Authors: Xiwen Li, Ross Whitaker, Tolga Tasdizen
Abstract: Idling vehicle detection (IVD) supports real-time systems that reduce pollution and emissions by dynamically messaging drivers to curb excess idling behavior. In computer vision, IVD has become an emerging task that leverages video from surveillance cameras and audio from remote microphones to localize and classify vehicles in each frame as moving, idling, or engine-off. As with other cross-modal tasks, the key challenge lies in modeling the correspondence between audio and visual modalities, which differ in representation but provide complementary cues -- video offers spatial and motion context, while audio conveys engine activity beyond the visual field. The previous end-to-end model, which uses a basic attention mechanism, struggles to align these modalities effectively, often missing vehicle detections. To address this issue, we propose AVIVDNetv2, a transformer-based end-to-end detection network. It incorporates a cross-modal transformer with global patch-level learning, a multiscale visual feature fusion module, and decoupled detection heads. Extensive experiments show that AVIVDNetv2 improves mAP by 7.66 over the disjoint baseline and 9.42 over the E2E baseline, with consistent AP gains across all vehicle categories. Furthermore, AVIVDNetv2 outperforms the state-of-the-art method for sounding object localization, establishing a new performance benchmark on the AVIVD dataset.
Authors: Oussema Dhaouadi, Johannes Meier, Jacques Kaiser, Daniel Cremers
Abstract: Road surface reconstruction from aerial images is fundamental for autonomous driving, urban planning, and virtual simulation, where smoothness, compactness, and accuracy are critical quality factors. Existing reconstruction methods often produce artifacts and inconsistencies that limit usability, while downstream tasks have a tendency to represent roads as planes for simplicity but at the cost of accuracy. We introduce FlexRoad, the first framework to directly address road surface smoothing by fitting Non-Uniform Rational B-Splines (NURBS) surfaces to 3D road points obtained from photogrammetric reconstructions or geodata providers. Our method at its core utilizes the Elevation-Constrained Spatial Road Clustering (ECSRC) algorithm for robust anomaly correction, significantly reducing surface roughness and fitting errors. To facilitate quantitative comparison between road surface reconstruction methods, we present GeoRoad Dataset (GeRoD), a diverse collection of road surface and terrain profiles derived from openly accessible geodata. Experiments on GeRoD and the photogrammetry-based DeepScenario Open 3D Dataset (DSC3D) demonstrate that FlexRoad considerably surpasses commonly used road surface representations across various metrics while being insensitive to various input sources, terrains, and noise types. By performing ablation studies, we identify the key role of each component towards high-quality reconstruction performance, making FlexRoad a generic method for realistic road surface modeling.
Authors: Johannes Ferner, Stefan Huber, Saverio Messineo, Angel Pop, Martin Uray
Abstract: The Hough transform is a popular and classical technique in computer vision for the detection of lines (or more general objects). It maps a pixel into a dual space -- the Hough space: each pixel is mapped to the set of lines through this pixel, which forms a curve in Hough space. The detection of lines then becomes a voting process to find those lines that received many votes by pixels. However, this voting is done by thresholding, which is susceptible to noise and other artifacts. In this work, we present an alternative voting technique to detect peaks in the Hough space based on persistent homology, which very naturally addresses limitations of simple thresholding. Experiments on synthetic data show that our method significantly outperforms the original method, while also demonstrating enhanced robustness. This work seeks to inspire future research in two key directions. First, we highlight the untapped potential of Topological Data Analysis techniques and advocate for their broader integration into existing methods, including well-established ones. Secondly, we initiate a discussion on the mathematical stability of the Hough transform, encouraging exploration of mathematically grounded improvements to enhance its robustness.
Authors: Sridevi Polavaram, Xin Zhou, Meenu Ravi, Mohammad Zarei, Anmol Srivastava
Abstract: Vision systems are increasingly deployed in critical domains such as surveillance, law enforcement, and transportation. However, their vulnerabilities to rare or unforeseen scenarios pose significant safety risks. To address these challenges, we introduce Context-Awareness and Interpretability of Rare Occurrences (CAIRO), an ontology-based human-assistive discovery framework for failure cases (or CP - Critical Phenomena) detection and formalization. CAIRO by design incentivizes human-in-the-loop for testing and evaluation of criticality that arises from misdetections, adversarial attacks, and hallucinations in AI black-box models. Our robust analysis of object detection model(s) failures in automated driving systems (ADS) showcases scalable and interpretable ways of formalizing the observed gaps between camera perception and real-world contexts, resulting in test cases stored as explicit knowledge graphs (in OWL/XML format) amenable for sharing, downstream analysis, logical reasoning, and accountability.
Authors: Xingxing Zuo, Nikhil Ranganathan, Connor Lee, Georgia Gkioxari, Soon-Jo Chung
Abstract: Monocular depth estimation (MDE) from thermal images is a crucial technology for robotic systems operating in challenging conditions such as fog, smoke, and low light. The limited availability of labeled thermal data constrains the generalization capabilities of thermal MDE models compared to foundational RGB MDE models, which benefit from datasets of millions of images across diverse scenarios. To address this challenge, we introduce a novel pipeline that enhances thermal MDE through knowledge distillation from a versatile RGB MDE model. Our approach features a confidence-aware distillation method that utilizes the predicted confidence of the RGB MDE to selectively strengthen the thermal MDE model, capitalizing on the strengths of the RGB model while mitigating its weaknesses. Our method significantly improves the accuracy of the thermal MDE, independent of the availability of labeled depth supervision, and greatly expands its applicability to new scenarios. In our experiments on new scenarios without labeled depth, the proposed confidence-aware distillation method reduces the absolute relative error of thermal MDE by 22.88\% compared to the baseline without distillation.
Authors: Stanley Mugisha, Rashid Kisitu, Florence Tushabe
Abstract: Integrating deep learning applications into agricultural IoT systems faces a serious challenge of balancing the high accuracy of Vision Transformers (ViTs) with the efficiency demands of resource-constrained edge devices. Large transformer models like the Swin Transformers excel in plant disease classification by capturing global-local dependencies. However, their computational complexity (34.1 GFLOPs) limits applications and renders them impractical for real-time on-device inference. Lightweight models such as MobileNetV3 and TinyML would be suitable for on-device inference but lack the required spatial reasoning for fine-grained disease detection. To bridge this gap, we propose a hybrid knowledge distillation framework that synergistically transfers logit and attention knowledge from a Swin Transformer teacher to a MobileNetV3 student model. Our method includes the introduction of adaptive attention alignment to resolve cross-architecture mismatch (resolution, channels) and a dual-loss function optimizing both class probabilities and spatial focus. On the lantVillage-Tomato dataset (18,160 images), the distilled MobileNetV3 attains 92.4% accuracy relative to 95.9% for Swin-L but at an 95% reduction on PC and < 82% in inference latency on IoT devices. (23ms on PC CPU and 86ms/image on smartphone CPUs). Key innovations include IoT-centric validation metrics (13 MB memory, 0.22 GFLOPs) and dynamic resolution-matching attention maps. Comparative experiments show significant improvements over standalone CNNs and prior distillation methods, with a 3.5% accuracy gain over MobileNetV3 baselines. Significantly, this work advances real-time, energy-efficient crop monitoring in precision agriculture and demonstrates how we can attain ViT-level diagnostic precision on edge devices. Code and models will be made available for replication after acceptance.
Authors: Mohammad Abu Tami, Mohammed Elhenawy, Huthaifa I. Ashqar
Abstract: Traffic safety remains a critical global challenge, with traditional Advanced Driver-Assistance Systems (ADAS) often struggling in dynamic real-world scenarios due to fragmented sensor processing and susceptibility to adversarial conditions. This paper reviews the transformative potential of Multimodal Large Language Models (MLLMs) in addressing these limitations by integrating cross-modal data such as visual, spatial, and environmental inputs to enable holistic scene understanding. Through a comprehensive analysis of MLLM-based approaches, we highlight their capabilities in enhancing perception, decision-making, and adversarial robustness, while also examining the role of key datasets (e.g., KITTI, DRAMA, ML4RoadSafety) in advancing research. Furthermore, we outline future directions, including real-time edge deployment, causality-driven reasoning, and human-AI collaboration. By positioning MLLMs as a cornerstone for next-generation traffic safety systems, this review underscores their potential to revolutionize the field, offering scalable, context-aware solutions that proactively mitigate risks and improve overall road safety.
Authors: Jingchao Wang, Hong Wang, Wenlong Zhang, Kunhua Ji, Dingjiang Huang, Yefeng Zheng
Abstract: Multi-task visual grounding (MTVG) includes two sub-tasks, i.e., Referring Expression Comprehension (REC) and Referring Expression Segmentation (RES). The existing representative approaches generally follow the research pipeline which mainly consists of three core procedures, including independent feature extraction for visual and linguistic modalities, respectively, cross-modal interaction module, and independent prediction heads for different sub-tasks. Albeit achieving remarkable performance, this research line has two limitations: 1) The linguistic content has not been fully injected into the entire visual backbone for boosting more effective visual feature extraction and it needs an extra cross-modal interaction module; 2) The relationship between REC and RES tasks is not effectively exploited to help the collaborative prediction for more accurate output. To deal with these problems, in this paper, we propose a Progressive Language-guided Visual Learning framework for multi-task visual grounding, called PLVL, which not only finely mine the inherent feature expression of the visual modality itself but also progressively inject the language information to help learn linguistic-related visual features. In this manner, our PLVL does not need additional cross-modal fusion module while fully introducing the language guidance. Furthermore, we analyze that the localization center for REC would help identify the to-be-segmented object region for RES to some extent. Inspired by this investigation, we design a multi-task head to accomplish collaborative predictions for these two sub-tasks. Extensive experiments conducted on several benchmark datasets comprehensively substantiate that our PLVL obviously outperforms the representative methods in both REC and RES tasks. https://github.com/jcwang0602/PLVL
Authors: Sarah Day, Jesse Dimino, Matt Jester, Kaitlin Keegan, Thomas Weighill
Abstract: In this paper we evaluate the performance of topological features for generalizable and robust classification of firn image data, with the broader goal of understanding the advantages, pitfalls, and trade-offs in topological featurization. Firn refers to layers of granular snow within glaciers that haven't been compressed into ice. This compactification process imposes distinct topological and geometric structure on firn that varies with depth within the firn column, making topological data analysis (TDA) a natural choice for understanding the connection between depth and structure. We use two classes of topological features, sublevel set features and distance transform features, together with persistence curves, to predict sample depth from microCT images. A range of challenging training-test scenarios reveals that no one choice of method dominates in all categories, and uncoveres a web of trade-offs between accuracy, interpretability, and generalizability.
Authors: Zezhang Yang, Zitong Yu, Nuri Choi, Abhinav K. Jha
Abstract: Myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT) is a widely used and cost-effective diagnostic tool for coronary artery disease. However, the lengthy scanning time in this imaging procedure can cause patient discomfort, motion artifacts, and potentially inaccurate diagnoses due to misalignment between the SPECT scans and the CT-scans which are acquired for attenuation compensation. Reducing projection angles is a potential way to shorten scanning time, but this can adversely impact the quality of the reconstructed images. To address this issue, we propose a detection-task-specific deep-learning method for sparse-view MPI SPECT images. This method integrates an observer loss term that penalizes the loss of anthropomorphic channel features with the goal of improving performance in perfusion defect-detection task. We observed that, on the task of detecting myocardial perfusion defects, the proposed method yielded an area under the receiver operating characteristic (ROC) curve (AUC) significantly larger than the sparse-view protocol. Further, the proposed method was observed to be able to restore the structure of the left ventricle wall, demonstrating ability to overcome sparse-sampling artifacts. Our preliminary results motivate further evaluations of the method.
