Authors: Shrinivas Pundlik, Seonggyu Choe, Patrick Baker, Chen-Yuan Lee, Naser Al-Madi, Alex R. Bowers, Gang Luo
Abstract: Naturalistic driving studies use devices in participants' own vehicles to record daily driving over many months. Due to diverse and extensive amounts of data recorded, automated processing is necessary. This report describes methods to extract and characterize driver head scans at intersections from data collected from an in-car recording system that logged vehicle speed, GPS location, scene videos, and cabin videos. Custom tools were developed to mark the intersections, synchronize location and video data, and clip the cabin and scene videos for +/-100 meters from the intersection location. A custom-developed head pose detection AI model for wide angle head turns was run on the cabin videos to estimate the driver head pose, from which head scans >20 deg were computed in the horizontal direction. The scene videos were processed using a YOLO object detection model to detect traffic lights, stop signs, pedestrians, and other vehicles on the road. Turning maneuvers were independently detected using vehicle self-motion patterns. Stop lines on the road surface were detected using changing intensity patterns over time as the vehicle moved. The information obtained from processing the scene videos, along with the speed data was used in a rule-based algorithm to infer the intersection type, maneuver, and bounds. We processed 190 intersections from 3 vehicles driven in cities and suburban areas from Massachusetts and California. The automated video processing algorithm correctly detected intersection signage and maneuvers in 100% and 94% of instances, respectively. The median [IQR] error in detecting vehicle entry into the intersection was 1.1[0.4-4.9] meters and 0.2[0.1-0.54] seconds. The median overlap between ground truth and estimated intersection bounds was 0.88[0.82-0.93].
Authors: Yunfan Lu, Xiaogang Xu, Pengteng Li, Yusheng Wang, Yi Cui, Huizai Yao, Hui Xiong
Abstract: Event cameras offering high dynamic range and low latency have emerged as disruptive technologies in imaging. Despite growing research on leveraging these benefits for different imaging tasks, a comprehensive study of recently advances and challenges are still lacking. This limits the broader understanding of how to utilize events in universal imaging applications. In this survey, we first introduce a physical model and the characteristics of different event sensors as the foundation. Following this, we highlight the advancement and interaction of image/video enhancement tasks with events. Additionally, we explore advanced tasks, which capture richer light information with events, \eg~light field estimation, multi-view generation, and photometric. Finally, we discuss new challenges and open questions offering a perspective for this rapidly evolving field. More continuously updated resources are at this link: https://github.com/yunfanLu/Awesome-Event-Imaging
Authors: TianYi Yu
Abstract: The Detection of small objects, especially traffic signs, is a critical sub-task in object detection and autonomous driving. Despite signficant progress in previous research, two main challenges remain. First, the issue of feature extraction being too singular. Second, the detection process struggles to efectively handle objects of varying sizes or scales. These problems are also prevalent in general object detection tasks. To address these challenges, we propose a novel object detection network, Mamba-based Dynamic Dual Fusion Network (MDDFNet), for traffic sign detection. The network integrates a dynamic dual fusion module and a Mamba-based backbone to simultaneously tackle the aforementioned issues. Specifically, the dynamic dual fusion module utilizes multiple branches to consolidate various spatial and semantic information, thus enhancing feature diversity. The Mamba-based backbone leverages global feature fusion and local feature interaction, combining features in an adaptive manner to generate unique classification characteristics. Extensive experiments conducted on the TT100K (Tsinghua-Tencent 100K) datasets demonstrate that MDDFNet outperforms other state-of-the-art detectors, maintaining real-time processing capabilities of single-stage models while achieving superior performance. This confirms the efectiveness of MDDFNet in detecting small traffic signs.
Authors: Ignacy St\k{e}pka, Lukasz Sztukiewicz, Micha{\l} Wili\'nski, Jerzy Stefanowski
Abstract: While machine learning fairness has made significant progress in recent years, most existing solutions focus on tabular data and are poorly suited for vision-based classification tasks, which rely heavily on deep learning. To bridge this gap, we introduce DetoxAI, an open-source Python library for improving fairness in deep learning vision classifiers through post-hoc debiasing. DetoxAI implements state-of-the-art debiasing algorithms, fairness metrics, and visualization tools. It supports debiasing via interventions in internal representations and includes attribution-based visualization tools and quantitative algorithmic fairness metrics to show how bias is mitigated. This paper presents the motivation, design, and use cases of DetoxAI, demonstrating its tangible value to engineers and researchers.
Authors: Siyuan Zhou, Yilun Du, Yuncong Yang, Lei Han, Peihao Chen, Dit-Yan Yeung, Chuang Gan
Abstract: The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing work has explored how to construct such world models using video models, they are often myopic in nature, without any memory of a scene not captured by currently observed images, preventing agents from making consistent long-horizon plans in complex environments where many parts of the scene are partially observed. We introduce a new persistent embodied world model with an explicit memory of previously generated content, enabling much more consistent long-horizon simulation. During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent. This generation is then aggregated into a persistent 3D map of the environment. By conditioning the video model on this 3D spatial map, we illustrate how this enables video world models to faithfully simulate both seen and unseen parts of the world. Finally, we illustrate the efficacy of such a world model in downstream embodied applications, enabling effective planning and policy learning.
Authors: Pu Cao, Feng Zhou, Junyi Ji, Qingye Kong, Zhixiang Lv, Mingjian Zhang, Xuekun Zhao, Siqi Wu, Yinghui Lin, Qing Song, Lu Yang
Abstract: Recently, the visual generation ability by GPT-4o(mni) has been unlocked by OpenAI. It demonstrates a very remarkable generation capability with excellent multimodal condition understanding and varied task instructions. In this paper, we aim to explore the capabilities of GPT-4o across various tasks. Inspired by previous study, we constructed a task taxonomy along with a carefully curated set of test samples to conduct a comprehensive qualitative test. Benefiting from GPT-4o's powerful multimodal comprehension, its image-generation process demonstrates abilities surpassing those of traditional image-generation tasks. Thus, regarding the dimensions of model capabilities, we evaluate its performance across six task categories: traditional image generation tasks, discriminative tasks, knowledge-based generation, commonsense-based generation, spatially-aware image generation, and temporally-aware image generation. These tasks not only assess the quality and conditional alignment of the model's outputs but also probe deeper into GPT-4o's understanding of real-world concepts. Our results reveal that GPT-4o performs impressively well in general-purpose synthesis tasks, showing strong capabilities in text-to-image generation, visual stylization, and low-level image processing. However, significant limitations remain in its ability to perform precise spatial reasoning, instruction-grounded generation, and consistent temporal prediction. Furthermore, when faced with knowledge-intensive or domain-specific scenarios, such as scientific illustrations or mathematical plots, the model often exhibits hallucinations, factual errors, or structural inconsistencies. These findings suggest that while GPT-4o marks a substantial advancement in unified multimodal generation, there is still a long way to go before it can be reliably applied to professional or safety-critical domains.
Authors: Yiming Qin, Zhu Xu, Yang Liu
Abstract: Recent text-to-3D models can render high-quality assets, yet they still stumble on objects with complex attributes. The key obstacles are: (1) existing text-to-3D approaches typically lift text-to-image models to extract semantics via text encoders, while the text encoder exhibits limited comprehension ability for long descriptions, leading to deviated cross-attention focus, subsequently wrong attribute binding in generated results. (2) Occluded object parts demand a disciplined generation order and explicit part disentanglement. Though some works introduce manual efforts to alleviate the above issues, their quality is unstable and highly reliant on manual information. To tackle above problems, we propose a automated method Hierarchical-Chain-of-Generation (HCoG). It leverages a large language model to decompose the long description into blocks representing different object parts, and orders them from inside out according to occlusions, forming a hierarchical chain. Within each block we first coarsely create components, then precisely bind attributes via target-region localization and corresponding 3D Gaussian kernel optimization. Between blocks, we introduce Gaussian Extension and Label Elimination to seamlessly generate new parts by extending new Gaussian kernels, re-assigning semantic labels, and eliminating unnecessary kernels, ensuring that only relevant parts are added without disrupting previously optimized parts. Experiments confirm that HCoG yields structurally coherent, attribute-faithful 3D objects with complex attributes. The code is available at https://github.com/Wakals/GASCOL .
Authors: Zhang Zhang, Qiang Zhang, Wei Cui, Shuai Shi, Yijie Guo, Gang Han, Wen Zhao, Jingkai Sun, Jiahang Cao, Jiaxu Wang, Hao Cheng, Xiaozhu Ju, Zhengping Che, Renjing Xu, Jian Tang
Abstract: Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajectory prediction of potential instances, current works use the occupancy world model as a generative framework for describing fine-grained overall scene dynamics. However, existing methods cluster on the outdoor structured road scenes, while ignoring the exploration of forecasting 3D occupancy scene evolutions for robots in indoor scenes. In this work, we explore a new framework for learning the scene evolutions of observed fine-grained occupancy and propose an occupancy world model based on the combined spatio-temporal receptive field and guided autoregressive transformer to forecast the scene evolutions, called RoboOccWorld. We propose the Conditional Causal State Attention (CCSA), which utilizes camera poses of next state as conditions to guide the autoregressive transformer to adapt and understand the indoor robotics scenarios. In order to effectively exploit the spatio-temporal cues from historical observations, Hybrid Spatio-Temporal Aggregation (HSTA) is proposed to obtain the combined spatio-temporal receptive field based on multi-scale spatio-temporal windows. In addition, we restructure the OccWorld-ScanNet benchmark based on local annotations to facilitate the evaluation of the indoor 3D occupancy scene evolution prediction task. Experimental results demonstrate that our RoboOccWorld outperforms state-of-the-art methods in indoor 3D occupancy scene evolution prediction task. The code will be released soon.
Authors: Muhammad Junaid Asif, Hamza Khan, Rabia Tehseen, Syed Tahir Hussain Rizvi, Mujtaba Asad, Shazia Saqib, Rana Fayyaz Ahmad
Abstract: Rice is an essential staple food worldwide that is important in promoting international trade, economic growth, and nutrition. Asian countries such as China, India, Pakistan, Thailand, Vietnam, and Indonesia are notable for their significant contribution to the cultivation and utilization of rice. These nations are also known for cultivating different rice grains, including short and long grains. These sizes are further classified as basmati, jasmine, kainat saila, ipsala, arborio, etc., catering to diverse culinary preferences and cultural traditions. For both local and international trade, inspecting and maintaining the quality of rice grains to satisfy customers and preserve a country's reputation is necessary. Manual quality check and classification is quite a laborious and time-consuming process. It is also highly prone to mistakes. Therefore, an automatic solution must be proposed for the effective and efficient classification of different varieties of rice grains. This research paper presents an automatic framework based on a convolutional neural network (CNN) for classifying different varieties of rice grains. We evaluated the proposed model based on performance metrics such as accuracy, recall, precision, and F1-Score. The CNN model underwent rigorous training and validation, achieving a remarkable accuracy rate and a perfect area under each class's Receiver Operating Characteristic (ROC) curve. The confusion matrix analysis confirmed the model's effectiveness in distinguishing between the different rice varieties, indicating minimal misclassifications. Additionally, the integration of explainability techniques such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations) provided valuable insights into the model's decision-making process, revealing how specific features of the rice grains influenced classification outcomes.
Authors: Hongyi Chen, Yunchao Yao, Yufei Ye, Zhixuan Xu, Homanga Bharadhwaj, Jiashun Wang, Shubham Tulsiani, Zackory Erickson, Jeffrey Ichnowski
Abstract: Functional grasp is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. However, most prior work either focuses on power grasping, which simply involves holding an object still, or relies on costly teleoperated robot demonstrations to teach robots how to grasp each object functionally. Instead, we propose extracting human grasp information from web images since they depict natural and functional object interactions, thereby bypassing the need for curated demonstrations. We reconstruct human hand-object interaction (HOI) 3D meshes from RGB images, retarget the human hand to multi-finger robot hands, and align the noisy object mesh with its accurate 3D shape. We show that these relatively low-quality HOI data from inexpensive web sources can effectively train a functional grasping model. To further expand the grasp dataset for seen and unseen objects, we use the initially-trained grasping policy with web data in the IsaacGym simulator to generate physically feasible grasps while preserving functionality. We train the grasping model on 10 object categories and evaluate it on 9 unseen objects, including challenging items such as syringes, pens, spray bottles, and tongs, which are underrepresented in existing datasets. The model trained on the web HOI dataset, achieving a 75.8% success rate on seen objects and 61.8% across all objects in simulation, with a 6.7% improvement in success rate and a 1.8x increase in functionality ratings over baselines. Simulator-augmented data further boosts performance from 61.8% to 83.4%. The sim-to-real transfer to the LEAP Hand achieves a 85% success rate. Project website is at: https://webgrasp.github.io/.
Authors: Minkyu Choi, Yunhao Yang, Neel P. Bhatt, Kushagra Gupta, Sahil Shah, Aditya Rai, David Fridovich-Keil, Ufuk Topcu, Sandeep P. Chinchali
Abstract: Many robots (e.g., iRobot's Roomba) operate based on visual observations from live video streams, and such observations may inadvertently include privacy-sensitive objects, such as personal identifiers. Existing approaches for preserving privacy rely on deep learning models, differential privacy, or cryptography. They lack guarantees for the complete concealment of all sensitive objects. Guaranteeing concealment requires post-processing techniques and thus is inadequate for real-time video streams. We develop a method for privacy-constrained video streaming, PCVS, that conceals sensitive objects within real-time video streams. PCVS takes a logical specification constraining the existence of privacy-sensitive objects, e.g., never show faces when a person exists. It uses a detection model to evaluate the existence of these objects in each incoming frame. Then, it blurs out a subset of objects such that the existence of the remaining objects satisfies the specification. We then propose a conformal prediction approach to (i) establish a theoretical lower bound on the probability of the existence of these objects in a sequence of frames satisfying the specification and (ii) update the bound with the arrival of each subsequent frame. Quantitative evaluations show that PCVS achieves over 95 percent specification satisfaction rate in multiple datasets, significantly outperforming other methods. The satisfaction rate is consistently above the theoretical bounds across all datasets, indicating that the established bounds hold. Additionally, we deploy PCVS on robots in real-time operation and show that the robots operate normally without being compromised when PCVS conceals objects.
Authors: Chengwei Ye, Huanzhen Zhang, Yufei Lin, Kangsheng Wang, Linuo Xu, Shuyan Liu
Abstract: Gliomas are aggressive brain tumors that pose serious health risks. Deep learning aids in lesion segmentation, but CNN and Transformer-based models often lack context modeling or demand heavy computation, limiting real-time use on mobile medical devices. We propose GaMNet, integrating the NMamba module for global modeling and a multi-scale CNN for efficient local feature extraction. To improve interpretability and mimic the human visual system, we apply Gabor filters at multiple scales. Our method achieves high segmentation accuracy with fewer parameters and faster computation. Extensive experiments show GaMNet outperforms existing methods, notably reducing false positives and negatives, which enhances the reliability of clinical diagnosis.
Authors: Hanxun Huang, Sarah Erfani, Yige Li, Xingjun Ma, James Bailey
Abstract: As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a critical concern. In this work, we introduce \textbf{X-Transfer}, a novel attack method that exposes a universal adversarial vulnerability in CLIP. X-Transfer generates a Universal Adversarial Perturbation (UAP) capable of deceiving various CLIP encoders and downstream VLMs across different samples, tasks, and domains. We refer to this property as \textbf{super transferability}--a single perturbation achieving cross-data, cross-domain, cross-model, and cross-task adversarial transferability simultaneously. This is achieved through \textbf{surrogate scaling}, a key innovation of our approach. Unlike existing methods that rely on fixed surrogate models, which are computationally intensive to scale, X-Transfer employs an efficient surrogate scaling strategy that dynamically selects a small subset of suitable surrogates from a large search space. Extensive evaluations demonstrate that X-Transfer significantly outperforms previous state-of-the-art UAP methods, establishing a new benchmark for adversarial transferability across CLIP models. The code is publicly available in our \href{https://github.com/HanxunH/XTransferBench}{GitHub repository}.
Authors: Hanie Moghaddasi, Christina Chambers, Sarah N. Mattson, Jeffrey R. Wozniak, Claire D. Coles, Raja Mukherjee, Michael Suttie
Abstract: Lip segmentation plays a crucial role in various domains, such as lip synchronization, lipreading, and diagnostics. However, the effectiveness of supervised lip segmentation is constrained by the availability of lip contour in the training phase. A further challenge with lip segmentation is its reliance on image quality , lighting, and skin tone, leading to inaccuracies in the detected boundaries. To address these challenges, we propose a sequential lip segmentation method that integrates attention UNet and multidimensional input. We unravel the micro-patterns in facial images using local binary patterns to build multidimensional inputs. Subsequently, the multidimensional inputs are fed into sequential attention UNets, where the lip contour is reconstructed. We introduce a mask generation method that uses a few anatomical landmarks and estimates the complete lip contour to improve segmentation accuracy. This mask has been utilized in the training phase for lip segmentation. To evaluate the proposed method, we use facial images to segment the upper lips and subsequently assess lip-related facial anomalies in subjects with fetal alcohol syndrome (FAS). Using the proposed lip segmentation method, we achieved a mean dice score of 84.75%, and a mean pixel accuracy of 99.77% in upper lip segmentation. To further evaluate the method, we implemented classifiers to identify those with FAS. Using a generative adversarial network (GAN), we reached an accuracy of 98.55% in identifying FAS in one of the study populations. This method could be used to improve lip segmentation accuracy, especially around Cupid's bow, and shed light on distinct lip-related characteristics of FAS.
Authors: Pranav Guruprasad, Yangyue Wang, Sudipta Chowdhury, Harshvardhan Sikka
Abstract: Vision-language-action (VLA) models represent an important step toward general-purpose robotic systems by integrating visual perception, language understanding, and action execution. However, systematic evaluation of these models, particularly their zero-shot generalization capabilities in out-of-distribution (OOD) environments, remains limited. In this paper, we introduce MultiNet v0.2, a comprehensive benchmark designed to evaluate and analyze the generalization performance of state-of-the-art VLM and VLA models-including GPT-4o, GPT-4.1, OpenVLA,Pi0 Base, and Pi0 FAST-on diverse procedural tasks from the Procgen benchmark. Our analysis reveals several critical insights: (1) all evaluated models exhibit significant limitations in zero-shot generalization to OOD tasks, with performance heavily influenced by factors such as action representation and task complexit; (2) VLAs generally outperform other models due to their robust architectural design; and (3) VLM variants demonstrate substantial improvements when constrained appropriately, highlighting the sensitivity of model performance to precise prompt engineering.
Authors: Mikhail Chaichuk, Sushant Gautam, Steven Hicks, Elena Tutubalina
Abstract: The generation of realistic medical images from text descriptions has significant potential to address data scarcity challenges in healthcare AI while preserving patient privacy. This paper presents a comprehensive study of text-to-image synthesis in the medical domain, comparing two distinct approaches: (1) fine-tuning large pre-trained latent diffusion models and (2) training small, domain-specific models. We introduce a novel model named MSDM, an optimized architecture based on Stable Diffusion that integrates a clinical text encoder, variational autoencoder, and cross-attention mechanisms to better align medical text prompts with generated images. Our study compares two approaches: fine-tuning large pre-trained models (FLUX, Kandinsky) versus training compact domain-specific models (MSDM). Evaluation across colonoscopy (MedVQA-GI) and radiology (ROCOv2) datasets reveals that while large models achieve higher fidelity, our optimized MSDM delivers comparable quality with lower computational costs. Quantitative metrics and qualitative evaluations by medical experts reveal strengths and limitations of each approach.
