https://anonymous.4open.science/r/color-vision-test-dataset-3BCD} that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose fine-tuning strategies to enhance their performance in color vision tests.
URLs: https://anonymous.4open.science/r/color-vision-test-dataset-3BCD
Authors: Jun Chen, Yonghua Yu, Weifu Li, Yaohui Chen, Hong Chen
Abstract: Citrus, as one of the most economically important fruit crops globally, suffers severe yield depressions due to various diseases. Accurate disease detection and classification serve as critical prerequisites for implementing targeted control measures. Recent advancements in artificial intelligence, particularly deep learning-based computer vision algorithms, have substantially decreased time and labor requirements while maintaining the accuracy of detection and classification. Nevertheless, these methods predominantly rely on massive, high-quality annotated training examples to attain promising performance. By introducing two key designs: contrasting with cluster centroids and a multi-layer contrastive training (MCT) paradigm, this paper proposes a novel clustering-guided self-supervised multi-layer contrastive representation learning (CMCRL) algorithm. The proposed method demonstrates several advantages over existing counterparts: (1) optimizing with massive unannotated samples; (2) effective adaptation to the symptom similarity across distinct citrus diseases; (3) hierarchical feature representation learning. The proposed method achieves state-of-the-art performance on the public citrus image set CDD, outperforming existing methods by 4.5\%-30.1\% accuracy. Remarkably, our method narrows the performance gap with fully supervised counterparts (all samples are labeled). Beyond classification accuracy, our method shows great performance on other evaluation metrics (F1 score, precision, and recall), highlighting the robustness against the class imbalance challenge.
Authors: Che Liu, Jiazhen Pan, Weixiang Shen, Wenjia Bai, Daniel Rueckert, Rossella Arcucci
Abstract: Vision-Language Models (VLMs) trained on web-scale corpora excel at natural image tasks and are increasingly repurposed for healthcare; however, their competence in medical tasks remains underexplored. We present a comprehensive evaluation of open-source general-purpose and medically specialised VLMs, ranging from 3B to 72B parameters, across eight benchmarks: MedXpert, OmniMedVQA, PMC-VQA, PathVQA, MMMU, SLAKE, and VQA-RAD. To observe model performance across different aspects, we first separate it into understanding and reasoning components. Three salient findings emerge. First, large general-purpose models already match or surpass medical-specific counterparts on several benchmarks, demonstrating strong zero-shot transfer from natural to medical images. Second, reasoning performance is consistently lower than understanding, highlighting a critical barrier to safe decision support. Third, performance varies widely across benchmarks, reflecting differences in task design, annotation quality, and knowledge demands. No model yet reaches the reliability threshold for clinical deployment, underscoring the need for stronger multimodal alignment and more rigorous, fine-grained evaluation protocols.
Authors: Xinkui Zhao, Jinsong Shu, Yangyang Wu, Guanjie Cheng, Zihe Liu, Naibo Wang, Shuiguang Deng, Zhongle Xie, Jianwei Yin
Abstract: Multimodal Emotion Recognition (MER) often encounters incomplete multimodality in practical applications due to sensor failures or privacy protection requirements. While existing methods attempt to address various incomplete multimodal scenarios by balancing the training of each modality combination through additional gradients, these approaches face a critical limitation: training gradients from different modality combinations conflict with each other, ultimately degrading the performance of the final prediction model. In this paper, we propose a unimodal decoupled dynamic low-rank adaptation method based on modality combinations, named MCULoRA, which is a novel framework for the parameter-efficient training of incomplete multimodal learning models. MCULoRA consists of two key modules, modality combination aware low-rank adaptation (MCLA) and dynamic parameter fine-tuning (DPFT). The MCLA module effectively decouples the shared information from the distinct characteristics of individual modality combinations. The DPFT module adjusts the training ratio of modality combinations based on the separability of each modality's representation space, optimizing the learning efficiency across different modality combinations. Our extensive experimental evaluation in multiple benchmark datasets demonstrates that MCULoRA substantially outperforms previous incomplete multimodal learning approaches in downstream task accuracy.
Authors: X. Feng, H. Yu, M. Wu, S. Hu, J. Chen, C. Zhu, J. Wu, X. Chu, K. Huang
Abstract: With the rapid development of foundation video generation technologies, long video generation models have exhibited promising research potential thanks to expanded content creation space. Recent studies reveal that the goal of long video generation tasks is not only to extend video duration but also to accurately express richer narrative content within longer videos. However, due to the lack of evaluation benchmarks specifically designed for long video generation models, the current assessment of these models primarily relies on benchmarks with simple narrative prompts (e.g., VBench). To the best of our knowledge, our proposed NarrLV is the first benchmark to comprehensively evaluate the Narrative expression capabilities of Long Video generation models. Inspired by film narrative theory, (i) we first introduce the basic narrative unit maintaining continuous visual presentation in videos as Temporal Narrative Atom (TNA), and use its count to quantitatively measure narrative richness. Guided by three key film narrative elements influencing TNA changes, we construct an automatic prompt generation pipeline capable of producing evaluation prompts with a flexibly expandable number of TNAs. (ii) Then, based on the three progressive levels of narrative content expression, we design an effective evaluation metric using the MLLM-based question generation and answering framework. (iii) Finally, we conduct extensive evaluations on existing long video generation models and the foundation generation models. Experimental results demonstrate that our metric aligns closely with human judgments. The derived evaluation outcomes reveal the detailed capability boundaries of current video generation models in narrative content expression.
Authors: Veronika Shilova, Emmanuel Malherbe, Giovanni Palma, Laurent Risser, Jean-Michel Loubes
Abstract: Within a legal framework, fairness in datasets and models is typically assessed by dividing observations into predefined groups and then computing fairness measures (e.g., Disparate Impact or Equality of Odds with respect to gender). However, when sensitive attributes such as skin color are continuous, dividing into default groups may overlook or obscure the discrimination experienced by certain minority subpopulations. To address this limitation, we propose a fairness-based grouping approach for continuous (possibly multidimensional) sensitive attributes. By grouping data according to observed levels of discrimination, our method identifies the partition that maximizes a novel criterion based on inter-group variance in discrimination, thereby isolating the most critical subgroups. We validate the proposed approach using multiple synthetic datasets and demonstrate its robustness under changing population distributions - revealing how discrimination is manifested within the space of sensitive attributes. Furthermore, we examine a specialized setting of monotonic fairness for the case of skin color. Our empirical results on both CelebA and FFHQ, leveraging the skin tone as predicted by an industrial proprietary algorithm, show that the proposed segmentation uncovers more nuanced patterns of discrimination than previously reported, and that these findings remain stable across datasets for a given model. Finally, we leverage our grouping model for debiasing purpose, aiming at predicting fair scores with group-by-group post-processing. The results demonstrate that our approach improves fairness while having minimal impact on accuracy, thus confirming our partition method and opening the door for industrial deployment.
Authors: Guanghao Wu, Chen Xu, Hai Song, Chong Wang, Qixing Zhang
Abstract: Smoke is the first visible indicator of a wildfire.With the advancement of deep learning, image-based smoke detection has become a crucial method for detecting and preventing forest fires. However, the scarcity of smoke image data from forest fires is one of the significant factors hindering the detection of forest fire smoke. Image generation models offer a promising solution for synthesizing realistic smoke images. However, current inpainting models exhibit limitations in generating high-quality smoke representations, particularly manifesting as inconsistencies between synthesized smoke and background contexts. To solve these problems, we proposed a comprehensive framework for generating forest fire smoke images. Firstly, we employed the pre-trained segmentation model and the multimodal model to obtain smoke masks and image captions.Then, to address the insufficient utilization of masks and masked images by inpainting models, we introduced a network architecture guided by mask and masked image features. We also proposed a new loss function, the mask random difference loss, which enhances the consistency of the generated effects around the mask by randomly expanding and eroding the mask edges.Finally, to generate a smoke image dataset using random masks for subsequent detection tasks, we incorporated smoke characteristics and use a multimodal large language model as a filtering tool to select diverse and reasonable smoke images, thereby improving the quality of the synthetic dataset. Experiments showed that our generated smoke images are realistic and diverse, and effectively enhance the performance of forest fire smoke detection models. Code is available at https://github.com/wghr123/MFGDiffusion.
Authors: Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He
Abstract: 3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsistencies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a framework that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Relation Decoupling (SRD) module restructures complex multi-anchor queries into a set of targeted single-anchor statements, generating a structured set of perspective-aware descriptions that clarify positional relationships. These decomposed representations serve as the foundation for the Multi-view Textual-Scene Interaction (Multi-TSI) module, which integrates textual and scene features across multiple viewpoints using shared, Cross-modal Consistent View Tokens (CCVTs) to preserve spatial correlations. Finally, a Textual-Scene Reasoning module synthesizes multi-view predictions into a unified and robust 3D visual grounding. Experiments on 3D visual grounding datasets show that ViewSRD significantly outperforms state-of-the-art methods, particularly in complex queries requiring precise spatial differentiation.
Authors: Aon Safdar, Usman Akram, Waseem Anwar, Basit Malik, Mian Ibad Ali
Abstract: Automatic Target Detection (ATD) and Recognition (ATR) from Thermal Infrared (TI) imagery in the defense and surveillance domain is a challenging computer vision (CV) task in comparison to the commercial autonomous vehicle perception domain. Limited datasets, peculiar domain-specific and TI modality-specific challenges, i.e., limited hardware, scale invariance issues due to greater distances, deliberate occlusion by tactical vehicles, lower sensor resolution and resultant lack of structural information in targets, effects of weather, temperature, and time of day variations, and varying target to clutter ratios all result in increased intra-class variability and higher inter-class similarity, making accurate real-time ATR a challenging CV task. Resultantly, contemporary state-of-the-art (SOTA) deep learning architectures underperform in the ATR domain. We propose a modified anchor-based single-stage detector, called YOLOatr, based on a modified YOLOv5s, with optimal modifications to the detection heads, feature fusion in the neck, and a custom augmentation profile. We evaluate the performance of our proposed model on a comprehensive DSIAC MWIR dataset for real-time ATR over both correlated and decorrelated testing protocols. The results demonstrate that our proposed model achieves state-of-the-art ATR performance of up to 99.6%.
Authors: Yujie Zhang, Sabine Struckmeyer, Andreas Kolb, Sven Reichardt
Abstract: Observer bias and inconsistencies in traditional plant phenotyping methods limit the accuracy and reproducibility of fine-grained plant analysis. To overcome these challenges, we developed TomatoMAP, a comprehensive dataset for Solanum lycopersicum using an Internet of Things (IoT) based imaging system with standardized data acquisition protocols. Our dataset contains 64,464 RGB images that capture 12 different plant poses from four camera elevation angles. Each image includes manually annotated bounding boxes for seven regions of interest (ROIs), including leaves, panicle, batch of flowers, batch of fruits, axillary shoot, shoot and whole plant area, along with 50 fine-grained growth stage classifications based on the BBCH scale. Additionally, we provide 3,616 high-resolution image subset with pixel-wise semantic and instance segmentation annotations for fine-grained phenotyping. We validated our dataset using a cascading model deep learning framework combining MobileNetv3 for classification, YOLOv11 for object detection, and MaskRCNN for segmentation. Through AI vs. Human analysis involving five domain experts, we demonstrate that the models trained on our dataset achieve accuracy and speed comparable to the experts. Cohen's Kappa and inter-rater agreement heatmap confirm the reliability of automated fine-grained phenotyping using our approach.
Authors: An-Lun Liu, Yu-Wei Chao, Yi-Ting Chen
Abstract: In this paper, we study task-oriented human grasp synthesis, a new grasp synthesis task that demands both task and context awareness. At the core of our method is the task-aware contact maps. Unlike traditional contact maps that only reason about the manipulated object and its relation with the hand, our enhanced maps take into account scene and task information. This comprehensive map is critical for hand-object interaction, enabling accurate grasping poses that align with the task. We propose a two-stage pipeline that first constructs a task-aware contact map informed by the scene and task. In the subsequent stage, we use this contact map to synthesize task-oriented human grasps. We introduce a new dataset and a metric for the proposed task to evaluate our approach. Our experiments validate the importance of modeling both scene and task, demonstrating significant improvements over existing methods in both grasp quality and task performance. See our project page for more details: https://hcis-lab.github.io/TOHGS/
Authors: Pa\'ul Maji, Marlon T\'uquerres, Stalin Valencia, Marcela Valenzuela, Christian Mejia-Escobar
Abstract: Fluvial erosion is a natural process that can generate significant impacts on soil stability and strategic infrastructures. The detection and monitoring of this phenomenon is traditionally addressed by photogrammetric methods and analysis in geographic information systems. These tasks require specific knowledge and intensive manual processing. This study proposes an artificial intelligence-based approach for automatic identification of eroded zones and estimation of their area. The state-of-the-art computer vision model YOLOv11, adjusted by fine-tuning and trained with photographs and LiDAR images, is used. This combined dataset was segmented and labeled using the Roboflow platform. Experimental results indicate efficient detection of erosion patterns with an accuracy of 70%, precise identification of eroded areas and reliable calculation of their extent in pixels and square meters. As a final product, the EROSCAN system has been developed, an interactive web application that allows users to upload images and obtain automatic segmentations of fluvial erosion, together with the estimated area. This tool optimizes the detection and quantification of the phenomenon, facilitating decision making in risk management and territorial planning.
Authors: Haoxuan Qu, Yujun Cai, Hossein Rahmani, Ajay Kumar, Junsong Yuan, Jun Liu
Abstract: Recently, Gaussian Splatting (GS) has received a lot of attention in surface reconstruction. However, while 3D objects can be of complex and diverse shapes in the real world, existing GS-based methods only limitedly use a single type of splatting primitive (Gaussian ellipse or Gaussian ellipsoid) to represent object surfaces during their reconstruction. In this paper, we highlight that this can be insufficient for object surfaces to be represented in high quality. Thus, we propose a novel framework that, for the first time, enables Gaussian Splatting to incorporate multiple types of (geometrical) primitives during its surface reconstruction process. Specifically, in our framework, we first propose a compositional splatting strategy, enabling the splatting and rendering of different types of primitives in the Gaussian Splatting pipeline. In addition, we also design our framework with a mixed-primitive-based initialization strategy and a vertex pruning mechanism to further promote its surface representation learning process to be well executed leveraging different types of primitives. Extensive experiments show the efficacy of our framework and its accurate surface reconstruction performance.
Authors: Jianfei Jiang, Qiankun Liu, Haochen Yu, Hongyuan Liu, Liyong Wang, Jiansheng Chen, Huimin Ma
Abstract: Learning-based Multi-View Stereo (MVS) methods aim to predict depth maps for a sequence of calibrated images to recover dense point clouds. However, existing MVS methods often struggle with challenging regions, such as textureless regions and reflective surfaces, where feature matching fails. In contrast, monocular depth estimation inherently does not require feature matching, allowing it to achieve robust relative depth estimation in these regions. To bridge this gap, we propose MonoMVSNet, a novel monocular feature and depth guided MVS network that integrates powerful priors from a monocular foundation model into multi-view geometry. Firstly, the monocular feature of the reference view is integrated into source view features by the attention mechanism with a newly designed cross-view position encoding. Then, the monocular depth of the reference view is aligned to dynamically update the depth candidates for edge regions during the sampling procedure. Finally, a relative consistency loss is further designed based on the monocular depth to supervise the depth prediction. Extensive experiments demonstrate that MonoMVSNet achieves state-of-the-art performance on the DTU and Tanks-and-Temples datasets, ranking first on the Tanks-and-Temples Intermediate and Advanced benchmarks. The source code is available at https://github.com/JianfeiJ/MonoMVSNet.