Authors: Banafsheh Karimian (LIVIA ILLS Dept. of Systems Engineering ETS Montreal Canada), Giulia Avanzato (Dept. of Computer Engineering University of Cagliari Italy), Soufian Belharbi (LIVIA ILLS Dept. of Systems Engineering ETS Montreal Canada), Luke McCaffrey (Goodman Cancer Research Centre Dept. of Oncology McGill University Canada), Mohammadhadi Shateri (LIVIA ILLS Dept. of Systems Engineering ETS Montreal Canada), Eric Granger (LIVIA ILLS Dept. of Systems Engineering ETS Montreal Canada)
Abstract: Multimodal learning has shown significant promise for improving medical image analysis by integrating information from complementary data sources. This is widely employed for training vision-language models (VLMs) for cancer detection based on histology images and text reports. However, one of the main limitations in training these VLMs is the requirement for large paired datasets, raising concerns over privacy, and data collection, annotation, and maintenance costs. To address this challenge, we introduce CLIP-IT method to train a vision backbone model to classify histology images by pairing them with privileged textual information from an external source. At first, the modality pairing step relies on a CLIP-based model to match histology images with semantically relevant textual report data from external sources, creating an augmented multimodal dataset without the need for manually paired samples. Then, we propose a multimodal training procedure that distills the knowledge from the paired text modality to the unimodal image classifier for enhanced performance without the need for the textual data during inference. A parameter-efficient fine-tuning method is used to efficiently address the misalignment between the main (image) and paired (text) modalities. During inference, the improved unimodal histology classifier is used, with only minimal additional computational complexity. Our experiments on challenging PCAM, CRC, and BACH histology image datasets show that CLIP-IT can provide a cost-effective approach to leverage privileged textual information and outperform unimodal classifiers for histology.
Authors: Henry Marichal, Ver\'onica Casaravilla, Candice Power, Karolain Mello, Joaqu\'in Mazarino, Christine Lucas, Ludmila Profumo, Diego Passarella, Gregory Randall
Abstract: Here, we propose Deep CS-TRD, a new automatic algorithm for detecting tree rings in whole cross-sections. It substitutes the edge detection step of CS-TRD by a deep-learning-based approach (U-Net), which allows the application of the method to different image domains: microscopy, scanner or smartphone acquired, and species (Pinus taeda, Gleditsia triachantos and Salix glauca). Additionally, we introduce two publicly available datasets of annotated images to the community. The proposed method outperforms state-of-the-art approaches in macro images (Pinus taeda and Gleditsia triacanthos) while showing slightly lower performance in microscopy images of Salix glauca. To our knowledge, this is the first paper that studies automatic tree ring detection for such different species and acquisition conditions. The dataset and source code are available in https://github.com/hmarichal93/deepcstrd
Authors: Andr\'e Longon
Abstract: An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic interpretability research has illuminated some invariance-building circuitry in InceptionV1, but the results are limited and networks with different architectures have remained largely unexplored. This work investigates ResNet18 with a particular focus on its residual stream, an architectural component which InceptionV1 lacks. We observe that many convolutional channels in intermediate blocks exhibit scale invariant properties, computed by the element-wise residual summation of scale equivariant representations: the block input's smaller-scale copy with the block pre-sum output's larger-scale copy. Through subsequent ablation experiments, we attempt to causally link these neural properties with scale-robust object recognition behavior. Our tentative findings suggest how the residual stream computes scale invariance and its possible role in behavior. Code is available at: https://github.com/cest-andre/residual-stream-interp
Authors: Wonjeong Jo, Magdalena Wojcieszak
Abstract: Short video platforms, such as YouTube, Instagram, or TikTok, are used by billions of users. These platforms expose users to harmful content, ranging from clickbait or physical harms to hate or misinformation. Yet, we lack a comprehensive understanding and measurement of online harm on short video platforms. Toward this end, we present two large-scale datasets of multi-modal and multi-categorical online harm: (1) 60,906 systematically selected potentially harmful YouTube videos and (2) 19,422 videos annotated by three labeling actors: trained domain experts, GPT-4-Turbo (using 14 image frames, 1 thumbnail, and text metadata), and crowdworkers (Amazon Mechanical Turk master workers). The annotated dataset includes both (a) binary classification (harmful vs. harmless) and (b) multi-label categorizations of six harm categories: Information, Hate and harassment, Addictive, Clickbait, Sexual, and Physical harms. Furthermore, the annotated dataset provides (1) ground truth data with videos annotated consistently across (a) all three actors and (b) the majority of the labeling actors, and (2) three data subsets labeled by individual actors. These datasets are expected to facilitate future work on online harm, aid in (multi-modal) classification efforts, and advance the identification and potential mitigation of harmful content on video platforms.
Authors: Sen Fang, Chunyu Sui, Hongwei Yi, Carol Neidle, Dimitris N. Metaxas
Abstract: The complexity of sign language data processing brings many challenges. The current approach to recognition of ASL signs aims to translate RGB sign language videos through pose information into English-based ID glosses, which serve to uniquely identify ASL signs. Note that there is no shared convention for assigning such glosses to ASL signs, so it is essential that the same glossing conventions are used for all of the data in the datasets that are employed. This paper proposes SignX, a foundation model framework for sign recognition. It is a concise yet powerful framework applicable to multiple human activity recognition scenarios. First, we developed a Pose2Gloss component based on an inverse diffusion model, which contains a multi-track pose fusion layer that unifies five of the most powerful pose information sources--SMPLer-X, DWPose, Mediapipe, PrimeDepth, and Sapiens Segmentation--into a single latent pose representation. Second, we trained a Video2Pose module based on ViT that can directly convert raw video into signer pose representation. Through this 2-stage training framework, we enable sign language recognition models to be compatible with existing pose formats, laying the foundation for the common pose estimation necessary for sign recognition. Experimental results show that SignX can recognize signs from sign language video, producing predicted gloss representations with greater accuracy than has been reported in prior work.
Authors: Colton R. Crum, Adam Czajka
Abstract: An ongoing research challenge within several domains in computer vision is how to increase model generalization capabilities. Several attempts to improve model generalization performance are heavily inspired by human perceptual intelligence, which is remarkable in both its performance and efficiency to generalize to unknown samples. Many of these methods attempt to force portions of the network to be orthogonal, following some observation within neuroscience related to early vision processes. In this paper, we propose a loss component that regularizes the filtering kernels in the first convolutional layer of a network to make them nearly orthogonal. Deviating from previous works, we give the network flexibility in which pairs of kernels it makes orthogonal, allowing the network to navigate to a better solution space, imposing harsh penalties. Without architectural modifications, we report substantial gains in generalization performance using the proposed loss against previous works (including orthogonalization- and saliency-based regularization methods) across three different architectures (ResNet-50, DenseNet-121, ViT-b-16) and two difficult open-set recognition tasks: presentation attack detection in iris biometrics, and anomaly detection in chest X-ray images.
Authors: Fengchun Liu, Tong Zhang, Chunying Zhang
Abstract: In recent years, a large number of works have introduced Convolutional Neural Networks (CNNs) into image steganography, which transform traditional steganography methods such as hand-crafted features and prior knowledge design into steganography methods that neural networks autonomically learn information embedding. However, due to the inherent complexity of digital images, issues of invisibility and security persist when using CNN models for information embedding. In this paper, we propose Curriculum Learning Progressive Steganophy Network (CLPSTNet). The network consists of multiple progressive multi-scale convolutional modules that integrate Inception structures and dilated convolutions. The module contains multiple branching pathways, starting from a smaller convolutional kernel and dilatation rate, extracting the basic, local feature information from the feature map, and gradually expanding to the convolution with a larger convolutional kernel and dilatation rate for perceiving the feature information of a larger receptive field, so as to realize the multi-scale feature extraction from shallow to deep, and from fine to coarse, allowing the shallow secret information features to be refined in different fusion stages. The experimental results show that the proposed CLPSTNet not only has high PSNR , SSIM metrics and decoding accuracy on three large public datasets, ALASKA2, VOC2012 and ImageNet, but also the steganographic images generated by CLPSTNet have low steganalysis scores.You can find our code at \href{https://github.com/chaos-boops/CLPSTNet}{https://github.com/chaos-boops/CLPSTNet}.
URLs: https://github.com/chaos-boops/CLPSTNet, https://github.com/chaos-boops/CLPSTNet
Authors: Linhua Kong, Dongxia Chang, Lian Liu, Zisen Kong, Pengyuan Li, Yao Zhao
Abstract: Recently, 3D object detection algorithms based on radar and camera fusion have shown excellent performance, setting the stage for their application in autonomous driving perception tasks. Existing methods have focused on dealing with feature misalignment caused by the domain gap between radar and camera. However, existing methods either neglect inter-modal features interaction during alignment or fail to effectively align features at the same spatial location across modalities. To alleviate the above problems, we propose a new alignment model called Radar Camera Alignment (RCAlign). Specifically, we design a Dual-Route Alignment (DRA) module based on contrastive learning to align and fuse the features between radar and camera. Moreover, considering the sparsity of radar BEV features, a Radar Feature Enhancement (RFE) module is proposed to improve the densification of radar BEV features with the knowledge distillation loss. Experiments show RCAlign achieves a new state-of-the-art on the public nuScenes benchmark in radar camera fusion for 3D Object Detection. Furthermore, the RCAlign achieves a significant performance gain (4.3\% NDS and 8.4\% mAP) in real-time 3D detection compared to the latest state-of-the-art method (RCBEVDet).
Authors: Yuanjian Wang, Yufei Deng, Rong Xiao, Jiahao Fan, Chenwei Tang, Deng Xiong, Jiancheng Lv
Abstract: Event cameras are neuromorphic vision sensors that asynchronously capture changes in logarithmic brightness changes, offering significant advantages such as low latency, low power consumption, low bandwidth, and high dynamic range. While these characteristics make them ideal for high-speed scenarios, reconstructing geometrically consistent and photometrically accurate 3D representations from event data remains fundamentally challenging. Current event-based Neural Radiance Fields (NeRF) methods partially address these challenges but suffer from persistent artifacts caused by aggressive network learning in early stages and the inherent noise of event cameras. To overcome these limitations, we present SaENeRF, a novel self-supervised framework that effectively suppresses artifacts and enables 3D-consistent, dense, and photorealistic NeRF reconstruction of static scenes solely from event streams. Our approach normalizes predicted radiance variations based on accumulated event polarities, facilitating progressive and rapid learning for scene representation construction. Additionally, we introduce regularization losses specifically designed to suppress artifacts in regions where photometric changes fall below the event threshold and simultaneously enhance the light intensity difference of non-zero events, thereby improving the visual fidelity of the reconstructed scene. Extensive qualitative and quantitative experiments demonstrate that our method significantly reduces artifacts and achieves superior reconstruction quality compared to existing methods. The code is available at https://github.com/Mr-firework/SaENeRF.
Authors: Md Fahimuzzman Sohan
Abstract: Cattle lameness is often caused by hoof injuries or interdigital dermatitis, leads to pain and significantly impacts essential physiological activities such as walking, feeding, and drinking. This study presents a deep learning-based model for detecting cattle lameness, sickness, or gait abnormalities using publicly available video data. The dataset consists of 50 unique videos from 40 individual cattle, recorded from various angles in both indoor and outdoor environments. Half of the dataset represents naturally walking (normal/non-lame) cattle, while the other half consists of cattle exhibiting gait abnormalities (lame). To enhance model robustness and generalizability, data augmentation was applied to the training data. The pre-processed videos were then classified using two deep learning models: ConvLSTM2D and 3D CNN. A comparative analysis of the results demonstrates strong classification performance. Specifically, the 3D CNN model achieved a video-level classification accuracy of 90%, with precision, recall, and f1-score of 90.9%, 90.9%, and 90.91% respectively. The ConvLSTM2D model exhibited a slightly lower accuracy of 85%. This study highlights the effectiveness of directly applying classification models to learn spatiotemporal features from video data, offering an alternative to traditional multi-stage approaches that typically involve object detection, pose estimation, and feature extraction. Besides, the findings demonstrate that the proposed deep learning models, particularly the 3D CNN, effectively classify and detect lameness in cattle while simplifying the processing pipeline.