Authors: Peihao Wang, Yuehao Wang, Dilin Wang, Sreyas Mohan, Zhiwen Fan, Lemeng Wu, Ruisi Cai, Yu-Ying Yeh, Zhangyang Wang, Qiang Liu, Rakesh Ranjan
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time, high-resolution novel view synthesis. By representing scenes as a mixture of Gaussian primitives, 3DGS leverages GPU rasterization pipelines for efficient rendering and reconstruction. To optimize scene coverage and capture fine details, 3DGS employs a densification algorithm to generate additional points. However, this process often leads to redundant point clouds, resulting in excessive memory usage, slower performance, and substantial storage demands - posing significant challenges for deployment on resource-constrained devices. To address this limitation, we propose a theoretical framework that demystifies and improves density control in 3DGS. Our analysis reveals that splitting is crucial for escaping saddle points. Through an optimization-theoretic approach, we establish the necessary conditions for densification, determine the minimal number of offspring Gaussians, identify the optimal parameter update direction, and provide an analytical solution for normalizing off-spring opacity. Building on these insights, we introduce SteepGS, incorporating steepest density control, a principled strategy that minimizes loss while maintaining a compact point cloud. SteepGS achieves a ~50% reduction in Gaussian points without compromising rendering quality, significantly enhancing both efficiency and scalability.
Authors: Jingzhong Lin, Yuanyuan Qi, Xinru Li, Wenxuan Huang, Xiangfeng Xu, Bangyan Li, Xuejiao Wang, Gaoqi He
Abstract: Reactive dance generation (RDG) produces follower movements conditioned on guiding dancer and music while ensuring spatial coordination and temporal coherence. However, existing methods overemphasize global constraints and optimization, overlooking local information, such as fine-grained spatial interactions and localized temporal context. Therefore, we present ReactDance, a novel diffusion-based framework for high-fidelity RDG with long-term coherence and multi-scale controllability. Unlike existing methods that struggle with interaction fidelity, synchronization, and temporal consistency in duet synthesis, our approach introduces two key innovations: 1)Group Residual Finite Scalar Quantization (GRFSQ), a multi-scale disentangled motion representation that captures interaction semantics from coarse body rhythms to fine-grained joint dynamics, and 2)Blockwise Local Context (BLC), a sampling strategy eliminating error accumulation in long sequence generation via local block causal masking and periodic positional encoding. Built on the decoupled multi-scale GRFSQ representation, we implement a diffusion model withLayer-Decoupled Classifier-free Guidance (LDCFG), allowing granular control over motion semantics across scales. Extensive experiments on standard benchmarks demonstrate that ReactDance surpasses existing methods, achieving state-of-the-art performance.
Authors: Yueh-Cheng Liu, Lukas H\"ollein, Matthias Nie{\ss}ner, Angela Dai
Abstract: Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumetric rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model under-observed or textureless regions. We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes. This provides a strong starting point for the reconstruction, which accelerates the convergence of the optimization and improves the geometry of flat wall structures. We further learn to jointly estimate the densification and update of the scene parameters during each iteration; our proposed densifier network predicts new Gaussians based on the rendering gradients of existing ones, removing the needs of heuristics for densification. Extensive experiments on large-scale indoor scene reconstruction demonstrate the superiority of our data-driven optimization. Concretely, we accelerate runtime by 8x, while decreasing depth errors by up to 48% in comparison to state of the art methods.
Authors: Seraj Al Mahmud Mostafa, Chenxi Wang, Jia Yue, Yuta Hozumi, Jianwu Wang
Abstract: Object localization in satellite imagery is particularly challenging due to the high variability of objects, low spatial resolution, and interference from noise and dominant features such as clouds and city lights. In this research, we focus on three satellite datasets: upper atmospheric Gravity Waves (GW), mesospheric Bores (Bore), and Ocean Eddies (OE), each presenting its own unique challenges. These challenges include the variability in the scale and appearance of the main object patterns, where the size, shape, and feature extent of objects of interest can differ significantly. To address these challenges, we introduce YOLO-DCAP, a novel enhanced version of YOLOv5 designed to improve object localization in these complex scenarios. YOLO-DCAP incorporates a Multi-scale Dilated Residual Convolution (MDRC) block to capture multi-scale features at scale with varying dilation rates, and an Attention-aided Spatial Pooling (AaSP) module to focus on the global relevant spatial regions, enhancing feature selection. These structural improvements help to better localize objects in satellite imagery. Experimental results demonstrate that YOLO-DCAP significantly outperforms both the YOLO base model and state-of-the-art approaches, achieving an average improvement of 20.95% in mAP50 and 32.23% in IoU over the base model, and 7.35% and 9.84% respectively over state-of-the-art alternatives, consistently across all three satellite datasets. These consistent gains across all three satellite datasets highlight the robustness and generalizability of the proposed approach. Our code is open sourced at https://github.com/AI-4-atmosphere-remote-sensing/satellite-object-localization.
URLs: https://github.com/AI-4-atmosphere-remote-sensing/satellite-object-localization.
Authors: Hao Yang, Yan Yang, Ruikun Zhang, Liyuan Pan
Abstract: OpenAI's GPT-4o model, integrating multi-modal inputs and outputs within an autoregressive architecture, has demonstrated unprecedented performance in image generation. In this work, we investigate its potential impact on the image restoration community. We present the first systematic evaluation of GPT-4o across diverse restoration tasks. Our experiments reveal that, although restoration outputs from GPT-4o are visually appealing, they often suffer from pixel-level structural fidelity when compared to ground-truth images. Common issues are variations in image proportions, shifts in object positions and quantities, and changes in viewpoint.To address it, taking image dehazing, derainning, and low-light enhancement as representative case studies, we show that GPT-4o's outputs can serve as powerful visual priors, substantially enhancing the performance of existing dehazing networks. It offers practical guidelines and a baseline framework to facilitate the integration of GPT-4o into future image restoration pipelines. We hope the study on GPT-4o image restoration will accelerate innovation in the broader field of image generation areas. To support further research, we will release GPT-4o-restored images from over 10 widely used image restoration datasets.
Authors: Aarti Ghatkesar, Uddeshya Upadhyay, Ganesh Venkatesh
Abstract: Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first provides insights into how MLLMs internally build visual understanding of image regions and then introduces techniques to amplify this capability. Specifically, we explore techniques designed both to deepen the model's understanding of visual content and to ensure that these visual insights actively guide language generation. We demonstrate the superior multimodal understanding of our resultant model through a detailed upstream analysis quantifying its ability to predict visually-dependent tokens as well as 10 pt boost on visually challenging tasks.
Authors: Faizan Farooq Khan, Jun Chen, Youssef Mohamed, Chun-Mei Feng, Mohamed Elhoseiny
Abstract: Open-vocabulary recognition remains a challenging problem in computer vision, as it requires identifying objects from an unbounded set of categories. This is particularly relevant in nature, where new species are discovered every year. In this work, we focus on open-vocabulary bird species recognition, where the goal is to classify species based on their descriptions without being constrained to a predefined set of taxonomic categories. Traditional benchmarks like CUB-200-2011 and Birdsnap have been evaluated in a closed-vocabulary paradigm, limiting their applicability to real-world scenarios where novel species continually emerge. We show that the performance of current systems when evaluated under settings closely aligned with open-vocabulary drops by a huge margin. To address this gap, we propose a scalable framework integrating structured textual knowledge from Wikipedia articles of 11,202 bird species distilled via GPT-4o into concise, discriminative summaries. We propose Visual Re-ranking Retrieval-Augmented Generation(VR-RAG), a novel, retrieval-augmented generation framework that uses visual similarities to rerank the top m candidates retrieved by a set of multimodal vision language encoders. This allows for the recognition of unseen taxa. Extensive experiments across five established classification benchmarks show that our approach is highly effective. By integrating VR-RAG, we improve the average performance of state-of-the-art Large Multi-Modal Model QWEN2.5-VL by 15.4% across five benchmarks. Our approach outperforms conventional VLM-based approaches, which struggle with unseen species. By bridging the gap between encyclopedic knowledge and visual recognition, our work advances open-vocabulary recognition, offering a flexible, scalable solution for biodiversity monitoring and ecological research.
Authors: Anadil Hussein, Anna Zamansky, George Martvel
Abstract: Neural Style Transfer (NST) is a technique for applying the visual characteristics of one image onto another while preserving structural content. Traditionally used for artistic transformations, NST has recently been adapted, e.g., for domain adaptation and data augmentation. This study investigates the use of this technique for enhancing animal facial landmark detectors training. As a case study, we use a recently introduced Ensemble Landmark Detector for 48 anatomical cat facial landmarks and the CatFLW dataset it was trained on, making three main contributions. First, we demonstrate that applying style transfer to cropped facial images rather than full-body images enhances structural consistency, improving the quality of generated images. Secondly, replacing training images with style-transferred versions raised challenges of annotation misalignment, but Supervised Style Transfer (SST) - which selects style sources based on landmark accuracy - retained up to 98% of baseline accuracy. Finally, augmenting the dataset with style-transferred images further improved robustness, outperforming traditional augmentation methods. These findings establish semantic style transfer as an effective augmentation strategy for enhancing the performance of facial landmark detection models for animals and beyond. While this study focuses on cat facial landmarks, the proposed method can be generalized to other species and landmark detection models.
Authors: Tom Sander, Moritz Tenthoff, Kay Wohlfarth, Christian W\"ohler
Abstract: Multimodal learning is an emerging research topic across multiple disciplines but has rarely been applied to planetary science. In this contribution, we identify that reflectance parameter estimation and image-based 3D reconstruction of lunar images can be formulated as a multimodal learning problem. We propose a single, unified transformer architecture trained to learn shared representations between multiple sources like grayscale images, digital elevation models, surface normals, and albedo maps. The architecture supports flexible translation from any input modality to any target modality. Predicting DEMs and albedo maps from grayscale images simultaneously solves the task of 3D reconstruction of planetary surfaces and disentangles photometric parameters and height information. Our results demonstrate that our foundation model learns physically plausible relations across these four modalities. Adding more input modalities in the future will enable tasks such as photometric normalization and co-registration.
Authors: Alexander Most, Joseph Winjum, Ayan Biswas, Shawn Jones, Nishath Rajiv Ranasinghe, Dan O'Malley, Manish Bhattarai
Abstract: Retrieval-Augmented Generation (RAG) has become a popular technique for enhancing the reliability and utility of Large Language Models (LLMs) by grounding responses in external documents. Traditional RAG systems rely on Optical Character Recognition (OCR) to first process scanned documents into text. However, even state-of-the-art OCRs can introduce errors, especially in degraded or complex documents. Recent vision-language approaches, such as ColPali, propose direct visual embedding of documents, eliminating the need for OCR. This study presents a systematic comparison between a vision-based RAG system (ColPali) and more traditional OCR-based pipelines utilizing Llama 3.2 (90B) and Nougat OCR across varying document qualities. Beyond conventional retrieval accuracy metrics, we introduce a semantic answer evaluation benchmark to assess end-to-end question-answering performance. Our findings indicate that while vision-based RAG performs well on documents it has been fine-tuned on, OCR-based RAG is better able to generalize to unseen documents of varying quality. We highlight the key trade-offs between computational efficiency and semantic accuracy, offering practical guidance for RAG practitioners in selecting between OCR-dependent and vision-based document retrieval systems in production environments.
Authors: Gengyan Li, Paulo Gotardo, Timo Bolkart, Stephan Garbin, Kripasindhu Sarkar, Abhimitra Meka, Alexandros Lattas, Thabo Beeler
Abstract: Sparse volumetric reconstruction and rendering via 3D Gaussian splatting have recently enabled animatable 3D head avatars that are rendered under arbitrary viewpoints with impressive photorealism. Today, such photoreal avatars are seen as a key component in emerging applications in telepresence, extended reality, and entertainment. Building a photoreal avatar requires estimating the complex non-rigid motion of different facial components as seen in input video images; due to inaccurate motion estimation, animatable models typically present a loss of fidelity and detail when compared to their non-animatable counterparts, built from an individual facial expression. Also, recent state-of-the-art models are often affected by memory limitations that reduce the number of 3D Gaussians used for modeling, leading to lower detail and quality. To address these problems, we present a new high-detail 3D head avatar model that improves upon the state of the art, largely increasing the number of 3D Gaussians and modeling quality for rendering at 4K resolution. Our high-quality model is reconstructed from multiview input video and builds on top of a mesh-based 3D morphable model, which provides a coarse deformation layer for the head. Photoreal appearance is modelled by 3D Gaussians embedded within the continuous UVD tangent space of this mesh, allowing for more effective densification where most needed. Additionally, these Gaussians are warped by a novel UVD deformation field to capture subtle, localized motion. Our key contribution is the novel deformable Gaussian encoding and overall fitting procedure that allows our head model to preserve appearance detail, while capturing facial motion and other transient high-frequency features such as skin wrinkling.
Authors: Etai Sella, Yanir Kleiman, Hadar Averbuch-Elor
Abstract: Despite rapid advancements in the capabilities of generative models, pretrained text-to-image models still struggle in capturing the semantics conveyed by complex prompts that compound multiple objects and instance-level attributes. Consequently, we are witnessing growing interests in integrating additional structural constraints, %leveraging additional structural inputs typically in the form of coarse bounding boxes, to better guide the generation process in such challenging cases. In this work, we take the idea of structural guidance a step further by making the observation that contemporary image generation models can directly provide a plausible \emph{fine-grained} structural initialization. We propose a technique that couples this image-based structural guidance with LLM-based instance-level instructions, yielding output images that adhere to all parts of the text prompt, including object counts, instance-level attributes, and spatial relations between instances.
Authors: Giulio Cesare Mastrocinque Santo, Patr\'icia Izar, Irene Delval, Victor de Napole Gregolin, Nina S. T. Hirata
Abstract: Video recordings of nonhuman primates in their natural habitat are a common source for studying their behavior in the wild. We fine-tune pre-trained video-text foundational models for the specific domain of capuchin monkeys, with the goal of developing useful computational models to help researchers to retrieve useful clips from videos. We focus on the challenging problem of training a model based solely on raw, unlabeled video footage, using weak audio descriptions sometimes provided by field collaborators. We leverage recent advances in Multimodal Large Language Models (MLLMs) and Vision-Language Models (VLMs) to address the extremely noisy nature of both video and audio content. Specifically, we propose a two-folded approach: an agentic data treatment pipeline and a fine-tuning process. The data processing pipeline automatically extracts clean and semantically aligned video-text pairs from the raw videos, which are subsequently used to fine-tune a pre-trained Microsoft's X-CLIP model through Low-Rank Adaptation (LoRA). We obtained an uplift in $Hits@5$ of $167\%$ for the 16 frames model and an uplift of $114\%$ for the 8 frame model on our domain data. Moreover, based on $NDCG@K$ results, our model is able to rank well most of the considered behaviors, while the tested raw pre-trained models are not able to rank them at all. The code will be made available upon acceptance.
Authors: Wooyoung Jeong, Hyun Jae Park, Seonghun Jeong, Jong Wook Jang, Tae Hoon Lim, Dae Seoung Kim
Abstract: Hyperspectral imagery provides rich spectral detail but poses unique challenges because of its high dimensionality in both spatial and spectral domains. We propose \textit{HyperspectralMAE}, a Transformer-based foundation model for hyperspectral data that employs a \textit{dual masking} strategy: during pre-training we randomly occlude 50\% of spatial patches and 50\% of spectral bands. This forces the model to learn representations capable of reconstructing missing information across both dimensions. To encode spectral order, we introduce learnable harmonic Fourier positional embeddings based on wavelength. The reconstruction objective combines mean-squared error (MSE) with the spectral angle mapper (SAM) to balance pixel-level accuracy and spectral-shape fidelity. The resulting model contains about $1.8\times10^{8}$ parameters and produces 768-dimensional embeddings, giving it sufficient capacity for transfer learning. We pre-trained HyperspectralMAE on two large hyperspectral corpora -- NASA EO-1 Hyperion ($\sim$1\,600 scenes, $\sim$$3\times10^{11}$ pixel spectra) and DLR EnMAP Level-0 ($\sim$1\,300 scenes, $\sim$$3\times10^{11}$ pixel spectra) -- and fine-tuned it for land-cover classification on the Indian Pines benchmark. HyperspectralMAE achieves state-of-the-art transfer-learning accuracy on Indian Pines, confirming that masked dual-dimensional pre-training yields robust spectral-spatial representations. These results demonstrate that dual masking and wavelength-aware embeddings advance hyperspectral image reconstruction and downstream analysis.
Authors: Ho-Joong Kim, Yearang Lee, Jung-Ho Hong, Seong-Whan Lee
Abstract: In this paper, we examine a key limitation in query-based detectors for temporal action detection (TAD), which arises from their direct adaptation of originally designed architectures for object detection. Despite the effectiveness of the existing models, they struggle to fully address the unique challenges of TAD, such as the redundancy in multi-scale features and the limited ability to capture sufficient temporal context. To address these issues, we propose a multi-dilated gated encoder and central-adjacent region integrated decoder for temporal action detection transformer (DiGIT). Our approach replaces the existing encoder that consists of multi-scale deformable attention and feedforward network with our multi-dilated gated encoder. Our proposed encoder reduces the redundant information caused by multi-level features while maintaining the ability to capture fine-grained and long-range temporal information. Furthermore, we introduce a central-adjacent region integrated decoder that leverages a more comprehensive sampling strategy for deformable cross-attention to capture the essential information. Extensive experiments demonstrate that DiGIT achieves state-of-the-art performance on THUMOS14, ActivityNet v1.3, and HACS-Segment. Code is available at: https://github.com/Dotori-HJ/DiGIT
Authors: Zixuan Li, Lei Meng, Guoqing Chao, Wei Wu, Xiaoshuo Yan, Yimeng Yang, Zhuang Qi, Xiangxu Meng
Abstract: Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual features. However, they typically face difficulties in finding such a projection due to the two modalities in both the distribution of class-wise samples and the range of their feature values. To address this issue, this paper proposes a novel Semantic-Space-Intervened Diffusive Alignment method, termed SeDA, models a semantic space as a bridge in the visual-to-textual projection, considering both types of features share the same class-level information in classification. More importantly, a bi-stage diffusion framework is developed to enable the progressive alignment between the two modalities. Specifically, SeDA first employs a Diffusion-Controlled Semantic Learner to model the semantic features space of visual features by constraining the interactive features of the diffusion model and the category centers of visual features. In the later stage of SeDA, the Diffusion-Controlled Semantic Translator focuses on learning the distribution of textual features from the semantic space. Meanwhile, the Progressive Feature Interaction Network introduces stepwise feature interactions at each alignment step, progressively integrating textual information into mapped features. Experimental results show that SeDA achieves stronger cross-modal feature alignment, leading to superior performance over existing methods across multiple scenarios.
Authors: Valay Bundele, Mehran Hosseinzadeh, Hendrik Lensch
Abstract: Synthetic datasets have enabled significant progress in point tracking by providing large-scale, densely annotated supervision. However, deploying these models in real-world domains remains challenging due to domain shift and lack of labeled data-issues that are especially severe in surgical videos, where scenes exhibit complex tissue deformation, occlusion, and lighting variation. While recent approaches adapt synthetic-trained trackers to natural videos using teacher ensembles or augmentation-heavy pseudo-labeling pipelines, their effectiveness in high-shift domains like surgery remains unexplored. This work presents SurgTracker, a semi-supervised framework for adapting synthetic-trained point trackers to surgical video using filtered self-distillation. Pseudo-labels are generated online by a fixed teacher-identical in architecture and initialization to the student-and are filtered using a cycle consistency constraint to discard temporally inconsistent trajectories. This simple yet effective design enforces geometric consistency and provides stable supervision throughout training, without the computational overhead of maintaining multiple teachers. Experiments on the STIR benchmark show that SurgTracker improves tracking performance using only 80 unlabeled videos, demonstrating its potential for robust adaptation in high-shift, data-scarce domains.