Authors: Peiran Wu, Yunze Liu, Zhengdong Zhu, Enmin Zhou, Shawn Shen
Abstract: Real-world user-generated videos, especially on platforms like TikTok, often feature rich and intertwined audio visual content. However, existing video captioning benchmarks and models remain predominantly visual centric, overlooking the crucial role of audio in conveying scene dynamics, speaker intent, and narrative context. This lack of omni datasets and lightweight, capable models hampers progress in fine grained, multimodal video understanding. To address these challenges, we introduce UGC-VideoCap, a new benchmark and model framework specifically designed for detailed omnimodal captioning of short form user-generated videos. Unlike prior datasets, UGC-VideoCap emphasizes balanced integration of audio and visual modalities, featuring 1000 TikTok videos annotated through a structured three stage human-in-the-loop pipeline covering audio only, visual only, and joint audio visual semantics. The benchmark also includes 4000 carefully crafted QA pairs probing both unimodal and cross modal understanding. Alongside the dataset, we propose UGC-VideoCaptioner(3B), a 3B parameter captioning model distilled from Gemini 2.5 Flash. Using a novel two-stage training strategy supervised fine tuning followed by Group Relative Policy Optimization (GRPO), our approach enables efficient adaptation from limited data while maintaining competitive performance. Together, our benchmark and model offer a high-quality foundation and a data-efficient solution for advancing omnimodal video captioning in unconstrained real-world UGC settings.
Authors: Pierrick Leroy, Antonio Mastropietro, Marco Nurisso, Francesco Vaccarino
Abstract: Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these contrastive losses focus exclusively on identity information as labels. However, we observe a multiscale geometric structure emerging in the embedding space, influenced by interpretable facial (e.g., hair color) and image attributes (e.g., contrast). We propose a geometric approach to describe the dependence or invariance of FR models to these attributes and introduce a physics-inspired alignment metric. We evaluate the proposed metric on controlled, simplified models and widely used FR models fine-tuned with synthetic data for targeted attribute augmentation. Our findings reveal that the models exhibit varying degrees of invariance across different attributes, providing insight into their strengths and weaknesses and enabling deeper interpretability. Code available here: https://github.com/mantonios107/attrs-fr-embs}{https://github.com/mantonios107/attrs-fr-embs
URLs: https://github.com/mantonios107/attrs-fr-embs, https://github.com/mantonios107/attrs-fr-embs
Authors: Kaif Shaikh, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic
Abstract: Vision AutoRegressive model (VAR) was recently introduced as an alternative to Diffusion Models (DMs) in image generation domain. In this work we focus on its adaptations, which aim to fine-tune pre-trained models to perform specific downstream tasks, like medical data generation. While for DMs there exist many techniques, adaptations for VAR remain underexplored. Similarly, differentially private (DP) adaptations-ones that aim to preserve privacy of the adaptation data-have been extensively studied for DMs, while VAR lacks such solutions. In our work, we implement and benchmark many strategies for VAR, and compare them to state-of-the-art DM adaptation strategies. We observe that VAR outperforms DMs for non-DP adaptations, however, the performance of DP suffers, which necessitates further research in private adaptations for VAR. Code is available at https://github.com/sprintml/finetuning_var_dp.
Authors: Haoran Wang, Hanyu Pei, Yang Lyu, Kai Zhang, Li Li, Feng-Lei Fan
Abstract: The escalating adoption of high-resolution, large-field-of-view imagery amplifies the need for efficient compression methodologies. Conventional techniques frequently fail to preserve critical image details, while data-driven approaches exhibit limited generalizability. Implicit Neural Representations (INRs) present a promising alternative by learning continuous mappings from spatial coordinates to pixel intensities for individual images, thereby storing network weights rather than raw pixels and avoiding the generalization problem. However, INR-based compression of large images faces challenges including slow compression speed and suboptimal compression ratios. To address these limitations, we introduce COLI (Compressor for Large Images), a novel framework leveraging Neural Representations for Videos (NeRV). First, recognizing that INR-based compression constitutes a training process, we accelerate its convergence through a pretraining-finetuning paradigm, mixed-precision training, and reformulation of the sequential loss into a parallelizable objective. Second, capitalizing on INRs' transformation of image storage constraints into weight storage, we implement Hyper-Compression, a novel post-training technique to substantially enhance compression ratios while maintaining minimal output distortion. Evaluations across two medical imaging datasets demonstrate that COLI consistently achieves competitive or superior PSNR and SSIM metrics at significantly reduced bits per pixel (bpp), while accelerating NeRV training by up to 4 times.
Authors: Pan Du, Mingqi Xu, Xiaozhi Zhu, Jian-xun Wang
Abstract: Accurate characterization of vascular geometry is essential for cardiovascular diagnosis and treatment planning. Traditional statistical shape modeling (SSM) methods rely on linear assumptions, limiting their expressivity and scalability to complex topologies such as multi-branch vascular structures. We introduce HUG-VAS, a Hierarchical NURBS Generative model for Vascular geometry Synthesis, which integrates NURBS surface parameterization with diffusion-based generative modeling to synthesize realistic, fine-grained aortic geometries. Trained with 21 patient-specific samples, HUG-VAS generates anatomically faithful aortas with supra-aortic branches, yielding biomarker distributions that closely match those of the original dataset. HUG-VAS adopts a hierarchical architecture comprising a denoising diffusion model that generates centerlines and a guided diffusion model that synthesizes radial profiles conditioned on those centerlines, thereby capturing two layers of anatomical variability. Critically, the framework supports zero-shot conditional generation from image-derived priors, enabling practical applications such as interactive semi-automatic segmentation, robust reconstruction under degraded imaging conditions, and implantable device optimization. To our knowledge, HUG-VAS is the first SSM framework to bridge image-derived priors with generative shape modeling via a unified integration of NURBS parameterization and hierarchical diffusion processes.
Authors: Esteban Rom\'an Catafau, Torbj\"orn E. M. Nordling
Abstract: This paper addresses the fundamental computer vision challenge of robust circle detection and fitting in degraded imaging conditions. We present Combinatorial Convolution-based Circle Fitting for Blurry Images (3C-FBI), an algorithm that bridges the gap between circle detection and precise parametric fitting by combining (1) efficient combinatorial edge pixel (edgel) sampling and (2) convolution-based density estimation in parameter space. We evaluate 3C-FBI across three experimental frameworks: (1) real-world medical data from Parkinson's disease assessments (144 frames from 36 videos), (2) controlled synthetic data following established circle-fitting benchmarks, and (3) systematic analysis across varying spatial resolutions and outlier contamination levels. Results show that 3C-FBI achieves state-of-the-art accuracy (Jaccard index 0.896) while maintaining real-time performance (40.3 fps), significantly outperforming classical methods like RCD (6.8 fps) on a standard CPU (i7-10875H). It maintains near-perfect accuracy (Jaccard almost 1.0) at high resolutions (480x480) and reliable performance (Jaccard higher than 0.95) down to 160x160 with up to 20% outliers. In extensive synthetic testing, 3C-FBI achieves a mean Jaccard Index of 0.989 across contamination levels, comparable to modern methods like Qi et al. (2024, 0.991), and surpassing RHT (0.964). This combination of accuracy, speed, and robustness makes 3C-FBI ideal for medical imaging, robotics, and industrial inspection under challenging conditions.
Authors: Pakizar Shamoi, Nuray Toganas, Muragul Muratbekova, Elnara Kadyrgali, Adilet Yerkin, Ayan Igali, Malika Ziyada, Ayana Adilova, Aron Karatayev, Yerdauit Torekhan
Abstract: Colors are omnipresent in today's world and play a vital role in how humans perceive and interact with their surroundings. However, it is challenging for computers to imitate human color perception. This paper introduces the Human Perception-Based Fuzzy Color Model, COLIBRI (Color Linguistic-Based Representation and Interpretation), designed to bridge the gap between computational color representations and human visual perception. The proposed model uses fuzzy sets and logic to create a framework for color categorization. Using a three-phase experimental approach, the study first identifies distinguishable color stimuli for hue, saturation, and intensity through preliminary experiments, followed by a large-scale human categorization survey involving more than 1000 human subjects. The resulting data are used to extract fuzzy partitions and generate membership functions that reflect real-world perceptual uncertainty. The model incorporates a mechanism for adaptation that allows refinement based on feedback and contextual changes. Comparative evaluations demonstrate the model's alignment with human perception compared to traditional color models, such as RGB, HSV, and LAB. To the best of our knowledge, no previous research has documented the construction of a model for color attribute specification based on a sample of this size or a comparable sample of the human population (n = 2496). Our findings are significant for fields such as design, artificial intelligence, marketing, and human-computer interaction, where perceptually relevant color representation is critical.
Authors: Tariq Mehmood, Hamza Ahmad, Muhammad Haroon Shakeel, Murtaza Taj
Abstract: EEG-based brain-computer interfaces (BCIs) have shown promise in various applications, such as motor imagery and cognitive state monitoring. However, decoding visual representations from EEG signals remains a significant challenge due to their complex and noisy nature. We thus propose a novel 5-stage framework for decoding visual representations from EEG signals: (1) an EEG encoder for concept classification, (2) cross-modal alignment of EEG and text embeddings in CLIP feature space, (3) caption refinement via re-ranking, (4) weighted interpolation of concept and caption embeddings for richer semantics, and (5) image generation using a pre-trained Stable Diffusion model. We enable context-aware EEG-to-image generation through cross-modal alignment and re-ranking. Experimental results demonstrate that our method generates high-quality images aligned with visual stimuli, outperforming SOTA approaches by 13.43% in Classification Accuracy, 15.21% in Generation Accuracy and reducing Fr\'echet Inception Distance by 36.61%, indicating superior semantic alignment and image quality.
Authors: Mengyu Wang, Henghui Ding, Jianing Peng, Yao Zhao, Yunpeng Chen, Yunchao Wei
Abstract: In text-to-image generation, producing a series of consistent contents that preserve the same identity is highly valuable for real-world applications. Although a few works have explored training-free methods to enhance the consistency of generated subjects, we observe that they suffer from the following problems. First, they fail to maintain consistent background details, which limits their applicability. Furthermore, when the foreground character undergoes large motion variations, inconsistencies in identity and clothing details become evident. To address these problems, we propose CharaConsist, which employs point-tracking attention and adaptive token merge along with decoupled control of the foreground and background. CharaConsist enables fine-grained consistency for both foreground and background, supporting the generation of one character in continuous shots within a fixed scene or in discrete shots across different scenes. Moreover, CharaConsist is the first consistent generation method tailored for text-to-image DiT model. Its ability to maintain fine-grained consistency, combined with the larger capacity of latest base model, enables it to produce high-quality visual outputs, broadening its applicability to a wider range of real-world scenarios. The source code has been released at https://github.com/Murray-Wang/CharaConsist
Authors: Dong Zhuo, Wenzhao Zheng, Jiahe Guo, Yuqi Wu, Jie Zhou, Jiwen Lu
Abstract: Perceiving and reconstructing 4D spatial-temporal geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and real-time applications, we propose a streaming 4D visual geometry transformer that shares a similar philosophy with autoregressive large language models. We explore a simple and efficient design and employ a causal transformer architecture to process the input sequence in an online manner. We use temporal causal attention and cache the historical keys and values as implicit memory to enable efficient streaming long-term 4D reconstruction. This design can handle real-time 4D reconstruction by incrementally integrating historical information while maintaining high-quality spatial consistency. For efficient training, we propose to distill knowledge from the dense bidirectional visual geometry grounded transformer (VGGT) to our causal model. For inference, our model supports the migration of optimized efficient attention operator (e.g., FlashAttention) from the field of large language models. Extensive experiments on various 4D geometry perception benchmarks demonstrate that our model increases the inference speed in online scenarios while maintaining competitive performance, paving the way for scalable and interactive 4D vision systems. Code is available at: https://github.com/wzzheng/StreamVGGT.
Authors: Zhen Xu, Hongyu Zhou, Sida Peng, Haotong Lin, Haoyu Guo, Jiahao Shao, Peishan Yang, Qinglin Yang, Sheng Miao, Xingyi He, Yifan Wang, Yue Wang, Ruizhen Hu, Yiyi Liao, Xiaowei Zhou, Hujun Bao
Abstract: Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware sensors like LiDAR are often limited by high costs, low resolution, and environmental sensitivity, limiting their applicability in real-world scenarios. Recent advances in vision-based methods offer a promising alternative, yet they face challenges in generalization and stability due to either the low-capacity model architectures or the reliance on domain-specific and small-scale datasets. The emergence of scaling laws and foundation models in other domains has inspired the development of "depth foundation models": deep neural networks trained on large datasets with strong zero-shot generalization capabilities. This paper surveys the evolution of deep learning architectures and paradigms for depth estimation across the monocular, stereo, multi-view, and monocular video settings. We explore the potential of these models to address existing challenges and provide a comprehensive overview of large-scale datasets that can facilitate their development. By identifying key architectures and training strategies, we aim to highlight the path towards robust depth foundation models, offering insights into their future research and applications.
Authors: Alessio Caviglia, Filippo Marostica, Alessio Carpegna, Alessandro Savino, Stefano Di Carlo
Abstract: Hardware accelerators are essential for achieving low-latency, energy-efficient inference in edge applications like image recognition. Spiking Neural Networks (SNNs) are particularly promising due to their event-driven and temporally sparse nature, making them well-suited for low-power Field Programmable Gate Array (FPGA)-based deployment. This paper explores using the open-source Spiker+ framework to generate optimized SNNs accelerators for handwritten digit recognition on the MNIST dataset. Spiker+ enables high-level specification of network topologies, neuron models, and quantization, automatically generating deployable HDL. We evaluate multiple configurations and analyze trade-offs relevant to edge computing constraints.
Authors: Gaurav Singh
Abstract: Pneumonia, particularly when induced by diseases like COVID-19, remains a critical global health challenge requiring rapid and accurate diagnosis. This study presents a comprehensive comparison of traditional machine learning and state-of-the-art deep learning approaches for automated pneumonia detection using chest X-rays (CXRs). We evaluate multiple methodologies, ranging from conventional machine learning techniques (PCA-based clustering, Logistic Regression, and Support Vector Classification) to advanced deep learning architectures including Convolutional Neural Networks (Modified LeNet, DenseNet-121) and various Vision Transformer (ViT) implementations (Deep-ViT, Compact Convolutional Transformer, and Cross-ViT). Using a dataset of 5,856 pediatric CXR images, we demonstrate that Vision Transformers, particularly the Cross-ViT architecture, achieve superior performance with 88.25% accuracy and 99.42% recall, surpassing traditional CNN approaches. Our analysis reveals that architectural choices impact performance more significantly than model size, with Cross-ViT's 75M parameters outperforming larger models. The study also addresses practical considerations including computational efficiency, training requirements, and the critical balance between precision and recall in medical diagnostics. Our findings suggest that Vision Transformers offer a promising direction for automated pneumonia detection, potentially enabling more rapid and accurate diagnosis during health crises.
Authors: Ruixi Zheng, Wei Zhang, Yijie Li, Xi Zhu, Zhou Lan, Jarrett Rushmore, Yogesh Rathi, Nikos Makris, Lauren J. O'Donnell, Fan Zhang
Abstract: Diffusion MRI (dMRI) tractography is currently the only method for in vivo mapping of the brain's white matter (WM) connections. Tractometry is an advanced tractography analysis technique for along-tract profiling to investigate the morphology and microstructural properties along the fiber tracts. Tractometry has become an essential tool for studying local along-tract differences between different populations (e.g., health vs disease). In this study, we propose a novel atlas-guided fine-scale tractometry method, namely AGFS-Tractometry, that leverages tract spatial information and permutation testing to enhance the along-tract statistical analysis between populations. There are two major contributions in AGFS-Tractometry. First, we create a novel atlas-guided tract profiling template that enables consistent, fine-scale, along-tract parcellation of subject-specific fiber tracts. Second, we propose a novel nonparametric permutation testing group comparison method to enable simultaneous analysis across all along-tract parcels while correcting for multiple comparisons. We perform experimental evaluations on synthetic datasets with known group differences and in vivo real data. We compare AGFS-Tractometry with two state-of-the-art tractometry methods, including Automated Fiber-tract Quantification (AFQ) and BUndle ANalytics (BUAN). Our results show that the proposed AGFS-Tractometry obtains enhanced sensitivity and specificity in detecting local WM differences. In the real data analysis experiments, AGFS-Tractometry can identify more regions with significant differences, which are anatomically consistent with the existing literature. Overall, these demonstrate the ability of AGFS-Tractometry to detect subtle or spatially localized WM group-level differences. The created tract profiling template and related code are available at: https://github.com/ZhengRuixi/AGFS-Tractometry.git.