Authors: Qi Yang, Weichen Bi, Haiyang Shen, Yaoqi Guo, Yun Ma
Abstract: Graphical User Interface (GUI) datasets are crucial for various downstream tasks. However, GUI datasets often generate annotation information through automatic labeling, which commonly results in inaccurate GUI element BBox annotations, including missing, duplicate, or meaningless BBoxes. These issues can degrade the performance of models trained on these datasets, limiting their effectiveness in real-world applications. Additionally, existing GUI datasets only provide BBox annotations visually, which restricts the development of visually related GUI downstream tasks. To address these issues, we introduce PixelWeb, a large-scale GUI dataset containing over 100,000 annotated web pages. PixelWeb is constructed using a novel automatic annotation approach that integrates visual feature extraction and Document Object Model (DOM) structure analysis through two core modules: channel derivation and layer analysis. Channel derivation ensures accurate localization of GUI elements in cases of occlusion and overlapping elements by extracting BGRA four-channel bitmap annotations. Layer analysis uses the DOM to determine the visibility and stacking order of elements, providing precise BBox annotations. Additionally, PixelWeb includes comprehensive metadata such as element images, contours, and mask annotations. Manual verification by three independent annotators confirms the high quality and accuracy of PixelWeb annotations. Experimental results on GUI element detection tasks show that PixelWeb achieves performance on the mAP95 metric that is 3-7 times better than existing datasets. We believe that PixelWeb has great potential for performance improvement in downstream tasks such as GUI generation and automated user interaction.
Authors: Hariseetharam Gunduboina (Indian Institute of Technology Bombay, India), Muhammad Haris Khan (Mohamed Bin Zayed University of Artificial Intelligence, UAE), Biplab Banerjee (Indian Institute of Technology Bombay, India)
Abstract: In recent years, large-scale vision-language models (VLMs) like CLIP have gained attention for their zero-shot inference using instructional text prompts. While these models excel in general computer vision, their potential for domain generalization in remote sensing (RS) remains underexplored. Existing approaches enhance prompt learning by generating visual prompt tokens but rely on full-image features, introducing noise and background artifacts that vary within a class, causing misclassification. To address this, we propose FrogDogNet, a novel prompt learning framework integrating Fourier frequency filtering and self-attention to improve RS scene classification and domain generalization. FrogDogNet selectively retains invariant low-frequency components while eliminating noise and irrelevant backgrounds, ensuring robust feature representation across domains. The model first extracts significant features via projection and self-attention, then applies frequency-based filtering to preserve essential structural information for prompt learning. Extensive experiments on four RS datasets and three domain generalization tasks show that FrogDogNet consistently outperforms state-of-the-art prompt learning methods, demonstrating superior adaptability across domain shifts. Our findings highlight the effectiveness of frequency-based invariant feature retention in generalization, paving the way for broader applications. Our code is available at https://github.com/HariseetharamG/FrogDogNet
Authors: Duy-Tho Le, Trung Pham, Jianfei Cai, Hamid Rezatofighi
Abstract: Optimizing the similarity between parametric shapes is crucial for numerous computer vision tasks, where Intersection over Union (IoU) stands as the canonical measure. However, existing optimization methods exhibit significant shortcomings: regression-based losses like L1/L2 lack correlation with IoU, IoU-based losses are unstable and limited to simple shapes, and task-specific methods are computationally intensive and not generalizable accross domains. As a result, the current landscape of parametric shape objective functions has become scattered, with each domain proposing distinct IoU approximations. To address this, we unify the parametric shape optimization objective functions by introducing Marginalized Generalized IoU (MGIoU), a novel loss function that overcomes these challenges by projecting structured convex shapes onto their unique shape Normals to compute one-dimensional normalized GIoU. MGIoU offers a simple, efficient, fully differentiable approximation strongly correlated with IoU. We then extend MGIoU to MGIoU+ that supports optimizing unstructured convex shapes. Together, MGIoU and MGIoU+ unify parametric shape optimization across diverse applications. Experiments on standard benchmarks demonstrate that MGIoU and MGIoU+ consistently outperform existing losses while reducing loss computation latency by 10-40x. Additionally, MGIoU and MGIoU+ satisfy metric properties and scale-invariance, ensuring robustness as an objective function. We further propose MGIoU- for minimizing overlaps in tasks like collision-free trajectory prediction. Code is available at https://ldtho.github.io/MGIoU
Authors: Shun Zou, Yi Zou, Juncheng Li, Guangwei Gao, Guojun Qi
Abstract: Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge single-paradigm architectures, necessitating a unified framework to integrate complementary global-local and spatial-channel representations. To address this, we propose a novel Cross Paradigm Representation and Alignment Transformer (CPRAformer). Its core idea is the hierarchical representation and alignment, leveraging the strengths of both paradigms (spatial-channel and global-local) to aid image reconstruction. It bridges the gap within and between paradigms, aligning and coordinating them to enable deep interaction and fusion of features. Specifically, we use two types of self-attention in the Transformer blocks: sparse prompt channel self-attention (SPC-SA) and spatial pixel refinement self-attention (SPR-SA). SPC-SA enhances global channel dependencies through dynamic sparsity, while SPR-SA focuses on spatial rain distribution and fine-grained texture recovery. To address the feature misalignment and knowledge differences between them, we introduce the Adaptive Alignment Frequency Module (AAFM), which aligns and interacts with features in a two-stage progressive manner, enabling adaptive guidance and complementarity. This reduces the information gap within and between paradigms. Through this unified cross-paradigm dynamic interaction framework, we achieve the extraction of the most valuable interactive fusion information from the two paradigms. Extensive experiments demonstrate that our model achieves state-of-the-art performance on eight benchmark datasets and further validates CPRAformer's robustness in other image restoration tasks and downstream applications.
Authors: Qishan He, Lingjun Zhao, Ru Luo, Siqian Zhang, Lin Lei, Kefeng Ji, Gangyao Kuang
Abstract: Aircraft recognition in synthetic aperture radar (SAR) imagery is a fundamental mission in both military and civilian applications. Recently deep learning (DL) has emerged a dominant paradigm for its explosive performance on extracting discriminative features. However, current classification algorithms focus primarily on learning decision hyperplane without enough comprehension on aircraft structural knowledge. Inspired by the fined aircraft annotation methods for optical remote sensing images (RSI), we first introduce a structure-based SAR aircraft annotations approach to provide structural and compositional supplement information. On this basis, we propose a multi-task structure guided learning (MTSGL) network for robust and interpretable SAR aircraft recognition. Besides the classification task, MTSGL includes a structural semantic awareness (SSA) module and a structural consistency regularization (SCR) module. The SSA is designed to capture structure semantic information, which is conducive to gain human-like comprehension of aircraft knowledge. The SCR helps maintain the geometric consistency between the aircraft structure in SAR imagery and the proposed annotation. In this process, the structural attribute can be disentangled in a geometrically meaningful manner. In conclusion, the MTSGL is presented with the expert-level aircraft prior knowledge and structure guided learning paradigm, aiming to comprehend the aircraft concept in a way analogous to the human cognitive process. Extensive experiments are conducted on a self-constructed multi-task SAR aircraft recognition dataset (MT-SARD) and the effective results illustrate the superiority of robustness and interpretation ability of the proposed MTSGL.
Authors: Boyue Xu, Ruichao Hou, Tongwei Ren, Gangshan Wu
Abstract: The RGB-Depth (RGB-D) Video Object Segmentation (VOS) aims to integrate the fine-grained texture information of RGB with the spatial geometric clues of depth modality, boosting the performance of segmentation. However, off-the-shelf RGB-D segmentation methods fail to fully explore cross-modal information and suffer from object drift during long-term prediction. In this paper, we propose a novel RGB-D VOS method via multi-store feature memory for robust segmentation. Specifically, we design the hierarchical modality selection and fusion, which adaptively combines features from both modalities. Additionally, we develop a segmentation refinement module that effectively utilizes the Segmentation Anything Model (SAM) to refine the segmentation mask, ensuring more reliable results as memory to guide subsequent segmentation tasks. By leveraging spatio-temporal embedding and modality embedding, mixed prompts and fused images are fed into SAM to unleash its potential in RGB-D VOS. Experimental results show that the proposed method achieves state-of-the-art performance on the latest RGB-D VOS benchmark.
Authors: Yahao Lu, Yuehui Li, Xingyuan Guo, Shuai Yuan, Yukai Shi, Liang Lin
Abstract: Infrared small target detection (ISTD) is highly sensitive to sensor type, observation conditions, and the intrinsic properties of the target. These factors can introduce substantial variations in the distribution of acquired infrared image data, a phenomenon known as domain shift. Such distribution discrepancies significantly hinder the generalization capability of ISTD models across diverse scenarios. To tackle this challenge, this paper introduces an ISTD framework enhanced by domain adaptation. To alleviate distribution shift between datasets and achieve cross-sample alignment, we introduce Cross-view Channel Alignment (CCA). Additionally, we propose the Cross-view Top-K Fusion strategy, which integrates target information with diverse background features, enhancing the model' s ability to extract critical data characteristics. To further mitigate the impact of noise on ISTD, we develop a Noise-guided Representation learning strategy. This approach enables the model to learn more noise-resistant feature representations, to improve its generalization capability across diverse noisy domains. Finally, we develop a dedicated infrared small target dataset, RealScene-ISTD. Compared to state-of-the-art methods, our approach demonstrates superior performance in terms of detection probability (Pd), false alarm rate (Fa), and intersection over union (IoU). The code is available at: https://github.com/luy0222/RealScene-ISTD.
Authors: Daniil Sinitsyn, Linus H\"arenstam-Nielsen, Daniel Cremers
Abstract: We tackle the problem of automatic calibration of radially distorted cameras in challenging conditions. Accurately determining distortion parameters typically requires either 1) solving the full Structure from Motion (SfM) problem involving camera poses, 3D points, and the distortion parameters, which is only possible if many images with sufficient overlap are provided, or 2) relying heavily on learning-based methods that are comparatively less accurate. In this work, we demonstrate that distortion calibration can be decoupled from 3D reconstruction, maintaining the accuracy of SfM-based methods while avoiding many of the associated complexities. This is achieved by working in Projective Space, where the geometry is unique up to a homography, which encapsulates all camera parameters except for distortion. Our proposed method, Projective Radial Distortion Averaging, averages multiple distortion estimates in a fully projective framework without creating 3d points and full bundle adjustment. By relying on pairwise projective relations, our methods support any feature-matching approaches without constructing point tracks across multiple images.
Authors: Meng Chu, Yukang Chen, Haokun Gui, Shaozuo Yu, Yi Wang, Jiaya Jia
Abstract: Tourism and travel planning increasingly rely on digital assistance, yet existing multimodal AI systems often lack specialized knowledge and contextual understanding of urban environments. We present TraveLLaMA, a specialized multimodal language model designed for urban scene understanding and travel assistance. Our work addresses the fundamental challenge of developing practical AI travel assistants through a novel large-scale dataset of 220k question-answer pairs. This comprehensive dataset uniquely combines 130k text QA pairs meticulously curated from authentic travel forums with GPT-enhanced responses, alongside 90k vision-language QA pairs specifically focused on map understanding and scene comprehension. Through extensive fine-tuning experiments on state-of-the-art vision-language models (LLaVA, Qwen-VL, Shikra), we demonstrate significant performance improvements ranging from 6.5\%-9.4\% in both pure text travel understanding and visual question answering tasks. Our model exhibits exceptional capabilities in providing contextual travel recommendations, interpreting map locations, and understanding place-specific imagery while offering practical information such as operating hours and visitor reviews. Comparative evaluations show TraveLLaMA significantly outperforms general-purpose models in travel-specific tasks, establishing a new benchmark for multi-modal travel assistance systems.
Authors: Abdul Hannaan, Zubair Shah, Aiman Erbad, Amr Mohamed, Ali Safa
Abstract: This paper introduces a novel federated learning framework termed LoRa-FL designed for training low-rank one-shot image detection models deployed on edge devices. By incorporating low-rank adaptation techniques into one-shot detection architectures, our method significantly reduces both computational and communication overhead while maintaining scalable accuracy. The proposed framework leverages federated learning to collaboratively train lightweight image recognition models, enabling rapid adaptation and efficient deployment across heterogeneous, resource-constrained devices. Experimental evaluations on the MNIST and CIFAR10 benchmark datasets, both in an independent-and-identically-distributed (IID) and non-IID setting, demonstrate that our approach achieves competitive detection performance while significantly reducing communication bandwidth and compute complexity. This makes it a promising solution for adaptively reducing the communication and compute power overheads, while not sacrificing model accuracy.