Authors: Zhangchi Hu, Peixi Wu, Jie Chen, Huyue Zhu, Yijun Wang, Yansong Peng, Hebei Li, Xiaoyan Sun
Abstract: Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage and high computational costs due to redundant feature processing and rigid query allocation. To address these challenges, we propose Dome-DETR, a novel framework with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection. To reduce feature redundancies, we introduce a lightweight Density-Focal Extractor (DeFE) to produce clustered compact foreground masks. Leveraging these masks, we incorporate Masked Window Attention Sparsification (MWAS) to focus computational resources on the most informative regions via sparse attention. Besides, we propose Progressive Adaptive Query Initialization (PAQI), which adaptively modulates query density across spatial areas for better query allocation. Extensive experiments demonstrate that Dome-DETR achieves state-of-the-art performance (+3.3 AP on AI-TOD-V2 and +2.5 AP on VisDrone) while maintaining low computational complexity and a compact model size. Code will be released upon acceptance.
Authors: Huan Yan, Junjie Hu
Abstract: Agglomerative clustering has emerged as a vital tool in data analysis due to its intuitive and flexible characteristics. However, existing agglomerative clustering methods often involve additional parameters for sub-cluster partitioning and inter-cluster similarity assessment. This necessitates different parameter settings across various datasets, which is undoubtedly challenging in the absence of prior knowledge. Moreover, existing agglomerative clustering techniques are constrained by the calculation method of connection distance, leading to unstable clustering results. To address these issues, this paper introduces a novel density-based agglomerative clustering method, termed kFuse. kFuse comprises four key components: (1) sub-cluster partitioning based on natural neighbors; (2) determination of boundary connectivity between sub-clusters through the computation of adjacent samples and shortest distances; (3) assessment of density similarity between sub-clusters via the calculation of mean density and variance; and (4) establishment of merging rules between sub-clusters based on boundary connectivity and density similarity. kFuse requires the specification of the number of clusters only at the final merging stage. Additionally, by comprehensively considering adjacent samples, distances, and densities among different sub-clusters, kFuse significantly enhances accuracy during the merging phase, thereby greatly improving its identification capability. Experimental results on both synthetic and real-world datasets validate the effectiveness of kFuse.
Authors: Amin Ghafourian, Andrew Lee, Dechen Gao, Tyler Beer, Kin Yen, Iman Soltani
Abstract: Automation can play a prominent role in improving efficiency, accuracy, and scalability in infrastructure surveying and assessing construction and compliance standards. This paper presents a framework for automation of geometric measurements and compliance assessment using point cloud data. The proposed approach integrates deep learning-based detection and segmentation, in conjunction with geometric and signal processing techniques, to automate surveying tasks. As a proof of concept, we apply this framework to automatically evaluate the compliance of curb ramps with the Americans with Disabilities Act (ADA), demonstrating the utility of point cloud data in survey automation. The method leverages a newly collected, large annotated dataset of curb ramps, made publicly available as part of this work, to facilitate robust model training and evaluation. Experimental results, including comparison with manual field measurements of several ramps, validate the accuracy and reliability of the proposed method, highlighting its potential to significantly reduce manual effort and improve consistency in infrastructure assessment. Beyond ADA compliance, the proposed framework lays the groundwork for broader applications in infrastructure surveying and automated construction evaluation, promoting wider adoption of point cloud data in these domains. The annotated database, manual ramp survey data, and developed algorithms are publicly available on the project's GitHub page: https://github.com/Soltanilara/SurveyAutomation.
Authors: Fangxue Liu, Lei Fan
Abstract: In low-light environments, the performance of computer vision algorithms often deteriorates significantly, adversely affecting key vision tasks such as segmentation, detection, and classification. With the rapid advancement of deep learning, its application to low-light image processing has attracted widespread attention and seen significant progress in recent years. However, there remains a lack of comprehensive surveys that systematically examine how recent deep-learning-based low-light image enhancement methods function and evaluate their effectiveness in enhancing downstream vison tasks. To address this gap, this review provides a detailed elaboration on how various recent approaches (from 2020) operate and their enhancement mechanisms, supplemented with clear illustrations. It also investigates the impact of different enhancement techniques on subsequent vision tasks, critically analyzing their strengths and limitations. Additionally, it proposes future research directions. This review serves as a useful reference for determining low-light image enhancement techniques and optimizing vision task performance in low-light conditions.
Authors: Xi Xiao, Yunbei Zhang, Thanh-Huy Nguyen, Ba-Thinh Lam, Janet Wang, Jihun Hamm, Tianyang Wang, Xingjian Li, Xiao Wang, Hao Xu, Tianming Liu, Min Xu
Abstract: Localized image captioning has made significant progress with models like the Describe Anything Model (DAM), which can generate detailed region-specific descriptions without explicit region-text supervision. However, such capabilities have yet to be widely applied to specialized domains like medical imaging, where diagnostic interpretation relies on subtle regional findings rather than global understanding. To mitigate this gap, we propose MedDAM, the first comprehensive framework leveraging large vision-language models for region-specific captioning in medical images. MedDAM employs medical expert-designed prompts tailored to specific imaging modalities and establishes a robust evaluation benchmark comprising a customized assessment protocol, data pre-processing pipeline, and specialized QA template library. This benchmark evaluates both MedDAM and other adaptable large vision-language models, focusing on clinical factuality through attribute-level verification tasks, thereby circumventing the absence of ground-truth region-caption pairs in medical datasets. Extensive experiments on the VinDr-CXR, LIDC-IDRI, and SkinCon datasets demonstrate MedDAM's superiority over leading peers (including GPT-4o, Claude 3.7 Sonnet, LLaMA-3.2 Vision, Qwen2.5-VL, GPT-4Rol, and OMG-LLaVA) in the task, revealing the importance of region-level semantic alignment in medical image understanding and establishing MedDAM as a promising foundation for clinical vision-language integration.
Authors: Kaili Qi, Wenli Yang, Ye Li, Zhongyi Huang
Abstract: Traditional image segmentation methods, such as variational models based on partial differential equations (PDEs), offer strong mathematical interpretability and precise boundary modeling, but often suffer from sensitivity to parameter settings and high computational costs. In contrast, deep learning models such as UNet, which are relatively lightweight in parameters, excel in automatic feature extraction but lack theoretical interpretability and require extensive labeled data. To harness the complementary strengths of both paradigms, we propose Variational Model Based Tailored UNet (VM_TUNet), a novel hybrid framework that integrates the fourth-order modified Cahn-Hilliard equation with the deep learning backbone of UNet, which combines the interpretability and edge-preserving properties of variational methods with the adaptive feature learning of neural networks. Specifically, a data-driven operator is introduced to replace manual parameter tuning, and we incorporate the tailored finite point method (TFPM) to enforce high-precision boundary preservation. Experimental results on benchmark datasets demonstrate that VM_TUNet achieves superior segmentation performance compared to existing approaches, especially for fine boundary delineation.
Authors: Zhiyuan Chen, Keyi Li, Yifan Jia, Le Ye, Yufei Ma
Abstract: Diffusion transformer (DiT) models have achieved remarkable success in image generation, thanks for their exceptional generative capabilities and scalability. Nonetheless, the iterative nature of diffusion models (DMs) results in high computation complexity, posing challenges for deployment. Although existing cache-based acceleration methods try to utilize the inherent temporal similarity to skip redundant computations of DiT, the lack of correction may induce potential quality degradation. In this paper, we propose increment-calibrated caching, a training-free method for DiT acceleration, where the calibration parameters are generated from the pre-trained model itself with low-rank approximation. To deal with the possible correction failure arising from outlier activations, we introduce channel-aware Singular Value Decomposition (SVD), which further strengthens the calibration effect. Experimental results show that our method always achieve better performance than existing naive caching methods with a similar computation resource budget. When compared with 35-step DDIM, our method eliminates more than 45% computation and improves IS by 12 at the cost of less than 0.06 FID increase. Code is available at https://github.com/ccccczzy/icc.
Authors: Chunlai Dong, Haochao Ying, Qibo Qiu, Jinhong Wang, Danny Chen, Jian Wu
Abstract: Ordinal regression bridges regression and classification by assigning objects to ordered classes. While human experts rely on discriminative patch-level features for decisions, current approaches are limited by the availability of only image-level ordinal labels, overlooking fine-grained patch-level characteristics. In this paper, we propose a Dual-level Fuzzy Learning with Patch Guidance framework, named DFPG that learns precise feature-based grading boundaries from ambiguous ordinal labels, with patch-level supervision. Specifically, we propose patch-labeling and filtering strategies to enable the model to focus on patch-level features exclusively with only image-level ordinal labels available. We further design a dual-level fuzzy learning module, which leverages fuzzy logic to quantitatively capture and handle label ambiguity from both patch-wise and channel-wise perspectives. Extensive experiments on various image ordinal regression datasets demonstrate the superiority of our proposed method, further confirming its ability in distinguishing samples from difficult-to-classify categories. The code is available at https://github.com/ZJUMAI/DFPG-ord.
Authors: Guohao Lin, Shidong Pan, Rasul Khanbayov, Changxi Yang, Ani Khaloian-Sarnaghi, Andriy Kovryga
Abstract: Knots in wood are critical to both aesthetics and structural integrity, making their detection and pairing essential in timber processing. However, traditional manual annotation was labor-intensive and inefficient, necessitating automation. This paper proposes a lightweight and fully automated pipeline for knot detection and pairing based on machine learning techniques. In the detection stage, high-resolution surface images of wooden boards were collected using industrial-grade cameras, and a large-scale dataset was manually annotated and preprocessed. After the transfer learning, the YOLOv8l achieves an mAP@0.5 of 0.887. In the pairing stage, detected knots were analyzed and paired based on multidimensional feature extraction. A triplet neural network was used to map the features into a latent space, enabling clustering algorithms to identify and pair corresponding knots. The triplet network with learnable weights achieved a pairing accuracy of 0.85. Further analysis revealed that he distances from the knot's start and end points to the bottom of the wooden board, and the longitudinal coordinates play crucial roles in achieving high pairing accuracy. Our experiments validate the effectiveness of the proposed solution, demonstrating the potential of AI in advancing wood science and industry.
Authors: Yue Yin, Enze Tao, Weijian Deng, Dylan Campbell
Abstract: Modern 3D reconstruction and novel view synthesis approaches have demonstrated strong performance on scenes with opaque Lambertian objects. However, most assume straight light paths and therefore cannot properly handle refractive and reflective materials. Moreover, datasets specialized for these effects are limited, stymieing efforts to evaluate performance and develop suitable techniques. In this work, we introduce a synthetic RefRef dataset and benchmark for reconstructing scenes with refractive and reflective objects from posed images. Our dataset has 50 such objects of varying complexity, from single-material convex shapes to multi-material non-convex shapes, each placed in three different background types, resulting in 150 scenes. We also propose an oracle method that, given the object geometry and refractive indices, calculates accurate light paths for neural rendering, and an approach based on this that avoids these assumptions. We benchmark these against several state-of-the-art methods and show that all methods lag significantly behind the oracle, highlighting the challenges of the task and dataset.
Authors: Tongda Xu, Jiahao Li, Bin Li, Yan Wang, Ya-Qin Zhang, Yan Lu
Abstract: Recently, perceptual image compression has achieved significant advancements, delivering high visual quality at low bitrates for natural images. However, for screen content, existing methods often produce noticeable artifacts when compressing text. To tackle this challenge, we propose versatile perceptual screen image compression with diffusion rendering (PICD), a codec that works well for both screen and natural images. More specifically, we propose a compression framework that encodes the text and image separately, and renders them into one image using diffusion model. For this diffusion rendering, we integrate conditional information into diffusion models at three distinct levels: 1). Domain level: We fine-tune the base diffusion model using text content prompts with screen content. 2). Adaptor level: We develop an efficient adaptor to control the diffusion model using compressed image and text as input. 3). Instance level: We apply instance-wise guidance to further enhance the decoding process. Empirically, our PICD surpasses existing perceptual codecs in terms of both text accuracy and perceptual quality. Additionally, without text conditions, our approach serves effectively as a perceptual codec for natural images.
Authors: Hongyu Rui, Yinzhe Wu, Fanwen Wang, Jiahao Huang, Liutao Yang, Zi Wang, Guang Yang
Abstract: Magnetic Resonance Imaging (MRI) is critical for clinical diagnostics but is often limited by long acquisition times and low signal-to-noise ratios, especially in modalities like diffusion and functional MRI. The multi-contrast nature of MRI presents a valuable opportunity for cross-modal enhancement, where high-resolution (HR) modalities can serve as references to boost the quality of their low-resolution (LR) counterparts-motivating the development of Multi-Contrast Super-Resolution (MCSR) techniques. Prior work has shown that leveraging complementary contrasts can improve SR performance; however, effective feature extraction and fusion across modalities with varying resolutions remains a major challenge. Moreover, existing MCSR methods often assume fixed resolution settings and all require large, perfectly paired training datasets-conditions rarely met in real-world clinical environments. To address these challenges, we propose a novel Modular Multi-Contrast Super-Resolution (MCSR) framework that eliminates the need for paired training data and supports arbitrary upscaling. Our method decouples the MCSR task into two stages: (1) Unpaired Cross-Modal Synthesis (U-CMS), which translates a high-resolution reference modality into a synthesized version of the target contrast, and (2) Unsupervised Super-Resolution (U-SR), which reconstructs the final output using implicit neural representations (INRs) conditioned on spatial coordinates. This design enables scale-agnostic and anatomically faithful reconstruction by bridging un-paired cross-modal synthesis with unsupervised resolution enhancement. Experiments show that our method achieves superior performance at 4x and 8x upscaling, with improved fidelity and anatomical consistency over existing baselines. Our framework demonstrates strong potential for scalable, subject-specific, and data-efficient MCSR in real-world clinical settings.
Authors: Yimin Zhou, Yichong Xia, Bin Chen, Baoyi An, Haoqian Wang, Zhi Wang, Yaowei Wang, Zikun Zhou
Abstract: With the widespread application of facial image data across various domains, the efficient storage and transmission of facial images has garnered significant attention. However, the existing learned face image compression methods often produce unsatisfactory reconstructed image quality at low bit rates. Simply adapting diffusion-based compression methods to facial compression tasks results in reconstructed images that perform poorly in downstream applications due to insufficient preservation of high-frequency information. To further explore the diffusion prior in facial image compression, we propose Facial Image Compression with a Stable Diffusion Prior (FaSDiff), a method that preserves consistency through frequency enhancement. FaSDiff employs a high-frequency-sensitive compressor in an end-to-end framework to capture fine image details and produce robust visual prompts. Additionally, we introduce a hybrid low-frequency enhancement module that disentangles low-frequency facial semantics and stably modulates the diffusion prior alongside visual prompts. The proposed modules allow FaSDiff to leverage diffusion priors for superior human visual perception while minimizing performance loss in machine vision due to semantic inconsistency. Extensive experiments show that FaSDiff outperforms state-of-the-art methods in balancing human visual quality and machine vision accuracy. The code will be released after the paper is accepted.
Authors: Alexander Lappe, Martin A. Giese
Abstract: Recent work has shown that the attention maps of the widely popular DINOv2 model exhibit artifacts, which hurt both model interpretability and performance on dense image tasks. These artifacts emerge due to the model repurposing patch tokens with redundant local information for the storage of global image information. To address this problem, additional register tokens have been incorporated in which the model can store such information instead. We carefully examine the influence of these register tokens on the relationship between global and local image features, showing that while register tokens yield cleaner attention maps, these maps do not accurately reflect the integration of local image information in large models. Instead, global information is dominated by information extracted from register tokens, leading to a disconnect between local and global features. Inspired by these findings, we show that the CLS token itself, which can be interpreted as a register, leads to a very similar phenomenon in models without explicit register tokens. Our work shows that care must be taken when interpreting attention maps of large ViTs. Further, by clearly attributing the faulty behaviour to register and CLS tokens, we show a path towards more interpretable vision models.
Authors: Benjamin Raphael Ernhofer, Daniil Prokhorov, Jannica Langner, Dominik Bollmann
Abstract: Modern automotive infotainment systems require intelligent and adaptive solutions to handle frequent User Interface (UI) updates and diverse design variations. We introduce a vision-language framework for understanding and interacting with automotive infotainment systems, enabling seamless adaptation across different UI designs. To further support research in this field, we release AutomotiveUI-Bench-4K, an open-source dataset of 998 images with 4,208 annotations. Additionally, we present a synthetic data pipeline to generate training data. We fine-tune a Molmo-7B-based model using Low-Rank Adaptation (LoRa) and incorporating reasoning generated by our pipeline, along with visual grounding and evaluation capabilities. The fine-tuned Evaluative Large Action Model (ELAM) achieves strong performance on AutomotiveUI-Bench-4K (model and dataset are available on Hugging Face) and demonstrating strong cross-domain generalization, including a +5.2% improvement on ScreenSpot over the baseline model. Notably, our approach achieves 80.4% average accuracy on ScreenSpot, closely matching or even surpassing specialized models for desktop, mobile, and web, such as ShowUI, despite being trained for the infotainment domain. This research investigates how data collection and subsequent fine-tuning can lead to AI-driven progress within automotive UI understanding and interaction. The applied method is cost-efficient and fine-tuned models can be deployed on consumer-grade GPUs.
Authors: Hanzhe Liang, Aoran Wang, Jie Zhou, Xin Jin, Can Gao, Jinbao Wang
Abstract: In this paper, we go beyond identifying anomalies only in structural terms and think about better anomaly detection motivated by anomaly causes. Most anomalies are regarded as the result of unpredictable defective forces from internal and external sources, and their opposite forces are sought to correct the anomalies. We introduced a Mechanics Complementary framework for 3D anomaly detection (MC4AD) to generate internal and external Corrective forces for each point. A Diverse Anomaly-Generation (DA-Gen) module is first proposed to simulate various anomalies. Then, we present a Corrective Force Prediction Network (CFP-Net) with complementary representations for point-level representation to simulate the different contributions of internal and external corrective forces. A combined loss was proposed, including a new symmetric loss and an overall loss, to constrain the corrective forces properly. As a highlight, we consider 3D anomaly detection in industry more comprehensively, creating a hierarchical quality control strategy based on a three-way decision and contributing a dataset named Anomaly-IntraVariance with intraclass variance to evaluate the model. On the proposed and existing five datasets, we obtained nine state-of-the-art performers with the minimum parameters and the fastest inference speed. The source is available at https://github.com/hzzzzzhappy/MC4AD
Authors: Jianjian Yin, Yi Chen, Chengyu Li, Zhichao Zheng, Yanhui Gu, Junsheng Zhou
Abstract: Current methods for medical image segmentation primarily focus on extracting contextual feature information from the perspective of the whole image. While these methods have shown effective performance, none of them take into account the fact that pixels at the boundary and regions with a low number of class pixels capture more contextual feature information from other classes, leading to misclassification of pixels by unequal contextual feature information. In this paper, we propose a dual feature equalization network based on the hybrid architecture of Swin Transformer and Convolutional Neural Network, aiming to augment the pixel feature representations by image-level equalization feature information and class-level equalization feature information. Firstly, the image-level feature equalization module is designed to equalize the contextual information of pixels within the image. Secondly, we aggregate regions of the same class to equalize the pixel feature representations of the corresponding class by class-level feature equalization module. Finally, the pixel feature representations are enhanced by learning weights for image-level equalization feature information and class-level equalization feature information. In addition, Swin Transformer is utilized as both the encoder and decoder, thereby bolstering the ability of the model to capture long-range dependencies and spatial correlations. We conducted extensive experiments on Breast Ultrasound Images (BUSI), International Skin Imaging Collaboration (ISIC2017), Automated Cardiac Diagnosis Challenge (ACDC) and PH$^2$ datasets. The experimental results demonstrate that our method have achieved state-of-the-art performance. Our code is publicly available at https://github.com/JianJianYin/DFEN.