Authors: Mengwen Ye, Yingzi Huangfu, Shujian Gao, Wei Ren, Weifan Liu, Zekuan Yu
Abstract: Federated Learning (FL) emerged as a solution for collaborative medical image classification while preserving data privacy. However, label noise, which arises from inter-institutional data variability, can cause training instability and degrade model performance. Existing FL methods struggle with noise heterogeneity and the imbalance in medical data. Motivated by these challenges, we propose FedGSCA, a novel framework for enhancing robustness in noisy medical FL. FedGSCA introduces a Global Sample Selector that aggregates noise knowledge from all clients, effectively addressing noise heterogeneity and improving global model stability. Furthermore, we develop a Client Adaptive Adjustment (CAA) mechanism that combines adaptive threshold pseudo-label generation and Robust Credal Labeling Loss. CAA dynamically adjusts to class distributions, ensuring the inclusion of minority samples and carefully managing noisy labels by considering multiple plausible labels. This dual approach mitigates the impact of noisy data and prevents overfitting during local training, which improves the generalizability of the model. We evaluate FedGSCA on one real-world colon slides dataset and two synthetic medical datasets under various noise conditions, including symmetric, asymmetric, extreme, and heterogeneous types. The results show that FedGSCA outperforms the state-of-the-art methods, excelling in extreme and heterogeneous noise scenarios. Moreover, FedGSCA demonstrates significant advantages in improving model stability and handling complex noise, making it well-suited for real-world medical federated learning scenarios.
Authors: Daniel Saragih, Deyu Cao, Tejas Balaji
Abstract: Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we extend these advances to weight space learning by leveraging recent techniques to incorporate structural priors derived from optimization dynamics. Central to our approach is modeling the trajectory induced by gradient descent as a trajectory inference problem. We unify several trajectory inference techniques under the framework of gradient flow matching, providing a theoretical framework for treating optimization paths as inductive bias. We further explore architectural and algorithmic choices, including reward fine-tuning by adjoint matching, the use of autoencoders for latent weight representation, conditioning on task-specific context data, and adopting informative source distributions such as Kaiming uniform. Experiments demonstrate that our method matches or surpasses baselines in generating in-distribution weights, improves initialization for downstream training, and supports fine-tuning to enhance performance. Finally, we illustrate a practical application in safety-critical systems: detecting harmful covariate shifts, where our method outperforms the closest comparable baseline.
Authors: \'E. K\"unzel, A. Jaziri, V. Ramesh
Abstract: Continual learning in computer vision requires that models adapt to a continuous stream of tasks without forgetting prior knowledge, yet existing approaches often tip the balance heavily toward either plasticity or stability. We introduce RDBP, a simple, low-overhead baseline that unites two complementary mechanisms: ReLUDown, a lightweight activation modification that preserves feature sensitivity while preventing neuron dormancy, and Decreasing Backpropagation, a biologically inspired gradient-scheduling scheme that progressively shields early layers from catastrophic updates. Evaluated on the Continual ImageNet benchmark, RDBP matches or exceeds the plasticity and stability of state-of-the-art methods while reducing computational cost. RDBP thus provides both a practical solution for real-world continual learning and a clear benchmark against which future continual learning strategies can be measured.
Authors: Bart Pogodzinski, Christopher Wewer, Bernt Schiele, Jan Eric Lenssen
Abstract: We present Spatial Reasoners, a software framework to perform spatial reasoning over continuous variables with generative denoising models. Denoising generative models have become the de-facto standard for image generation, due to their effectiveness in sampling from complex, high-dimensional distributions. Recently, they have started being explored in the context of reasoning over multiple continuous variables. Providing infrastructure for generative reasoning with such models requires a high effort, due to a wide range of different denoising formulations, samplers, and inference strategies. Our presented framework aims to facilitate research in this area, providing easy-to-use interfaces to control variable mapping from arbitrary data domains, generative model paradigms, and inference strategies. Spatial Reasoners are openly available at https://spatialreasoners.github.io/
Authors: Howard H. Qian, Yiting Chen, Gaotian Wang, Podshara Chanrungmaneekul, Kaiyu Hang
Abstract: Successful execution of dexterous robotic manipulation tasks in new environments, such as grasping, depends on the ability to proficiently segment unseen objects from the background and other objects. Previous works in unseen object instance segmentation (UOIS) train models on large-scale datasets, which often leads to overfitting on static visual features. This dependency results in poor generalization performance when confronted with out-of-distribution scenarios. To address this limitation, we rethink the task of UOIS based on the principle that vision is inherently interactive and occurs over time. We propose a novel real-time interactive perception framework, rt-RISeg, that continuously segments unseen objects by robot interactions and analysis of a designed body frame-invariant feature (BFIF). We demonstrate that the relative rotational and linear velocities of randomly sampled body frames, resulting from selected robot interactions, can be used to identify objects without any learned segmentation model. This fully self-contained segmentation pipeline generates and updates object segmentation masks throughout each robot interaction without the need to wait for an action to finish. We showcase the effectiveness of our proposed interactive perception method by achieving an average object segmentation accuracy rate 27.5% greater than state-of-the-art UOIS methods. Furthermore, although rt-RISeg is a standalone framework, we show that the autonomously generated segmentation masks can be used as prompts to vision foundation models for significantly improved performance.
Authors: Yilun Zhao, Chengye Wang, Chuhan Li, Arman Cohan
Abstract: This paper introduces MISS-QA, the first benchmark specifically designed to evaluate the ability of models to interpret schematic diagrams within scientific literature. MISS-QA comprises 1,500 expert-annotated examples over 465 scientific papers. In this benchmark, models are tasked with interpreting schematic diagrams that illustrate research overviews and answering corresponding information-seeking questions based on the broader context of the paper. We assess the performance of 18 frontier multimodal foundation models, including o4-mini, Gemini-2.5-Flash, and Qwen2.5-VL. We reveal a significant performance gap between these models and human experts on MISS-QA. Our analysis of model performance on unanswerable questions and our detailed error analysis further highlight the strengths and limitations of current models, offering key insights to enhance models in comprehending multimodal scientific literature.
Authors: Chetan Madan, Aarjav Satia, Soumen Basu, Pankaj Gupta, Usha Dutta, Chetan Arora
Abstract: Masked Autoencoders (MAEs) have emerged as a dominant strategy for self-supervised representation learning in natural images, where models are pre-trained to reconstruct masked patches with a pixel-wise mean squared error (MSE) between original and reconstructed RGB values as the loss. We observe that MSE encourages blurred image re-construction, but still works for natural images as it preserves dominant edges. However, in medical imaging, when the texture cues are more important for classification of a visual abnormality, the strategy fails. Taking inspiration from Gray Level Co-occurrence Matrix (GLCM) feature in Radiomics studies, we propose a novel MAE based pre-training framework, GLCM-MAE, using reconstruction loss based on matching GLCM. GLCM captures intensity and spatial relationships in an image, hence proposed loss helps preserve morphological features. Further, we propose a novel formulation to convert matching GLCM matrices into a differentiable loss function. We demonstrate that unsupervised pre-training on medical images with the proposed GLCM loss improves representations for downstream tasks. GLCM-MAE outperforms the current state-of-the-art across four tasks - gallbladder cancer detection from ultrasound images by 2.1%, breast cancer detection from ultrasound by 3.1%, pneumonia detection from x-rays by 0.5%, and COVID detection from CT by 0.6%. Source code and pre-trained models are available at: https://github.com/ChetanMadan/GLCM-MAE.
Authors: Zongtao He, Liuyi Wang, Lu Chen, Chengju Liu, Qijun Chen
Abstract: Language-guided navigation is a cornerstone of embodied AI, enabling agents to interpret language instructions and navigate complex environments. However, expert-provided instructions are limited in quantity, while synthesized annotations often lack quality, making them insufficient for large-scale research. To address this, we propose NavComposer, a novel framework for automatically generating high-quality navigation instructions. NavComposer explicitly decomposes semantic entities such as actions, scenes, and objects, and recomposes them into natural language instructions. Its modular architecture allows flexible integration of state-of-the-art techniques, while the explicit use of semantic entities enhances both the richness and accuracy of instructions. Moreover, it operates in a data-agnostic manner, supporting adaptation to diverse navigation trajectories without domain-specific training. Complementing NavComposer, we introduce NavInstrCritic, a comprehensive annotation-free evaluation system that assesses navigation instructions on three dimensions: contrastive matching, semantic consistency, and linguistic diversity. NavInstrCritic provides a holistic evaluation of instruction quality, addressing limitations of traditional metrics that rely heavily on expert annotations. By decoupling instruction generation and evaluation from specific navigation agents, our method enables more scalable and generalizable research. Extensive experiments provide direct and practical evidence for the effectiveness of our method.
Authors: He Zhu, Ryo Miyoshi, Yuki Okafuji
Abstract: Prior human-robot interaction (HRI) research has primarily focused on single-user interactions, where robots do not need to consider the timing or recipient of their responses. However, in multi-party interactions, such as at malls and hospitals, social robots must understand the context and decide both when and to whom they should respond. In this paper, we propose a Transformer-based multi-task learning framework to improve the decision-making process of social robots, particularly in multi-user environments. Considering the characteristics of HRI, we propose two novel loss functions: one that enforces constraints on active speakers to improve scene modeling, and another that guides response selection towards utterances specifically directed at the robot. Additionally, we construct a novel multi-party HRI dataset that captures real-world complexities, such as gaze misalignment. Experimental results demonstrate that our model achieves state-of-the-art performance in respond decisions, outperforming existing heuristic-based and single-task approaches. Our findings contribute to the development of socially intelligent social robots capable of engaging in natural and context-aware multi-party interactions.
Authors: Zhaoyi An, Rei Kawakami
Abstract: Large language models, with their strong reasoning ability and rich knowledge, have brought revolution to many tasks of AI, but their impact on sign language generation remains limited due to its complexity and unique rules. In this paper, we propose TEAch Me Sign (TEAM-Sign), treating sign language as another natural language. By fine-tuning an LLM, we enable it to learn the correspondence between text and sign language, and facilitate generation. Considering the differences between sign and spoken language, we employ a stepwise prompting strategy to extract the inherent sign language knowledge within the LLM, thereby supporting the learning and generation process. Experimental results on How2Sign and Phoenix14T datasets demonstrate that our approach effectively leverages both the sign language knowledge and reasoning capabilities of LLM to align the different distribution and grammatical rules between sign and spoken language.
Authors: Yanbo Wang, Zipeng Fang, Lei Zhao, Weidong Chen
Abstract: Service robots are increasingly deployed in diverse and dynamic environments, where both physical layouts and social contexts change over time and across locations. In these unstructured settings, conventional navigation systems that rely on fixed parameters often fail to generalize across scenarios, resulting in degraded performance and reduced social acceptance. Although recent approaches have leveraged reinforcement learning to enhance traditional planners, these methods often fail in real-world deployments due to poor generalization and limited simulation diversity, which hampers effective sim-to-real transfer. To tackle these issues, we present LE-Nav, an interpretable and scene-aware navigation framework that leverages multi-modal large language model reasoning and conditional variational autoencoders to adaptively tune planner hyperparameters. To achieve zero-shot scene understanding, we utilize one-shot exemplars and chain-of-thought prompting strategies. Additionally, a conditional variational autoencoder captures the mapping between natural language instructions and navigation hyperparameters, enabling expert-level tuning. Experiments show that LE-Nav can generate hyperparameters achieving human-level tuning across diverse planners and scenarios. Real-world navigation trials and a user study on a smart wheelchair platform demonstrate that it outperforms state-of-the-art methods on quantitative metrics such as success rate, efficiency, safety, and comfort, while receiving higher subjective scores for perceived safety and social acceptance. Code is available at https://github.com/Cavendish518/LE-Nav.
Authors: Xingyu Zheng, Haotong Qin, Yuye Li, Jiakai Wang, Jinyang Guo, Michele Magno, Xianglong Liu
Abstract: Post-training quantization (PTQ) offers an efficient approach to compressing large language models (LLMs), significantly reducing memory access and computational costs. Existing compensation-based weight calibration methods often rely on a second-order Taylor expansion to model quantization error, under the assumption that the first-order term is negligible in well-trained full-precision models. However, we reveal that the progressive compensation process introduces accumulated first-order deviations between latent weights and their full-precision counterparts, making this assumption fundamentally flawed. To address this, we propose FOEM, a novel PTQ method that explicitly incorporates first-order gradient terms to improve quantization error compensation. FOEM approximates gradients by directly computing the difference between latent and full-precision weights, avoiding the high cost and limited generalization of backpropagation-based gradient computation. This approach introduces minimal additional computational overhead. Moreover, FOEM leverages precomputed Cholesky factors to efficiently recover the inverse of Hessian submatrices in real time. Extensive experiments across a wide range of models and benchmarks demonstrate that FOEM consistently outperforms the classical GPTQ method. In 3-bit weight-only quantization, FOEM reduces the perplexity of Llama3-8B by 89.6%, and improves the 5-shot MMLU accuracy of Llama3-70B from 51.7% to 74.9%, approaching the full-precision performance of 78.6%. Furthermore, FOEM can be seamlessly integrated with advanced techniques such as GPTAQ and SpinQuant, yielding additional improvements under the challenging W4A4KV4 setting, and further narrowing the accuracy gap with full-precision baselines beyond what current state-of-the-art methods achieve. The code is available at https://github.com/Xingyu-Zheng/FOEM.
Authors: Jeongyun Kim, Seunghoon Jeong, Giseop Kim, Myung-Hwan Jeon, Eunji Jun, Ayoung Kim
Abstract: Understanding the 3D geometry of transparent objects from RGB images is challenging due to their inherent physical properties, such as reflection and refraction. To address these difficulties, especially in scenarios with sparse views and dynamic environments, we introduce TRAN-D, a novel 2D Gaussian Splatting-based depth reconstruction method for transparent objects. Our key insight lies in separating transparent objects from the background, enabling focused optimization of Gaussians corresponding to the object. We mitigate artifacts with an object-aware loss that places Gaussians in obscured regions, ensuring coverage of invisible surfaces while reducing overfitting. Furthermore, we incorporate a physics-based simulation that refines the reconstruction in just a few seconds, effectively handling object removal and chain-reaction movement of remaining objects without the need for rescanning. TRAN-D is evaluated on both synthetic and real-world sequences, and it consistently demonstrated robust improvements over existing GS-based state-of-the-art methods. In comparison with baselines, TRAN-D reduces the mean absolute error by over 39% for the synthetic TRansPose sequences. Furthermore, despite being updated using only one image, TRAN-D reaches a {\delta} < 2.5 cm accuracy of 48.46%, over 1.5 times that of baselines, which uses six images. Code and more results are available at https://jeongyun0609.github.io/TRAN-D/.
Authors: Isaiah Thompson Ocansey, Ritwik Bhattacharya, Tanmay Sen
Abstract: Log anomaly detection using traditional rule based or deep learning based methods is often challenging due to the large volume and highly complex nature of log sequence. So effective way of detection of anomalous sequence of logs is crucial for system maintenance and development. This paper proposes parameter efficient finetuning specifically low rank adaptation (LoRA) and adapter based approaches for finding contextual anomalies in sequence of logs in large log data set. It compares different tiny large language models (LLMs) on the Thunderbird dataset. The results show that LoRA based finetuning provides substantial performance improvements of 18 to 19 percentage over LogBert based full finetuning approach, achieving accuracy scores between 97.76% and 98.83% compared to 79.37%.
Authors: Duoyou Chen, Yunqing Chen, Can Zhang, Zhou Wang, Cheng Chen, Ruoxiu Xiao
Abstract: Computed Tomography (CT) is a widely utilized imaging modality in clinical settings. Using densely acquired rotational X-ray arrays, CT can capture 3D spatial features. However, it is confronted with challenged such as significant time consumption and high radiation exposure. CT reconstruction methods based on sparse-view X-ray images have garnered substantial attention from researchers as they present a means to mitigate costs and risks. In recent years, diffusion models, particularly the Latent Diffusion Model (LDM), have demonstrated promising potential in the domain of 3D CT reconstruction. Nonetheless, due to the substantial differences between the 2D latent representation of X-ray modalities and the 3D latent representation of CT modalities, the vanilla LDM is incapable of achieving effective alignment within the latent space. To address this issue, we propose the Consistent Latent Space Diffusion Model (CLS-DM), which incorporates cross-modal feature contrastive learning to efficiently extract latent 3D information from 2D X-ray images and achieve latent space alignment between modalities. Experimental results indicate that CLS-DM outperforms classical and state-of-the-art generative models in terms of standard voxel-level metrics (PSNR, SSIM) on the LIDC-IDRI and CTSpine1K datasets. This methodology not only aids in enhancing the effectiveness and economic viability of sparse X-ray reconstructed CT but can also be generalized to other cross-modal transformation tasks, such as text-to-image synthesis. We have made our code publicly available at https://anonymous.4open.science/r/CLS-DM-50D6/ to facilitate further research and applications in other domains.