Authors: Junrong Yue, Yifan Zhang, Chuan Qin, Bo Li, Xiaomin Lie, Xinlei Yu, Wenxin Zhang, Zhendong Zhao
Abstract: Vision-and-Language Navigation (VLN) aims to enable embodied agents to follow natural language instructions and reach target locations in real-world environments. While prior methods often rely on either global scene representations or object-level features, these approaches are insufficient for capturing the complex interactions across modalities required for accurate navigation. In this paper, we propose a Multi-level Fusion and Reasoning Architecture (MFRA) to enhance the agent's ability to reason over visual observations, language instructions and navigation history. Specifically, MFRA introduces a hierarchical fusion mechanism that aggregates multi-level features-ranging from low-level visual cues to high-level semantic concepts-across multiple modalities. We further design a reasoning module that leverages fused representations to infer navigation actions through instruction-guided attention and dynamic context integration. By selectively capturing and combining relevant visual, linguistic, and temporal signals, MFRA improves decision-making accuracy in complex navigation scenarios. Extensive experiments on benchmark VLN datasets including REVERIE, R2R, and SOON demonstrate that MFRA achieves superior performance compared to state-of-the-art methods, validating the effectiveness of multi-level modal fusion for embodied navigation.
Authors: Wenwei Li, Liyi Cai, Wu Chen, Anan Li
Abstract: In neuroscience research, achieving single-neuron matching across different imaging modalities is critical for understanding the relationship between neuronal structure and function. However, modality gaps and limited annotations present significant challenges. We propose a few-shot metric learning method with a dual-channel attention mechanism and a pretrained vision transformer to enable robust cross-modal neuron identification. The local and global channels extract soma morphology and fiber context, respectively, and a gating mechanism fuses their outputs. To enhance the model's fine-grained discrimination capability, we introduce a hard sample mining strategy based on the MultiSimilarityMiner algorithm, along with the Circle Loss function. Experiments on two-photon and fMOST datasets demonstrate superior Top-K accuracy and recall compared to existing methods. Ablation studies and t-SNE visualizations validate the effectiveness of each module. The method also achieves a favorable trade-off between accuracy and training efficiency under different fine-tuning strategies. These results suggest that the proposed approach offers a promising technical solution for accurate single-cell level matching and multimodal neuroimaging integration.
Authors: Joan Perez (Urban Geo Analytics, France), Giovanni Fusco (Universite Cote-Azur-CNRS-AMU-Avignon Universite, ESPACE, France)
Abstract: Streetscapes are an essential component of urban space. Their assessment is presently either limited to morphometric properties of their mass skeleton or requires labor-intensive qualitative evaluations of visually perceived qualities. This paper introduces SAGAI: Streetscape Analysis with Generative Artificial Intelligence, a modular workflow for scoring street-level urban scenes using open-access data and vision-language models. SAGAI integrates OpenStreetMap geometries, Google Street View imagery, and a lightweight version of the LLaVA model to generate structured spatial indicators from images via customizable natural language prompts. The pipeline includes an automated mapping module that aggregates visual scores at both the point and street levels, enabling direct cartographic interpretation. It operates without task-specific training or proprietary software dependencies, supporting scalable and interpretable analysis of urban environments. Two exploratory case studies in Nice and Vienna illustrate SAGAI's capacity to produce geospatial outputs from vision-language inference. The initial results show strong performance for binary urban-rural scene classification, moderate precision in commercial feature detection, and lower estimates, but still informative, of sidewalk width. Fully deployable by any user, SAGAI can be easily adapted to a wide range of urban research themes, such as walkability, safety, or urban design, through prompt modification alone.
Authors: Andrea Conti, Matteo Poggi, Valerio Cambareri, Martin R. Oswald, Stefano Mattoccia
Abstract: Time-of-Flight (ToF) sensors provide efficient active depth sensing at relatively low power budgets; among such designs, only very sparse measurements from low-resolution sensors are considered to meet the increasingly limited power constraints of mobile and AR/VR devices. However, such extreme sparsity levels limit the seamless usage of ToF depth in SLAM. In this work, we propose ToF-Splatting, the first 3D Gaussian Splatting-based SLAM pipeline tailored for using effectively very sparse ToF input data. Our approach improves upon the state of the art by introducing a multi-frame integration module, which produces dense depth maps by merging cues from extremely sparse ToF depth, monocular color, and multi-view geometry. Extensive experiments on both synthetic and real sparse ToF datasets demonstrate the viability of our approach, as it achieves state-of-the-art tracking and mapping performances on reference datasets.
Authors: Murat Bilgehan Ertan, Ronak Sahu, Phuong Ha Nguyen, Kaleel Mahmood, Marten van Dijk
Abstract: We introduce ROAR (Robust Object Removal and Re-annotation), a scalable framework for privacy-preserving dataset obfuscation that eliminates sensitive objects instead of modifying them. Our method integrates instance segmentation with generative inpainting to remove identifiable entities while preserving scene integrity. Extensive evaluations on 2D COCO-based object detection show that ROAR achieves 87.5% of the baseline detection average precision (AP), whereas image dropping achieves only 74.2% of the baseline AP, highlighting the advantage of scrubbing in preserving dataset utility. The degradation is even more severe for small objects due to occlusion and loss of fine-grained details. Furthermore, in NeRF-based 3D reconstruction, our method incurs a PSNR loss of at most 1.66 dB while maintaining SSIM and improving LPIPS, demonstrating superior perceptual quality. Our findings establish object removal as an effective privacy framework, achieving strong privacy guarantees with minimal performance trade-offs. The results highlight key challenges in generative inpainting, occlusion-robust segmentation, and task-specific scrubbing, setting the foundation for future advancements in privacy-preserving vision systems.
Authors: Zhongtao Wang, Xizhe Cao, Yisong Chen, Guoping Wang
Abstract: Semantic segmentation of remote sensing imagery demands precise spatial boundaries and robust intra-class consistency, challenging conventional hierarchical models. To address limitations arising from spatial domain feature fusion and insufficient receptive fields, this paper introduces SAIP-Net, a novel frequency-aware segmentation framework that leverages Spectral Adaptive Information Propagation. SAIP-Net employs adaptive frequency filtering and multi-scale receptive field enhancement to effectively suppress intra-class feature inconsistencies and sharpen boundary lines. Comprehensive experiments demonstrate significant performance improvements over state-of-the-art methods, highlighting the effectiveness of spectral-adaptive strategies combined with expanded receptive fields for remote sensing image segmentation.
Authors: Giacomo Pacini, Lorenzo Bianchi, Luca Ciampi, Nicola Messina, Giuseppe Amato, Fabrizio Falchi
Abstract: Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods offer flexibility at inference time, they still rely heavily on labeled data for training, which limits scalability and generalization to many downstream use cases. In this paper, we introduce CountingDINO, the first training-free exemplar-based CAC framework that exploits a fully unsupervised feature extractor. Specifically, our approach employs self-supervised vision-only backbones to extract object-aware features, and it eliminates the need for annotated data throughout the entire proposed pipeline. At inference time, we extract latent object prototypes via ROI-Align from DINO features and use them as convolutional kernels to generate similarity maps. These are then transformed into density maps through a simple yet effective normalization scheme. We evaluate our approach on the FSC-147 benchmark, where we outperform a baseline under the same label-free setting. Our method also achieves competitive -- and in some cases superior -- results compared to training-free approaches relying on supervised backbones, as well as several fully supervised state-of-the-art methods. This demonstrates that training-free CAC can be both scalable and competitive. Website: https://lorebianchi98.github.io/CountingDINO/
Authors: Tristan Kenneweg, Philip Kenneweg, Barbara Hammer
Abstract: Joint-Embedding Predictive Architectures (JEPA) have recently become popular as promising architectures for self-supervised learning. Vision transformers have been trained using JEPA to produce embeddings from images and videos, which have been shown to be highly suitable for downstream tasks like classification and segmentation. In this paper, we show how to adapt the JEPA architecture to reinforcement learning from images. We discuss model collapse, show how to prevent it, and provide exemplary data on the classical Cart Pole task.
Authors: Max Kirchner, Alexander C. Jenke, Sebastian Bodenstedt, Fiona R. Kolbinger, Oliver Saldanha, Jakob N. Kather, Martin Wagner, Stefanie Speidel
Abstract: Purpose: In this study, we investigate the training of foundation models using federated learning to address data-sharing limitations and enable collaborative model training without data transfer for minimally invasive surgery. Methods: Inspired by the EndoViT study, we adapt the Masked Autoencoder for federated learning, enhancing it with adaptive Sharpness-Aware Minimization (FedSAM) and Stochastic Weight Averaging (SWA). Our model is pretrained on the Endo700k dataset collection and later fine-tuned and evaluated for tasks such as Semantic Segmentation, Action Triplet Recognition, and Surgical Phase Recognition. Results: Our findings demonstrate that integrating adaptive FedSAM into the federated MAE approach improves pretraining, leading to a reduction in reconstruction loss per patch. The application of FL-EndoViT in surgical downstream tasks results in performance comparable to CEN-EndoViT. Furthermore, FL-EndoViT exhibits advantages over CEN-EndoViT in surgical scene segmentation when data is limited and in action triplet recognition when large datasets are used. Conclusion: These findings highlight the potential of federated learning for privacy-preserving training of surgical foundation models, offering a robust and generalizable solution for surgical data science. Effective collaboration requires adapting federated learning methods, such as the integration of FedSAM, which can accommodate the inherent data heterogeneity across institutions. In future, exploring FL in video-based models may enhance these capabilities by incorporating spatiotemporal dynamics crucial for real-world surgical environments.
Authors: Haosheng Chen, Lian Luo, Mengjingcheng Mo, Zhanjie Wu, Guobao Xiao, Ji Gan, Jiaxu Leng, Xinbo Gao
Abstract: Event cameras, with microsecond temporal resolution and high dynamic range (HDR) characteristics, emit high-speed event stream for perception tasks. Despite the recent advancement in GNN-based perception methods, they are prone to use straightforward pairwise connectivity mechanisms in the pure Euclidean space where they struggle to capture long-range dependencies and fail to effectively characterize the inherent hierarchical structures of non-uniformly distributed event stream. To this end, in this paper we propose a novel approach named EHGCN, which is a pioneer to perceive event stream in both Euclidean and hyperbolic spaces for event vision. In EHGCN, we introduce an adaptive sampling strategy to dynamically regulate sampling rates, retaining discriminative events while attenuating chaotic noise. Then we present a Markov Vector Field (MVF)-driven motion-aware hyperedge generation method based on motion state transition probabilities, thereby eliminating cross-target spurious associations and providing critically topological priors while capturing long-range dependencies between events. Finally, we propose a Euclidean-Hyperbolic GCN to fuse the information locally aggregated and globally hierarchically modeled in Euclidean and hyperbolic spaces, respectively, to achieve hybrid event perception. Experimental results on event perception tasks such as object detection and recognition validate the effectiveness of our approach.
Authors: Xianrui Luo, Zijin Wu, Juewen Peng, Huiqiang Sun, Zhiguo Cao, Guosheng Lin
Abstract: We present the first framework capable of synthesizing the all-in-focus neural radiance field (NeRF) from inputs without manual refocusing. Without refocusing, the camera will automatically focus on the fixed object for all views, and current NeRF methods typically using one camera fail due to the consistent defocus blur and a lack of sharp reference. To restore the all-in-focus NeRF, we introduce the dual-camera from smartphones, where the ultra-wide camera has a wider depth-of-field (DoF) and the main camera possesses a higher resolution. The dual camera pair saves the high-fidelity details from the main camera and uses the ultra-wide camera's deep DoF as reference for all-in-focus restoration. To this end, we first implement spatial warping and color matching to align the dual camera, followed by a defocus-aware fusion module with learnable defocus parameters to predict a defocus map and fuse the aligned camera pair. We also build a multi-view dataset that includes image pairs of the main and ultra-wide cameras in a smartphone. Extensive experiments on this dataset verify that our solution, termed DC-NeRF, can produce high-quality all-in-focus novel views and compares favorably against strong baselines quantitatively and qualitatively. We further show DoF applications of DC-NeRF with adjustable blur intensity and focal plane, including refocusing and split diopter.