Authors: Weihong Li, Xiaoqiong Liu, Heng Fan, Libo Zhang
Abstract: Recent advancements in visual object tracking have markedly improved the capabilities of unmanned aerial vehicle (UAV) tracking, which is a critical component in real-world robotics applications. While the integration of hierarchical lightweight networks has become a prevalent strategy for enhancing efficiency in UAV tracking, it often results in a significant drop in network capacity, which further exacerbates challenges in UAV scenarios, such as frequent occlusions and extreme changes in viewing angles. To address these issues, we introduce a novel family of UAV trackers, termed CGTrack, which combines explicit and implicit techniques to expand network capacity within a coarse-to-fine framework. Specifically, we first introduce a Hierarchical Feature Cascade (HFC) module that leverages the spirit of feature reuse to increase network capacity by integrating the deep semantic cues with the rich spatial information, incurring minimal computational costs while enhancing feature representation. Based on this, we design a novel Lightweight Gated Center Head (LGCH) that utilizes gating mechanisms to decouple target-oriented coordinates from previously expanded features, which contain dense local discriminative information. Extensive experiments on three challenging UAV tracking benchmarks demonstrate that CGTrack achieves state-of-the-art performance while running fast. Code will be available at https://github.com/Nightwatch-Fox11/CGTrack.
Authors: Maan Alhazmi, Abdulrahman Altahhan
Abstract: The emergence of ConvNeXt and its variants has reaffirmed the conceptual and structural suitability of CNN-based models for vision tasks, re-establishing them as key players in image classification in general, and in facial expression recognition (FER) in particular. In this paper, we propose a new set of models that build on these advancements by incorporating a new set of attention mechanisms that combines Triplet attention with Squeeze-and-Excitation (TripSE) in four different variants. We demonstrate the effectiveness of these variants by applying them to the ResNet18, DenseNet and ConvNext architectures to validate their versatility and impact. Our study shows that incorporating a TripSE block in these CNN models boosts their performances, particularly for the ConvNeXt architecture, indicating its utility. We evaluate the proposed mechanisms and associated models across four datasets, namely CIFAR100, ImageNet, FER2013 and AffectNet datasets, where ConvNext with TripSE achieves state-of-the-art results with an accuracy of \textbf{78.27\%} on the popular FER2013 dataset, a new feat for this dataset.
Authors: Congqi Cao, Peiheng Han, Yueran zhang, Yating Yu, Qinyi Lv, Lingtong Min, Yanning zhang
Abstract: Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of few-shot action recognition (FSAR). However, current methods generally suffer from several problems: 1) Direct fine-tuning often undermines the generalization capability of the pre-trained model; 2) The exploration of task-specific information is insufficient in the visual tasks; 3) The semantic order information is typically overlooked during text modeling; 4) Existing cross-modal alignment techniques ignore the temporal coupling of multimodal information. To address these, we propose Task-Adapter++, a parameter-efficient dual adaptation method for both image and text encoders. Specifically, to make full use of the variations across different few-shot learning tasks, we design a task-specific adaptation for the image encoder so that the most discriminative information can be well noticed during feature extraction. Furthermore, we leverage large language models (LLMs) to generate detailed sequential sub-action descriptions for each action class, and introduce semantic order adapters into the text encoder to effectively model the sequential relationships between these sub-actions. Finally, we develop an innovative fine-grained cross-modal alignment strategy that actively maps visual features to reside in the same temporal stage as semantic descriptions. Extensive experiments fully demonstrate the effectiveness and superiority of the proposed method, which achieves state-of-the-art performance on 5 benchmarks consistently. The code is open-sourced at https://github.com/Jaulin-Bage/Task-Adapter-pp.
Authors: Moritz Vandenhirtz, Julia E. Vogt
Abstract: Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures. In this work, we propose a method that performs inherently interpretable predictions through the instance-wise sparsification of input images. To align the sparsification with human perception, we learn the masking in the space of semantically meaningful pixel regions rather than on pixel-level. Additionally, we introduce an explicit way to dynamically determine the required level of sparsity for each instance. We show empirically on semi-synthetic and natural image datasets that our inherently interpretable classifier produces more meaningful, human-understandable predictions than state-of-the-art benchmarks.
Authors: Heng Li, Xiangping Wu, Qingcai Chen
Abstract: Deformed document image rectification is essential for real-world document understanding tasks, such as layout analysis and text recognition. However, current multi-task methods -- such as background removal, 3D coordinate prediction, and text line segmentation -- often overlook the complementary features between tasks and their interactions. To address this gap, we propose a self-adaptive learnable multi-task fusion rectification network named SalmRec. This network incorporates an inter-task feature aggregation module that adaptively improves the perception of geometric distortions, enhances feature complementarity, and reduces negative interference. We also introduce a gating mechanism to balance features both within global tasks and between local tasks effectively. Experimental results on two English benchmarks (DIR300 and DocUNet) and one Chinese benchmark (DocReal) demonstrate that our method significantly improves rectification performance. Ablation studies further highlight the positive impact of different tasks on dewarping and the effectiveness of our proposed module.
Authors: Dongqian Guo, Wencheng Han, Pang Lyu, Yuxi Zhou, Jianbing Shen
Abstract: Cephalometric landmark detection is essential for orthodontic diagnostics and treatment planning. Nevertheless, the scarcity of samples in data collection and the extensive effort required for manual annotation have significantly impeded the availability of diverse datasets. This limitation has restricted the effectiveness of deep learning-based detection methods, particularly those based on large-scale vision models. To address these challenges, we have developed an innovative data generation method capable of producing diverse cephalometric X-ray images along with corresponding annotations without human intervention. To achieve this, our approach initiates by constructing new cephalometric landmark annotations using anatomical priors. Then, we employ a diffusion-based generator to create realistic X-ray images that correspond closely with these annotations. To achieve precise control in producing samples with different attributes, we introduce a novel prompt cephalometric X-ray image dataset. This dataset includes real cephalometric X-ray images and detailed medical text prompts describing the images. By leveraging these detailed prompts, our method improves the generation process to control different styles and attributes. Facilitated by the large, diverse generated data, we introduce large-scale vision detection models into the cephalometric landmark detection task to improve accuracy. Experimental results demonstrate that training with the generated data substantially enhances the performance. Compared to methods without using the generated data, our approach improves the Success Detection Rate (SDR) by 6.5%, attaining a notable 82.2%. All code and data are available at: https://um-lab.github.io/cepha-generation
Authors: Kunpeng Qiu, Zhiqiang Gao, Zhiying Zhou, Mingjie Sun, Yongxin Guo
Abstract: Deep learning has revolutionized medical image segmentation, yet its full potential remains constrained by the paucity of annotated datasets. While diffusion models have emerged as a promising approach for generating synthetic image-mask pairs to augment these datasets, they paradoxically suffer from the same data scarcity challenges they aim to mitigate. Traditional mask-only models frequently yield low-fidelity images due to their inability to adequately capture morphological intricacies, which can critically compromise the robustness and reliability of segmentation models. To alleviate this limitation, we introduce Siamese-Diffusion, a novel dual-component model comprising Mask-Diffusion and Image-Diffusion. During training, a Noise Consistency Loss is introduced between these components to enhance the morphological fidelity of Mask-Diffusion in the parameter space. During sampling, only Mask-Diffusion is used, ensuring diversity and scalability. Comprehensive experiments demonstrate the superiority of our method. Siamese-Diffusion boosts SANet's mDice and mIoU by 3.6% and 4.4% on the Polyps, while UNet improves by 1.52% and 1.64% on the ISIC2018. Code is available at GitHub.
Authors: Anupkumar Bochare
Abstract: Autonomous vehicle perception systems have traditionally relied on costly LiDAR sensors to generate precise environmental representations. In this paper, we propose a camera-only perception framework that produces Bird's Eye View (BEV) maps by extending the Lift-Splat-Shoot architecture. Our method combines YOLOv11-based object detection with DepthAnythingV2 monocular depth estimation across multi-camera inputs to achieve comprehensive 360-degree scene understanding. We evaluate our approach on the OpenLane-V2 and NuScenes datasets, achieving up to 85% road segmentation accuracy and 85-90% vehicle detection rates when compared against LiDAR ground truth, with average positional errors limited to 1.2 meters. These results highlight the potential of deep learning to extract rich spatial information using only camera inputs, enabling cost-efficient autonomous navigation without sacrificing accuracy.
Authors: Dongying Li, Binyi Su, Hua Zhang, Yong Li, Haiyong Chen
Abstract: Accurate defect detection of photovoltaic (PV) cells is critical for ensuring quality and efficiency in intelligent PV manufacturing systems. However, the scarcity of rich defect data poses substantial challenges for effective model training. While existing methods have explored generative models to augment datasets, they often suffer from instability, limited diversity, and domain shifts. To address these issues, we propose PDIG, a Photovoltaic Defect Image Generator based on Stable Diffusion (SD). PDIG leverages the strong priors learned from large-scale datasets to enhance generation quality under limited data. Specifically, we introduce a Semantic Concept Embedding (SCE) module that incorporates text-conditioned priors to capture the relational concepts between defect types and their appearances. To further enrich the domain distribution, we design a Lightweight Industrial Style Adaptor (LISA), which injects industrial defect characteristics into the SD model through cross-disentangled attention. At inference, we propose a Text-Image Dual-Space Constraints (TIDSC) module, enforcing the quality of generated images via positional consistency and spatial smoothing alignment. Extensive experiments demonstrate that PDIG achieves superior realism and diversity compared to state-of-the-art methods. Specifically, our approach improves Frechet Inception Distance (FID) by 19.16 points over the second-best method and significantly enhances the performance of downstream defect detection tasks.
Authors: Hongming Wang, Yifeng Wu, Huimin Huang, Hongtao Wu, Jia-Xuan Jiang, Xiaodong Zhang, Hao Zheng, Xian Wu, Yefeng Zheng, Jinping Xu, Jing Cheng
Abstract: The segmentation of substantial brain lesions is a significant and challenging task in the field of medical image segmentation. Substantial brain lesions in brain imaging exhibit high heterogeneity, with indistinct boundaries between lesion regions and normal brain tissue. Small lesions in single slices are difficult to identify, making the accurate and reproducible segmentation of abnormal regions, as well as their feature description, highly complex. Existing methods have the following limitations: 1) They rely solely on single-modal information for learning, neglecting the multi-modal information commonly used in diagnosis. This hampers the ability to comprehensively acquire brain lesion information from multiple perspectives and prevents the effective integration and utilization of multi-modal data inputs, thereby limiting a holistic understanding of lesions. 2) They are constrained by the amount of data available, leading to low sensitivity to small lesions and difficulty in detecting subtle pathological changes. 3) Current SAM-based models rely on external prompts, which cannot achieve automatic segmentation and, to some extent, affect diagnostic efficiency.To address these issues, we have developed a large-scale fully automated segmentation model specifically designed for brain lesion segmentation, named BrainSegDMLF. This model has the following features: 1) Dynamic Modal Interactive Fusion (DMIF) module that processes and integrates multi-modal data during the encoding process, providing the SAM encoder with more comprehensive modal information. 2) Layer-by-Layer Upsampling Decoder, enabling the model to extract rich low-level and high-level features even with limited data, thereby detecting the presence of small lesions. 3) Automatic segmentation masks, allowing the model to generate lesion masks automatically without requiring manual prompts.
Authors: Wenqi Zeng, Yuqi Sun, Chenxi Ma, Weimin Tan, Bo Yan
Abstract: Medical vision-language models (VLMs) have shown promise as clinical assistants across various medical fields. However, specialized dermatology VLM capable of delivering professional and detailed diagnostic analysis remains underdeveloped, primarily due to less specialized text descriptions in current dermatology multimodal datasets. To address this issue, we propose MM-Skin, the first large-scale multimodal dermatology dataset that encompasses 3 imaging modalities, including clinical, dermoscopic, and pathological and nearly 10k high-quality image-text pairs collected from professional textbooks. In addition, we generate over 27k diverse, instruction-following vision question answering (VQA) samples (9 times the size of current largest dermatology VQA dataset). Leveraging public datasets and MM-Skin, we developed SkinVL, a dermatology-specific VLM designed for precise and nuanced skin disease interpretation. Comprehensive benchmark evaluations of SkinVL on VQA, supervised fine-tuning (SFT) and zero-shot classification tasks across 8 datasets, reveal its exceptional performance for skin diseases in comparison to both general and medical VLM models. The introduction of MM-Skin and SkinVL offers a meaningful contribution to advancing the development of clinical dermatology VLM assistants. MM-Skin is available at https://github.com/ZwQ803/MM-Skin
Authors: Radu Alexandru Rosu, Keyu Wu, Yao Feng, Youyi Zheng, Michael J. Black
Abstract: We address the task of generating 3D hair geometry from a single image, which is challenging due to the diversity of hairstyles and the lack of paired image-to-3D hair data. Previous methods are primarily trained on synthetic data and cope with the limited amount of such data by using low-dimensional intermediate representations, such as guide strands and scalp-level embeddings, that require post-processing to decode, upsample, and add realism. These approaches fail to reconstruct detailed hair, struggle with curly hair, or are limited to handling only a few hairstyles. To overcome these limitations, we propose DiffLocks, a novel framework that enables detailed reconstruction of a wide variety of hairstyles directly from a single image. First, we address the lack of 3D hair data by automating the creation of the largest synthetic hair dataset to date, containing 40K hairstyles. Second, we leverage the synthetic hair dataset to learn an image-conditioned diffusion-transfomer model that generates accurate 3D strands from a single frontal image. By using a pretrained image backbone, our method generalizes to in-the-wild images despite being trained only on synthetic data. Our diffusion model predicts a scalp texture map in which any point in the map contains the latent code for an individual hair strand. These codes are directly decoded to 3D strands without post-processing techniques. Representing individual strands, instead of guide strands, enables the transformer to model the detailed spatial structure of complex hairstyles. With this, DiffLocks can recover highly curled hair, like afro hairstyles, from a single image for the first time. Data and code is available at https://radualexandru.github.io/difflocks/
Authors: Pengfei Gu, Haoteng Tang, Islam A. Ebeid, Jose A. Nunez, Fabian Vazquez, Diego Adame, Marcus Zhan, Huimin Li, Bin Fu, Danny Z. Chen
Abstract: Recent advancements in foundation models, such as the Segment Anything Model (SAM), have shown strong performance in various vision tasks, particularly image segmentation, due to their impressive zero-shot segmentation capabilities. However, effectively adapting such models for medical image classification is still a less explored topic. In this paper, we introduce a new framework to adapt SAM for medical image classification. First, we utilize the SAM image encoder as a feature extractor to capture segmentation-based features that convey important spatial and contextual details of the image, while freezing its weights to avoid unnecessary overhead during training. Next, we propose a novel Spatially Localized Channel Attention (SLCA) mechanism to compute spatially localized attention weights for the feature maps. The features extracted from SAM's image encoder are processed through SLCA to compute attention weights, which are then integrated into deep learning classification models to enhance their focus on spatially relevant or meaningful regions of the image, thus improving classification performance. Experimental results on three public medical image classification datasets demonstrate the effectiveness and data-efficiency of our approach.
Authors: Noah Frahm, Dongxu Zhao, Andrea Dunn Beltran, Ron Alterovitz, Jan-Michael Frahm, Junier Oliva, Roni Sengupta
Abstract: Next Best View (NBV) algorithms aim to acquire an optimal set of images using minimal resources, time, or number of captures to enable efficient 3D reconstruction of a scene. Existing approaches often rely on prior scene knowledge or additional image captures and often develop policies that maximize coverage. Yet, for many real scenes with complex geometry and self-occlusions, coverage maximization does not lead to better reconstruction quality directly. In this paper, we propose the View Introspection Network (VIN), which is trained to predict the reconstruction quality improvement of views directly, and the VIN-NBV policy. A greedy sequential sampling-based policy, where at each acquisition step, we sample multiple query views and choose the one with the highest VIN predicted improvement score. We design the VIN to perform 3D-aware featurization of the reconstruction built from prior acquisitions, and for each query view create a feature that can be decoded into an improvement score. We then train the VIN using imitation learning to predict the reconstruction improvement score. We show that VIN-NBV improves reconstruction quality by ~30% over a coverage maximization baseline when operating with constraints on the number of acquisitions or the time in motion.
Authors: Sainan xiao, Wangdong Yang, Buwen Cao, Jintao Wu
Abstract: Electrocardiogram (ECG) signals are frequently corrupted by noise, such as baseline wander (BW), muscle artifacts (MA), and electrode motion (EM), which significantly degrade their diagnostic utility. To address this issue, we propose ECGDeDRDNet, a deep learning-based ECG Denoising framework leveraging a Double Recurrent Dense Network architecture. In contrast to traditional approaches, we introduce a double recurrent scheme to enhance information reuse from both ECG waveforms and the estimated clean image. For ECG waveform processing, our basic model employs LSTM layers cascaded with DenseNet blocks. The estimated clean ECG image, obtained by subtracting predicted noise components from the noisy input, is iteratively fed back into the model. This dual recurrent architecture enables comprehensive utilization of both temporal waveform features and spatial image details, leading to more effective noise suppression. Experimental results on the MIT-BIH dataset demonstrate that our method achieves superior performance compared to conventional image denoising methods in terms of PSNR and SSIM while also surpassing classical ECG denoising techniques in both SNR and RMSE.
Authors: Xingyu Jiang, Ning Gao, Xiuhui Zhang, Hongkun Dou, Shaowen Fu, Xiaoqing Zhong, Hongjue Li, Yue Deng
Abstract: Due to adverse atmospheric and imaging conditions, natural images suffer from various degradation phenomena. Consequently, image restoration has emerged as a key solution and garnered substantial attention. Although recent Transformer architectures have demonstrated impressive success across various restoration tasks, their considerable model complexity poses significant challenges for both training and real-time deployment. Furthermore, instead of investigating the commonalities among different degradations, most existing restoration methods focus on modifying Transformer under limited restoration priors. In this work, we first review various degradation phenomena under multi-domain perspective, identifying common priors. Then, we introduce a novel restoration framework, which integrates multi-domain learning into Transformer. Specifically, in Token Mixer, we propose a Spatial-Wavelet-Fourier multi-domain structure that facilitates local-region-global multi-receptive field modeling to replace vanilla self-attention. Additionally, in Feed-Forward Network, we incorporate multi-scale learning to fuse multi-domain features at different resolutions. Comprehensive experimental results across ten restoration tasks, such as dehazing, desnowing, motion deblurring, defocus deblurring, rain streak/raindrop removal, cloud removal, shadow removal, underwater enhancement and low-light enhancement, demonstrate that our proposed model outperforms state-of-the-art methods and achieves a favorable trade-off among restoration performance, parameter size, computational cost and inference latency. The code is available at: https://github.com/deng-ai-lab/SWFormer.
Authors: Yi Liu, Xinyi Liu, Panwang Xia, Qiong Wu, Yi Wan, Yongjun Zhang
Abstract: Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) often overlook cross-view geometric consistency and are limited to fixed-scale upsampling. The key issue is that previous upsampling methods use convolution to independently process deep features of different views, lacking cross-view and non-local information perception, making it difficult to select beneficial information from multi-view scenes adaptively. In this work, we propose Stereo Implicit Neural Representation (StereoINR), which innovatively models stereo image pairs as continuous implicit representations. This continuous representation breaks through the scale limitations, providing a unified solution for arbitrary-scale stereo super-resolution reconstruction of left-right views. Furthermore, by incorporating spatial warping and cross-attention mechanisms, StereoINR enables effective cross-view information fusion and achieves significant improvements in pixel-level geometric consistency. Extensive experiments across multiple datasets show that StereoINR outperforms out-of-training-distribution scale upsampling and matches state-of-the-art SSR methods within training-distribution scales.