Authors: J. Senthilnath, Chen Hao, F. C. Wellstood
Abstract: In semiconductor packaging, accurately recovering 3D information is crucial for non-destructive testing (NDT) to localize circuit defects. This paper presents a novel approach called the 3D Magnetic Inverse Routine (3D MIR), which leverages Magnetic Field Images (MFI) to retrieve the parameters for the 3D current flow of a single-segment. The 3D MIR integrates a deep learning (DL)-based Convolutional Neural Network (CNN), spatial-physics-based constraints, and optimization techniques. The method operates in three stages: i) The CNN model processes the MFI data to predict ($\ell/z_o$), where $\ell$ is the wire length and $z_o$ is the wire's vertical depth beneath the magnetic sensors and classify segment type ($c$). ii) By leveraging spatial-physics-based constraints, the routine provides initial estimates for the position ($x_o$, $y_o$, $z_o$), length ($\ell$), current ($I$), and current flow direction (positive or negative) of the current segment. iii) An optimizer then adjusts these five parameters ($x_o$, $y_o$, $z_o$, $\ell$, $I$) to minimize the difference between the reconstructed MFI and the actual MFI. The results demonstrate that the 3D MIR method accurately recovers 3D information with high precision, setting a new benchmark for magnetic image reconstruction in semiconductor packaging. This method highlights the potential of combining DL and physics-driven optimization in practical applications.
Authors: Jesse J. Hagenaars, Stein Stroobants, Sander M. Bohte, Guido C. H. E. De Croon
Abstract: Vision is an essential part of attitude control for many flying animals, some of which have no dedicated sense of gravity. Flying robots, on the other hand, typically depend heavily on accelerometers and gyroscopes for attitude stabilization. In this work, we present the first vision-only approach to flight control for use in generic environments. We show that a quadrotor drone equipped with a downward-facing event camera can estimate its attitude and rotation rate from just the event stream, enabling flight control without inertial sensors. Our approach uses a small recurrent convolutional neural network trained through supervised learning. Real-world flight tests demonstrate that our combination of event camera and low-latency neural network is capable of replacing the inertial measurement unit in a traditional flight control loop. Furthermore, we investigate the network's generalization across different environments, and the impact of memory and different fields of view. While networks with memory and access to horizon-like visual cues achieve best performance, variants with a narrower field of view achieve better relative generalization. Our work showcases vision-only flight control as a promising candidate for enabling autonomous, insect-scale flying robots.
Authors: Arefin Ittesafun Abian, Ripon Kumar Debnath, Md. Abdur Rahman, Mohaimenul Azam Khan Raiaan, Md Rafiqul Islam, Asif Karim, Reem E. Mohamed, Sami Azam
Abstract: Accurate liver and tumor segmentation on abdominal CT images is critical for reliable diagnosis and treatment planning, but remains challenging due to complex anatomical structures, variability in tumor appearance, and limited annotated data. To address these issues, we introduce Hyperbolic-convolutions Adaptive-temporal-attention with Neural-representation and Synaptic-plasticity Network (HANS-Net), a novel segmentation framework that synergistically combines hyperbolic convolutions for hierarchical geometric representation, a wavelet-inspired decomposition module for multi-scale texture learning, a biologically motivated synaptic plasticity mechanism for adaptive feature enhancement, and an implicit neural representation branch to model fine-grained and continuous anatomical boundaries. Additionally, we incorporate uncertainty-aware Monte Carlo dropout to quantify prediction confidence and lightweight temporal attention to improve inter-slice consistency without sacrificing efficiency. Extensive evaluations of the LiTS dataset demonstrate that HANS-Net achieves a mean Dice score of 93.26%, an IoU of 88.09%, an average symmetric surface distance (ASSD) of 0.72 mm, and a volume overlap error (VOE) of 11.91%. Furthermore, cross-dataset validation on the 3D-IRCADb-01 dataset obtains an average Dice of 87.45%, IoU of 80.30%, ASSD of 1.525 mm, and VOE of 19.71%, indicating strong generalization across different datasets. These results confirm the effectiveness and robustness of HANS-Net in providing anatomically consistent, accurate, and confident liver and tumor segmentation.
Authors: Mehri Mehrnia, Mohammed S. M. Elbaz
Abstract: Efficient entanglement strategies are essential for advancing variational quantum circuits (VQCs) for quantum machine learning (QML). However, most current approaches use fixed entanglement topologies that are not adaptive to task requirements, limiting potential gains over classical models. We introduce a novel stochastic entanglement configuration method that systematically generates diverse entanglement topologies to identify a subspace of constructive entanglement configurations, defined as entanglement topologies that boost hybrid model performance (e.g., classification accuracy) beyond classical baselines. Each configuration is encoded as a stochastic binary matrix, denoting directed entanglement between qubits. This enables scalable exploration of the hyperspace of candidate entanglement topologies using entanglement density and per-qubit constraints as key metrics. We define unconstrained and constrained sampling modes, controlling entanglement per qubit. Using our method, 400 stochastic configurations were generated and evaluated in a hybrid QML for cardiac MRI disease classification. We identified 64 (16%) novel constructive entanglement configurations that consistently outperformed the classical baseline. Ensemble aggregation of top-performing configurations achieved ~0.92 classification accuracy, exceeding the classical model (~0.87) by over 5%. Compared to four conventional topologies (ring, nearest neighbor, no entanglement, fully entangled), none surpassed the classical baseline (maximum accuracy ~0.82), while our configurations delivered up to ~20% higher accuracy. Thus, highlighting the robustness and generalizability of the identified constructive entanglements.
Authors: Hongbo Ye, Fenghe Tang, Peiang Zhao, Zhen Huang, Dexin Zhao, Minghao Bian, S. Kevin Zhou
Abstract: Achieving equity in healthcare accessibility requires lightweight yet high-performance solutions for medical image segmentation, particularly in resource-limited settings. Existing methods like U-Net and its variants often suffer from limited global Effective Receptive Fields (ERFs), hindering their ability to capture long-range dependencies. To address this, we propose U-RWKV, a novel framework leveraging the Recurrent Weighted Key-Value(RWKV) architecture, which achieves efficient long-range modeling at O(N) computational cost. The framework introduces two key innovations: the Direction-Adaptive RWKV Module(DARM) and the Stage-Adaptive Squeeze-and-Excitation Module(SASE). DARM employs Dual-RWKV and QuadScan mechanisms to aggregate contextual cues across images, mitigating directional bias while preserving global context and maintaining high computational efficiency. SASE dynamically adapts its architecture to different feature extraction stages, balancing high-resolution detail preservation and semantic relationship capture. Experiments demonstrate that U-RWKV achieves state-of-the-art segmentation performance with high computational efficiency, offering a practical solution for democratizing advanced medical imaging technologies in resource-constrained environments. The code is available at https://github.com/hbyecoding/U-RWKV.
Authors: Christian Daniele, Silvia Villa, Samuel Vaiter, Luca Calatroni
Abstract: Deep Equilibrium Models (DEQs) are implicit neural networks with fixed points, which have recently gained attention for learning image regularization functionals, particularly in settings involving Gaussian fidelities, where assumptions on the forward operator ensure contractiveness of standard (proximal) Gradient Descent operators. In this work, we extend the application of DEQs to Poisson inverse problems, where the data fidelity term is more appropriately modeled by the Kullback-Leibler divergence. To this end, we introduce a novel DEQ formulation based on Mirror Descent defined in terms of a tailored non-Euclidean geometry that naturally adapts with the structure of the data term. This enables the learning of neural regularizers within a principled training framework. We derive sufficient conditions to guarantee the convergence of the learned reconstruction scheme and propose computational strategies that enable both efficient training and fully parameter-free inference. Numerical experiments show that our method outperforms traditional model-based approaches and it is comparable to the performance of Bregman Plug-and-Play methods, while mitigating their typical drawbacks - namely, sensitivity to initialization and careful tuning of hyperparameters. The code is publicly available at https://github.com/christiandaniele/DEQ-MD.
Authors: Nuri Ryu, Jiyun Won, Jooeun Son, Minsu Gong, Joo-Haeng Lee, Sunghyun Cho
Abstract: High-quality 3D assets are essential for various applications in computer graphics and 3D vision but remain scarce due to significant acquisition costs. To address this shortage, we introduce Elevate3D, a novel framework that transforms readily accessible low-quality 3D assets into higher quality. At the core of Elevate3D is HFS-SDEdit, a specialized texture enhancement method that significantly improves texture quality while preserving the appearance and geometry while fixing its degradations. Furthermore, Elevate3D operates in a view-by-view manner, alternating between texture and geometry refinement. Unlike previous methods that have largely overlooked geometry refinement, our framework leverages geometric cues from images refined with HFS-SDEdit by employing state-of-the-art monocular geometry predictors. This approach ensures detailed and accurate geometry that aligns seamlessly with the enhanced texture. Elevate3D outperforms recent competitors by achieving state-of-the-art quality in 3D model refinement, effectively addressing the scarcity of high-quality open-source 3D assets.
Authors: Md Rakibul Hasan, Shreya Ghosh, Pradyumna Agrawal, Zhixi Cai, Abhinav Dhall, Tom Gedeon
Abstract: This paper proposes an atomic behaviour intervention strategy using the Pavlok wearable device. Pavlok utilises beeps, vibration and shocks as a mode of aversion technique to help individuals with behaviour modification. While the device can be useful in certain periodic daily life situations, like alarms and exercise notifications, it relies on manual operations that limit its usage. To automate behaviour modification, we propose a framework that first detects targeted behaviours through a lightweight deep learning model and subsequently nudges the user. Our proposed solution is implemented and verified in the context of snoring, which captures audio from the environment following a prediction of whether the audio content is a snore or not using a lightweight 1D convolutional neural network. Based on the prediction, we use Pavlok to nudge users for preventive measures, such as a change in sleeping posture. We believe that this simple solution can help people change their atomic habits, which may lead to long-term health benefits. Our proposed lightweight model (99.8% fewer parameters over SOTA; 790,273$\rightarrow$1,337) achieves SOTA test accuracy of 0.99 on a public benchmark. The code and model are publicly available at https://github.com/hasan-rakibul/pavlok-nudge-snore.
Authors: Amit Singh
Abstract: In recent years, end to end steering prediction for autonomous vehicles has become a major area of research. The primary method for achieving end to end steering was to use computer vision models on a live feed of video data. However, to further increase accuracy, many companies have added data from light detection and ranging (LiDAR) and or radar sensors through sensor fusion. However, the addition of lasers and sensors comes at a high financial cost. In this paper, I address both of these issues by increasing the accuracy of the computer vision models without the increased cost of using LiDAR and or sensors. I achieved this by improving the accuracy of computer vision models by sensor fusing CAN bus data, a vehicle protocol, with video data. CAN bus data is a rich source of information about the vehicle's state, including its speed, steering angle, and acceleration. By fusing this data with video data, the accuracy of the computer vision model's predictions can be improved. When I trained the model without CAN bus data, I obtained an RMSE of 0.02492, while the model trained with the CAN bus data achieved an RMSE of 0.01970. This finding indicates that fusing CAN Bus data with video data can reduce the computer vision model's prediction error by 20% with some models decreasing the error by 80%.
Authors: Yechi Ma, Yanan Li, Wei Hua, Shu Kong
Abstract: Roadside monocular 3D detection requires detecting objects of predefined classes in an RGB frame and predicting their 3D attributes, such as bird's-eye-view (BEV) locations. It has broad applications in traffic control, vehicle-vehicle communication, and vehicle-infrastructure cooperative perception. To address this task, we introduce Promptable 3D Detector (Pro3D), a novel detector design that leverages 2D detections as prompts. We build our Pro3D upon two key insights. First, compared to a typical 3D detector, a 2D detector is ``easier'' to train due to fewer loss terms and performs significantly better at localizing objects w.r.t 2D metrics. Second, once 2D detections precisely locate objects in the image, a 3D detector can focus on lifting these detections into 3D BEV, especially when fixed camera pose or scene geometry provide an informative prior. To encode and incorporate 2D detections, we explore three methods: (a) concatenating features from both 2D and 3D detectors, (b) attentively fusing 2D and 3D detector features, and (c) encoding properties of predicted 2D bounding boxes \{$x$, $y$, width, height, label\} and attentively fusing them with the 3D detector feature. Interestingly, the third method significantly outperforms the others, underscoring the effectiveness of 2D detections as prompts that offer precise object targets and allow the 3D detector to focus on lifting them into 3D. Pro3D is adaptable for use with a wide range of 2D and 3D detectors with minimal modifications. Comprehensive experiments demonstrate that our Pro3D significantly enhances existing methods, achieving state-of-the-art results on two contemporary benchmarks.
Authors: Alexandros Xenos, Niki Maria Foteinopoulou, Ioanna Ntinou, Ioannis Patras, Georgios Tzimiropoulos
Abstract: Recognising emotions in context involves identifying an individual's apparent emotions while considering contextual cues from the surrounding scene. Previous approaches to this task have typically designed explicit scene-encoding architectures or incorporated external scene-related information, such as captions. However, these methods often utilise limited contextual information or rely on intricate training pipelines to decouple noise from relevant information. In this work, we leverage the capabilities of Vision-and-Large-Language Models (VLLMs) to enhance in-context emotion classification in a more straightforward manner. Our proposed method follows a simple yet effective two-stage approach. First, we prompt VLLMs to generate natural language descriptions of the subject's apparent emotion in relation to the visual context. Second, the descriptions, along with the visual input, are used to train a transformer-based architecture that fuses text and visual features before the final classification task. This method not only simplifies the training process but also significantly improves performance. Experimental results demonstrate that the textual descriptions effectively guide the model to constrain the noisy visual input, allowing our fused architecture to outperform individual modalities. Our approach achieves state-of-the-art performance across three datasets, BoLD, EMOTIC, and CAER-S, without bells and whistles. The code will be made publicly available on github: https://github.com/NickyFot/EmoCommonSense.git
Authors: Jiangning Zhang, Haoyang He, Zhenye Gan, Qingdong He, Yuxuan Cai, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong Liu
Abstract: Visual anomaly detection aims to identify anomalous regions in images through unsupervised learning paradigms, with increasing application demand and value in fields such as industrial inspection and medical lesion detection. Despite significant progress in recent years, there is a lack of comprehensive benchmarks to adequately evaluate the performance of various mainstream methods across different datasets under the practical multi-class setting. The absence of standardized experimental setups can lead to potential biases in training epochs, resolution, and metric results, resulting in erroneous conclusions. This paper addresses this issue by proposing a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework that is highly extensible for new methods. The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics. Additionally, we have proposed the GPU-assisted ADEval package to address the slow evaluation problem of metrics like time-consuming mAU-PRO on large-scale data, significantly reducing evaluation time by more than \textit{1000-fold}. Through extensive experimental results, we objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection. We hope that ADer will become a valuable resource for researchers and practitioners in the field, promoting the development of more robust and generalizable anomaly detection systems. Full codes are open-sourced at https://github.com/zhangzjn/ader.
Authors: Jinhua Zhang, Hualian Sheng, Sijia Cai, Bing Deng, Qiao Liang, Wen Li, Ying Fu, Jieping Ye, Shuhang Gu
Abstract: Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or ControlNet, to produce commendable outcomes in controllable generation. However, such approaches intrinsically restrict generation performance to the learning capacities of predefined network architectures. In this paper, we explore the innovative integration of controlling information and introduce PerLDiff (\textbf{Per}spective-\textbf{L}ayout \textbf{Diff}usion Models), a novel method for effective street view image generation that fully leverages perspective 3D geometric information. Our PerLDiff employs 3D geometric priors to guide the generation of street view images with precise object-level control within the network learning process, resulting in a more robust and controllable output. Moreover, it demonstrates superior controllability compared to alternative layout control methods. Empirical results justify that our PerLDiff markedly enhances the precision of controllable generation on the NuScenes and KITTI datasets.