Authors: Qifan Li, Tianyi Liang, Xingtao Wang, Xiaopeng Fan
Abstract: Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical necessity, as degradation and context are typically localized. Normalized average attention distance across various degradation datasets shows that middle-range attention is enough for image restoration. Building on this insight, we propose RouteWinFormer, a novel window-based Transformer that models middle-range context for image restoration. RouteWinFormer incorporates Route-Windows Attnetion Module, which dynamically selects relevant nearby windows based on regional similarity for attention aggregation, extending the receptive field to a mid-range size efficiently. In addition, we introduce Multi-Scale Structure Regularization during training, enabling the sub-scale of the U-shaped network to focus on structural information, while the original-scale learns degradation patterns based on generalized image structure priors. Extensive experiments demonstrate that RouteWinFormer outperforms state-of-the-art methods across 9 datasets in various image restoration tasks.
Authors: Hasan Algafri, Hamzah Luqman, Sarah Alyami, Issam Laradji
Abstract: Sign language is the primary communication language for people with disabling hearing loss. Sign language recognition (SLR) systems aim to recognize sign gestures and translate them into spoken language. One of the main challenges in SLR is the scarcity of annotated datasets. To address this issue, we propose a semi-supervised learning (SSL) approach for SLR (SSLR), employing a pseudo-label method to annotate unlabeled samples. The sign gestures are represented using pose information that encodes the signer's skeletal joint points. This information is used as input for the Transformer backbone model utilized in the proposed approach. To demonstrate the learning capabilities of SSL across various labeled data sizes, several experiments were conducted using different percentages of labeled data with varying numbers of classes. The performance of the SSL approach was compared with a fully supervised learning-based model on the WLASL-100 dataset. The obtained results of the SSL model outperformed the supervised learning-based model with less labeled data in many cases.
Authors: Younggeol Cho, Elisa Motta, Olivia Nocentini, Marta Lagomarsino, Andrea Merello, Marco Crepaldi, Arash Ajoudani
Abstract: Human pose estimation and action recognition have received attention due to their critical roles in healthcare monitoring, rehabilitation, and assistive technologies. In this study, we proposed a novel architecture named Transformer based Encoder Decoder Network (TED Net) designed for estimating human skeleton poses from WiFi Channel State Information (CSI). TED Net integrates convolutional encoders with transformer based attention mechanisms to capture spatiotemporal features from CSI signals. The estimated skeleton poses were used as input to a customized Directed Graph Neural Network (DGNN) for action recognition. We validated our model on two datasets: a publicly available multi modal dataset for assessing general pose estimation, and a newly collected dataset focused on fall related scenarios involving 20 participants. Experimental results demonstrated that TED Net outperformed existing approaches in pose estimation, and that the DGNN achieves reliable action classification using CSI based skeletons, with performance comparable to RGB based systems. Notably, TED Net maintains robust performance across both fall and non fall cases. These findings highlight the potential of CSI driven human skeleton estimation for effective action recognition, particularly in home environments such as elderly fall detection. In such settings, WiFi signals are often readily available, offering a privacy preserving alternative to vision based methods, which may raise concerns about continuous camera monitoring.
Authors: Chris, Yichen Wei, Yi Peng, Xiaokun Wang, Weijie Qiu, Wei Shen, Tianyidan Xie, Jiangbo Pei, Jianhao Zhang, Yunzhuo Hao, Xuchen Song, Yang Liu, Yahui Zhou
Abstract: We present Skywork R1V2, a next-generation multimodal reasoning model and a major leap forward from its predecessor, Skywork R1V. At its core, R1V2 introduces a hybrid reinforcement learning paradigm that harmonizes reward-model guidance with rule-based strategies, thereby addressing the long-standing challenge of balancing sophisticated reasoning capabilities with broad generalization. To further enhance training efficiency, we propose the Selective Sample Buffer (SSB) mechanism, which effectively counters the ``Vanishing Advantages'' dilemma inherent in Group Relative Policy Optimization (GRPO) by prioritizing high-value samples throughout the optimization process. Notably, we observe that excessive reinforcement signals can induce visual hallucinations--a phenomenon we systematically monitor and mitigate through calibrated reward thresholds throughout the training process. Empirical results affirm the exceptional capability of R1V2, with benchmark-leading performances such as 62.6 on OlympiadBench, 79.0 on AIME2024, 63.6 on LiveCodeBench, and 74.0 on MMMU. These results underscore R1V2's superiority over existing open-source models and demonstrate significant progress in closing the performance gap with premier proprietary systems, including Gemini 2.5 and OpenAI o4-mini. The Skywork R1V2 model weights have been publicly released to promote openness and reproducibility https://huggingface.co/Skywork/Skywork-R1V2-38B.
Authors: Ole-Christian Galbo Engstr{\o}m, Erik Schou Dreier, Birthe M{\o}ller Jespersen, Kim Steenstrup Pedersen
Abstract: We provide an open-source dataset of RGB and NIR-HSI (near-infrared hyperspectral imaging) images with associated segmentation masks and NIR spectra of 2242 individual malting barley kernels. We imaged every kernel pre-exposure to moisture and every 24 hours after exposure to moisture for five consecutive days. Every barley kernel was labeled as germinated or not germinated during each image acquisition. The barley kernels were imaged with black filter paper as the background, facilitating straight-forward intensity threshold-based segmentation, e.g., by Otsu's method. This dataset facilitates time series analysis of germination time for barley kernels using either RGB image analysis, NIR spectral analysis, NIR-HSI analysis, or a combination hereof.
Authors: Wenping Ma, Boyou Xue, Mengru Ma, Chuang Chen, Hekai Zhang, Hao Zhu
Abstract: Multispectral (MS) and panchromatic (PAN) images describe the same land surface, so these images not only have their own advantages, but also have a lot of similar information. In order to separate these similar information and their respective advantages, reduce the feature redundancy in the fusion stage. This paper introduces a diff-attention aware state space fusion model (DAS2F-Model) for multimodal remote sensing image classification. Based on the selective state space model, a cross-modal diff-attention module (CMDA-Module) is designed to extract and separate the common features and their respective dominant features of MS and PAN images. Among this, space preserving visual mamba (SPVM) retains image spatial features and captures local features by optimizing visual mamba's input reasonably. Considering that features in the fusion stage will have large semantic differences after feature separation and simple fusion operations struggle to effectively integrate these significantly different features, an attention-aware linear fusion module (AALF-Module) is proposed. It performs pixel-wise linear fusion by calculating influence coefficients. This mechanism can fuse features with large semantic differences while keeping the feature size unchanged. Empirical evaluations indicate that the presented method achieves better results than alternative approaches. The relevant code can be found at:https://github.com/AVKSKVL/DAS-F-Model
Authors: Gerardus Croonen, Andreas Trondl, Julia Simon, Daniel Steininger
Abstract: While sugar beets are stored prior to processing, they lose sugar due to factors such as microorganisms present in adherent soil and excess vegetation. Their automated visual inspection promises to aide in quality assurance and thereby increase efficiency throughout the processing chain of sugar production. In this work, we present a novel high-quality annotated dataset and two-stage method for the detection, semantic segmentation and mass estimation of post-harvest and post-storage sugar beets in monocular RGB images. We conduct extensive ablation experiments for the detection of sugar beets and their fine-grained semantic segmentation regarding damages, rot, soil adhesion and excess vegetation. For these tasks, we evaluate multiple image sizes, model architectures and encoders, as well as the influence of environmental conditions. Our experiments show an mAP50-95 of 98.8 for sugar-beet detection and an mIoU of 64.0 for the best-performing segmentation model.
Authors: Xinru Meng, Han Sun, Jiamei Liu, Ningzhong Liu, Huiyu Zhou
Abstract: Source-free domain adaptation (SFDA), which involves adapting models without access to source data, is both demanding and challenging. Existing SFDA techniques typically rely on pseudo-labels generated from confidence levels, leading to negative transfer due to significant noise. To tackle this problem, Energy-Based Pseudo-Label Refining (EBPR) is proposed for SFDA. Pseudo-labels are created for all sample clusters according to their energy scores. Global and class energy thresholds are computed to selectively filter pseudo-labels. Furthermore, a contrastive learning strategy is introduced to filter difficult samples, aligning them with their augmented versions to learn more discriminative features. Our method is validated on the Office-31, Office-Home, and VisDA-C datasets, consistently finding that our model outperformed state-of-the-art methods.
Authors: Yingjie Xi, Jian Jun Zhang, Xiaosong Yang
Abstract: In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level semantic guidance but struggle to describe complex actions accurately; trajectory-based techniques provide intuitive global motion direction yet often fall short in generating precise or customized character movements; and anchor poses-guided methods are typically confined to synthesize only simple motion patterns. To generate more controllable and precise human motions, we propose \textbf{ProMoGen (Progressive Motion Generation)}, a novel framework that integrates trajectory guidance with sparse anchor motion control. Global trajectories ensure consistency in spatial direction and displacement, while sparse anchor motions only deliver precise action guidance without displacement. This decoupling enables independent refinement of both aspects, resulting in a more controllable, high-fidelity, and sophisticated motion synthesis. ProMoGen supports both dual and single control paradigms within a unified training process. Moreover, we recognize that direct learning from sparse motions is inherently unstable, we introduce \textbf{SAP-CL (Sparse Anchor Posture Curriculum Learning)}, a curriculum learning strategy that progressively adjusts the number of anchors used for guidance, thereby enabling more precise and stable convergence. Extensive experiments demonstrate that ProMoGen excels in synthesizing vivid and diverse motions guided by predefined trajectory and arbitrary anchor frames. Our approach seamlessly integrates personalized motion with structured guidance, significantly outperforming state-of-the-art methods across multiple control scenarios.
Authors: Ali Anaissi, Junaid Akram, Kunal Chaturvedi, Ali Braytee
Abstract: Memes are widely used for humor and cultural commentary, but they are increasingly exploited to spread hateful content. Due to their multimodal nature, hateful memes often evade traditional text-only or image-only detection systems, particularly when they employ subtle or coded references. To address these challenges, we propose a multimodal hate detection framework that integrates key components: OCR to extract embedded text, captioning to describe visual content neutrally, sub-label classification for granular categorization of hateful content, RAG for contextually relevant retrieval, and VQA for iterative analysis of symbolic and contextual cues. This enables the framework to uncover latent signals that simpler pipelines fail to detect. Experimental results on the Facebook Hateful Memes dataset reveal that the proposed framework exceeds the performance of unimodal and conventional multimodal models in both accuracy and AUC-ROC.
Authors: Zhiyuan Fan (May), Yumeng Wang (May), Sandeep Polisetty (May), Yi R. (May), Fung
Abstract: Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V$^2$R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment. Through extensive evaluation on 21 LVLMs, we reveal a surprising vulnerability to visual variations, in which even advanced models that excel at complex vision-language tasks significantly underperform on simple tasks such as object recognition. Interestingly, these models exhibit a distinct visual position bias that contradicts theories of effective receptive fields, and demonstrate a human-like visual acuity threshold. To identify the source of these vulnerabilities, we present a systematic framework for component-level analysis, featuring a novel visualization approach for aligned visual features. Results show that these vulnerabilities stem from error accumulation in the pipeline architecture and inadequate multimodal alignment. Complementary experiments with synthetic data further demonstrate that these limitations are fundamentally architectural deficiencies, scoring the need for architectural innovations in future LVLM designs.
Authors: Tristan Piater, Bj\"orn Barz, Alexander Freytag
Abstract: The Segment Anything Model (SAM) is widely used for segmenting a diverse range of objects in natural images from simple user prompts like points or bounding boxes. However, SAM's performance decreases substantially when applied to non-natural domains like microscopic imaging. Furthermore, due to SAM's interactive design, it requires a precise prompt for each image and object, which is unfeasible in many automated biomedical applications. Previous solutions adapt SAM by training millions of parameters via fine-tuning large parts of the model or of adapter layers. In contrast, we show that as little as 2,048 additional parameters are sufficient for turning SAM into a use-case specialist for a certain downstream task. Our novel PTSAM (prompt-tuned SAM) method uses prompt-tuning, a parameter-efficient fine-tuning technique, to adapt SAM for a specific task. We validate the performance of our approach on multiple microscopic and one medical dataset. Our results show that prompt-tuning only SAM's mask decoder already leads to a performance on-par with state-of-the-art techniques while requiring roughly 2,000x less trainable parameters. For addressing domain gaps, we find that additionally prompt-tuning SAM's image encoder is beneficial, further improving segmentation accuracy by up to 18% over state-of-the-art results. Since PTSAM can be reliably trained with as little as 16 annotated images, we find it particularly helpful for applications with limited training data and domain shifts.