Authors: Thomas Sommariva, Simone Calderara, Angelo Porrello
Abstract: Neural Metamorphosis (NeuMeta) is a recent paradigm for generating neural networks of varying width and depth. Based on Implicit Neural Representation (INR), NeuMeta learns a continuous weight manifold, enabling the direct generation of compressed models, including those with configurations not seen during training. While promising, the original formulation of NeuMeta proves effective only for the final layers of the undelying model, limiting its broader applicability. In this work, we propose a training algorithm that extends the capabilities of NeuMeta to enable full-network metamorphosis with minimal accuracy degradation. Our approach follows a structured recipe comprising block-wise incremental training, INR initialization, and strategies for replacing batch normalization. The resulting metamorphic networks maintain competitive accuracy across a wide range of compression ratios, offering a scalable solution for adaptable and efficient deployment of deep models. The code is available at: https://github.com/TSommariva/HTTY_NeuMeta.
Authors: Jaeyoung Huh, Ankur Kapoor, Young-Ho Kim
Abstract: Intra-cardiac Echocardiography (ICE) plays a critical role in Electrophysiology (EP) and Structural Heart Disease (SHD) interventions by providing real-time visualization of intracardiac structures. However, maintaining continuous visibility of the therapy device tip remains a challenge due to frequent adjustments required during manual ICE catheter manipulation. To address this, we propose an AI-driven tracking model that estimates the device tip incident angle and passing point within the ICE imaging plane, ensuring continuous visibility and facilitating robotic ICE catheter control. A key innovation of our approach is the hybrid dataset generation strategy, which combines clinical ICE sequences with synthetic data augmentation to enhance model robustness. We collected ICE images in a water chamber setup, equipping both the ICE catheter and device tip with electromagnetic (EM) sensors to establish precise ground-truth locations. Synthetic sequences were created by overlaying catheter tips onto real ICE images, preserving motion continuity while simulating diverse anatomical scenarios. The final dataset consists of 5,698 ICE-tip image pairs, ensuring comprehensive training coverage. Our model architecture integrates a pretrained ultrasound (US) foundation model, trained on 37.4M echocardiography images, for feature extraction. A transformer-based network processes sequential ICE frames, leveraging historical passing points and incident angles to improve prediction accuracy. Experimental results demonstrate that our method achieves 3.32 degree entry angle error, 12.76 degree rotation angle error. This AI-driven framework lays the foundation for real-time robotic ICE catheter adjustments, minimizing operator workload while ensuring consistent therapy device visibility. Future work will focus on expanding clinical datasets to further enhance model generalization.
Authors: Noriaki Hirose, Lydia Ignatova, Kyle Stachowicz, Catherine Glossop, Sergey Levine, Dhruv Shah
Abstract: Developing broadly generalizable visual navigation policies for robots is a significant challenge, primarily constrained by the availability of large-scale, diverse training data. While curated datasets collected by researchers offer high quality, their limited size restricts policy generalization. To overcome this, we explore leveraging abundant, passively collected data sources, including large volumes of crowd-sourced teleoperation data and unlabeled YouTube videos, despite their potential for lower quality or missing action labels. We propose Model-Based ReAnnotation (MBRA), a framework that utilizes a learned short-horizon, model-based expert model to relabel or generate high-quality actions for these passive datasets. This relabeled data is then distilled into LogoNav, a long-horizon navigation policy conditioned on visual goals or GPS waypoints. We demonstrate that LogoNav, trained using MBRA-processed data, achieves state-of-the-art performance, enabling robust navigation over distances exceeding 300 meters in previously unseen indoor and outdoor environments. Our extensive real-world evaluations, conducted across a fleet of robots (including quadrupeds) in six cities on three continents, validate the policy's ability to generalize and navigate effectively even amidst pedestrians in crowded settings.
Authors: Jiachen Tu, Yaokun Shi, Fan Lam
Abstract: Magnetic resonance imaging (MRI) is a powerful noninvasive diagnostic imaging tool that provides unparalleled soft tissue contrast and anatomical detail. Noise contamination, especially in accelerated and/or low-field acquisitions, can significantly degrade image quality and diagnostic accuracy. Supervised learning based denoising approaches have achieved impressive performance but require high signal-to-noise ratio (SNR) labels, which are often unavailable. Self-supervised learning holds promise to address the label scarcity issue, but existing self-supervised denoising methods tend to oversmooth fine spatial features and often yield inferior performance than supervised methods. We introduce Corruption2Self (C2S), a novel score-based self-supervised framework for MRI denoising. At the core of C2S is a generalized denoising score matching (GDSM) loss, which extends denoising score matching to work directly with noisy observations by modeling the conditional expectation of higher-SNR images given further corrupted observations. This allows the model to effectively learn denoising across multiple noise levels directly from noisy data. Additionally, we incorporate a reparameterization of noise levels to stabilize training and enhance convergence, and introduce a detail refinement extension to balance noise reduction with the preservation of fine spatial features. Moreover, C2S can be extended to multi-contrast denoising by leveraging complementary information across different MRI contrasts. We demonstrate that our method achieves state-of-the-art performance among self-supervised methods and competitive results compared to supervised counterparts across varying noise conditions and MRI contrasts on the M4Raw and fastMRI dataset.
Authors: Mark C. Eid, Ana I. L. Namburete, Jo\~ao F. Henriques
Abstract: Ultrasound imaging is widely used due to its safety, affordability, and real-time capabilities, but its 2D interpretation is highly operator-dependent, leading to variability and increased cognitive demand. 2D-to-3D reconstruction mitigates these challenges by providing standardized volumetric views, yet existing methods are often computationally expensive, memory-intensive, or incompatible with ultrasound physics. We introduce UltraGauss: the first ultrasound-specific Gaussian Splatting framework, extending view synthesis techniques to ultrasound wave propagation. Unlike conventional perspective-based splatting, UltraGauss models probe-plane intersections in 3D, aligning with acoustic image formation. We derive an efficient rasterization boundary formulation for GPU parallelization and introduce a numerically stable covariance parametrization, improving computational efficiency and reconstruction accuracy. On real clinical ultrasound data, UltraGauss achieves state-of-the-art reconstructions in 5 minutes, and reaching 0.99 SSIM within 20 minutes on a single GPU. A survey of expert clinicians confirms UltraGauss' reconstructions are the most realistic among competing methods. Our CUDA implementation will be released upon publication.
Authors: Chin-Cheng Chan, Justin P. Haldar
Abstract: For the past several decades, it has been popular to reconstruct Fourier imaging data using model-based approaches that can easily incorporate physical constraints and advanced regularization/machine learning priors. The most common modeling approach is to represent the continuous image as a linear combination of shifted "voxel" basis functions. Although well-studied and widely-deployed, this voxel-based model is associated with longstanding limitations, including high computational costs, slow convergence, and a propensity for artifacts. In this work, we reexamine this model from a fresh perspective, identifying new issues that may have been previously overlooked (including undesirable approximation, periodicity, and nullspace characteristics). Our insights motivate us to propose a new model that is more resilient to the limitations (old and new) of the previous approach. Specifically, the new model is based on a Fourier-domain basis expansion rather than the standard image-domain voxel-based approach. Illustrative results, which are presented in the context of non-Cartesian MRI reconstruction, demonstrate that the new model enables improved image quality (reduced artifacts) and/or reduced computational complexity (faster computations and improved convergence).
Authors: Guilherme Vieira Neto, Marcos Eduardo Valle
Abstract: EfficientNet models are convolutional neural networks optimized for parameter allocation by jointly balancing network width, depth, and resolution. Renowned for their exceptional accuracy, these models have become a standard for image classification tasks across diverse computer vision benchmarks. While traditional neural networks learn correlations between feature channels during training, vector-valued neural networks inherently treat multidimensional data as coherent entities, taking for granted the inter-channel relationships. This paper introduces vector-valued EfficientNets (V-EfficientNets), a novel extension of EfficientNet designed to process arbitrary vector-valued data. The proposed models are evaluated on a medical image classification task, achieving an average accuracy of 99.46% on the ALL-IDB2 dataset for detecting acute lymphoblastic leukemia. V-EfficientNets demonstrate remarkable efficiency, significantly reducing parameters while outperforming state-of-the-art models, including the original EfficientNet. The source code is available at https://github.com/mevalle/v-nets.
Authors: Fuyao Chen, Yuexi Du, Tal Zeevi, Nicha C. Dvornek, John A. Onofrey
Abstract: Histopathology evaluation of tissue specimens through microscopic examination is essential for accurate disease diagnosis and prognosis. However, traditional manual analysis by specially trained pathologists is time-consuming, labor-intensive, cost-inefficient, and prone to inter-rater variability, potentially affecting diagnostic consistency and accuracy. As digital pathology images continue to proliferate, there is a pressing need for automated analysis to address these challenges. Recent advancements in artificial intelligence-based tools such as machine learning (ML) models, have significantly enhanced the precision and efficiency of analyzing histopathological slides. However, despite their impressive performance, ML models are invariant only to translation, lacking invariance to rotation and reflection. This limitation restricts their ability to generalize effectively, particularly in histopathology, where images intrinsically lack meaningful orientation. In this study, we develop robust, equivariant histopathological biomarkers through a novel symmetric convolutional kernel via unsupervised segmentation. The approach is validated using prostate tissue micro-array (TMA) images from 50 patients in the Gleason 2019 Challenge public dataset. The biomarkers extracted through this approach demonstrate enhanced robustness and generalizability against rotation compared to models using standard convolution kernels, holding promise for enhancing the accuracy, consistency, and robustness of ML models in digital pathology. Ultimately, this work aims to improve diagnostic and prognostic capabilities of histopathology beyond prostate cancer through equivariant imaging.
Authors: Haoyang Pei, Ding Xia, Xiang Xu, William Moore, Yao Wang, Hersh Chandarana, Li Feng
Abstract: Purpose: Deep learning has demonstrated strong potential for MRI reconstruction, but conventional supervised learning methods require high-quality reference images, which are often unavailable in practice. Self-supervised learning offers an alternative, yet its performance degrades at high acceleration rates. To overcome these limitations, we propose hybrid learning, a novel two-stage training framework that combines self-supervised and supervised learning for robust image reconstruction. Methods: Hybrid learning is implemented in two sequential stages. In the first stage, self-supervised learning is employed to generate improved images from noisy or undersampled reference data. These enhanced images then serve as pseudo-ground truths for the second stage, which uses supervised learning to refine reconstruction performance and support higher acceleration rates. We evaluated hybrid learning in two representative applications: (1) accelerated 0.55T spiral-UTE lung MRI using noisy reference data, and (2) 3D T1 mapping of the brain without access to fully sampled ground truth. Results: For spiral-UTE lung MRI, hybrid learning consistently improved image quality over both self-supervised and conventional supervised methods across different acceleration rates, as measured by SSIM and NMSE. For 3D T1 mapping, hybrid learning achieved superior T1 quantification accuracy across a wide dynamic range, outperforming self-supervised learning in all tested conditions. Conclusions: Hybrid learning provides a practical and effective solution for training deep MRI reconstruction networks when only low-quality or incomplete reference data are available. It enables improved image quality and accurate quantitative mapping across different applications and field strengths, representing a promising technique toward broader clinical deployment of deep learning-based MRI.
Authors: Limai Jiang, Yunpeng Cai
Abstract: Generative models capture the true distribution of data, yielding semantically rich representations. Denoising diffusion models (DDMs) exhibit superior generative capabilities, though efficient representation learning for them are lacking. In this work, we employ a multi-level denoising autoencoder framework to expand the representation capacity of DDMs, which introduces sequentially consistent Diffusion Transformers and an additional timestep-dependent encoder to acquire embedding representations on the denoising Markov chain through self-conditional diffusion learning. Intuitively, the encoder, conditioned on the entire diffusion process, compresses high-dimensional data into directional vectors in latent under different noise levels, facilitating the learning of image embeddings across all timesteps. To verify the semantic adequacy of embeddings generated through this approach, extensive experiments are conducted on various datasets, demonstrating that optimally learned embeddings by DDMs surpass state-of-the-art self-supervised representation learning methods in most cases, achieving remarkable discriminative semantic representation quality. Our work justifies that DDMs are not only suitable for generative tasks, but also potentially advantageous for general-purpose deep learning applications.
Authors: Da Wu, Zhanliang Wang, Quan Nguyen, Zhuoran Xu, Kai Wang
Abstract: The scarcity of high-quality multimodal biomedical data limits the ability to effectively fine-tune pretrained Large Language Models (LLMs) for specialized biomedical tasks. To address this challenge, we introduce MINT (Multimodal Integrated kNowledge Transfer), a framework that aligns unimodal large decoder models with domain-specific decision patterns from multimodal biomedical data through preference optimization. While MINT supports different optimization techniques, we primarily implement it with the Odds Ratio Preference Optimization (ORPO) framework as its backbone. This strategy enables the aligned LLMs to perform predictive tasks using text-only or image-only inputs while retaining knowledge learnt from multimodal data. MINT leverages an upstream multimodal machine learning (MML) model trained on high-quality multimodal data to transfer domain-specific insights to downstream text-only or image-only LLMs. We demonstrate its effectiveness through two key applications: (1) Rare genetic disease prediction from texts, where MINT uses a multimodal encoder model, trained on facial photos and clinical notes, to generate a preference dataset for aligning a lightweight Llama 3.2-3B-Instruct. Despite relying on text input only, the MINT-derived model outperforms models trained with SFT, RAG, or DPO, and even outperforms Llama 3.1-405B-Instruct. (2) Tissue type classification using cell nucleus images, where MINT uses a vision-language foundation model as the preference generator, containing knowledge learnt from both text and histopathological images to align downstream image-only models. The resulting MINT-derived model significantly improves the performance of Llama 3.2-Vision-11B-Instruct on tissue type classification. In summary, MINT provides an effective strategy to align unimodal LLMs with high-quality multimodal expertise through preference optimization.
Authors: Weiyi Zhang, Peranut Chotcomwongse, Yinwen Li, Pusheng Xu, Ruijie Yao, Lianhao Zhou, Yuxuan Zhou, Hui Feng, Qiping Zhou, Xinyue Wang, Shoujin Huang, Zihao Jin, Florence H. T. Chung, Shujun Wang, Yalin Zheng, Mingguang He, Danli Shi, Paisan Ruamviboonsuk
Abstract: Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for patient stratification to predict therapeutic benefits and enable personalized strategies. To our knowledge, this study is the first to explore pre-treatment stratification for predicting DME treatment responses. To advance this research, we organized the 2nd Asia-Pacific Tele-Ophthalmology Society (APTOS) Big Data Competition in 2021. The competition focused on improving predictive accuracy for anti-VEGF therapy responses using ophthalmic OCT images. We provided a dataset containing tens of thousands of OCT images from 2,000 patients with labels across four sub-tasks. This paper details the competition's structure, dataset, leading methods, and evaluation metrics. The competition attracted strong scientific community participation, with 170 teams initially registering and 41 reaching the final round. The top-performing team achieved an AUC of 80.06%, highlighting the potential of AI in personalized DME treatment and clinical decision-making.
Authors: Youngjoon Lee, Jinu Gong, Joonhyuk Kang
Abstract: Kolmogorov-Arnold Networks (KAN) offer universal function approximation using univariate spline compositions without nonlinear activations. In this work, we integrate Error-Correcting Output Codes (ECOC) into the KAN framework to transform multi-class classification into multiple binary tasks, improving robustness via Hamming-distance decoding. Our proposed KAN with ECOC method outperforms vanilla KAN on a challenging blood cell classification dataset, achieving higher accuracy under diverse hyperparameter settings. Ablation studies further confirm that ECOC consistently enhances performance across FastKAN and FasterKAN variants. These results demonstrate that ECOC integration significantly boosts KAN generalizability in critical healthcare AI applications. To the best of our knowledge, this is the first integration of ECOC with KAN for enhancing multi-class medical image classification performance.
Authors: Vineet Bhat, Yu-Hsiang Lan, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami
Abstract: Robotic manipulation in 3D requires learning an $N$ degree-of-freedom joint space trajectory of a robot manipulator. Robots must possess semantic and visual perception abilities to transform real-world mappings of their workspace into the low-level control necessary for object manipulation. Recent work has demonstrated the capabilities of fine-tuning large Vision-Language Models (VLMs) to learn the mapping between RGB images, language instructions, and joint space control. These models typically take as input RGB images of the workspace and language instructions, and are trained on large datasets of teleoperated robot demonstrations. In this work, we explore methods to improve the scene context awareness of a popular recent Vision-Language-Action model by integrating chain-of-thought reasoning, depth perception, and task-oriented region of interest detection. Our experiments in the LIBERO simulation environment show that our proposed model, 3D-CAVLA, improves the success rate across various LIBERO task suites, achieving an average success rate of 98.1$\%$. We also evaluate the zero-shot capabilities of our method, demonstrating that 3D scene awareness leads to robust learning and adaptation for completely unseen tasks. 3D-CAVLA achieves an absolute improvement of 8.8$\%$ on unseen tasks. We will open-source our code and the unseen tasks dataset to promote community-driven research here: https://3d-cavla.github.io
Authors: Ashkan Pakzad, Robert Turnbull, Simon J. Mutch, Thomas A. Leatham, Darren Lockie, Jane Fox, Beena Kumar, Daniel H\"asermann, Christopher J. Hall, Anton Maksimenko, Benedicta D. Arhatari, Yakov I. Nesterets, Amir Entezam, Seyedamir T. Taba, Patrick C. Brennan, Timur E. Gureyev, Harry M. Quiney
Abstract: Breast cancer is the most frequently diagnosed human cancer in the United States at present. Early detection is crucial for its successful treatment. X-ray mammography and digital breast tomosynthesis are currently the main methods for breast cancer screening. However, both have known limitations in terms of their sensitivity and specificity to breast cancers, while also frequently causing patient discomfort due to the requirement for breast compression. Breast computed tomography is a promising alternative, however, to obtain high-quality images, the X-ray dose needs to be sufficiently high. As the breast is highly radiosensitive, dose reduction is particularly important. Phase-contrast computed tomography (PCT) has been shown to produce higher-quality images at lower doses and has no need for breast compression. It is demonstrated in the present study that, when imaging full fresh mastectomy samples with PCT, deep learning-based image denoising can further reduce the radiation dose by a factor of 16 or more, without any loss of image quality. The image quality has been assessed both in terms of objective metrics, such as spatial resolution and contrast-to-noise ratio, as well as in an observer study by experienced medical imaging specialists and radiologists. This work was carried out in preparation for live patient PCT breast cancer imaging, initially at specialized synchrotron facilities.
Authors: Peter R\"oseler, Oliver Schaudt, Helmut Berg, Christian Bauckhage, Matthias Koch
Abstract: While classical convolutional neural networks (CNNs) have revolutionized image classification, the emergence of quantum computing presents new opportunities for enhancing neural network architectures. Quantum CNNs (QCNNs) leverage quantum mechanical properties and hold potential to outperform classical approaches. However, their implementation on current noisy intermediate-scale quantum (NISQ) devices remains challenging due to hardware limitations. In our research, we address this challenge by introducing an encoding scheme that significantly reduces the input dimensionality. We demonstrate that a primitive QCNN architecture with 49 qubits is sufficient to directly process $28\times 28$ pixel MNIST images, eliminating the need for classical dimensionality reduction pre-processing. Additionally, we propose an automated framework based on expressibility, entanglement, and complexity characteristics to identify the building blocks of QCNNs, parameterized quantum circuits (PQCs). Our approach demonstrates advantages in accuracy and convergence speed with a similar parameter count compared to both hybrid QCNNs and classical CNNs. We validated our experiments on IBM's Heron r2 quantum processor, achieving $96.08\%$ classification accuracy, surpassing the $71.74\%$ benchmark of traditional approaches under identical training conditions. These results represent one of the first implementations of image classifications on real quantum hardware and validate the potential of quantum computing in this area.