Authors: Aditya Murali, Farahdiba Zarin, Adrien Meyer, Pietro Mascagni, Didier Mutter, Nicolas Padoy
Abstract: Surgical image segmentation is highly challenging, primarily due to scarcity of annotated data. Generalist prompted segmentation models like the Segment-Anything Model (SAM) can help tackle this task, but because they require image-specific visual prompts for effective performance, their use is limited to improving data annotation efficiency. Recent approaches extend SAM to automatic segmentation by using a few labeled reference images to predict point prompts; however, they rely on feature matching pipelines that lack robustness to out-of-domain data like surgical images. To tackle this problem, we introduce CycleSAM, an improved visual prompt learning approach that employs a data-efficient training phase and enforces a series of soft constraints to produce high-quality feature similarity maps. CycleSAM label-efficiently addresses domain gap by leveraging surgery-specific self-supervised feature extractors, then adapts the resulting features through a short parameter-efficient training stage, enabling it to produce informative similarity maps. CycleSAM further filters the similarity maps with a series of consistency constraints before robustly sampling diverse point prompts for each object instance. In our experiments on four diverse surgical datasets, we find that CycleSAM outperforms existing few-shot SAM approaches by a factor of 2-4x in both 1-shot and 5-shot settings, while also achieving strong performance gains over traditional linear probing, parameter-efficient adaptation, and pseudo-labeling methods.
Authors: Jikang Cheng, Ying Zhang, Qin Zou, Zhiyuan Yan, Chao Liang, Zhongyuan Wang, Chen Li
Abstract: Learning intrinsic bias from limited data has been considered the main reason for the failure of deepfake detection with generalizability. Apart from the discovered content and specific-forgery bias, we reveal a novel spatial bias, where detectors inertly anticipate observing structural forgery clues appearing at the image center, also can lead to the poor generalization of existing methods. We present ED$^4$, a simple and effective strategy, to address aforementioned biases explicitly at the data level in a unified framework rather than implicit disentanglement via network design. In particular, we develop ClockMix to produce facial structure preserved mixtures with arbitrary samples, which allows the detector to learn from an exponentially extended data distribution with much more diverse identities, backgrounds, local manipulation traces, and the co-occurrence of multiple forgery artifacts. We further propose the Adversarial Spatial Consistency Module (AdvSCM) to prevent extracting features with spatial bias, which adversarially generates spatial-inconsistent images and constrains their extracted feature to be consistent. As a model-agnostic debiasing strategy, ED$^4$ is plug-and-play: it can be integrated with various deepfake detectors to obtain significant benefits. We conduct extensive experiments to demonstrate its effectiveness and superiority over existing deepfake detection approaches.
Authors: Xianmin Chen, Longfei Han, Peiliang Huang, Xiaoxu Feng, Dingwen Zhang, Junwei Han
Abstract: Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge. Many deep learning-based methods have been developed to address this issue and have shown promising results in recent years. However, single-stage methods, which attempt to unify the complex mapping across both domains, leading to limited denoising performance. In contrast, existing two-stage approaches typically overlook the characteristic of demosaicing within the Image Signal Processing (ISP) pipeline, leading to color distortions under varying lighting conditions, especially in low-light scenarios. To address these issues, we propose a novel Mamba-based method customized for low light RAW images, called RAWMamba, to effectively handle raw images with different CFAs. Furthermore, we introduce a Retinex Decomposition Module (RDM) grounded in Retinex prior, which decouples illumination from reflectance to facilitate more effective denoising and automatic non-linear exposure correction, reducing the effect of manual linear illumination enhancement. By bridging demosaicing and denoising, better enhancement for low light RAW images is achieved. Experimental evaluations conducted on public datasets SID and MCR demonstrate that our proposed RAWMamba achieves state-of-the-art performance on cross-domain mapping. The code is available at https://github.com/Cynicarlos/RetinexRawMamba.
Authors: Bojian Li, Bo Liu, Xinning Yao, Jinghua Yue, Fugen Zhou
Abstract: Depth estimation is a cornerstone of 3D reconstruction and plays a vital role in minimally invasive endoscopic surgeries. However, most current depth estimation networks rely on traditional convolutional neural networks, which are limited in their ability to capture global information. Foundation models offer a promising approach to enhance depth estimation, but those models currently available are primarily trained on natural images, leading to suboptimal performance when applied to endoscopic images. In this work, we introduce a novel fine-tuning strategy for the Depth Anything Model and integrate it with an intrinsic-based unsupervised monocular depth estimation framework. Our approach includes a low-rank adaptation technique based on random vectors, which improves the model's adaptability to different scales. Additionally, we propose a residual block built on depthwise separable convolution to compensate for the transformer's limited ability to capture local features. Our experimental results on the SCARED dataset and Hamlyn dataset show that our method achieves state-of-the-art performance while minimizing the number of trainable parameters. Applying this method in minimally invasive endoscopic surgery can enhance surgeons' spatial awareness, thereby improving the precision and safety of the procedures.
Authors: Hongyu Chen, Weiming Zeng, Chengcheng Chen, Luhui Cai, Fei Wang, Yuhu Shi, Lei Wang, Wei Zhang, Yueyang Li, Hongjie Yan, Wai Ting Siok, Nizhuan Wang
Abstract: In the fields of affective computing (AC) and brain-machine interface (BMI), the analysis of physiological and behavioral signals to discern individual emotional states has emerged as a critical research frontier. While deep learning-based approaches have made notable strides in EEG emotion recognition, particularly in feature extraction and pattern recognition, significant challenges persist in achieving end-to-end emotion computation, including real-time processing, individual adaptation, and seamless user interaction. This paper presents the EEG Emotion Copilot, a system optimizing a lightweight large language model (LLM) with 0.5B parameters operating in a local setting, which first recognizes emotional states directly from EEG signals, subsequently generates personalized diagnostic and treatment suggestions, and finally supports the automation of assisted electronic medical records. Specifically, we demonstrate the critical techniques in the novel data structure of prompt, model pruning and fine-tuning training, and deployment strategies aiming at improving real-time performance and computational efficiency. Extensive experiments show that our optimized lightweight LLM-based copilot achieves an enhanced intuitive interface for participant interaction, superior accuracy of emotion recognition and assisted electronic medical records generation, in comparison to such models with similar scale parameters or large-scale parameters such as 1.5B, 1.8B, 3B and 7B. In summary, through these efforts, the proposed copilot is expected to advance the application of AC in the medical domain, offering innovative solution to mental health monitoring. The codes will be released at https://github.com/NZWANG/EEG_Emotion_Copilot.
Authors: Yongkun Du, Zhineng Chen, Hongtao Xie, Caiyan Jia, Yu-Gang Jiang
Abstract: Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture, which only contains a visual model and a CTC-aligned linear classifier, and therefore fast inference. However, they generally exhibit worse accuracy than encoder-decoder-based methods (EDTRs) due to struggling with text irregularity and linguistic missing. To address these challenges, we propose SVTRv2, a CTC model endowed with the ability to handle text irregularities and model linguistic context. First, a multi-size resizing strategy is proposed to resize text instances to appropriate predefined sizes, effectively avoiding severe text distortion. Meanwhile, we introduce a feature rearrangement module to ensure that visual features accommodate the requirement of CTC, thus alleviating the alignment puzzle. Second, we propose a semantic guidance module. It integrates linguistic context into the visual features, allowing CTC model to leverage language information for accuracy improvement. This module can be omitted at the inference stage and would not increase the time cost. We extensively evaluate SVTRv2 in both standard and recent challenging benchmarks, where SVTRv2 is fairly compared to popular STR models across multiple scenarios, including different types of text irregularity, languages, long text, and whether employing pretraining. SVTRv2 surpasses most EDTRs across the scenarios in terms of accuracy and inference speed. Code: https://github.com/Topdu/OpenOCR.
Authors: M. M. A. Valiuddin, R. J. G. van Sloun, C. G. A. Viviers, P. H. N. de With, F. van der Sommen
Abstract: Advances in architectural design, data availability, and compute have driven remarkable progress in semantic segmentation. Yet, these models often rely on relaxed Bayesian assumptions, omitting critical uncertainty information needed for robust decision-making. The resulting reliance on point estimates has fueled interest in probabilistic segmentation, but the literature remains fragmented. In response, this review consolidates and contextualizes foundational concepts in uncertainty modeling, including the non-trivial task of distinguishing between epistemic and aleatoric uncertainty and examining their roles across four key downstream segmentation tasks, highlighting Active Learning as particularly promising. By unifying theory, terminology, and applications, we provide a coherent foundation for researchers and identify critical challenges, such as strong assumptions in spatial aggregation, lack of standardized benchmarks, and pitfalls in current uncertainty quantification methods. We identify trends such as the adoption of contemporary generative models, driven by advances in the broader field of generative modeling, with segmentation-specific innovation primarily in the conditioning mechanisms. Moreover, we observe growing interest in distribution- and sampling-free approaches to uncertainty estimation. We further propose directions for advancing uncertainty-aware segmentation in deep learning, including pragmatic strategies for disentangling different sources of uncertainty, novel uncertainty modeling approaches and improved Transformer-based backbones. In this way, we aim to support the development of more reliable, efficient, and interpretable segmentation models that effectively incorporate uncertainty into real-world applications.
Authors: Zhaofeng Hu, Sifan Zhou, Zhihang Yuan, Dawei Yang, Shibo Zhao, Ci-Jyun Liang
Abstract: 3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset.
Authors: Pooyan Rahmanzadehgervi, Hung Huy Nguyen, Rosanne Liu, Long Mai, Anh Totti Nguyen
Abstract: Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the attribution of each input patch to the output of a model. We propose a novel 1-head Transformer Attention Bottleneck (TAB) layer, inserted after the traditional MHSA architecture, to serve as an attention bottleneck for interpretability and intervention. Unlike standard self-attention, TAB constrains the total attention over all patches to $\in [0, 1]$. That is, when the total attention is 0, no visual information is propagated further into the network, and the vision-language model (VLM) would default to a generic, image-independent response. To demonstrate the advantages of TAB, we train VLMs with TAB to perform image-difference captioning. Over three datasets, our models perform similarly to baseline VLMs in captioning but the bottleneck is superior in localizing changes and in identifying when no changes occur. TAB is the first architecture to enable users to debug by editing attention, which often produces expected outputs by VLMs.
Authors: Genc Hoxha, Oliv\'er Angyal, Beg\"um Demir
Abstract: The development of image time series retrieval (ITSR) methods is a growing research interest in remote sensing (RS). Given a user-defined image time series (i.e., the query time series), ITSR methods search and retrieve from large archives the image time series that have similar content to the query time series. Existing ITSR methods in RS are designed for unimodal retrieval problems, relying on an assumption that users always have access to a query image time series in the considered image modality. In operational scenarios, this assumption may not hold. To overcome this issue, as a first time in RS we introduce the task of cross-modal text-image time series retrieval (text-ITSR). In detail, we present a self-supervised cross-modal text-ITSR method that enables the retrieval of image time series using text sentences as queries, and vice versa. We focus our attention on text-ITSR in pairs of images (i.e., bitemporal images). Our text-ITSR method consists of two key components: 1) modality-specific encoders to model the semantic content of bitemporal images and text sentences with discriminative features; and 2) modality-specific projection heads to align textual and image representations in a shared embedding space. To effectively model the temporal information in the bitemporal images, we exploit two fusion strategies: i) global feature fusion (GFF) strategy that combines global image features through simple yet effective operators; and ii) transformer-based feature fusion (TFF) strategy that leverages transformers for fine-grained temporal integration. Extensive experiments conducted on two benchmark RS archives demonstrate the effectiveness of our method in accurately retrieving semantically relevant bitemporal images (or text sentences) to a query text sentence (or bitemporal image). The code of this work is publicly available at https://git.tu-berlin.de/rsim/cross-modal-text-tsir .
Authors: Zixi Kang, Xinghan Wang, Yadong Mu
Abstract: Human pose, action, and motion generation are critical for applications in digital humans, character animation, and humanoid robotics. However, many existing methods struggle to produce physically plausible movements that are consistent with biomechanical principles. Although recent autoregressive and diffusion models deliver impressive visual quality, they often neglect key biodynamic features and fail to ensure physically realistic motions. Reinforcement Learning (RL) approaches can address these shortcomings but are highly dependent on simulation environments, limiting their generalizability. To overcome these challenges, we propose BioVAE, a biomechanics-aware framework with three core innovations: (1) integration of muscle electromyography (EMG) signals and kinematic features with acceleration constraints to enable physically plausible motion without simulations; (2) seamless coupling with diffusion models for stable end-to-end training; and (3) biomechanical priors that promote strong generalization across diverse motion generation and estimation tasks. Extensive experiments demonstrate that BioVAE achieves state-of-the-art performance on multiple benchmarks, bridging the gap between data-driven motion synthesis and biomechanical authenticity while setting new standards for physically accurate motion generation and pose estimation.
Authors: Zhixuan Li, Hyunse Yoon, Sanghoon Lee, Weisi Lin
Abstract: Amodal segmentation aims to infer the complete shape of occluded objects, even when the occluded region's appearance is unavailable. However, current amodal segmentation methods lack the capability to interact with users through text input and struggle to understand or reason about implicit and complex purposes. While methods like LISA integrate multi-modal large language models (LLMs) with segmentation for reasoning tasks, they are limited to predicting only visible object regions and face challenges in handling complex occlusion scenarios. To address these limitations, we propose a novel task named amodal reasoning segmentation, aiming to predict the complete amodal shape of occluded objects while providing answers with elaborations based on user text input. We develop a generalizable dataset generation pipeline and introduce a new dataset focusing on daily life scenarios, encompassing diverse real-world occlusions. Furthermore, we present AURA (Amodal Understanding and Reasoning Assistant), a novel model with advanced global and spatial-level designs specifically tailored to handle complex occlusions. Extensive experiments validate AURA's effectiveness on the proposed dataset.
Authors: Rui Hu, Lianghui Zhu, Yuxuan Zhang, Tianheng Cheng, Lei Liu, Heng Liu, Longjin Ran, Xiaoxin Chen, Wenyu Liu, Xinggang Wang
Abstract: Pixel grounding, encompassing tasks such as Referring Expression Segmentation (RES), has garnered considerable attention due to its immense potential for bridging the gap between vision and language modalities. However, advancements in this domain are currently constrained by limitations inherent in existing datasets, including limited object categories, insufficient textual diversity, and a scarcity of high-quality annotations. To mitigate these limitations, we introduce GroundingSuite, which comprises: (1) an automated data annotation framework leveraging multiple Vision-Language Model (VLM) agents; (2) a large-scale training dataset encompassing 9.56 million diverse referring expressions and their corresponding segmentations; and (3) a meticulously curated evaluation benchmark consisting of 3,800 images. The GroundingSuite training dataset facilitates substantial performance improvements, enabling models trained on it to achieve state-of-the-art results. Specifically, a cIoU of 68.9 on gRefCOCO and a gIoU of 55.3 on RefCOCOm. Moreover, the GroundingSuite annotation framework demonstrates superior efficiency compared to the current leading data annotation method, i.e., $4.5 \times$ faster than GLaMM.
Authors: Sanghyun Jo, Seo Jin Lee, Seungwoo Lee, Seohyung Hong, Hyungseok Seo, Kyungsu Kim
Abstract: Cell instance segmentation (CIS) is crucial for identifying individual cell morphologies in histopathological images, providing valuable insights for biological and medical research. While unsupervised CIS (UCIS) models aim to reduce the heavy reliance on labor-intensive image annotations, they fail to accurately capture cell boundaries, causing missed detections and poor performance. Recognizing the absence of error-free instances as a key limitation, we present COIN (COnfidence score-guided INstance distillation), a novel annotation-free framework with three key steps: (1) Increasing the sensitivity for the presence of error-free instances via unsupervised semantic segmentation with optimal transport, leveraging its ability to discriminate spatially minor instances, (2) Instance-level confidence scoring to measure the consistency between model prediction and refined mask and identify highly confident instances, offering an alternative to ground truth annotations, and (3) Progressive expansion of confidence with recursive self-distillation. Extensive experiments across six datasets show COIN outperforming existing UCIS methods, even surpassing semi- and weakly-supervised approaches across all metrics on the MoNuSeg and TNBC datasets. The code is available at https://github.com/shjo-april/COIN.