Authors: Farhad G. Zanjani, Davide Abati, Auke Wiggers, Dimitris Kalatzis, Jens Petersen, Hong Cai, Amirhossein Habibian
Abstract: We investigate data augmentation for 3D object detection in autonomous driving. We utilize recent advancements in 3D reconstruction based on Gaussian Splatting for 3D object placement in driving scenes. Unlike existing diffusion-based methods that synthesize images conditioned on BEV layouts, our approach places 3D objects directly in the reconstructed 3D space with explicitly imposed geometric transformations. This ensures both the physical plausibility of object placement and highly accurate 3D pose and position annotations. Our experiments demonstrate that even by integrating a limited number of external 3D objects into real scenes, the augmented data significantly enhances 3D object detection performance and outperforms existing diffusion-based 3D augmentation for object detection. Extensive testing on the nuScenes dataset reveals that imposing high geometric diversity in object placement has a greater impact compared to the appearance diversity of objects. Additionally, we show that generating hard examples, either by maximizing detection loss or imposing high visual occlusion in camera images, does not lead to more efficient 3D data augmentation for camera-based 3D object detection in autonomous driving.
Authors: Rupak Bose, Chinedu Innocent Nwoye, Jorge Lazo, Jo\"el Lukas Lavanchy, Nicolas Padoy
Abstract: Intraoperative adverse events (IAEs), such as bleeding or thermal injury, can lead to severe postoperative complications if undetected. However, their rarity results in highly imbalanced datasets, posing challenges for AI-based detection and severity quantification. We propose BetaMixer, a novel deep learning model that addresses these challenges through a Beta distribution-based mixing approach, converting discrete IAE severity scores into continuous values for precise severity regression (0-5 scale). BetaMixer employs Beta distribution-based sampling to enhance underrepresented classes and regularizes intermediate embeddings to maintain a structured feature space. A generative approach aligns the feature space with sampled IAE severity, enabling robust classification and severity regression via a transformer. Evaluated on the MultiBypass140 dataset, which we extended with IAE labels, BetaMixer achieves a weighted F1 score of 0.76, recall of 0.81, PPV of 0.73, and NPV of 0.84, demonstrating strong performance on imbalanced data. By integrating Beta distribution-based sampling, feature mixing, and generative modeling, BetaMixer offers a robust solution for IAE detection and quantification in clinical settings.
Authors: Lakshita Agarwal, Bindu Verma
Abstract: Image description generation is essential for accessibility and AI understanding of visual content. Recent advancements in deep learning have significantly improved natural language processing and computer vision. In this work, we propose Tri-FusionNet, a novel image description generation model that integrates transformer modules: a Vision Transformer (ViT) encoder module with dual-attention mechanism, a Robustly Optimized BERT Approach (RoBERTa) decoder module, and a Contrastive Language-Image Pre-Training (CLIP) integrating module. The ViT encoder, enhanced with dual attention, focuses on relevant spatial regions and linguistic context, improving image feature extraction. The RoBERTa decoder is employed to generate precise textual descriptions. CLIP's integrating module aligns visual and textual data through contrastive learning, ensuring effective combination of both modalities. This fusion of ViT, RoBERTa, and CLIP, along with dual attention, enables the model to produce more accurate, contextually rich, and flexible descriptions. The proposed framework demonstrated competitive performance on the Flickr30k and Flickr8k datasets, with BLEU scores ranging from 0.767 to 0.456 and 0.784 to 0.479, CIDEr scores of 1.679 and 1.483, METEOR scores of 0.478 and 0.358, and ROUGE-L scores of 0.567 and 0.789, respectively. On MS-COCO, the framework obtained BLEU scores of 0.893 (B-1), 0.821 (B-2), 0.794 (B-3), and 0.725 (B-4). The results demonstrate the effectiveness of Tri-FusionNet in generating high-quality image descriptions.
Authors: Lakshita Agarwal, Bindu Verma
Abstract: Understanding and analyzing video actions are essential for producing insightful and contextualized descriptions, especially for video-based applications like intelligent monitoring and autonomous systems. The proposed work introduces a novel framework for generating natural language descriptions from video datasets by combining textual and visual modalities. The suggested architecture makes use of ResNet50 to extract visual features from video frames that are taken from the Microsoft Research Video Description Corpus (MSVD), and Berkeley DeepDrive eXplanation (BDD-X) datasets. The extracted visual characteristics are converted into patch embeddings and then run through an encoder-decoder model based on Generative Pre-trained Transformer-2 (GPT-2). In order to align textual and visual representations and guarantee high-quality description production, the system uses multi-head self-attention and cross-attention techniques. The model's efficacy is demonstrated by performance evaluation using BLEU (1-4), CIDEr, METEOR, and ROUGE-L. The suggested framework outperforms traditional methods with BLEU-4 scores of 0.755 (BDD-X) and 0.778 (MSVD), CIDEr scores of 1.235 (BDD-X) and 1.315 (MSVD), METEOR scores of 0.312 (BDD-X) and 0.329 (MSVD), and ROUGE-L scores of 0.782 (BDD-X) and 0.795 (MSVD). By producing human-like, contextually relevant descriptions, strengthening interpretability, and improving real-world applications, this research advances explainable AI.
Authors: Xiaoxing Hu, Kaicheng Yang, Jun Wang, Haoran Xu, Ziyong Feng, Yupei Wang
Abstract: Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional concepts, such as relations and attributes. Although recent studies employ global hard negative samples to improve compositional understanding, these methods significantly compromise the model's inherent general capabilities by forcibly distancing textual negative samples from images in the embedding space. To overcome this limitation, we introduce a Decoupled Global-Local Alignment (DeGLA) framework that improves compositional understanding while substantially mitigating losses in general capabilities. To optimize the retention of the model's inherent capabilities, we incorporate a self-distillation mechanism within the global alignment process, aligning the learnable image-text encoder with a frozen teacher model derived from an exponential moving average. Under the constraint of self-distillation, it effectively mitigates the catastrophic forgetting of pretrained knowledge during fine-tuning. To improve compositional understanding, we first leverage the in-context learning capability of Large Language Models (LLMs) to construct about 2M high-quality negative captions across five types. Subsequently, we propose the Image-Grounded Contrast (IGC) loss and Text-Grounded Contrast (TGC) loss to enhance vision-language compositionally. Extensive experimental results demonstrate the effectiveness of the DeGLA framework. Compared to previous state-of-the-art methods, DeGLA achieves an average enhancement of 3.5% across the VALSE, SugarCrepe, and ARO benchmarks. Concurrently, it obtains an average performance improvement of 13.0% on zero-shot classification tasks across eleven datasets. Our code will be released at https://github.com/xiaoxing2001/DeGLA
Authors: Joe Hrzich, Michael A. Beck, Christopher P. Bidinosti, Christopher J. Henry, Kalhari Manawasinghe, Karen Tanino
Abstract: We present an open-source, low-cost photogrammetry system for 3D plant modeling and phenotyping. The system uses a structure-from-motion approach to reconstruct 3D representations of the plants via point clouds. Using wheat as an example, we demonstrate how various phenotypic traits can be computed easily from the point clouds. These include standard measurements such as plant height and radius, as well as features that would be more cumbersome to measure by hand, such as leaf angles and convex hull. We further demonstrate the utility of the system through the investigation of specific metrics that may yield objective classifications of erectophile versus planophile wheat canopy architectures.
Authors: Ruben Gonzalez Avil\'es, Linus Scheibenreif, Nassim Ait Ali Braham, Benedikt Blumenstiel, Thomas Brunschwiler, Ranjini Guruprasad, Damian Borth, Conrad Albrecht, Paolo Fraccaro, Devyani Lambhate, Johannes Jakubik
Abstract: Hyperspectral imaging provides detailed spectral information and holds significant potential for monitoring of greenhouse gases (GHGs). However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging offers broader spatial and temporal coverage but often lacks the spectral detail that can enhance GHG detection. To address these challenges, this study proposes a spectral transformer model that synthesizes hyperspectral data from multispectral inputs. The model is pre-trained via a band-wise masked autoencoder and subsequently fine-tuned on spatio-temporally aligned multispectral-hyperspectral image pairs. The resulting synthetic hyperspectral data retain the spatial and temporal benefits of multispectral imagery and improve GHG prediction accuracy relative to using multispectral data alone. This approach effectively bridges the trade-off between spectral resolution and coverage, highlighting its potential to advance atmospheric monitoring by combining the strengths of hyperspectral and multispectral systems with self-supervised deep learning.
Authors: Chenxi Duan
Abstract: Addressing gaps caused by cloud cover and the long revisit cycle of satellites is vital for providing essential data to support remote sensing applications. This paper tackles the challenges of missing optical data synthesis, particularly in complex scenarios with cloud cover. We propose CRSynthNet, a novel image synthesis network that incorporates innovative designed modules such as the DownUp Block and Fusion Attention to enhance accuracy. Experimental results validate the effectiveness of CRSynthNet, demonstrating substantial improvements in restoring structural details, preserving spectral consist, and achieving superior visual effects that far exceed those produced by comparison methods. It achieves quantitative improvements across multiple metrics: a peak signal-to-noise ratio (PSNR) of 26.978, a structural similarity index measure (SSIM) of 0.648, and a root mean square error (RMSE) of 0.050. Furthermore, this study creates the TCSEN12 dataset, a valuable resource specifically designed to address cloud cover challenges in missing optical data synthesis study. The dataset uniquely includes cloud-covered images and leverages earlier image to predict later image, offering a realistic representation of real-world scenarios. This study offer practical method and valuable resources for optical satellite image synthesis task.
Authors: Ruotong Wang, Mingli Zhu, Jiarong Ou, Rui Chen, Xin Tao, Pengfei Wan, Baoyuan Wu
Abstract: Text-to-video (T2V) generative models have rapidly advanced and found widespread applications across fields like entertainment, education, and marketing. However, the adversarial vulnerabilities of these models remain rarely explored. We observe that in T2V generation tasks, the generated videos often contain substantial redundant information not explicitly specified in the text prompts, such as environmental elements, secondary objects, and additional details, providing opportunities for malicious attackers to embed hidden harmful content. Exploiting this inherent redundancy, we introduce BadVideo, the first backdoor attack framework tailored for T2V generation. Our attack focuses on designing target adversarial outputs through two key strategies: (1) Spatio-Temporal Composition, which combines different spatiotemporal features to encode malicious information; (2) Dynamic Element Transformation, which introduces transformations in redundant elements over time to convey malicious information. Based on these strategies, the attacker's malicious target seamlessly integrates with the user's textual instructions, providing high stealthiness. Moreover, by exploiting the temporal dimension of videos, our attack successfully evades traditional content moderation systems that primarily analyze spatial information within individual frames. Extensive experiments demonstrate that BadVideo achieves high attack success rates while preserving original semantics and maintaining excellent performance on clean inputs. Overall, our work reveals the adversarial vulnerability of T2V models, calling attention to potential risks and misuse. Our project page is at https://wrt2000.github.io/BadVideo2025/.
Authors: Chong Mou, Yanze Wu, Wenxu Wu, Zinan Guo, Pengze Zhang, Yufeng Cheng, Yiming Luo, Fei Ding, Shiwen Zhang, Xinghui Li, Mengtian Li, Songtao Zhao, Jian Zhang, Qian He, Xinglong Wu
Abstract: Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative models. However, most approaches are designed for specific tasks, restricting their generalizability to combine different types of condition. Developing a unified framework for image customization remains an open challenge. In this paper, we present DreamO, an image customization framework designed to support a wide range of tasks while facilitating seamless integration of multiple conditions. Specifically, DreamO utilizes a diffusion transformer (DiT) framework to uniformly process input of different types. During training, we construct a large-scale training dataset that includes various customization tasks, and we introduce a feature routing constraint to facilitate the precise querying of relevant information from reference images. Additionally, we design a placeholder strategy that associates specific placeholders with conditions at particular positions, enabling control over the placement of conditions in the generated results. Moreover, we employ a progressive training strategy consisting of three stages: an initial stage focused on simple tasks with limited data to establish baseline consistency, a full-scale training stage to comprehensively enhance the customization capabilities, and a final quality alignment stage to correct quality biases introduced by low-quality data. Extensive experiments demonstrate that the proposed DreamO can effectively perform various image customization tasks with high quality and flexibly integrate different types of control conditions.