Authors: Shuai Wang, Ivona Najdenkoska, Hongyi Zhu, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
Abstract: Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image captioning, they often fail to capture the nuanced interpretations that fine art demands. We propose ArtRAG, a novel, training-free framework that combines structured knowledge with retrieval-augmented generation (RAG) for multi-perspective artwork explanation. ArtRAG automatically constructs an Art Context Knowledge Graph (ACKG) from domain-specific textual sources, organizing entities such as artists, movements, themes, and historical events into a rich, interpretable graph. At inference time, a multi-granular structured retriever selects semantically and topologically relevant subgraphs to guide generation. This enables MLLMs to produce contextually grounded, culturally informed art descriptions. Experiments on the SemArt and Artpedia datasets show that ArtRAG outperforms several heavily trained baselines. Human evaluations further confirm that ArtRAG generates coherent, insightful, and culturally enriched interpretations.
Authors: Tobias Preintner, Weixuan Yuan, Qi Huang, Adrian K\"onig, Thomas B\"ack, Elena Raponi, Niki van Stein
Abstract: Combining natural language and geometric shapes is an emerging research area with multiple applications in robotics and language-assisted design. A crucial task in this domain is object referent identification, which involves selecting a 3D object given a textual description of the target. Variability in language descriptions and spatial relationships of 3D objects makes this a complex task, increasing the need to better understand the behavior of neural network models in this domain. However, limited research has been conducted in this area. Specifically, when a model makes an incorrect prediction despite being provided with a seemingly correct object description, practitioners are left wondering: "Why is the model wrong?". In this work, we present a method answering this question by generating counterfactual examples. Our method takes a misclassified sample, which includes two objects and a text description, and generates an alternative yet similar formulation that would have resulted in a correct prediction by the model. We have evaluated our approach with data from the ShapeTalk dataset along with three distinct models. Our counterfactual examples maintain the structure of the original description, are semantically similar and meaningful. They reveal weaknesses in the description, model bias and enhance the understanding of the models behavior. Theses insights help practitioners to better interact with systems as well as engineers to improve models.
Authors: Shuaiyi Huang, Mara Levy, Anubhav Gupta, Daniel Ekpo, Ruijie Zheng, Abhinav Shrivastava
Abstract: Preference feedback collected by human or VLM annotators is often noisy, presenting a significant challenge for preference-based reinforcement learning that relies on accurate preference labels. To address this challenge, we propose TREND, a novel framework that integrates few-shot expert demonstrations with a tri-teaching strategy for effective noise mitigation. Our method trains three reward models simultaneously, where each model views its small-loss preference pairs as useful knowledge and teaches such useful pairs to its peer network for updating the parameters. Remarkably, our approach requires as few as one to three expert demonstrations to achieve high performance. We evaluate TREND on various robotic manipulation tasks, achieving up to 90% success rates even with noise levels as high as 40%, highlighting its effective robustness in handling noisy preference feedback. Project page: https://shuaiyihuang.github.io/publications/TREND.
Authors: Xilin Gong, Yongkai Chen, Shushan Wu, Fang Wang, Ping Ma, Wenxuan Zhong
Abstract: Echocardiogram is the most commonly used imaging modality in cardiac assessment duo to its non-invasive nature, real-time capability, and cost-effectiveness. Despite its advantages, most clinical echocardiograms provide only two-dimensional views, limiting the ability to fully assess cardiac anatomy and function in three dimensions. While three-dimensional echocardiography exists, it often suffers from reduced resolution, limited availability, and higher acquisition costs. To overcome these challenges, we propose a deep learning framework S2MNet that reconstructs continuous and high-fidelity 3D heart models by integrating six slices of routinely acquired 2D echocardiogram views. Our method has three advantages. First, our method avoid the difficulties on training data acquasition by simulate six of 2D echocardiogram images from corresponding slices of a given 3D heart mesh. Second, we introduce a deformation field-based method, which avoid spatial discontinuities or structural artifacts in 3D echocardiogram reconstructions. We validate our method using clinically collected echocardiogram and demonstrate that our estimated left ventricular volume, a key clinical indicator of cardiac function, is strongly correlated with the doctor measured GLPS, a clinical measurement that should demonstrate a negative correlation with LVE in medical theory. This association confirms the reliability of our proposed 3D construction method.
Authors: Jingguo Qu, Xinyang Han, Man-Lik Chui, Yao Pu, Simon Takadiyi Gunda, Ziman Chen, Jing Qin, Ann Dorothy King, Winnie Chiu-Wing Chu, Jing Cai, Michael Tin-Cheung Ying
Abstract: Automatic lymph node segmentation is the cornerstone for advances in computer vision tasks for early detection and staging of cancer. Traditional segmentation methods are constrained by manual delineation and variability in operator proficiency, limiting their ability to achieve high accuracy. The introduction of deep learning technologies offers new possibilities for improving the accuracy of lymph node image analysis. This study evaluates the application of deep learning in lymph node segmentation and discusses the methodologies of various deep learning architectures such as convolutional neural networks, encoder-decoder networks, and transformers in analyzing medical imaging data across different modalities. Despite the advancements, it still confronts challenges like the shape diversity of lymph nodes, the scarcity of accurately labeled datasets, and the inadequate development of methods that are robust and generalizable across different imaging modalities. To the best of our knowledge, this is the first study that provides a comprehensive overview of the application of deep learning techniques in lymph node segmentation task. Furthermore, this study also explores potential future research directions, including multimodal fusion techniques, transfer learning, and the use of large-scale pre-trained models to overcome current limitations while enhancing cancer diagnosis and treatment planning strategies.
Authors: Philip Naumann, Jacob Kauffmann, Gr\'egoire Montavon
Abstract: Wasserstein distances provide a powerful framework for comparing data distributions. They can be used to analyze processes over time or to detect inhomogeneities within data. However, simply calculating the Wasserstein distance or analyzing the corresponding transport map (or coupling) may not be sufficient for understanding what factors contribute to a high or low Wasserstein distance. In this work, we propose a novel solution based on Explainable AI that allows us to efficiently and accurately attribute Wasserstein distances to various data components, including data subgroups, input features, or interpretable subspaces. Our method achieves high accuracy across diverse datasets and Wasserstein distance specifications, and its practical utility is demonstrated in two use cases.
Authors: Niladri Shekhar Dutt, Duygu Ceylan, Niloy J. Mitra
Abstract: Retouching is an essential task in post-manipulation of raw photographs. Generative editing, guided by text or strokes, provides a new tool accessible to users but can easily change the identity of the original objects in unacceptable and unpredictable ways. In contrast, although traditional procedural edits, as commonly supported by photoediting tools (e.g., Gimp, Lightroom), are conservative, they are still preferred by professionals. Unfortunately, professional quality retouching involves many individual procedural editing operations that is challenging to plan for most novices. In this paper, we ask if a multimodal large language model (MLLM) can be taught to critique raw photographs, suggest suitable remedies, and finally realize them with a given set of pre-authored procedural image operations. We demonstrate that MLLMs can be first made aware of the underlying image processing operations, by training them to solve specially designed visual puzzles. Subsequently, such an operation-aware MLLM can both plan and propose edit sequences. To facilitate training, given a set of expert-edited photos, we synthesize a reasoning dataset by procedurally manipulating the expert edits and then grounding a pretrained LLM on the visual adjustments, to synthesize reasoning for finetuning. The proposed retouching operations are, by construction, understandable by the users, preserve object details and resolution, and can be optionally overridden. We evaluate our setup on a variety of test examples and show advantages, in terms of explainability and identity preservation, over existing generative and other procedural alternatives. Code, data, models, and supplementary results can be found via our project website at https://monetgpt.github.io.
Authors: Kodai Hirata, Tsuyoshi Okita
Abstract: This paper proposes a method MTL-Swin-Unet which is multi-task learning using transformers for classification and semantic segmentation. For spurious-correlation problems, this method allows us to enhance the image representation with two other image representations: representation obtained by semantic segmentation and representation obtained by image reconstruction. In our experiments, the proposed method outperformed in F-value measure than other classifiers when the test data included slices from the same patient (no covariate shift). Similarly, when the test data did not include slices from the same patient (covariate shift setting), the proposed method outperformed in AUC measure.
Authors: Jiayuan Mao, Joshua B. Tenenbaum, Jiajun Wu
Abstract: This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and action concepts, are grounded on sensory inputs and actuation outputs. They are also compositional, allowing for the creation of novel concepts through their structural combination. To facilitate learning and reasoning, the concepts are typed and represented using a combination of symbolic programs and neural network representations. Leveraging such neuro-symbolic concepts, the agent can efficiently learn and recombine them to solve various tasks across different domains, ranging from 2D images, videos, 3D scenes, and robotic manipulation tasks. This concept-centric framework offers several advantages, including data efficiency, compositional generalization, continual learning, and zero-shot transfer.
Authors: Diego Adame, Jose A. Nunez, Fabian Vazquez, Nayeli Gurrola, Huimin Li, Haoteng Tang, Bin Fu, Pengfei Gu
Abstract: Convolutional neural network (CNN) and Transformer-based architectures are two dominant deep learning models for polyp segmentation. However, CNNs have limited capability for modeling long-range dependencies, while Transformers incur quadratic computational complexity. Recently, State Space Models such as Mamba have been recognized as a promising approach for polyp segmentation because they not only model long-range interactions effectively but also maintain linear computational complexity. However, Mamba-based architectures still struggle to capture topological features (e.g., connected components, loops, voids), leading to inaccurate boundary delineation and polyp segmentation. To address these limitations, we propose a new approach called Topo-VM-UNetV2, which encodes topological features into the Mamba-based state-of-the-art polyp segmentation model, VM-UNetV2. Our method consists of two stages: Stage 1: VM-UNetV2 is used to generate probability maps (PMs) for the training and test images, which are then used to compute topology attention maps. Specifically, we first compute persistence diagrams of the PMs, then we generate persistence score maps by assigning persistence values (i.e., the difference between death and birth times) of each topological feature to its birth location, finally we transform persistence scores into attention weights using the sigmoid function. Stage 2: These topology attention maps are integrated into the semantics and detail infusion (SDI) module of VM-UNetV2 to form a topology-guided semantics and detail infusion (Topo-SDI) module for enhancing the segmentation results. Extensive experiments on five public polyp segmentation datasets demonstrate the effectiveness of our proposed method. The code will be made publicly available.
Authors: Kwan-Yee Lin, Stella X. Yu
Abstract: Hiking on complex trails demands balance, agility, and adaptive decision-making over unpredictable terrain. Current humanoid research remains fragmented and inadequate for hiking: locomotion focuses on motor skills without long-term goals or situational awareness, while semantic navigation overlooks real-world embodiment and local terrain variability. We propose training humanoids to hike on complex trails, driving integrative skill development across visual perception, decision making, and motor execution. We develop a learning framework, LEGO-H, that enables a vision-equipped humanoid robot to hike complex trails autonomously. We introduce two technical innovations: 1) A temporal vision transformer variant - tailored into Hierarchical Reinforcement Learning framework - anticipates future local goals to guide movement, seamlessly integrating locomotion with goal-directed navigation. 2) Latent representations of joint movement patterns, combined with hierarchical metric learning - enhance Privileged Learning scheme - enable smooth policy transfer from privileged training to onboard execution. These components allow LEGO-H to handle diverse physical and environmental challenges without relying on predefined motion patterns. Experiments across varied simulated trails and robot morphologies highlight LEGO-H's versatility and robustness, positioning hiking as a compelling testbed for embodied autonomy and LEGO-H as a baseline for future humanoid development.
Authors: Yufan Deng, Yuhao Zhang, Chen Geng, Shangzhe Wu, Jiajun Wu
Abstract: Rigging and skinning are essential steps to create realistic 3D animations, often requiring significant expertise and manual effort. Traditional attempts at automating these processes rely heavily on geometric heuristics and often struggle with objects of complex geometry. Recent data-driven approaches show potential for better generality, but are often constrained by limited training data. We present the Anymate Dataset, a large-scale dataset of 230K 3D assets paired with expert-crafted rigging and skinning information -- 70 times larger than existing datasets. Using this dataset, we propose a learning-based auto-rigging framework with three sequential modules for joint, connectivity, and skinning weight prediction. We systematically design and experiment with various architectures as baselines for each module and conduct comprehensive evaluations on our dataset to compare their performance. Our models significantly outperform existing methods, providing a foundation for comparing future methods in automated rigging and skinning. Code and dataset can be found at https://anymate3d.github.io/.
Authors: Julio Silva-Rodr\'iguez, Jose Dolz, Ismail Ben Ayed
Abstract: The recent popularity of foundation models and the pre-train-and-adapt paradigm, where a large-scale model is transferred to downstream tasks, is gaining attention for volumetric medical image segmentation. However, current transfer learning strategies devoted to full fine-tuning for transfer learning may require significant resources and yield sub-optimal results when the labeled data of the target task is scarce. This makes its applicability in real clinical settings challenging since these institutions are usually constrained on data and computational resources to develop proprietary solutions. To address this challenge, we formalize Few-Shot Efficient Fine-Tuning (FSEFT), a novel and realistic scenario for adapting medical image segmentation foundation models. This setting considers the key role of both data- and parameter-efficiency during adaptation. Building on a foundation model pre-trained on open-access CT organ segmentation sources, we propose leveraging Parameter-Efficient Fine-Tuning and black-box Adapters to address such challenges. Furthermore, novel efficient adaptation methodologies are introduced in this work, which include Spatial black-box Adapters that are more appropriate for dense prediction tasks and constrained transductive inference, leveraging task-specific prior knowledge. Our comprehensive transfer learning experiments confirm the suitability of foundation models in medical image segmentation and unveil the limitations of popular fine-tuning strategies in few-shot scenarios.
Authors: Pu Ren, N. Benjamin Erichson, Junyi Guo, Shashank Subramanian, Omer San, Zarija Lukic, Michael W. Mahoney
Abstract: Super-resolution (SR) techniques aim to enhance data resolution, enabling the retrieval of finer details, and improving the overall quality and fidelity of the data representation. There is growing interest in applying SR methods to complex spatiotemporal systems within the Scientific Machine Learning (SciML) community, with the hope of accelerating numerical simulations and/or improving forecasts in weather, climate, and related areas. However, the lack of standardized benchmark datasets for comparing and validating SR methods hinders progress and adoption in SciML. To address this, we introduce SuperBench, the first benchmark dataset featuring high-resolution datasets, including data from fluid flows, cosmology, and weather. Here, we focus on validating spatial SR performance from data-centric and physics-preserved perspectives, as well as assessing robustness to data degradation tasks. While deep learning-based SR methods (developed in the computer vision community) excel on certain tasks, despite relatively limited prior physics information, we identify limitations of these methods in accurately capturing intricate fine-scale features and preserving fundamental physical properties and constraints in scientific data. These shortcomings highlight the importance and subtlety of incorporating domain knowledge into ML models. We anticipate that SuperBench will help to advance SR methods for science.
Authors: Peter Dawood, Felix Breuer, Istvan Homolya, Maximilian Gram, Peter M. Jakob, Moritz Zaiss, Martin Blaimer
Abstract: Purpose: Noise resilience in image reconstructions by scan-specific robust artificial neural networks for k-space interpolation (RAKI) is linked to nonlinear activations in k-space. To gain a deeper understanding of this relationship, an image space formalism of RAKI is introduced for analyzing noise propagation analytically, identifying and characterizing image reconstruction features and to describe the role of nonlinear activations in a human readable manner. Methods: The image space formalism for RAKI inference is employed by expressing nonlinear activations in k-space as element-wise multiplications with activation masks, which transform into convolutions in image space. Jacobians of the de-aliased, coil-combined image relative to the aliased coil images can be expressed algebraically, and thus, the noise amplification is quantified analytically (g-factor maps). We analyze the role of nonlinearity for noise resilience by controlling the degree of nonlinearity in the reconstruction model via the negative slope parameter in leaky ReLU. Results: The analytical g-factor maps correspond with those obtained from Monte Carlo simulations and from an auto differentiation approach for in vivo brain images. Apparent blurring and contrast loss artifacts are identified as implications of enhanced noise resilience. These residual artifacts can be traded against noise resilience by adjusting the degree of nonlinearity in the model (Tikhonov-like regularization) in case of limited training data. The inspection of image space activations reveals an autocorrelation pattern leading to a potential center artifact. Conclusion: The image space formalism of RAKI provides the means for analytical quantitative noisepropagation analysis and human-readable visualization of the effects of the nonlinear activation functions in k-space.
Authors: Bhishma Dedhia, Niraj K. Jha
Abstract: Several accounts of human cognition posit that our intelligence is rooted in our ability to form abstract composable concepts, ground them in our environment, and reason over these grounded entities. This trifecta of human thought has remained elusive in modern intelligent machines. In this work, we investigate whether slot representations extracted from visual scenes serve as appropriate compositional abstractions for grounding and reasoning. We present the Neural Slot Interpreter (NSI), which learns to ground object semantics in slots. At the core of NSI is a nested schema that uses simple syntax rules to organize the object semantics of a scene into object-centric schema primitives. Then, the NSI metric learns to ground primitives into slots through a structured contrastive learning objective that reasons over the intermodal alignment. Experiments with a bi-modal object-property and scene retrieval task demonstrate the grounding efficacy and interpretability of correspondences learned by NSI. From a scene representation standpoint, we find that emergent NSI slots that move beyond the image grid by binding to spatial objects facilitate improved visual grounding compared to conventional bounding-box-based approaches. From a data efficiency standpoint, we empirically validate that NSI learns more generalizable representations from a fixed amount of annotation data than the traditional approach. We also show that the grounded slots surpass unsupervised slots in real-world object discovery and scale with scene complexity. Finally, we investigate the downstream efficacy of the grounded slots. Vision Transformers trained on grounding-aware NSI tokenizers using as few as ten tokens outperform patch-based tokens on challenging few-shot classification tasks.
Authors: Hanxue Gu, Haoyu Dong, Jichen Yang, Maciej A. Mazurowski
Abstract: Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning. While foundation models have been useful in natural language processing and some vision tasks for some time, the foundation model developed with image segmentation in mind - Segment Anything Model (SAM) - has been developed only recently and has shown similar promise. However, there are still no systematic analyses or "best-practice" guidelines for optimal fine-tuning of SAM for medical image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning algorithms across 18 combinations, and evaluates them on 17 datasets covering all common radiology modalities. Our study reveals that (1) fine-tuning SAM leads to slightly better performance than previous segmentation methods, (2) fine-tuning strategies that use parameter-efficient learning in both the encoder and decoder are superior to other strategies, (3) network architecture has a small impact on final performance, (4) further training SAM with self-supervised learning can improve final model performance. We also demonstrate the ineffectiveness of some methods popular in the literature and further expand our experiments into few-shot and prompt-based settings. Lastly, we released our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM, at https://github.com/mazurowski-lab/finetune-SAM.
Authors: Da Chang, Yu Li
Abstract: With the rapid development of OCR technology, mixed-scene text recognition has become a key technical challenge. Although deep learning models have achieved significant results in specific scenarios, their generality and stability still need improvement, and the high demand for computing resources affects flexibility. To address these issues, this paper proposes DLoRA-TrOCR, a parameter-efficient hybrid text spotting method based on a pre-trained OCR Transformer. By embedding a weight-decomposed DoRA module in the image encoder and a LoRA module in the text decoder, this method can be efficiently fine-tuned on various downstream tasks. Our method requires no more than 0.7\% trainable parameters, not only accelerating the training efficiency but also significantly improving the recognition accuracy and cross-dataset generalization performance of the OCR system in mixed text scenes. Experiments show that our proposed DLoRA-TrOCR outperforms other parameter-efficient fine-tuning methods in recognizing complex scenes with mixed handwritten, printed, and street text, achieving a CER of 4.02 on the IAM dataset, a F1 score of 94.29 on the SROIE dataset, and a WAR of 86.70 on the STR Benchmark, reaching state-of-the-art performance.