Authors: Martin Ki\v{s}\v{s}, Michal Hradi\v{s}, Martina Dvo\v{r}\'akov\'a, V\'aclav Jirou\v{s}ek, Filip Kersch
Abstract: We introduce the AnnoPage Dataset, a novel collection of 7,550 pages from historical documents, primarily in Czech and German, spanning from 1485 to the present, focusing on the late 19th and early 20th centuries. The dataset is designed to support research in document layout analysis and object detection. Each page is annotated with axis-aligned bounding boxes (AABB) representing elements of 25 categories of non-textual elements, such as images, maps, decorative elements, or charts, following the Czech Methodology of image document processing. The annotations were created by expert librarians to ensure accuracy and consistency. The dataset also incorporates pages from multiple, mainly historical, document datasets to enhance variability and maintain continuity. The dataset is divided into development and test subsets, with the test set carefully selected to maintain the category distribution. We provide baseline results using YOLO and DETR object detectors, offering a reference point for future research. The AnnoPage Dataset is publicly available on Zenodo (https://doi.org/10.5281/zenodo.12788419), along with ground-truth annotations in YOLO format.
Authors: Marek Va\v{s}ko, Adam Herout, Michal Hradi\v{s}
Abstract: When digitizing historical archives, it is necessary to search for the faces of celebrities and ordinary people, especially in newspapers, link them to the surrounding text, and make them searchable. Existing face detectors on datasets of scanned historical documents fail remarkably -- current detection tools only achieve around 24% mAP at 50:90% IoU. This work compensates for this failure by introducing a new manually annotated domain-specific dataset in the style of the popular Wider Face dataset, containing 2.2k new images from digitized historical newspapers from the 19th to 20th century, with 11k new bounding-box annotations and associated facial landmarks. This dataset allows existing detectors to be retrained to bring their results closer to the standard in the field of face detection in the wild. We report several experimental results comparing different families of fine-tuned detectors against publicly available pre-trained face detectors and ablation studies of multiple detector sizes with comprehensive detection and landmark prediction performance results.
Authors: Lin Liu, Caiyan Jia, Ziying Song, Hongyu Pan, Bencheng Liao, Wenchao Sun, Yongchang Zhang, Lei Yang, Yandan Luo
Abstract: Current end-to-end autonomous driving methods typically learn only from expert planning data collected from a single ego vehicle, severely limiting the diversity of learnable driving policies and scenarios. However, a critical yet overlooked fact is that in any driving scenario, multiple high-quality trajectories from other vehicles coexist with a specific ego vehicle's trajectory. Existing methods fail to fully exploit this valuable resource, missing important opportunities to improve the models' performance (including long-tail scenarios) through learning from other experts. Intuitively, Jointly learning from both ego and other vehicles' expert data is beneficial for planning tasks. However, this joint learning faces two critical challenges. (1) Different scene observation perspectives across vehicles hinder inter-vehicle alignment of scene feature representations; (2) The absence of partial modality in other vehicles' data (e.g., vehicle states) compared to ego-vehicle data introduces learning bias. To address these challenges, we propose FUMP (Fully Unified Motion Planning), a novel two-stage trajectory generation framework. Building upon probabilistic decomposition, we model the planning task as a specialized subtask of motion prediction. Specifically, our approach decouples trajectory planning into two stages. In Stage 1, a shared decoder jointly generates initial trajectories for both tasks. In Stage 2, the model performs planning-specific refinement conditioned on an ego-vehicle's state. The transition between the two stages is bridged by a state predictor trained exclusively on ego-vehicle data. To address the cross-vehicle discrepancy in observational perspectives, we propose an Equivariant Context-Sharing Adapter (ECSA) before Stage 1 for improving cross-vehicle generalization of scene representations.
Authors: Siyu Chen, Ting Han, Changshe Zhang, Xin Luo, Meiliu Wu, Guorong Cai, Jinhe Su
Abstract: Vision Foundation Models (VFMs) have delivered remarkable performance in Domain Generalized Semantic Segmentation (DGSS). However, recent methods often overlook the fact that visual cues are susceptible, whereas the underlying geometry remains stable, rendering depth information more robust. In this paper, we investigate the potential of integrating depth information with features from VFMs, to improve the geometric consistency within an image and boost the generalization performance of VFMs. We propose a novel fine-tuning DGSS framework, named DepthForge, which integrates the visual cues from frozen DINOv2 or EVA02 and depth cues from frozen Depth Anything V2. In each layer of the VFMs, we incorporate depth-aware learnable tokens to continuously decouple domain-invariant visual and spatial information, thereby enhancing depth awareness and attention of the VFMs. Finally, we develop a depth refinement decoder and integrate it into the model architecture to adaptively refine multi-layer VFM features and depth-aware learnable tokens. Extensive experiments are conducted based on various DGSS settings and five different datsets as unseen target domains. The qualitative and quantitative results demonstrate that our method significantly outperforms alternative approaches with stronger performance, steadier visual-spatial attention, and superior generalization ability. In particular, DepthForge exhibits outstanding performance under extreme conditions (e.g., night and snow). Code is available at https://github.com/anonymouse-xzrptkvyqc/DepthForge.
Authors: Kesen Zhao, Beier Zhu, Qianru Sun, Hanwang Zhang
Abstract: Chain-of-thought (CoT) reasoning greatly improves the interpretability and problem-solving abilities of multimodal large language models (MLLMs). However, existing approaches are focused on text CoT, limiting their ability to leverage visual cues. Visual CoT remains underexplored, and the only work is based on supervised fine-tuning (SFT) that relies on extensive labeled bounding-box data and is hard to generalize to unseen cases. In this paper, we introduce Unsupervised Visual CoT (UV-CoT), a novel framework for image-level CoT reasoning via preference optimization. UV-CoT performs preference comparisons between model-generated bounding boxes (one is preferred and the other is dis-preferred), eliminating the need for bounding-box annotations. We get such preference data by introducing an automatic data generation pipeline. Given an image, our target MLLM (e.g., LLaVA-1.5-7B) generates seed bounding boxes using a template prompt and then answers the question using each bounded region as input. An evaluator MLLM (e.g., OmniLLM-12B) ranks the responses, and these rankings serve as supervision to train the target MLLM with UV-CoT by minimizing negative log-likelihood losses. By emulating human perception--identifying key regions and reasoning based on them--UV-CoT can improve visual comprehension, particularly in spatial reasoning tasks where textual descriptions alone fall short. Our experiments on six datasets demonstrate the superiority of UV-CoT, compared to the state-of-the-art textual and visual CoT methods. Our zero-shot testing on four unseen datasets shows the strong generalization of UV-CoT. The code is available in https://github.com/kesenzhao/UV-CoT.
Authors: Hong Zhang, Zhongjie Duan, Xingjun Wang, Yuze Zhao, Weiyi Lu, Zhipeng Di, Yixuan Xu, Yingda Chen, Yu Zhang
Abstract: Unified multimodal generative models aim to integrate image understanding and generation abilities, offering significant advantages in harnessing multimodal corpora, particularly interleaved text-image data. However, existing unified models exhibit limitations in image synthesis quality, autoregressive error accumulation, and image editing capability. In this work, we propose Nexus-Gen, a novel architecture that unifies image understanding, generation, and editing tasks in a shared image embedding space. This shared space serves as a bridge for the autoregressive and diffusion models, which seamlessly integrates their complementary strengths in cross-modal modeling. To mitigate the severe error accumulation during autoregressive embedding prediction, we propose a novel prefilled autoregression strategy that aligns training-inference dynamics by prefilling input sequences with learnable embeddings. After multi-stage and multi-task training on our constructed large-scale dataset with 26.3 million samples, Nexus-Gen achieves state-of-the-art performance on the evaluation benchmarks spanning image understanding, generation and editing tasks. All models, datasets, and source codes are released in https://github.com/modelscope/Nexus-Gen to facilitate further advancements across the field.
Authors: Dung Nguyen, Minh Khoi Ho, Huy Ta, Thanh Tam Nguyen, Qi Chen, Kumar Rav, Quy Duong Dang, Satwik Ramchandre, Son Lam Phung, Zhibin Liao, Minh-Son To, Johan Verjans, Phi Le Nguyen, Vu Minh Hieu Phan
Abstract: Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate localization reasoning. This work reveals a critical limitation in current medical LMMs: instead of analyzing relevant pathological regions, they often rely on linguistic patterns or attend to irrelevant image areas when responding to disease-related queries. To address this, we introduce HEAL-MedVQA (Hallucination Evaluation via Localization MedVQA), a comprehensive benchmark designed to evaluate LMMs' localization abilities and hallucination robustness. HEAL-MedVQA features (i) two innovative evaluation protocols to assess visual and textual shortcut learning, and (ii) a dataset of 67K VQA pairs, with doctor-annotated anatomical segmentation masks for pathological regions. To improve visual reasoning, we propose the Localize-before-Answer (LobA) framework, which trains LMMs to localize target regions of interest and self-prompt to emphasize segmented pathological areas, generating grounded and reliable answers. Experimental results demonstrate that our approach significantly outperforms state-of-the-art biomedical LMMs on the challenging HEAL-MedVQA benchmark, advancing robustness in medical VQA.
Authors: Giuseppe Guarino, Matteo Ciotola, Gemine Vivone, Giovanni Poggi, Giuseppe Scarpa
Abstract: Hyperspectral pansharpening has received much attention in recent years due to technological and methodological advances that open the door to new application scenarios. However, research on this topic is only now gaining momentum. The most popular methods are still borrowed from the more mature field of multispectral pansharpening and often overlook the unique challenges posed by hyperspectral data fusion, such as i) the very large number of bands, ii) the overwhelming noise in selected spectral ranges, iii) the significant spectral mismatch between panchromatic and hyperspectral components, iv) a typically high resolution ratio. Imprecise data modeling especially affects spectral fidelity. Even state-of-the-art methods perform well in certain spectral ranges and much worse in others, failing to ensure consistent quality across all bands, with the risk of generating unreliable results. Here, we propose a hyperspectral pansharpening method that explicitly addresses this problem and ensures uniform spectral quality. To this end, a single lightweight neural network is used, with weights that adapt on the fly to each band. During fine-tuning, the spatial loss is turned on and off to ensure a fast convergence of the spectral loss to the desired level, according to a hysteresis-like dynamic. Furthermore, the spatial loss itself is appropriately redefined to account for nonlinear dependencies between panchromatic and spectral bands. Overall, the proposed method is fully unsupervised, with no prior training on external data, flexible, and low-complexity. Experiments on a recently published benchmarking toolbox show that it ensures excellent sharpening quality, competitive with the state-of-the-art, consistently across all bands. The software code and the full set of results are shared online on https://github.com/giu-guarino/rho-PNN.
Authors: Jeongsol Kim, Yeobin Hong, Jonghyun Park, Jong Chul Ye
Abstract: Recent inversion-free, flow-based image editing methods such as FlowEdit leverages a pre-trained noise-to-image flow model such as Stable Diffusion 3, enabling text-driven manipulation by solving an ordinary differential equation (ODE). While the lack of exact latent inversion is a core advantage of these methods, it often results in unstable editing trajectories and poor source consistency. To address this limitation, we propose {\em FlowAlign}, a novel inversion-free flow-based framework for consistent image editing with optimal control-based trajectory control. Specifically, FlowAlign introduces source similarity at the terminal point as a regularization term to promote smoother and more consistent trajectories during the editing process. Notably, our terminal point regularization is shown to explicitly balance semantic alignment with the edit prompt and structural consistency with the source image along the trajectory. Furthermore, FlowAlign naturally supports reverse editing by simply reversing the ODE trajectory, highliting the reversible and consistent nature of the transformation. Extensive experiments demonstrate that FlowAlign outperforms existing methods in both source preservation and editing controllability.
Authors: Jeonghyeok Do, Sungpyo Kim, Geunhyuk Youk, Jaehyup Lee, Munchurl Kim
Abstract: PAN-sharpening aims to fuse high-resolution panchromatic (PAN) images with low-resolution multi-spectral (MS) images to generate high-resolution multi-spectral (HRMS) outputs. However, cross-modality misalignment -- caused by sensor placement, acquisition timing, and resolution disparity -- induces a fundamental challenge. Conventional deep learning methods assume perfect pixel-wise alignment and rely on per-pixel reconstruction losses, leading to spectral distortion, double edges, and blurring when misalignment is present. To address this, we propose PAN-Crafter, a modality-consistent alignment framework that explicitly mitigates the misalignment gap between PAN and MS modalities. At its core, Modality-Adaptive Reconstruction (MARs) enables a single network to jointly reconstruct HRMS and PAN images, leveraging PAN's high-frequency details as auxiliary self-supervision. Additionally, we introduce Cross-Modality Alignment-Aware Attention (CM3A), a novel mechanism that bidirectionally aligns MS texture to PAN structure and vice versa, enabling adaptive feature refinement across modalities. Extensive experiments on multiple benchmark datasets demonstrate that our PAN-Crafter outperforms the most recent state-of-the-art method in all metrics, even with 50.11$\times$ faster inference time and 0.63$\times$ the memory size. Furthermore, it demonstrates strong generalization performance on unseen satellite datasets, showing its robustness across different conditions.
Authors: Shuo Zhang
Abstract: Crack detection on road surfaces is a critical measurement technology in the instrumentation domain, essential for ensuring infrastructure safety and transportation reliability. However, due to limited energy and low-resolution imaging, smart terminal devices struggle to maintain real-time monitoring performance. To overcome these challenges, this paper proposes a multi-stage detection approach for road crack detection, EECD-Net, to enhance accuracy and energy efficiency of instrumentation. Specifically, the sophisticated Super-Resolution Convolutional Neural Network (SRCNN) is employed to address the inherent challenges of low-quality images, which effectively enhance image resolution while preserving critical structural details. Meanwhile, a Spike Convolution Unit (SCU) with Continuous Integrate-and-Fire (CIF) neurons is proposed to convert these images into sparse pulse sequences, significantly reducing power consumption. Additionally, a Gated Attention Transformer (GAT) module is designed to strategically fuse multi-scale feature representations through adaptive attention mechanisms, effectively capturing both long-range dependencies and intricate local crack patterns, and significantly enhancing detection robustness across varying crack morphologies. The experiments on the CrackVision12K benchmark demonstrate that EECD-Net achieves a remarkable 98.6\% detection accuracy, surpassing state-of-the-art counterparts such as Hybrid-Segmentor by a significant 1.5\%. Notably, the EECD-Net maintains exceptional energy efficiency, consuming merely 5.6 mJ, which is a substantial 33\% reduction compared to baseline implementations. This work pioneers a transformative approach in instrumentation-based crack detection, offering a scalable, low-power solution for real-time, large-scale infrastructure monitoring in resource-constrained environments.
Authors: Ruicheng Zhang, Yu Sun, Zeyu Zhang, Jinai Li, Xiaofan Liu, Au Hoi Fan, Haowei Guo, Puxin Yan
Abstract: We introduce MARL-MambaContour, the first contour-based medical image segmentation framework based on Multi-Agent Reinforcement Learning (MARL). Our approach reframes segmentation as a multi-agent cooperation task focused on generate topologically consistent object-level contours, addressing the limitations of traditional pixel-based methods which could lack topological constraints and holistic structural awareness of anatomical regions. Each contour point is modeled as an autonomous agent that iteratively adjusts its position to align precisely with the target boundary, enabling adaptation to blurred edges and intricate morphologies common in medical images. This iterative adjustment process is optimized by a contour-specific Soft Actor-Critic (SAC) algorithm, further enhanced with the Entropy Regularization Adjustment Mechanism (ERAM) which dynamically balance agent exploration with contour smoothness. Furthermore, the framework incorporates a Mamba-based policy network featuring a novel Bidirectional Cross-attention Hidden-state Fusion Mechanism (BCHFM). This mechanism mitigates potential memory confusion limitations associated with long-range modeling in state space models, thereby facilitating more accurate inter-agent information exchange and informed decision-making. Extensive experiments on five diverse medical imaging datasets demonstrate the state-of-the-art performance of MARL-MambaContour, highlighting its potential as an accurate and robust clinical application.