Authors: Ali Hassani, Fengzhe Zhou, Aditya Kane, Jiannan Huang, Chieh-Yun Chen, Min Shi, Steven Walton, Markus Hoehnerbach, Vijay Thakkar, Michael Isaev, Qinsheng Zhang, Bing Xu, Haicheng Wu, Wen-mei Hwu, Ming-Yu Liu, Humphrey Shi
Abstract: Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the level of complexity in attention infrastructure, and the rapid evolution of AI hardware architecture. At the same time, many state-of-the-art foundational models, particularly in computer vision, are heavily bound by attention, and need reliable sparsity to escape the O(n^2) complexity. In this paper, we study a class of promising sparse attention mechanisms that focus on locality, and aim to develop a better analytical model of their performance improvements. We first introduce Generalized Neighborhood Attention (GNA), which can describe sliding window, strided sliding window, and blocked attention. We then consider possible design choices in implementing these approaches, and create a simulator that can provide much more realistic speedup upper bounds for any given setting. Finally, we implement GNA on top of a state-of-the-art fused multi-headed attention (FMHA) kernel designed for the NVIDIA Blackwell architecture in CUTLASS. Our implementation can fully realize the maximum speedup theoretically possible in many perfectly block-sparse cases, and achieves an effective utilization of 1.3 petaFLOPs/second in FP16. In addition, we plug various GNA configurations into off-the-shelf generative models, such as Cosmos-7B, HunyuanVideo, and FLUX, and show that it can deliver 28% to 46% end-to-end speedup on B200 without any fine-tuning. We will open source our simulator and Blackwell kernels directly through the NATTEN project.
Authors: David Yan, Alexander Raistrick, Jia Deng
Abstract: Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains largely unexplored. We investigate the design space of synthetic datasets by varying the parameters of a procedural dataset generator, and report the effects on zero-shot stereo matching performance using standard benchmarks. We collect the best settings to produce Infinigen-Stereo, a procedural generator specifically optimized for zero-shot stereo datasets. Models trained only on data from our system outperform robust baselines trained on a combination of existing synthetic datasets and have stronger zero-shot stereo matching performance than public checkpoints from prior works. We open source our system at https://github.com/princeton-vl/InfinigenStereo to enable further research on procedural stereo datasets.
Authors: Jiaxing Xu, Kai He, Yue Tang, Wei Li, Mengcheng Lan, Xia Dong, Yiping Ke, Mengling Feng
Abstract: Neurological conditions, such as Alzheimer's Disease, are challenging to diagnose, particularly in the early stages where symptoms closely resemble healthy controls. Existing brain network analysis methods primarily focus on graph-based models that rely solely on imaging data, which may overlook important non-imaging factors and limit the model's predictive power and interpretability. In this paper, we present BrainPrompt, an innovative framework that enhances Graph Neural Networks (GNNs) by integrating Large Language Models (LLMs) with knowledge-driven prompts, enabling more effective capture of complex, non-imaging information and external knowledge for neurological disease identification. BrainPrompt integrates three types of knowledge-driven prompts: (1) ROI-level prompts to encode the identity and function of each brain region, (2) subject-level prompts that incorporate demographic information, and (3) disease-level prompts to capture the temporal progression of disease. By leveraging these multi-level prompts, BrainPrompt effectively harnesses knowledge-enhanced multi-modal information from LLMs, enhancing the model's capability to predict neurological disease stages and meanwhile offers more interpretable results. We evaluate BrainPrompt on two resting-state functional Magnetic Resonance Imaging (fMRI) datasets from neurological disorders, showing its superiority over state-of-the-art methods. Additionally, a biomarker study demonstrates the framework's ability to extract valuable and interpretable information aligned with domain knowledge in neuroscience.
Authors: Obed Korshie Dzikunu, Amirhossein Toosi, Shadab Ahamed, Sara Harsini, Francois Benard, Xiaoxiao Li, Arman Rahmim
Abstract: This study performs a comprehensive evaluation of quantitative measurements as extracted from automated deep-learning-based segmentation methods, beyond traditional Dice Similarity Coefficient assessments, focusing on six quantitative metrics, namely SUVmax, SUVmean, total lesion activity (TLA), tumor volume (TMTV), lesion count, and lesion spread. We analyzed 380 prostate-specific membrane antigen (PSMA) targeted [18F]DCFPyL PET/CT scans of patients with biochemical recurrence of prostate cancer, training deep neural networks, U-Net, Attention U-Net and SegResNet with four loss functions: Dice Loss, Dice Cross Entropy, Dice Focal Loss, and our proposed L1 weighted Dice Focal Loss (L1DFL). Evaluations indicated that Attention U-Net paired with L1DFL achieved the strongest correlation with the ground truth (concordance correlation = 0.90-0.99 for SUVmax and TLA), whereas models employing the Dice Loss and the other two compound losses, particularly with SegResNet, underperformed. Equivalence testing (TOST, alpha = 0.05, Delta = 20%) confirmed high performance for SUV metrics, lesion count and TLA, with L1DFL yielding the best performance. By contrast, tumor volume and lesion spread exhibited greater variability. Bland-Altman, Coverage Probability, and Total Deviation Index analyses further highlighted that our proposed L1DFL minimizes variability in quantification of the ground truth clinical measures. The code is publicly available at: https://github.com/ObedDzik/pca\_segment.git.
Authors: Jannis Born, Filip Skogh, Kahn Rhrissorrakrai, Filippo Utro, Nico Wagner, Aleksandros Sobczyk
Abstract: At the core of the Transformer, the Softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often destabilizes training and that enforcing the attention matrix to be doubly stochastic (through Sinkhorn's algorithm) consistently improves performance across different tasks, domains and Transformer flavors. However, Sinkhorn's algorithm is iterative, approximative, non-parametric and thus inflexible w.r.t. the obtained doubly stochastic matrix (DSM). Recently, it has been proven that DSMs can be obtained with a parametric quantum circuit, yielding a novel quantum inductive bias for DSMs with no known classical analogue. Motivated by this, we demonstrate the feasibility of a hybrid classical-quantum doubly stochastic Transformer (QDSFormer) that replaces the Softmax in the self-attention layer with a variational quantum circuit. We study the expressive power of the circuit and find that it yields more diverse DSMs that better preserve information than classical operators. Across multiple small-scale object recognition tasks, we find that our QDSFormer consistently surpasses both a standard Vision Transformer and other doubly stochastic Transformers. Beyond the established Sinkformer, this comparison includes a novel quantum-inspired doubly stochastic Transformer (based on QR decomposition) that can be of independent interest. The QDSFormer also shows improved training stability and lower performance variation suggesting that it may mitigate the notoriously unstable training of ViTs on small-scale data.
Authors: Abhishek Jana, Moeumu Uili, James Atherton, Mark O'Brien, Joe Wood, Leandra Brickson
Abstract: This paper presents an automated one-shot bird call classification pipeline designed for rare species absent from large publicly available classifiers like BirdNET and Perch. While these models excel at detecting common birds with abundant training data, they lack options for species with only 1-3 known recordings-a critical limitation for conservationists monitoring the last remaining individuals of endangered birds. To address this, we leverage the embedding space of large bird classification networks and develop a classifier using cosine similarity, combined with filtering and denoising preprocessing techniques, to optimize detection with minimal training data. We evaluate various embedding spaces using clustering metrics and validate our approach in both a simulated scenario with Xeno-Canto recordings and a real-world test on the critically endangered tooth-billed pigeon (Didunculus strigirostris), which has no existing classifiers and only three confirmed recordings. The final model achieved 1.0 recall and 0.95 accuracy in detecting tooth-billed pigeon calls, making it practical for use in the field. This open-source system provides a practical tool for conservationists seeking to detect and monitor rare species on the brink of extinction.
Authors: Yanlin Zhou, Mostafa El-Khamy, Kee-Bong Song
Abstract: Differentiable Architecture Search (DARTS) is an efficient Neural Architecture Search (NAS) method but suffers from robustness, generalization, and discrepancy issues. Many efforts have been made towards the performance collapse issue caused by skip dominance with various regularization techniques towards operation weights, path weights, noise injection, and super-network redesign. It had become questionable at a certain point if there could exist a better and more elegant way to retract the search to its intended goal -- NAS is a selection problem. In this paper, we undertake a simple but effective approach, named Smooth Activation DARTS (SA-DARTS), to overcome skip dominance and discretization discrepancy challenges. By leveraging a smooth activation function on architecture weights as an auxiliary loss, our SA-DARTS mitigates the unfair advantage of weight-free operations, converging to fanned-out architecture weight values, and can recover the search process from skip-dominance initialization. Through theoretical and empirical analysis, we demonstrate that the SA-DARTS can yield new state-of-the-art (SOTA) results on NAS-Bench-201, classification, and super-resolution. Further, we show that SA-DARTS can help improve the performance of SOTA models with fewer parameters, such as Information Multi-distillation Network on the super-resolution task.
Authors: Andrew Ilyas, Logan Engstrom
Abstract: The goal of predictive data attribution is to estimate how adding or removing a given set of training datapoints will affect model predictions. In convex settings, this goal is straightforward (i.e., via the infinitesimal jackknife). In large-scale (non-convex) settings, however, existing methods are far less successful -- current methods' estimates often only weakly correlate with ground truth. In this work, we present a new data attribution method (MAGIC) that combines classical methods and recent advances in metadifferentiation to (nearly) optimally estimate the effect of adding or removing training data on model predictions.
Authors: Zhongtao Wang, Mai Su, Huishan Au, Yilong Li, Xizhe Cao, Chengwei Pan, Yisong Chen, Guoping Wang
Abstract: As urban 3D scenes become increasingly complex and the demand for high-quality rendering grows, efficient scene reconstruction and rendering techniques become crucial. We present HUG, a novel approach to address inefficiencies in handling large-scale urban environments and intricate details based on 3D Gaussian splatting. Our method optimizes data partitioning and the reconstruction pipeline by incorporating a hierarchical neural Gaussian representation. We employ an enhanced block-based reconstruction pipeline focusing on improving reconstruction quality within each block and reducing the need for redundant training regions around block boundaries. By integrating neural Gaussian representation with a hierarchical architecture, we achieve high-quality scene rendering at a low computational cost. This is demonstrated by our state-of-the-art results on public benchmarks, which prove the effectiveness and advantages in large-scale urban scene representation.
Authors: Zhaohan Daniel Guo, Bernardo Avila Pires, Khimya Khetarpal, Dale Schuurmans, Bo Dai
Abstract: Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al., 2020) or BYOL (Grill et al., 2020) have been very successful at learning meaningful latent representations from unlabeled image data, resulting in much more general and transferable representations for downstream tasks. Broadly, self-supervised methods fall into two types: 1) Contrastive methods, such as SimCLR; and 2) Non-Contrastive methods, such as BYOL. Contrastive methods are generally trying to maximize mutual information between related data points, so they need to compare every data point to every other data point, resulting in high variance, and thus requiring large batch sizes to work well. Non-contrastive methods like BYOL have much lower variance as they do not need to make pairwise comparisons, but are much trickier to implement as they have the possibility of collapsing to a constant vector. In this paper, we aim to develop a self-supervised objective that combines the strength of both types. We start with a particular contrastive method called the Spectral Contrastive Loss (HaoChen et al., 2021; Lu et al., 2024), and we convert it into a more general non-contrastive form; this removes the pairwise comparisons resulting in lower variance, but keeps the mutual information formulation of the contrastive method preventing collapse. We call our new objective the Mutual Information Non-Contrastive (MINC) loss. We test MINC by learning image representations on ImageNet (similar to SimCLR and BYOL) and show that it consistently improves upon the Spectral Contrastive loss baseline.