Authors: Qiujie Dong, Huibiao Wen, Rui Xu, Shuangmin Chen, Jiaran Zhou, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang
Abstract: Quadrilateral mesh generation plays a crucial role in numerical simulations within Computer-Aided Design and Engineering (CAD/E). Producing high-quality quadrangulation typically requires satisfying four key criteria. First, the quadrilateral mesh should closely align with principal curvature directions. Second, singular points should be strategically placed and effectively minimized. Third, the mesh should accurately conform to sharp feature edges. Lastly, quadrangulation results should exhibit robustness against noise and minor geometric variations. Existing methods generally involve first computing a regular cross field to represent quad element orientations across the surface, followed by extracting a quadrilateral mesh aligned closely with this cross field. A primary challenge with this approach is balancing the smoothness of the cross field with its alignment to pre-computed principal curvature directions, which are sensitive to small surface perturbations and often ill-defined in spherical or planar regions. To tackle this challenge, we propose NeurCross, a novel framework that simultaneously optimizes a cross field and a neural signed distance function (SDF), whose zero-level set serves as a proxy of the input shape. Our joint optimization is guided by three factors: faithful approximation of the optimized SDF surface to the input surface, alignment between the cross field and the principal curvature field derived from the SDF surface, and smoothness of the cross field. Acting as an intermediary, the neural SDF contributes in two essential ways. First, it provides an alternative, optimizable base surface exhibiting more regular principal curvature directions for guiding the cross field. Second, we leverage the Hessian matrix of the neural SDF to implicitly enforce cross field alignment with principal curvature directions...
Authors: Yukang Cao, Xinying Guo, Mingyuan Zhang, Haozhe Xie, Chenyang Gu, Ziwei Liu
Abstract: While recent advances in text-to-motion generation have shown promising results, they typically assume all individuals are grouped as a single unit. Scaling these methods to handle larger crowds and ensuring that individuals respond appropriately to specific events remains a significant challenge. This is primarily due to the complexities of scene planning, which involves organizing groups, planning their activities, and coordinating interactions, and controllable motion generation. In this paper, we present CrowdMoGen, the first zero-shot framework for collective motion generation, which effectively groups individuals and generates event-aligned motion sequences from text prompts. 1) Being limited by the available datasets for training an effective scene planning module in a supervised manner, we instead propose a crowd scene planner that leverages pre-trained large language models (LLMs) to organize individuals into distinct groups. While LLMs offer high-level guidance for group divisions, they lack the low-level understanding of human motion. To address this, we further propose integrating an SMPL-based joint prior to generate context-appropriate activities, which consists of both joint trajectories and textual descriptions. 2) Secondly, to incorporate the assigned activities into the generative network, we introduce a collective motion generator that integrates the activities into a transformer-based network in a joint-wise manner, maintaining the spatial constraints during the multi-step denoising process. Extensive experiments demonstrate that CrowdMoGen significantly outperforms previous approaches, delivering realistic, event-driven motion sequences that are spatially coherent. As the first framework of collective motion generation, CrowdMoGen has the potential to advance applications in urban simulation, crowd planning, and other large-scale interactive environments.
Authors: Mang Ning, Albert Ali Salah, Itir Onal Ertugrul
Abstract: Facial Action Unit (AU) detection has gained significant attention as it enables the breakdown of complex facial expressions into individual muscle movements. In this paper, we revisit two fundamental factors in AU detection: diverse and large-scale data and subject identity regularization. Motivated by recent advances in foundation models, we highlight the importance of data and introduce Face9M, a diverse dataset comprising 9 million facial images from multiple public sources. Pretraining a masked autoencoder on Face9M yields strong performance in AU detection and facial expression tasks. More importantly, we emphasize that the Identity Adversarial Training (IAT) has not been well explored in AU tasks. To fill this gap, we first show that subject identity in AU datasets creates shortcut learning for the model and leads to sub-optimal solutions to AU predictions. Secondly, we demonstrate that strong IAT regularization is necessary to learn identity-invariant features. Finally, we elucidate the design space of IAT and empirically show that IAT circumvents the identity-based shortcut learning and results in a better solution. Our proposed methods, Facial Masked Autoencoder (FMAE) and IAT, are simple, generic and effective. Remarkably, the proposed FMAE-IAT approach achieves new state-of-the-art F1 scores on BP4D (67.1\%), BP4D+ (66.8\%), and DISFA (70.1\%) databases, significantly outperforming previous work. We release the code and model at https://github.com/forever208/FMAE-IAT.
Authors: Hongyang Li, Hao Zhang, Shilong Liu, Zhaoyang Zeng, Feng Li, Tianhe Ren, Bohan Li, Lei Zhang
Abstract: In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-like algorithms. TAPTRv2 improves TAPTR by addressing a critical issue regarding its reliance on cost-volume,which contaminates the point query\'s content feature and negatively impacts both visibility prediction and cost-volume computation. In TAPTRv2, we propose a novel attention-based position update (APU) operation and use key-aware deformable attention to realize. For each query, this operation uses key-aware attention weights to combine their corresponding deformable sampling positions to predict a new query position. This design is based on the observation that local attention is essentially the same as cost-volume, both of which are computed by dot-production between a query and its surrounding features. By introducing this new operation, TAPTRv2 not only removes the extra burden of cost-volume computation, but also leads to a substantial performance improvement. TAPTRv2 surpasses TAPTR and achieves state-of-the-art performance on many challenging datasets, demonstrating the superiority
Authors: Ling Xing, Hongyu Qu, Rui Yan, Xiangbo Shu, Jinhui Tang
Abstract: Dense-localization Audio-Visual Events (DAVE) aims to identify time boundaries and corresponding categories for events that are both audible and visible in a long video, where events may co-occur and exhibit varying durations. However, complex audio-visual scenes often involve asynchronization between modalities, making accurate localization challenging. Existing DAVE solutions extract audio and visual features through unimodal encoders, and fuse them via dense cross-modal interaction. However, independent unimodal encoding struggles to emphasize shared semantics between modalities without cross-modal guidance, while dense cross-modal attention may over-attend to semantically unrelated audio-visual features. To address these problems, we present LoCo, a Locality-aware cross-modal Correspondence learning framework for DAVE. LoCo leverages the local temporal continuity of audio-visual events as important guidance to filter irrelevant cross-modal signals and enhance cross-modal alignment throughout both unimodal and cross-modal encoding stages. i) Specifically, LoCo applies Local Correspondence Feature (LCF) Modulation to enforce unimodal encoders to focus on modality-shared semantics by modulating agreement between audio and visual features based on local cross-modal coherence. ii) To better aggregate cross-modal relevant features, we further customize Local Adaptive Cross-modal (LAC) Interaction, which dynamically adjusts attention regions in a data-driven manner. This adaptive mechanism focuses attention on local event boundaries and accommodates varying event durations. By incorporating LCF and LAC, LoCo provides solid performance gains and outperforms existing DAVE methods.
Authors: Yihang Tao, Senkang Hu, Zhengru Fang, Yuguang Fang
Abstract: Collaborative perception (CP) leverages visual data from connected and autonomous vehicles (CAV) to enhance an ego vehicle's field of view (FoV). Despite recent progress, current CP methods expand the ego vehicle's 360-degree perceptual range almost equally, which faces two key challenges. Firstly, in areas with uneven traffic distribution, focusing on directions with little traffic offers limited benefits. Secondly, under limited communication budgets, allocating excessive bandwidth to less critical directions lowers the perception accuracy in more vital areas. To address these issues, we propose Direct-CP, a proactive and direction-aware CP system aiming at improving CP in specific directions. Our key idea is to enable an ego vehicle to proactively signal its interested directions and readjust its attention to enhance local directional CP performance. To achieve this, we first propose an RSU-aided direction masking mechanism that assists an ego vehicle in identifying vital directions. Additionally, we design a direction-aware selective attention module to wisely aggregate pertinent features based on ego vehicle's directional priorities, communication budget, and the positional data of CAVs. Moreover, we introduce a direction-weighted detection loss (DWLoss) to capture the divergence between directional CP outcomes and the ground truth, facilitating effective model training. Extensive experiments on the V2X-Sim 2.0 dataset demonstrate that our approach achieves 19.8\% higher local perception accuracy in interested directions and 2.5\% higher overall perception accuracy than the state-of-the-art methods in collaborative 3D object detection tasks.
Authors: Xinlong Hou, Sen Shen, Xueshen Li, Xinran Gao, Ziyi Huang, Steven J. Holiday, Matthew R. Cribbet, Susan W. White, Edward Sazonov, Yu Gan
Abstract: Being able to accurately monitor the screen exposure of young children is important for research on phenomena linked to screen use such as childhood obesity, physical activity, and social interaction. Most existing studies rely upon self-report or manual measures from bulky wearable sensors, thus lacking efficiency and accuracy in capturing quantitative screen exposure data. In this work, we developed a novel sensor informatics framework that utilizes egocentric images from a wearable sensor, termed the screen time tracker (STT), and a vision language model (VLM). In particular, we devised a multi-view VLM that takes multiple views from egocentric image sequences and interprets screen exposure dynamically. We validated our approach by using a dataset of children's free-living activities, demonstrating significant improvement over existing methods in plain vision language models and object detection models. Results supported the promise of this monitoring approach, which could optimize behavioral research on screen exposure in children's naturalistic settings.
Authors: Anirudh Thatipelli, Shao-Yuan Lo, Amit K. Roy-Chowdhury
Abstract: Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The community has regained interest in the field of egocentric vision. While the third-person view and first-person have been thoroughly investigated, very few works aim to study both synchronously. Exocentric videos contain many relevant signals that are transferrable to egocentric videos. This paper provides a timely overview of works combining egocentric and exocentric visions, a very new but promising research topic. We describe in detail the datasets and present a survey of the key applications of ego-exo joint learning, where we identify the most recent advances. With the presentation of the current status of the progress, we believe this short but timely survey will be valuable to the broad video-understanding community, particularly when multi-view modeling is critical.
Authors: Yassine Ouali, Adrian Bulat, Alexandros Xenos, Anestis Zaganidis, Ioannis Maniadis Metaxas, Brais Martinez, Georgios Tzimiropoulos
Abstract: Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag of words" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown to be capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks. In this work, we propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs that results in strong discriminative and compositional capabilities. Essentially, our approach converts a generative LVLM into a discriminative one, unlocking its capability for powerful image-text discrimination combined with enhanced language understanding. Our contributions include (1) a carefully designed training/optimization framework that utilizes image-text pairs of variable length and granularity for training the model with both contrastive and next-token prediction losses. This is accompanied by ablation studies that justify the necessity of our framework's components; (2) a parameter-efficient adaptation method using a combination of soft prompting and LoRA adapters; (3) significant improvements over state-of-the-art CLIP-like models of similar size, including standard image-text retrieval benchmarks and notable gains in compositionality.
Authors: Guillaume Astruc, Nicolas Gonthier, Clement Mallet, Loic Landrieu
Abstract: Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose AnySat, a multimodal model based on joint embedding predictive architecture (JEPA) and scale-adaptive spatial encoders, allowing us to train a single model on highly heterogeneous data in a self-supervised manner. To demonstrate the advantages of this unified approach, we compile GeoPlex, a collection of 5 multimodal datasets with varying characteristics and $11$ distinct sensors. We then train a single powerful model on these diverse datasets simultaneously. Once fine-tuned or probed, we reach state-of-the-art results on the test sets of GeoPlex and for 6 external datasets across various environment monitoring tasks: land cover mapping, tree species identification, crop type classification, change detection, climate type classification, and segmentation of flood, burn scar, and deforestation. The code and models are available at https://github.com/gastruc/AnySat.
Authors: You Wu, Yongxin Li, Mengyuan Liu, Xucheng Wang, Xiangyang Yang, Hengzhou Ye, Dan Zeng, Qijun Zhao, Shuiwang Li
Abstract: Visual tracking has made significant strides due to the adoption of transformer-based models. Most state-of-the-art trackers struggle to meet real-time processing demands on mobile platforms with constrained computing resources, particularly for real-time unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and efficiency, we introduce AVTrack, an adaptive computation framework designed to selectively activate transformer blocks for real-time UAV tracking. The proposed Activation Module (AM) dynamically optimizes the ViT architecture by selectively engaging relevant components, thereby enhancing inference efficiency without significant compromise to tracking performance. Furthermore, to tackle the challenges posed by extreme changes in viewing angles often encountered in UAV tracking, the proposed method enhances ViTs' effectiveness by learning view-invariant representations through mutual information (MI) maximization. Two effective design principles are proposed in the AVTrack. Building on it, we propose an improved tracker, dubbed AVTrack-MD, which introduces the novel MI maximization-based multi-teacher knowledge distillation (MD) framework. It harnesses the benefits of multiple teachers, specifically the off-the-shelf tracking models from the AVTrack, by integrating and refining their outputs, thereby guiding the learning process of the compact student network. Specifically, we maximize the MI between the softened feature representations from the multi-teacher models and the student model, leading to improved generalization and performance of the student model, particularly in noisy conditions. Extensive experiments on multiple UAV tracking benchmarks demonstrate that AVTrack-MD not only achieves performance comparable to the AVTrack baseline but also reduces model complexity, resulting in a significant 17\% increase in average tracking speed.
Authors: Cuong Manh Hoang, Yeejin Lee, Byeongkeun Kang
Abstract: This work addresses the task of generalized class discovery (GCD) in instance segmentation. The goal is to discover novel classes and obtain a model capable of segmenting instances of both known and novel categories, given labeled and unlabeled data. Since the real world contains numerous objects with long-tailed distributions, the instance distribution for each class is inherently imbalanced. To address the imbalanced distributions, we propose an instance-wise temperature assignment (ITA) method for contrastive learning and class-wise reliability criteria for pseudo-labels. The ITA method relaxes instance discrimination for samples belonging to head classes to enhance GCD. The reliability criteria are to avoid excluding most pseudo-labels for tail classes when training an instance segmentation network using pseudo-labels from GCD. Additionally, we propose dynamically adjusting the criteria to leverage diverse samples in the early stages while relying only on reliable pseudo-labels in the later stages. We also introduce an efficient soft attention module to encode object-specific representations for GCD. Finally, we evaluate our proposed method by conducting experiments on two settings: COCO$_{half}$ + LVIS and LVIS + Visual Genome. The experimental results demonstrate that the proposed method outperforms previous state-of-the-art methods.
Authors: Joona Kareinen, Tuomas Eerola, Kaisa Kraft, Lasse Lensu, Sanna Suikkanen, Heikki K\"alvi\"ainen
Abstract: Plankton recognition is an important computer vision problem due to plankton's essential role in ocean food webs and carbon capture, highlighting the need for species-level monitoring. However, this task is challenging due to its fine-grained nature and dataset shifts caused by different imaging instruments and varying species distributions. As new plankton image datasets are collected at an increasing pace, there is a need for general plankton recognition models that require minimal expert effort for data labeling. In this work, we study large-scale self-supervised pretraining for fine-grained plankton recognition. We first employ masked autoencoding and a large volume of diverse plankton image data to pretrain a general-purpose plankton image encoder. Then we utilize fine-tuning to obtain accurate plankton recognition models for new datasets with a very limited number of labeled training images. Our experiments show that self-supervised pretraining with diverse plankton data clearly increases plankton recognition accuracy compared to standard ImageNet pretraining when the amount of training data is limited. Moreover, the accuracy can be further improved when unlabeled target data is available and utilized during the pretraining.
Authors: Saron Samuel, Dan DeGenaro, Jimena Guallar-Blasco, Kate Sanders, Oluwaseun Eisape, Tanner Spendlove, Arun Reddy, Alexander Martin, Andrew Yates, Eugene Yang, Cameron Carpenter, David Etter, Efsun Kayi, Matthew Wiesner, Kenton Murray, Reno Kriz
Abstract: Videos inherently contain multiple modalities, including visual events, text overlays, sounds, and speech, all of which are important for retrieval. However, state-of-the-art multimodal language models like VAST and LanguageBind are built on vision-language models (VLMs), and thus overly prioritize visual signals. Retrieval benchmarks further reinforce this bias by focusing on visual queries and neglecting other modalities. We create a search system MMMORRF that extracts text and features from both visual and audio modalities and integrates them with a novel modality-aware weighted reciprocal rank fusion. MMMORRF is both effective and efficient, demonstrating practicality in searching videos based on users' information needs instead of visual descriptive queries. We evaluate MMMORRF on MultiVENT 2.0 and TVR, two multimodal benchmarks designed for more targeted information needs, and find that it improves nDCG@20 by 81% over leading multimodal encoders and 37% over single-modality retrieval, demonstrating the value of integrating diverse modalities.
Authors: Jiahui Zhang, Yurui Chen, Yanpeng Zhou, Yueming Xu, Ze Huang, Jilin Mei, Junhui Chen, Yu-Jie Yuan, Xinyue Cai, Guowei Huang, Xingyue Quan, Hang Xu, Li Zhang
Abstract: Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations into models to improve spatial understanding, we aim to unlock the potential of VLMs by leveraging spatially relevant image data. To this end, we introduce a novel 2D spatial data generation and annotation pipeline built upon scene data with 3D ground-truth. This pipeline enables the creation of a diverse set of spatial tasks, ranging from basic perception tasks to more complex reasoning tasks. Leveraging this pipeline, we construct SPAR-7M, a large-scale dataset generated from thousands of scenes across multiple public datasets. In addition, we introduce SPAR-Bench, a benchmark designed to offer a more comprehensive evaluation of spatial capabilities compared to existing spatial benchmarks, supporting both single-view and multi-view inputs. Training on both SPAR-7M and large-scale 2D datasets enables our models to achieve state-of-the-art performance on 2D spatial benchmarks. Further fine-tuning on 3D task-specific datasets yields competitive results, underscoring the effectiveness of our dataset in enhancing spatial reasoning.
Authors: Fabian Fuchs, Mario Ruben Fernandez, Norman Ettrich, Janis Keuper
Abstract: Seismic processing plays a crucial role in transforming raw data into high-quality subsurface images, pivotal for various geoscience applications. Despite its importance, traditional seismic processing techniques face challenges such as noisy and damaged data and the reliance on manual, time-consuming workflows. The emergence of deep learning approaches has introduced effective and user-friendly alternatives, yet many of these deep learning approaches rely on synthetic datasets and specialized neural networks. Recently, foundation models have gained traction in the seismic domain, due to their success in the natural image domain. Therefore, we investigate the application of natural image foundation models on the three seismic processing tasks: demultiple, interpolation, and denoising. We evaluate the impact of different model characteristics, such as pre-training technique and neural network architecture, on performance and efficiency. Rather than proposing a single seismic foundation model, we critically examine various natural image foundation models and suggest some promising candidates for future exploration.
Authors: Leszek Luchowski, Dariusz Pojda
Abstract: The article presents an innovative approach to the visualization of multidimensional data, using icons inspired by Chernoff faces. The approach merges classical projection techniques with the assignment of particular data dimensions to mimic features, capitalizing on the natural ability of the human brain to interpret facial expressions. We introduce a semantic division of data dimensions into intuitive and technical categories, assigning the former to avatar features and projecting the latter into a hyperspace of four, or potentially more dimensions. The technique is implemented as a plugin to the dpVision open-source image handling platform. The plugin allows the data to be interactively explored in the form of a swarm of avatars whose position in hyperspace as well as facial features represent various aspects of the data. Sample visualizations, based on synthetic test data as well as the 12-dimensional database on Portuguese Vinho Verde wines, confirm the usefulness of our approach to the analysis of complex data structures.