Authors: Kun Yuan, Tingxuan Chen, Shi Li, Joel L. Lavanchy, Christian Heiliger, Ege \"Ozsoy, Yiming Huang, Long Bai, Nassir Navab, Vinkle Srivastav, Hongliang Ren, Nicolas Padoy
Abstract: The complexity and diversity of surgical workflows, driven by heterogeneous operating room settings, institutional protocols, and anatomical variability, present a significant challenge in developing generalizable models for cross-institutional and cross-procedural surgical understanding. While recent surgical foundation models pretrained on large-scale vision-language data offer promising transferability, their zero-shot performance remains constrained by domain shifts, limiting their utility in unseen surgical environments. To address this, we introduce Surgical Phase Anywhere (SPA), a lightweight framework for versatile surgical workflow understanding that adapts foundation models to institutional settings with minimal annotation. SPA leverages few-shot spatial adaptation to align multi-modal embeddings with institution-specific surgical scenes and phases. It also ensures temporal consistency through diffusion modeling, which encodes task-graph priors derived from institutional procedure protocols. Finally, SPA employs dynamic test-time adaptation, exploiting the mutual agreement between multi-modal phase prediction streams to adapt the model to a given test video in a self-supervised manner, enhancing the reliability under test-time distribution shifts. SPA is a lightweight adaptation framework, allowing hospitals to rapidly customize phase recognition models by defining phases in natural language text, annotating a few images with the phase labels, and providing a task graph defining phase transitions. The experimental results show that the SPA framework achieves state-of-the-art performance in few-shot surgical phase recognition across multiple institutions and procedures, even outperforming full-shot models with 32-shot labeled data. Code is available at https://github.com/CAMMA-public/SPA
Authors: Nuoye Xiong, Anqi Dong, Ning Wang, Cong Hua, Guangming Zhu, Lin Mei, Peiyi Shen, Liang Zhang
Abstract: Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU.
Authors: Quang-Huy Che, Vinh-Tiep Nguyen
Abstract: Open-vocabulary semantic segmentation (OVSS) aims to segment objects from arbitrary text categories without requiring densely annotated datasets. Although contrastive learning based models enable zero-shot segmentation, they often lose fine spatial precision at pixel level, due to global representation bias. In contrast, diffusion-based models naturally encode fine-grained spatial features via attention mechanisms that capture both global context and local details. However, they often face challenges in balancing the computation costs and the quality of the segmentation mask. In this work, we present FA-Seg, a Fast and Accurate training-free framework for open-vocabulary segmentation based on diffusion models. FA-Seg performs segmentation using only a (1+1)-step from a pretrained diffusion model. Moreover, instead of running multiple times for different classes, FA-Seg performs segmentation for all classes at once. To further enhance the segmentation quality, FA-Seg introduces three key components: (i) a dual-prompt mechanism for discriminative, class-aware attention extraction, (ii) a Hierarchical Attention Refinement Method (HARD) that enhances semantic precision via multi-resolution attention fusion, and (iii) a Test-Time Flipping (TTF) scheme designed to improve spatial consistency. Extensive experiments show that FA-Seg achieves state-of-the-art training-free performance, obtaining 43.8% average mIoU across PASCAL VOC, PASCAL Context, and COCO Object benchmarks while maintaining superior inference efficiency. Our results demonstrate that FA-Seg provides a strong foundation for extendability, bridging the gap between segmentation quality and inference efficiency. The source code will be open-sourced after this paper is accepted.
Authors: Hao Tang, Zhiqing Guo, Liejun Wang, Chao Liu
Abstract: In recent years, it has been found that "grandmother cells" in the primary visual cortex (V1) of macaques can directly recognize visual input with complex shapes. This inspires us to examine the value of these cells in promoting the research of medical image segmentation. In this paper, we design a Similarity Memory Prior Network (Sim-MPNet) for medical image segmentation. Specifically, we propose a Dynamic Memory Weights-Loss Attention (DMW-LA), which matches and remembers the category features of specific lesions or organs in medical images through the similarity memory prior in the prototype memory bank, thus helping the network to learn subtle texture changes between categories. DMW-LA also dynamically updates the similarity memory prior in reverse through Weight-Loss Dynamic (W-LD) update strategy, effectively assisting the network directly extract category features. In addition, we propose the Double-Similarity Global Internal Enhancement Module (DS-GIM) to deeply explore the internal differences in the feature distribution of input data through cosine similarity and euclidean distance. Extensive experiments on four public datasets show that Sim-MPNet has better segmentation performance than other state-of-the-art methods. Our code is available on https://github.com/vpsg-research/Sim-MPNet.
Authors: Robert Aufschl\"ager, Youssef Shoeb, Azarm Nowzad, Michael Heigl, Fabian Bally, Martin Schramm
Abstract: The collection and release of street-level recordings as Open Data play a vital role in advancing autonomous driving systems and AI research. However, these datasets pose significant privacy risks, particularly for pedestrians, due to the presence of Personally Identifiable Information (PII) that extends beyond biometric traits such as faces. In this paper, we present cRID, a novel cross-modal framework combining Large Vision-Language Models, Graph Attention Networks, and representation learning to detect textual describable clues of PII and enhance person re-identification (Re-ID). Our approach focuses on identifying and leveraging interpretable features, enabling the detection of semantically meaningful PII beyond low-level appearance cues. We conduct a systematic evaluation of PII presence in person image datasets. Our experiments show improved performance in practical cross-dataset Re-ID scenarios, notably from Market-1501 to CUHK03-np (detected), highlighting the framework's practical utility. Code is available at https://github.com/RAufschlaeger/cRID.
Authors: Maria Damanaki, Ioulia Kapsali, Nikos Piperigkos, Alexandros Gkillas, Aris S. Lalos
Abstract: The critical perception capabilities of EdgeAI systems, such as autonomous vehicles, are required to be resilient against adversarial threats, by enabling accurate identification and localization of multiple objects in the scene over time, mitigating their impact. Single-agent tracking offers resilience to adversarial attacks but lacks situational awareness, underscoring the need for multi-agent cooperation to enhance context understanding and robustness. This paper proposes a novel mitigation framework on 3D LiDAR scene against adversarial noise by tracking objects based on least-squares graph on multi-agent adversarial bounding boxes. Specifically, we employ the least-squares graph tool to reduce the induced positional error of each detection's centroid utilizing overlapped bounding boxes on a fully connected graph via differential coordinates and anchor points. Hence, the multi-vehicle detections are fused and refined mitigating the adversarial impact, and associated with existing tracks in two stages performing tracking to further suppress the adversarial threat. An extensive evaluation study on the real-world V2V4Real dataset demonstrates that the proposed method significantly outperforms both state-of-the-art single and multi-agent tracking frameworks by up to 23.3% under challenging adversarial conditions, operating as a resilient approach without relying on additional defense mechanisms.
Authors: Yaoqi Huang, Julie Stephany Berrio, Mao Shan, Stewart Worrall
Abstract: Advances in vision-based sensors and computer vision algorithms have significantly improved the analysis and understanding of traffic scenarios. To facilitate the use of these improvements for road safety, this survey systematically categorizes the critical elements that demand attention in traffic scenarios and comprehensively analyzes available vision-driven tasks and datasets. Compared to existing surveys that focus on isolated domains, our taxonomy categorizes attention-worthy traffic entities into two main groups that are anomalies and normal but critical entities, integrating ten categories and twenty subclasses. It establishes connections between inherently related fields and provides a unified analytical framework. Our survey highlights the analysis of 35 vision-driven tasks and comprehensive examinations and visualizations of 73 available datasets based on the proposed taxonomy. The cross-domain investigation covers the pros and cons of each benchmark with the aim of providing information on standards unification and resource optimization. Our article concludes with a systematic discussion of the existing weaknesses, underlining the potential effects and promising solutions from various perspectives. The integrated taxonomy, comprehensive analysis, and recapitulatory tables serve as valuable contributions to this rapidly evolving field by providing researchers with a holistic overview, guiding strategic resource selection, and highlighting critical research gaps.
Authors: Mathias Schulz, Alexander Spenke, Pia Funk, Florian Bl\"umel, Markus Rohde, Ralph Breithaupt, Gerd Nolden, Norbert Jung, Robert Lange
Abstract: This study presents findings from long-term biometric evaluations conducted at the Biometric Evaluation Center (bez). Over the course of two and a half years, our ongoing research with over 400 participants representing diverse ethnicities, genders, and age groups were regularly assessed using a variety of biometric tools and techniques at the controlled testing facilities. Our findings are based on the General Data Protection Regulation-compliant local bez database with more than 238.000 biometric data sets categorized into multiple biometric modalities such as face and finger. We used state-of-the-art face recognition algorithms to analyze long-term comparison scores. Our results show that these scores fluctuate more significantly between individual days than over the entire measurement period. These findings highlight the importance of testing biometric characteristics of the same individuals over a longer period of time in a controlled measurement environment and lays the groundwork for future advancements in biometric data analysis.
Authors: Jiaxu Wan, Xu Wang, Mengwei Xie, Xinyuan Chang, Xinran Liu, Zheng Pan, Mu Xu, Ding Yuan
Abstract: Autonomous vehicles rely on global standard-definition (SD) maps for road-level route planning and online local high-definition (HD) maps for lane-level navigation. However, recent work concentrates on construct online HD maps, often overlooking the association of global SD maps with online HD maps for hybrid navigation, making challenges in utilizing online HD maps in the real world. Observing the lack of the capability of autonomous vehicles in navigation, we introduce \textbf{O}nline \textbf{M}ap \textbf{A}ssociation, the first benchmark for the association of hybrid navigation-oriented online maps, which enhances the planning capabilities of autonomous vehicles. Based on existing datasets, the OMA contains 480k of roads and 260k of lane paths and provides the corresponding metrics to evaluate the performance of the model. Additionally, we propose a novel framework, named Map Association Transformer, as the baseline method, using path-aware attention and spatial attention mechanisms to enable the understanding of geometric and topological correspondences. The code and dataset can be accessed at https://github.com/WallelWan/OMA-MAT.
Authors: Ruixiang Chen, Guolei Sun, Yawei Li, Jie Qin, Luca Benini
Abstract: This paper presents enhancements to the SAM2 framework for video object tracking task, addressing challenges such as occlusions, background clutter, and target reappearance. We introduce a hierarchical motion estimation strategy, combining lightweight linear prediction with selective non-linear refinement to improve tracking accuracy without requiring additional training. In addition, we optimize the memory bank by distinguishing long-term and short-term memory frames, enabling more reliable tracking under long-term occlusions and appearance changes. Experimental results show consistent improvements across different model scales. Our method achieves state-of-the-art performance on LaSOT and LaSOText with the large model, achieving 9.6% and 7.2% relative improvements in AUC over the original SAM2, and demonstrates even larger relative gains on smaller models, highlighting the effectiveness of our trainless, low-overhead improvements for boosting long-term tracking performance. The code is available at https://github.com/LouisFinner/HiM2SAM.
Authors: Ethan Dack, Chengliang Dai
Abstract: Recent works have revisited the infamous task ``Name That Dataset'', demonstrating that non-medical datasets contain underlying biases and that the dataset origin task can be solved with high accuracy. In this work, we revisit the same task applied to popular open-source chest X-ray datasets. Medical images are naturally more difficult to release for open-source due to their sensitive nature, which has led to certain open-source datasets being extremely popular for research purposes. By performing the same task, we wish to explore whether dataset bias also exists in these datasets. To extend our work, we apply simple transformations to the datasets, repeat the same task, and perform an analysis to identify and explain any detected biases. Given the importance of AI applications in medical imaging, it's vital to establish whether modern methods are taking shortcuts or are focused on the relevant pathology. We implement a range of different network architectures on the datasets: NIH, CheXpert, MIMIC-CXR and PadChest. We hope this work will encourage more explainable research being performed in medical imaging and the creation of more open-source datasets in the medical domain. Our code can be found here: https://github.com/eedack01/x_ray_ds_bias.
Authors: Josh Qixuan Sun, Xiaoying Xing, Huaiyuan Weng, Chul Min Yeum, Mark Crowley
Abstract: Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most navigation policies are sensitive to viewpoint changes, i.e., variations in camera height and viewing angle that alter the agent's observation. In this paper, we introduce a generalized scenario, V2-VLNCE (VLNCE with Varied Viewpoints), and propose VIL (View Invariant Learning), a view-invariant post-training strategy that enhances the robustness of existing navigation policies to changes in camera viewpoint. VIL employs a contrastive learning framework to learn sparse and view-invariant features. Additionally, we introduce a teacher-student framework for the Waypoint Predictor Module, a core component of most VLNCE baselines, where a view-dependent teacher model distills knowledge into a view-invariant student model. We employ an end-to-end training paradigm to jointly optimize these components, thus eliminating the cost for individual module training. Empirical results show that our method outperforms state-of-the-art approaches on V2-VLNCE by 8-15% measured on Success Rate for two standard benchmark datasets R2R-CE and RxR-CE. Furthermore, we evaluate VIL under the standard VLNCE setting and find that, despite being trained for varied viewpoints, it often still improves performance. On the more challenging RxR-CE dataset, our method also achieved state-of-the-art performance across all metrics when compared to other map-free methods. This suggests that adding VIL does not diminish the standard viewpoint performance and can serve as a plug-and-play post-training method.
Authors: Zichun Xu, Yuntao Li, Zhaomin Wang, Lei Zhuang, Guocai Yang, Jingdong Zhao
Abstract: Depth information is robust to scene appearance variations and inherently carries 3D spatial details. In this paper, a visual backbone based on the vision transformer is proposed to fuse RGB and depth modalities for enhancing generalization. Different modalities are first processed by separate CNN stems, and the combined convolutional features are delivered to the scalable vision transformer to obtain visual representations. Moreover, a contrastive unsupervised learning scheme is designed with masked and unmasked tokens to accelerate the sample efficiency during the reinforcement learning progress. For sim2real transfer, a flexible curriculum learning schedule is developed to deploy domain randomization over training processes.
Authors: Anita Kriz, Elizabeth Laura Janes, Xing Shen, Tal Arbel
Abstract: Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a tendency to generate incorrect responses with high confidence. As clinicians may rely on a model's stated confidence to gauge the reliability of its predictions, it is especially important that when a model expresses high confidence, it is also highly accurate. We introduce Prompt4Trust, the first reinforcement learning (RL) framework for prompt augmentation targeting confidence calibration in MLLMs. A lightweight LLM is trained to produce context-aware auxiliary prompts that guide a downstream task MLLM to generate responses in which the expressed confidence more accurately reflects predictive accuracy. Unlike conventional calibration techniques, Prompt4Trust specifically prioritizes aspects of calibration most critical for safe and trustworthy clinical decision-making. Beyond improvements driven by this clinically motivated calibration objective, our proposed method also improves task accuracy, achieving state-of-the-art medical visual question answering (VQA) performance on the PMC-VQA benchmark, which is composed of multiple-choice questions spanning diverse medical imaging modalities. Moreover, our framework trained with a small downstream task MLLM showed promising zero-shot generalization to larger MLLMs in our experiments, suggesting the potential for scalable calibration without the associated computational costs. This work demonstrates the potential of automated yet human-aligned prompt engineering for improving the the trustworthiness of MLLMs in safety critical settings. Our codebase can be found at https://github.com/xingbpshen/prompt4trust.
Authors: Yuval Grader, Hadar Averbuch-Elor
Abstract: Floorplans provide a compact representation of the building's structure, revealing not only layout information but also detailed semantics such as the locations of windows and doors. However, contemporary floorplan localization techniques mostly focus on matching depth-based structural cues, ignoring the rich semantics communicated within floorplans. In this work, we introduce a semantic-aware localization framework that jointly estimates depth and semantic rays, consolidating over both for predicting a structural-semantic probability volume. Our probability volume is constructed in a coarse-to-fine manner: We first sample a small set of rays to obtain an initial low-resolution probability volume. We then refine these probabilities by performing a denser sampling only in high-probability regions and process the refined values for predicting a 2D location and orientation angle. We conduct an evaluation on two standard floorplan localization benchmarks. Our experiments demonstrate that our approach substantially outperforms state-of-the-art methods, achieving significant improvements in recall metrics compared to prior works. Moreover, we show that our framework can easily incorporate additional metadata such as room labels, enabling additional gains in both accuracy and efficiency.
Authors: Yueqian Wang, Xiaojun Meng, Yifan Wang, Huishuai Zhang, Dongyan Zhao
Abstract: With the growing research focus on multimodal dialogue systems, the capability for proactive interaction is gradually gaining recognition. As an alternative to conventional turn-by-turn dialogue, users increasingly expect multimodal systems to be more initiative, for example, by autonomously determining the timing of multi-turn responses in real time during video playback. To facilitate progress in this emerging area, we introduce ProactiveVideoQA, the first comprehensive benchmark to evaluate a system's ability to engage in proactive interaction. Since model responses are generated at varying timestamps, we further propose PAUC, the first metric that accounts for the temporal dynamics of model responses. This enables a more accurate evaluation of systems operating in proactive settings. Through extensive benchmarking of various baseline systems on ProactiveVideoQA and a user study of human preferences, we show that PAUC is in better agreement with human preferences than traditional evaluation metrics, which typically only consider the textual content of responses. These findings demonstrate that PAUC provides a more faithful assessment of user experience in proactive interaction scenarios. Project homepage: https://github.com/yellow-binary-tree/ProactiveVideoQA
URLs: https://github.com/yellow-binary-tree/ProactiveVideoQA
Authors: Jaisidh Singh, Diganta Misra, Boris Knyazev, Antonio Orvieto
Abstract: Foundation multi-modal models are often designed by stitching of multiple existing pretrained uni-modal models: for example, an image classifier with an text model. This stitching process is performed by training a connector module that aims to align the representation spaces of these uni-modal models towards a multi-modal objective. However, given the complexity of training such connectors on large scale web-based datasets coupled with the ever-increasing number of available pretrained uni-modal models, the task of uni-modal models selection and subsequent connector module training becomes computationally demanding. To address this under-studied critical problem, we propose Hypernetwork Model Alignment (Hyma), a novel all-in-one solution for optimal uni-modal model selection and connector training by leveraging hypernetworks. Specifically, our framework utilizes the parameter prediction capability of a hypernetwork to obtain jointly trained connector modules for $N \times M$ combinations of uni-modal models. In our experiments, Hyma reduces the cost of searching for the best performing uni-modal model pair by $10\times$, while matching the ranking and trained connector performance obtained via grid search across a suite of diverse multi-modal benchmarks.
Authors: Hongjae Lee, Myungjun Son, Dongjea Kang, Seung-Won Jung
Abstract: Despite the success of diffusion models in image generation tasks such as text-to-image, the enormous computational complexity of diffusion models limits their use in resource-constrained environments. To address this, network quantization has emerged as a promising solution for designing efficient diffusion models. However, existing diffusion model quantization methods do not consider input conditions, such as text prompts, as an essential source of information for quantization. In this paper, we propose a novel quantization method dubbed Quantization of Language-to-Image diffusion models using text Prompts (QLIP). QLIP leverages text prompts to guide the selection of bit precision for every layer at each time step. In addition, QLIP can be seamlessly integrated into existing quantization methods to enhance quantization efficiency. Our extensive experiments demonstrate the effectiveness of QLIP in reducing computational complexity and improving the quality of the generated images across various datasets.
Authors: Qiang Li, Qingsen Yan, Haojian Huang, Peng Wu, Haokui Zhang, Yanning Zhang
Abstract: With the rapid advancements in Artificial Intelligence Generated Image (AGI) technology, the accurate assessment of their quality has become an increasingly vital requirement. Prevailing methods typically rely on cross-modal models like CLIP or BLIP to evaluate text-image alignment and visual quality. However, when applied to AGIs, these methods encounter two primary challenges: semantic misalignment and details perception missing. To address these limitations, we propose Text-Visual Semantic Constrained AI-Generated Image Quality Assessment (SC-AGIQA), a unified framework that leverages text-visual semantic constraints to significantly enhance the comprehensive evaluation of both text-image consistency and perceptual distortion in AI-generated images. Our approach integrates key capabilities from multiple models and tackles the aforementioned challenges by introducing two core modules: the Text-assisted Semantic Alignment Module (TSAM), which leverages Multimodal Large Language Models (MLLMs) to bridge the semantic gap by generating an image description and comparing it against the original prompt for a refined consistency check, and the Frequency-domain Fine-Grained Degradation Perception Module (FFDPM), which draws inspiration from Human Visual System (HVS) properties by employing frequency domain analysis combined with perceptual sensitivity weighting to better quantify subtle visual distortions and enhance the capture of fine-grained visual quality details in images. Extensive experiments conducted on multiple benchmark datasets demonstrate that SC-AGIQA outperforms existing state-of-the-art methods. The code is publicly available at https://github.com/mozhu1/SC-AGIQA.
Authors: Jianguo Huang, Jianqing Song, Xuanning Zhou, Bingyi Jing, Hongxin Wei
Abstract: Conformal prediction (CP) is a robust statistical framework that generates prediction intervals or sets with guaranteed coverage probability, addressing the challenge of quantifying predictive uncertainty in deep learning. Despite advancements in deep learning architectures and datasets, reliable uncertainty estimation remains elusive, making CP increasingly vital. This paper introduces TorchCP, a PyTorch-native library designed to integrate state-of-the-art CP algorithms into deep learning tasks, including classification, regression, graph neural networks, and large language models. TorchCP offers a comprehensive suite of advanced methodologies, a modular design for easy customization, and full GPU-accelerated scalability. Released under the LGPL-3.0 license, TorchCP has gained widespread adoption with over 12,582 PyPi downloads. It is supported by approximately 16,132 lines of code, 564 unit tests achieving 100\% coverage, and comprehensive documentation. By bridging statistics and computer science, TorchCP empowers researchers and practitioners to advance conformal prediction in diverse deep learning applications.
Authors: Jingwei Zhang, Mohammad Jalali, Cheuk Ting Li, Farzan Farnia
Abstract: A fine-grained comparison of generative models requires the identification of sample types generated differently by each of the involved models. While quantitative scores have been proposed in the literature to rank different generative models, score-based evaluation and ranking do not reveal the nuanced differences between the generative models in producing different sample types. In this work, we propose solving a differential clustering problem to detect sample types generated differently by two generative models. To solve the differential clustering problem, we develop a spectral method called Fourier-based Identification of Novel Clusters (FINC) to identify modes produced by a generative model with a higher frequency in comparison to a reference distribution. FINC provides a scalable algorithm based on random Fourier features to estimate the eigenspace of kernel covariance matrices of two generative models and utilize the principal eigendirections to detect the sample types present more dominantly in each model. We demonstrate the application of the FINC method to large-scale computer vision datasets and generative modeling frameworks. Our numerical results suggest the scalability of the developed Fourier-based method in highlighting the sample types produced with different frequencies by generative models. The project code is available at https://github.com/buyeah1109/FINC.
Authors: Qing Wu, Chenhe Du, Xuanyu Tian, Jingyi Yu, Yuyao Zhang, Hongjiang Wei
Abstract: Motion correction (MoCo) in radial MRI is a particularly challenging problem due to the unpredictability of subject movement. Current state-of-the-art (SOTA) MoCo algorithms often rely on extensive high-quality MR images to pre-train neural networks, which constrains the solution space and leads to outstanding image reconstruction results. However, the need for large-scale datasets significantly increases costs and limits model generalization. In this work, we propose Moner, an unsupervised MoCo method that jointly reconstructs artifact-free MR images and estimates accurate motion from undersampled, rigid motion-corrupted k-space data, without requiring any training data. Our core idea is to leverage the continuous prior of implicit neural representation (INR) to constrain this ill-posed inverse problem, facilitating optimal solutions. Specifically, we integrate a quasi-static motion model into the INR, granting its ability to correct subject's motion. To stabilize model optimization, we reformulate radial MRI reconstruction as a back-projection problem using the Fourier-slice theorem. Additionally, we propose a novel coarse-to-fine hash encoding strategy, significantly enhancing MoCo accuracy. Experiments on multiple MRI datasets show our Moner achieves performance comparable to SOTA MoCo techniques on in-domain data, while demonstrating significant improvements on out-of-domain data. The code is available at: https://github.com/iwuqing/Moner
Authors: Junyang Wu, Fangfang Xie, Jiayuan Sun, Yun Gu, Guang-Zhong Yang
Abstract: Domain adaptation, which bridges the distributions across different modalities, plays a crucial role in multimodal medical image analysis. In endoscopic imaging, combining pre-operative data with intra-operative imaging is important for surgical planning and navigation. However, existing domain adaptation methods are hampered by distribution shift caused by in vivo artifacts, necessitating robust techniques for aligning noisy and artifact abundant patient endoscopic videos with clean virtual images reconstructed from pre-operative tomographic data for pose estimation during intraoperative guidance. This paper presents an artifact-resilient image translation method and an associated benchmark for this purpose. The method incorporates a novel ``local-global'' translation framework and a noise-resilient feature extraction strategy. For the former, it decouples the image translation process into a local step for feature denoising, and a global step for global style transfer. For feature extraction, a new contrastive learning strategy is proposed, which can extract noise-resilient features for establishing robust correspondence across domains. Detailed validation on both public and in-house clinical datasets has been conducted, demonstrating significantly improved performance compared to the current state-of-the-art.
Authors: Rang Meng, Xingyu Zhang, Yuming Li, Chenguang Ma
Abstract: Recent work on human animation usually involves audio, pose, or movement maps conditions, thereby achieves vivid animation quality. However, these methods often face practical challenges due to extra control conditions, cumbersome condition injection modules, or limitation to head region driving. Hence, we ask if it is possible to achieve striking half-body human animation while simplifying unnecessary conditions. To this end, we propose a half-body human animation method, dubbed EchoMimicV2, that leverages a novel Audio-Pose Dynamic Harmonization strategy, including Pose Sampling and Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize Head Partial Attention to seamlessly accommodate headshot data into our training framework, which can be omitted during inference, providing a free lunch for animation. Furthermore, we design the Phase-specific Denoising Loss to guide motion, detail, and low-level quality for animation in specific phases, respectively. Besides, we also present a novel benchmark for evaluating the effectiveness of half-body human animation. Extensive experiments and analyses demonstrate that EchoMimicV2 surpasses existing methods in both quantitative and qualitative evaluations.
Authors: Xinmin Feng, Zhuoyuan Li, Li Li, Dong Liu, Feng Wu
Abstract: Among the new techniques of Versatile Video Coding (VVC), the quadtree with nested multi-type tree (QT+MTT) block structure yields significant coding gains by providing more flexible block partitioning patterns. However, the recursive partition search in the VVC encoder increases the encoder complexity substantially. To address this issue, we propose a partition map-based algorithm to pursue fast block partitioning in inter coding. Based on our previous work on partition map-based methods for intra coding, we analyze the characteristics of VVC inter coding, and thus improve the partition map by incorporating an MTT mask for early termination. Next, we develop a neural network that uses both spatial and temporal features to predict the partition map. It consists of several special designs including stacked top-down and bottom-up processing, quantization parameter modulation layers, and partitioning-adaptive warping. Furthermore, we present a dual-threshold decision scheme to achieve a fine-grained trade-off between complexity reduction and rate-distortion (RD) performance loss. The experimental results demonstrate that the proposed method achieves an average 51.30% encoding time saving with a 2.12% Bjontegaard Delta Bit Rate (BDBR) under the random access configuration.
Authors: Hao Wang, Pinzhi Huang, Jihan Yang, Saining Xie, Daisuke Kawahara
Abstract: The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages, especially when integrating cultural knowledge, remains a significant challenge. To better assess this issue, we introduce two new benchmarks: KnowRecall and VisRecall, which evaluate cross-lingual consistency in MLLMs. KnowRecall is a visual question answering benchmark designed to measure factual knowledge consistency in 15 languages, focusing on cultural and historical questions about global landmarks. VisRecall assesses visual memory consistency by asking models to describe landmark appearances in 9 languages without access to images. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, still struggle to achieve cross-lingual consistency. This underscores the need for more robust approaches that produce truly multilingual and culturally aware models.
Authors: Pierrick Coup\'e, Boris Mansencal, Flor\'eal Morandat, Sergio Morell-Ortega, Nicolas Villain, Jose V. Manj\'on, Vincent Planche
Abstract: INTRODUCTION: Quantification of amyloid plaques (A), neurofibrillary tangles (T2), and neurodegeneration (N) using PET and MRI is critical for Alzheimer's disease (AD) diagnosis and prognosis. Existing pipelines face limitations regarding processing time, variability in tracer types, and challenges in multimodal integration. METHODS: We developed petBrain, a novel end-to-end processing pipeline for amyloid-PET, tau-PET, and structural MRI. It leverages deep learning-based segmentation, standardized biomarker quantification (Centiloid, CenTauR, HAVAs), and simultaneous estimation of A, T2, and N biomarkers. The pipeline is implemented as a web-based platform, requiring no local computational infrastructure or specialized software knowledge. RESULTS: petBrain provides reliable and rapid biomarker quantification, with results comparable to existing pipelines for A and T2. It shows strong concordance with data processed in ADNI databases. The staging and quantification of A/T2/N by petBrain demonstrated good agreement with CSF/plasma biomarkers, clinical status, and cognitive performance. DISCUSSION: petBrain represents a powerful and openly accessible platform for standardized AD biomarker analysis, facilitating applications in clinical research.
Authors: Sejin Park, Sangmin Lee, Kyong Hwan Jin, Seung-Won Jung
Abstract: Super-resolution (SR) has been a pivotal task in image processing, aimed at enhancing image resolution across various applications. Recently, look-up table (LUT)-based approaches have attracted interest due to their efficiency and performance. However, these methods are typically designed for fixed scale factors, making them unsuitable for arbitrary-scale image SR (ASISR). Existing ASISR techniques often employ implicit neural representations, which come with considerable computational cost and memory demands. To address these limitations, we propose Interpolation Mixing LUT (IM-LUT), a novel framework that operates ASISR by learning to blend multiple interpolation functions to maximize their representational capacity. Specifically, we introduce IM-Net, a network trained to predict mixing weights for interpolation functions based on local image patterns and the target scale factor. To enhance efficiency of interpolation-based methods, IM-Net is transformed into IM-LUT, where LUTs are employed to replace computationally expensive operations, enabling lightweight and fast inference on CPUs while preserving reconstruction quality. Experimental results on several benchmark datasets demonstrate that IM-LUT consistently achieves a superior balance between image quality and efficiency compared to existing methods, highlighting its potential as a promising solution for resource-constrained applications.
Authors: Guohao Huo, Ruiting Dai, Hao Tang
Abstract: Brain tumor segmentation plays a critical role in clinical diagnosis and treatment planning, yet the variability in imaging quality across different MRI scanners presents significant challenges to model generalization. To address this, we propose the Edge Iterative MRI Lesion Localization System (EdgeIMLocSys), which integrates Continuous Learning from Human Feedback to adaptively fine-tune segmentation models based on clinician feedback, thereby enhancing robustness to scanner-specific imaging characteristics. Central to this system is the Graph-based Multi-Modal Interaction Lightweight Network for Brain Tumor Segmentation (GMLN-BTS), which employs a Modality-Aware Adaptive Encoder (M2AE) to extract multi-scale semantic features efficiently, and a Graph-based Multi-Modal Collaborative Interaction Module (G2MCIM) to model complementary cross-modal relationships via graph structures. Additionally, we introduce a novel Voxel Refinement UpSampling Module (VRUM) that synergistically combines linear interpolation and multi-scale transposed convolutions to suppress artifacts while preserving high-frequency details, improving segmentation boundary accuracy. Our proposed GMLN-BTS model achieves a Dice score of 85.1% on the BraTS2017 dataset with only 4.58 million parameters, representing a 98% reduction compared to mainstream 3D Transformer models, and significantly outperforms existing lightweight approaches. This work demonstrates a synergistic breakthrough in achieving high-accuracy, resource-efficient brain tumor segmentation suitable for deployment in resource-constrained clinical environments.
Authors: Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa, Joost van de Weijer, Antonio Carta
Abstract: Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply with a fixed computational budget, and task boundaries are absent. We introduce Continual Latent Alignment (CLA), a novel SSL strategy for Online CL that aligns the representations learned by the current model with past representations to mitigate forgetting. We found that our CLA is able to speed up the convergence of the training process in the online scenario, outperforming state-of-the-art approaches under the same computational budget. Surprisingly, we also discovered that using CLA as a pretraining protocol in the early stages of pretraining leads to a better final performance when compared to a full i.i.d. pretraining.