Authors: Angelina Ibarra, Joshua Peeples
Abstract: This work presents a new approach to anomaly detection and localization in synthetic aperture radar imagery (SAR), expanding upon the existing patch distribution modeling framework (PaDiM). We introduce the adaptive cosine estimator (ACE) detection statistic. PaDiM uses the Mahalanobis distance at inference, an unbounded metric. ACE instead uses the cosine similarity metric, providing bounded anomaly detection scores. The proposed method is evaluated across multiple SAR datasets, with performance metrics including the area under the receiver operating curve (AUROC) at the image and pixel level, aiming for increased performance in anomaly detection and localization of SAR imagery. The code is publicly available: https://github.com/Advanced-Vision-and-Learning-Lab/PaDiM-ACE.
URLs: https://github.com/Advanced-Vision-and-Learning-Lab/PaDiM-ACE.
Authors: Yuchen Rao, Stefan Ainetter, Sinisa Stekovic, Vincent Lepetit, Friedrich Fraundorfer
Abstract: High-level 3D scene understanding is essential in many applications. However, the challenges of generating accurate 3D annotations make development of deep learning models difficult. We turn to recent advancements in automatic retrieval of synthetic CAD models, and show that data generated by such methods can be used as high-quality ground truth for training supervised deep learning models. More exactly, we employ a pipeline akin to the one previously used to automatically annotate objects in ScanNet scenes with their 9D poses and CAD models. This time, we apply it to the recent ScanNet++ v1 dataset, which previously lacked such annotations. Our findings demonstrate that it is not only possible to train deep learning models on these automatically-obtained annotations but that the resulting models outperform those trained on manually annotated data. We validate this on two distinct tasks: point cloud completion and single-view CAD model retrieval and alignment. Our results underscore the potential of automatic 3D annotations to enhance model performance while significantly reducing annotation costs. To support future research in 3D scene understanding, we will release our annotations, which we call SCANnotate++, along with our trained models.
Authors: Jakub Wasala, Bartlomiej Wrzalski, Kornelia Noculak, Yuliia Tarasenko, Oliwer Krupa, Jan Kocon, Grzegorz Chodak
Abstract: This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are consistent and, therefore, learnable within a specialized domain, like portrait generation. We generate a synthetic paired dataset and train a fast image-to-image translation head. Using two sets of low- and high-quality synthetic images, our model is trained to refine the output of a distilled generator (e.g., FLUX.1-schnell) to a level comparable to a baseline model like FLUX.1-dev, which is more computationally intensive. Our results show that the pipeline, which combines a distilled version of a large generative model with our enhancement layer, delivers similar photorealistic portraits to the baseline version with up to an 82% decrease in computational cost compared to FLUX.1-dev. This study demonstrates the potential for improving the efficiency of AI solutions involving large-scale image generation.
Authors: Nahuel Garcia-D'Urso, Bernabe Sanchez-Sos, Jorge Azorin-Lopez, Andres Fuster-Guillo, Antonio Macia-Lillo, Higinio Mora-Mora
Abstract: Accurate 3D reconstruction using multi-camera RGB-D systems critically depends on precise extrinsic calibration to achieve proper alignment between captured views. In this paper, we introduce an iterative extrinsic calibration method that leverages the geometric constraints provided by a three-dimensional marker to significantly improve calibration accuracy. Our proposed approach systematically segments and refines marker planes through clustering, regression analysis, and iterative reassignment techniques, ensuring robust geometric correspondence across camera views. We validate our method comprehensively in both controlled environments and practical real-world settings within the Tech4Diet project, aimed at modeling the physical progression of patients undergoing nutritional treatments. Experimental results demonstrate substantial reductions in alignment errors, facilitating accurate and reliable 3D reconstructions.
Authors: Yi-Fan Zhang, Xingyu Lu, Xiao Hu, Chaoyou Fu, Bin Wen, Tianke Zhang, Changyi Liu, Kaiyu Jiang, Kaibing Chen, Kaiyu Tang, Haojie Ding, Jiankang Chen, Fan Yang, Zhang Zhang, Tingting Gao, Liang Wang
Abstract: Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there has been limited exploration into the effectiveness of long-term reasoning capabilities for reward modeling and how to activate these capabilities in MRMs. In this paper, we explore how Reinforcement Learning (RL) can be used to improve reward modeling. Specifically, we reformulate the reward modeling problem as a rule-based RL task. However, we observe that directly applying existing RL algorithms, such as Reinforce++, to reward modeling often leads to training instability or even collapse due to the inherent limitations of these algorithms. To address this issue, we propose the StableReinforce algorithm, which refines the training loss, advantage estimation strategy, and reward design of existing RL methods. These refinements result in more stable training dynamics and superior performance. To facilitate MRM training, we collect 200K preference data from diverse datasets. Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks. Compared to previous SOTA models, R1-Reward achieves a $8.4\%$ improvement on the VL Reward-Bench and a $14.3\%$ improvement on the Multimodal Reward Bench. Moreover, with more inference compute, R1-Reward's performance is further enhanced, highlighting the potential of RL algorithms in optimizing MRMs.
Authors: Fangming Cui, Yonggang Zhang, Xuan Wang, Xinmei Tian, Jun Yu
Abstract: Recent developments in prompt learning of large vision-language models have significantly improved performance in target-specific tasks. However, these prompt optimizing methods often struggle to tackle the target-unspecific or generalizable tasks effectively. It may be attributed to the fact that overfitting training causes the model to forget its general knowledge having strong promotion on target-unspecific tasks. To alleviate this issue, we propose a novel Features Matrix (FM) regularization approach designed to enhance these models on target-unspecific tasks. Our method extracts and leverages general knowledge, shaping a Features Matrix (FM). Specifically, the FM captures the semantics of diverse inputs from a deep and fine perspective, preserving essential general knowledge, which mitigates the risk of overfitting. Representative evaluations demonstrate that: 1) the FM is compatible with existing frameworks as a generic and flexible module, and 2) the FM significantly showcases its effectiveness in enhancing target-unspecific tasks, achieving state-of-the-art performance.
Authors: Sriram Mandalika, Harsha Vardhan, Athira Nambiar
Abstract: Continual Learning entails progressively acquiring knowledge from new data while retaining previously acquired knowledge, thereby mitigating ``Catastrophic Forgetting'' in neural networks. Our work presents a novel uncertainty-driven Unsupervised Continual Learning framework using Generative Replay, namely ``Replay to Remember (R2R)''. The proposed R2R architecture efficiently uses unlabelled and synthetic labelled data in a balanced proportion using a cluster-level uncertainty-driven feedback mechanism and a VLM-powered generative replay module. Unlike traditional memory-buffer methods that depend on pretrained models and pseudo-labels, our R2R framework operates without any prior training. It leverages visual features from unlabeled data and adapts continuously using clustering-based uncertainty estimation coupled with dynamic thresholding. Concurrently, a generative replay mechanism along with DeepSeek-R1 powered CLIP VLM produces labelled synthetic data representative of past experiences, resembling biological visual thinking that replays memory to remember and act in new, unseen tasks. Extensive experimental analyses are carried out in CIFAR-10, CIFAR-100, CINIC-10, SVHN and TinyImageNet datasets. Our proposed R2R approach improves knowledge retention, achieving a state-of-the-art performance of 98.13%, 73.06%, 93.41%, 95.18%, 59.74%, respectively, surpassing state-of-the-art performance by over 4.36%.
Authors: Ying Zhang, Shuai Guo, Chenxi Sun, Yuchen Zhu, Jinhai Xiang
Abstract: In recent years, deformable medical image registration techniques have made significant progress. However, existing models still lack efficiency in parallel extraction of coarse and fine-grained features. To address this, we construct a new pyramid registration network based on feature and deformation field (FF-PNet). For coarse-grained feature extraction, we design a Residual Feature Fusion Module (RFFM), for fine-grained image deformation, we propose a Residual Deformation Field Fusion Module (RDFFM). Through the parallel operation of these two modules, the model can effectively handle complex image deformations. It is worth emphasizing that the encoding stage of FF-PNet only employs traditional convolutional neural networks without any attention mechanisms or multilayer perceptrons, yet it still achieves remarkable improvements in registration accuracy, fully demonstrating the superior feature decoding capabilities of RFFM and RDFFM. We conducted extensive experiments on the LPBA and OASIS datasets. The results show our network consistently outperforms popular methods in metrics like the Dice Similarity Coefficient.
Authors: Timo Kaiser, Thomas Norrenbrock, Bodo Rosenhahn
Abstract: The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of particular interest. However, the ambiguous nature of the class-agnostic foundation model SAM challenges current uncertainty quantification (UQ) approaches. This paper presents a theoretically motivated uncertainty quantification model based on a Bayesian entropy formulation jointly respecting aleatoric, epistemic, and the newly introduced task uncertainty. We use this formulation to train USAM, a lightweight post-hoc UQ method. Our model traces the root of uncertainty back to under-parameterised models, insufficient prompts or image ambiguities. Our proposed deterministic USAM demonstrates superior predictive capabilities on the SA-V, MOSE, ADE20k, DAVIS, and COCO datasets, offering a computationally cheap and easy-to-use UQ alternative that can support user-prompting, enhance semi-supervised pipelines, or balance the tradeoff between accuracy and cost efficiency.
Authors: Kejie Zhao, Wenjia Hua, Aiersi Tuerhong, Luziwei Leng, Yuxin Ma, Qinghai Guo
Abstract: Recently, spiking neural networks (SNNs), deployed on neuromorphic chips, provide highly efficient solutions on edge devices in different scenarios. However, their ability to adapt to distribution shifts after deployment has become a crucial challenge. Online test-time adaptation (OTTA) offers a promising solution by enabling models to dynamically adjust to new data distributions without requiring source data or labeled target samples. Nevertheless, existing OTTA methods are largely designed for traditional artificial neural networks and are not well-suited for SNNs. To address this gap, we propose a low-power, neuromorphic chip-friendly online test-time adaptation framework, aiming to enhance model generalization under distribution shifts. The proposed approach is called Threshold Modulation (TM), which dynamically adjusts the firing threshold through neuronal dynamics-inspired normalization, being more compatible with neuromorphic hardware. Experimental results on benchmark datasets demonstrate the effectiveness of this method in improving the robustness of SNNs against distribution shifts while maintaining low computational cost. The proposed method offers a practical solution for online test-time adaptation of SNNs, providing inspiration for the design of future neuromorphic chips. The demo code is available at github.com/NneurotransmitterR/TM-OTTA-SNN.
Authors: Doruk Aksoy, Huolin L. Xin, Timothy J. Rupert, William J. Bowman
Abstract: Automated detection of grain boundaries in electron microscope images of polycrystalline materials could help accelerate the nanoscale characterization of myriad engineering materials and novel materials under scientific research. Accurate segmentation of interconnected line networks, such as grain boundaries in polycrystalline material microstructures, poses a significant challenge due to the fragmented masks produced by conventional computer vision algorithms, including convolutional neural networks. These algorithms struggle with thin masks, often necessitating post-processing for effective contour closure and continuity. Previous approaches in this domain have typically relied on custom post-processing techniques that are problem-specific and heavily dependent on the quality of the mask obtained from a computer vision algorithm. Addressing this issue, this paper introduces a fast, high-fidelity post-processing technique that is universally applicable to segmentation masks of interconnected line networks. Leveraging domain knowledge about grain boundary connectivity, this method employs conditional random fields and perceptual grouping rules to refine segmentation masks of any image with a discernible grain structure. This approach significantly enhances segmentation mask accuracy, achieving a 79% segment identification accuracy in validation with a U-Net model on electron microscopy images of a polycrystalline oxide. Additionally, a novel grain alignment metric is introduced, showing a 51% improvement in grain alignment. This method not only enables rapid and accurate segmentation but also facilitates an unprecedented level of data analysis, significantly improving the statistical representation of grain boundary networks, making it suitable for a range of disciplines where precise segmentation of interconnected line networks is essential.
Authors: Yusen Wu, Phuong Nguyen, Rose Yesha, Yelena Yesha
Abstract: Distributional drift detection is important in medical applications as it helps ensure the accuracy and reliability of models by identifying changes in the underlying data distribution that could affect the prediction results of machine learning models. However, current methods have limitations in detecting drift, for example, the inclusion of abnormal datasets can lead to unfair comparisons. This paper presents an accurate and sensitive approach to detect distributional drift in CT-scan medical images by leveraging data-sketching and fine-tuning techniques. We developed a robust baseline library model for real-time anomaly detection, allowing for efficient comparison of incoming images and identification of anomalies. Additionally, we fine-tuned a pre-trained Vision Transformer model to extract relevant features, using mammography as a case study, significantly enhancing model accuracy to 99.11%. Combining with data-sketches and fine-tuning, our feature extraction evaluation demonstrated that cosine similarity scores between similar datasets provide greater improvements, from around 50% increased to 99.1%. Finally, the sensitivity evaluation shows that our solutions are highly sensitive to even 1% salt-and-pepper and speckle noise, and it is not sensitive to lighting noise (e.g., lighting conditions have no impact on data drift). The proposed methods offer a scalable and reliable solution for maintaining the accuracy of diagnostic models in dynamic clinical environments.
Authors: Valiyeh A. Nezhad, Gokberk Elmas, Bilal Kabas, Fuat Arslan, Tolga \c{C}ukur
Abstract: Although learning-based models hold great promise for MRI reconstruction, single-site models built on limited local datasets often suffer from poor generalization. This challenge has spurred interest in collaborative model training on multi-site datasets via federated learning (FL) -- a privacy-preserving framework that aggregates model updates instead of sharing imaging data. Conventional FL aggregates locally trained model weights into a global model, inherently constraining all sites to use a homogeneous model architecture. This rigidity forces sites to compromise on architectures tailored to their compute resources and application-specific needs, making conventional FL unsuitable for model-heterogeneous settings where each site may prefer a distinct architecture. To overcome this limitation, we introduce FedGAT, a novel model-agnostic FL technique based on generative autoregressive transformers. FedGAT decentralizes the training of a global generative prior that learns the distribution of multi-site MR images. For high-fidelity synthesis, we propose a novel site-prompted GAT prior that controllably synthesizes realistic MR images from desired sites via autoregressive prediction across spatial scales. Each site then trains its own reconstruction model -- using an architecture of its choice -- on a hybrid dataset augmenting its local MRI dataset with GAT-generated synthetic MR images emulating datasets from other sites. This hybrid training strategy enables site-specific reconstruction models to generalize more effectively across diverse data distributions while preserving data privacy. Comprehensive experiments on multi-institutional datasets demonstrate that FedGAT enables flexible, model-heterogeneous collaborations and achieves superior within-site and cross-site reconstruction performance compared to state-of-the-art FL baselines.
Authors: Yiru Jiao, Sander van Cranenburgh, Simeon Calvert, Hans van Lint
Abstract: The effectiveness of neural network models largely relies on learning meaningful latent patterns from data, where self-supervised learning of informative representations can enhance model performance and generalisability. However, self-supervised representation learning for spatially characterised time series, which are ubiquitous in transportation domain, poses unique challenges due to the necessity of maintaining fine-grained spatio-temporal similarities in the latent space. In this study, we introduce two structure-preserving regularisers for the contrastive learning of spatial time series: one regulariser preserves the topology of similarities between instances, and the other preserves the graph geometry of similarities across spatial and temporal dimensions. To balance the contrastive learning objective and the need for structure preservation, we propose a dynamic weighting mechanism that adaptively manages this trade-off and stabilises training. We validate the proposed method through extensive experiments, including multivariate time series classification to demonstrate its general applicability, as well as macroscopic and microscopic traffic prediction to highlight its particular usefulness in encoding traffic interactions. Across all tasks, our method preserves the similarity structures more effectively and improves state-of-the-art task performances. This method can be integrated with an arbitrary neural network model and is particularly beneficial for time series data with spatial or geographical features. Furthermore, our findings suggest that well-preserved similarity structures in the latent space indicate more informative and useful representations. This provides insights to design more effective neural networks for data-driven transportation research. Our code is made openly accessible with all resulting data at https://github.com/yiru-jiao/spclt
Authors: Ruidan Xing, Runyi Huang, Qing Xu, Lei He
Abstract: End-to-end autonomous driving solutions, which process multi-modal sensory data to directly generate refined control commands, have become a dominant paradigm in autonomous driving research. However, these approaches predominantly depend on single-vehicle data collection for model training and optimization, resulting in significant challenges such as high data acquisition and annotation costs, the scarcity of critical driving scenarios, and fragmented datasets that impede model generalization. To mitigate these limitations, we introduce RS2AD, a novel framework for reconstructing and synthesizing vehicle-mounted LiDAR data from roadside sensor observations. Specifically, our method transforms roadside LiDAR point clouds into the vehicle-mounted LiDAR coordinate system by leveraging the target vehicle's relative pose. Subsequently, high-fidelity vehicle-mounted LiDAR data is synthesized through virtual LiDAR modeling, point cloud classification, and resampling techniques. To the best of our knowledge, this is the first approach to reconstruct vehicle-mounted LiDAR data from roadside sensor inputs. Extensive experimental evaluations demonstrate that incorporating the data generated by the RS2AD method (the RS2V-L dataset) into model training as a supplement to the KITTI dataset can significantly enhance the accuracy of 3D object detection and greatly improve the efficiency of end-to-end autonomous driving data generation. These findings strongly validate the effectiveness of the proposed method and underscore its potential in reducing dependence on costly vehicle-mounted data collection while improving the robustness of autonomous driving models.
Authors: Anita Srbinovska, Angela Srbinovska, Vivek Senthil, Adrian Martin, John McCluskey, Jonathan Bateman, Ernest Fokou\'e
Abstract: This paper proposes a novel interdisciplinary framework for analyzing police body-worn camera (BWC) footage from the Rochester Police Department (RPD) using advanced artificial intelligence (AI) and statistical machine learning (ML) techniques. Our goal is to detect, classify, and analyze patterns of interaction between police officers and civilians to identify key behavioral dynamics, such as respect, disrespect, escalation, and de-escalation. We apply multimodal data analysis by integrating video, audio, and natural language processing (NLP) techniques to extract meaningful insights from BWC footage. We present our methodology, computational techniques, and findings, outlining a practical approach for law enforcement while advancing the frontiers of knowledge discovery from police BWC data.
Authors: Andrew Zhang, Hao Wang, Shuchang Ye, Michael Fulham, Jinman Kim
Abstract: Patient motion during medical image acquisition causes blurring, ghosting, and distorts organs, which makes image interpretation challenging. Current state-of-the-art algorithms using Generative Adversarial Network (GAN)-based methods with their ability to learn the mappings between corrupted images and their ground truth via Structural Similarity Index Measure (SSIM) loss effectively generate motion-free images. However, we identified the following limitations: (i) they mainly focus on global structural characteristics and therefore overlook localized features that often carry critical pathological information, and (ii) the SSIM loss function struggles to handle images with varying pixel intensities, luminance factors, and variance. In this study, we propose Motion-Aware Image SYnthesis (MAISY) which initially characterize motion and then uses it for correction by: (a) leveraging the foundation model Segment Anything Model (SAM), to dynamically learn spatial patterns along anatomical boundaries where motion artifacts are most pronounced and, (b) introducing the Variance-Selective SSIM (VS-SSIM) loss which adaptively emphasizes spatial regions with high pixel variance to preserve essential anatomical details during artifact correction. Experiments on chest and head CT datasets demonstrate that our model outperformed the state-of-the-art counterparts, with Peak Signal-to-Noise Ratio (PSNR) increasing by 40%, SSIM by 10%, and Dice by 16%.