Authors: Jialiang Zhang, Feng Gao, Yanhai Gan, Junyu Dong, Qian Du
Abstract: Accurately forecasting sea ice concentration (SIC) in the Arctic is critical to global ecosystem health and navigation safety. However, current methods still is confronted with two challenges: 1) these methods rarely explore the long-term feature dependencies in the frequency domain. 2) they can hardly preserve the high-frequency details, and the changes in the marginal area of the sea ice cannot be accurately captured. To this end, we present a Frequency-Compensated Network (FCNet) for Arctic SIC prediction on a daily basis. In particular, we design a dual-branch network, including branches for frequency feature extraction and convolutional feature extraction. For frequency feature extraction, we design an adaptive frequency filter block, which integrates trainable layers with Fourier-based filters. By adding frequency features, the FCNet can achieve refined prediction of edges and details. For convolutional feature extraction, we propose a high-frequency enhancement block to separate high and low-frequency information. Moreover, high-frequency features are enhanced via channel-wise attention, and temporal attention unit is employed for low-frequency feature extraction to capture long-range sea ice changes. Extensive experiments are conducted on a satellite-derived daily SIC dataset, and the results verify the effectiveness of the proposed FCNet. Our codes and data will be made public available at: https://github.com/oucailab/FCNet .
Authors: Edison Mucllari, Aswin Raghavan, Zachary Alan Daniels
Abstract: Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks while minimizing forgetting of previous tasks.However, CL opens up avenues for noise to enter the training pipeline and disrupt the CL. This work focuses on label noise and instance noise in the context of class-incremental learning (CIL), where new classes are added to a classifier over time, and there is no access to external data from past classes. We aim to understand the sensitivity of CL methods that work by replaying items from a memory constructed using the idea of Coresets. We derive a new bound for the robustness of such a method to uncorrelated instance noise under a general additive noise threat model, revealing several insights. Putting the theory into practice, we create two continual learning algorithms to construct noise-tolerant replay buffers. We empirically compare the effectiveness of prior memory-based continual learners and the proposed algorithms under label and uncorrelated instance noise on five diverse datasets. We show that existing memory-based CL are not robust whereas the proposed methods exhibit significant improvements in maximizing classification accuracy and minimizing forgetting in the noisy CIL setting.
Authors: Lakshita Agarwal, Bindu Verma
Abstract: The examination of chest X-ray images is a crucial component in detecting various thoracic illnesses. This study introduces a new image description generation model that integrates a Vision Transformer (ViT) encoder with cross-modal attention and a GPT-4-based transformer decoder. The ViT captures high-quality visual features from chest X-rays, which are fused with text data through cross-modal attention to improve the accuracy, context, and richness of image descriptions. The GPT-4 decoder transforms these fused features into accurate and relevant captions. The model was tested on the National Institutes of Health (NIH) and Indiana University (IU) Chest X-ray datasets. On the IU dataset, it achieved scores of 0.854 (B-1), 0.883 (CIDEr), 0.759 (METEOR), and 0.712 (ROUGE-L). On the NIH dataset, it achieved the best performance on all metrics: BLEU 1--4 (0.825, 0.788, 0.765, 0.752), CIDEr (0.857), METEOR (0.726), and ROUGE-L (0.705). This framework has the potential to enhance chest X-ray evaluation, assisting radiologists in more precise and efficient diagnosis.
Authors: Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, Vince D. Calhoun
Abstract: Multimodal neuroimaging provides complementary structural and functional insights into both human brain organization and disease-related dynamics. Recent studies demonstrate enhanced diagnostic sensitivity for Alzheimer's disease (AD) through synergistic integration of neuroimaging data (e.g., sMRI, fMRI) with behavioral cognitive scores tabular data biomarkers. However, the intrinsic heterogeneity across modalities (e.g., 4D spatiotemporal fMRI dynamics vs. 3D anatomical sMRI structure) presents critical challenges for discriminative feature fusion. To bridge this gap, we propose M2M-AlignNet: a geometry-aware multimodal co-attention network with latent alignment for early AD diagnosis using sMRI and fMRI. At the core of our approach is a multi-patch-to-multi-patch (M2M) contrastive loss function that quantifies and reduces representational discrepancies via geometry-weighted patch correspondence, explicitly aligning fMRI components across brain regions with their sMRI structural substrates without one-to-one constraints. Additionally, we propose a latent-as-query co-attention module to autonomously discover fusion patterns, circumventing modality prioritization biases while minimizing feature redundancy. We conduct extensive experiments to confirm the effectiveness of our method and highlight the correspondance between fMRI and sMRI as AD biomarkers.
Authors: Shaden Alshammari, John Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton
Abstract: As the field of representation learning grows, there has been a proliferation of different loss functions to solve different classes of problems. We introduce a single information-theoretic equation that generalizes a large collection of modern loss functions in machine learning. In particular, we introduce a framework that shows that several broad classes of machine learning methods are precisely minimizing an integrated KL divergence between two conditional distributions: the supervisory and learned representations. This viewpoint exposes a hidden information geometry underlying clustering, spectral methods, dimensionality reduction, contrastive learning, and supervised learning. This framework enables the development of new loss functions by combining successful techniques from across the literature. We not only present a wide array of proofs, connecting over 23 different approaches, but we also leverage these theoretical results to create state-of-the-art unsupervised image classifiers that achieve a +8% improvement over the prior state-of-the-art on unsupervised classification on ImageNet-1K. We also demonstrate that I-Con can be used to derive principled debiasing methods which improve contrastive representation learners.
Authors: Utkarsh Singhal, Yifei Xing, Stella X. Yu
Abstract: We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations. Deep Complex Networks (DCN) extends real-valued algebra to the complex domain without addressing complex-valued scaling. SurReal takes a restrictive manifold view of complex numbers, adopting a distance metric to achieve complex-scaling invariance while losing rich complex-valued information. We analyze complex-valued scaling as a co-domain transformation and design novel equivariant and invariant neural network layer functions for this special transformation. We also propose novel complex-valued representations of RGB images, where complex-valued scaling indicates hue shift or correlated changes across color channels. Benchmarked on MSTAR, CIFAR10, CIFAR100, and SVHN, our co-domain symmetric (CDS) classifiers deliver higher accuracy, better generalization, robustness to co-domain transformations, and lower model bias and variance than DCN and SurReal with far fewer parameters.
Authors: Pei Lin, Sihang Xu, Hongdi Yang, Yiran Liu, Xin Chen, Jingya Wang, Jingyi Yu, Lan Xu
Abstract: Existing hands datasets are largely short-range and the interaction is weak due to the self-occlusion and self-similarity of hands, which can not yet fit the need for interacting hands motion generation. To rescue the data scarcity, we propose HandDiffuse12.5M, a novel dataset that consists of temporal sequences with strong two-hand interactions. HandDiffuse12.5M has the largest scale and richest interactions among the existing two-hand datasets. We further present a strong baseline method HandDiffuse for the controllable motion generation of interacting hands using various controllers. Specifically, we apply the diffusion model as the backbone and design two motion representations for different controllers. To reduce artifacts, we also propose Interaction Loss which explicitly quantifies the dynamic interaction process. Our HandDiffuse enables various applications with vivid two-hand interactions, i.e., motion in-betweening and trajectory control. Experiments show that our method outperforms the state-of-the-art techniques in motion generation and can also contribute to data augmentation for other datasets. Our dataset, corresponding codes, and pre-trained models will be disseminated to the community for future research towards two-hand interaction modeling.
Authors: Yirui Wang, Qinji Yu, Ke Yan, Haoshen Li, Dazhou Guo, Li Zhang, Le Lu, Na Shen, Qifeng Wang, Xiaowei Ding, Xianghua Ye, Dakai Jin
Abstract: Lymph node (LN) assessment is a critical, indispensable yet very challenging task in the routine clinical workflow of radiology and oncology. Accurate LN analysis is essential for cancer diagnosis, staging, and treatment planning. Finding scatteredly distributed, low-contrast clinically relevant LNs in 3D CT is difficult even for experienced physicians under high inter-observer variations. Previous automatic LN detection works typically yield limited recall and high false positives (FPs) due to adjacent anatomies with similar image intensities, shapes, or textures (vessels, muscles, esophagus, etc). In this work, we propose a new LN DEtection TRansformer, named LN-DETR, to achieve more accurate performance. By enhancing the 2D backbone with a multi-scale 2.5D feature fusion to incorporate 3D context explicitly, more importantly, we make two main contributions to improve the representation quality of LN queries. 1) Considering that LN boundaries are often unclear, an IoU prediction head and a location debiased query selection are proposed to select LN queries of higher localization accuracy as the decoder query's initialization. 2) To reduce FPs, query contrastive learning is employed to explicitly reinforce LN queries towards their best-matched ground-truth queries over unmatched query predictions. Trained and tested on 3D CT scans of 1067 patients (with 10,000+ labeled LNs) via combining seven LN datasets from different body parts (neck, chest, and abdomen) and pathologies/cancers, our method significantly improves the performance of previous leading methods by > 4-5% average recall at the same FP rates in both internal and external testing. We further evaluate on the universal lesion detection task using NIH DeepLesion benchmark, and our method achieves the top performance of 88.46% averaged recall across 0.5 to 4 FPs per image, compared with other leading reported results.
Authors: Xingrui Wang, Wufei Ma, Angtian Wang, Shuo Chen, Adam Kortylewski, Alan Yuille
Abstract: For vision-language models (VLMs), understanding the dynamic properties of objects and their interactions in 3D scenes from videos is crucial for effective reasoning about high-level temporal and action semantics. Although humans are adept at understanding these properties by constructing 3D and temporal (4D) representations of the world, current video understanding models struggle to extract these dynamic semantics, arguably because these models use cross-frame reasoning without underlying knowledge of the 3D/4D scenes. In this work, we introduce DynSuperCLEVR, the first video question answering dataset that focuses on language understanding of the dynamic properties of 3D objects. We concentrate on three physical concepts -- velocity, acceleration, and collisions within 4D scenes. We further generate three types of questions, including factual queries, future predictions, and counterfactual reasoning that involve different aspects of reasoning about these 4D dynamic properties. To further demonstrate the importance of explicit scene representations in answering these 4D dynamics questions, we propose NS-4DPhysics, a Neural-Symbolic VideoQA model integrating Physics prior for 4D dynamic properties with explicit scene representation of videos. Instead of answering the questions directly from the video text input, our method first estimates the 4D world states with a 3D generative model powered by physical priors, and then uses neural symbolic reasoning to answer the questions based on the 4D world states. Our evaluation on all three types of questions in DynSuperCLEVR shows that previous video question answering models and large multimodal models struggle with questions about 4D dynamics, while our NS-4DPhysics significantly outperforms previous state-of-the-art models. Our code and data are released in https://xingruiwang.github.io/projects/DynSuperCLEVR/.
URLs: https://xingruiwang.github.io/projects/DynSuperCLEVR/.
Authors: Jiahao Nie, Fei Xie, Sifan Zhou, Xueyi Zhou, Dong-Kyu Chae, Zhiwei He
Abstract: 3D single object tracking (SOT) methods based on appearance matching has long suffered from insufficient appearance information incurred by incomplete, textureless and semantically deficient LiDAR point clouds. While motion paradigm exploits motion cues instead of appearance matching for tracking, it incurs complex multi-stage processing and segmentation module. In this paper, we first provide in-depth explorations on motion paradigm, which proves that (\textbf{i}) it is feasible to directly infer target relative motion from point clouds across consecutive frames; (\textbf{ii}) fine-grained information comparison between consecutive point clouds facilitates target motion modeling. We thereby propose to perform part-to-part motion modeling for consecutive point clouds and introduce a novel tracking framework, termed \textbf{P2P}. The novel framework fuses each corresponding part information between consecutive point clouds, effectively exploring detailed information changes and thus modeling accurate target-related motion cues. Following this framework, we present P2P-point and P2P-voxel models, incorporating implicit and explicit part-to-part motion modeling by point- and voxel-based representation, respectively. Without bells and whistles, P2P-voxel sets a new state-of-the-art performance ($\sim$\textbf{89\%}, \textbf{72\%} and \textbf{63\%} precision on KITTI, NuScenes and Waymo Open Dataset, respectively). Moreover, under the same point-based representation, P2P-point outperforms the previous motion tracker M$^2$Track by \textbf{3.3\%} and \textbf{6.7\%} on the KITTI and NuScenes, while running at a considerably high speed of \textbf{107 Fps} on a single RTX3090 GPU. The source code and pre-trained models are available at https://github.com/haooozi/P2P.
Authors: Ruixiang Jiang, Changwen Chen
Abstract: Artistic style includes both structural and appearance elements. Existing neural stylization techniques primarily focus on transferring appearance features such as color and texture, often neglecting the equally crucial aspect of structural stylization. In this paper, we present a comprehensive study on the simultaneous stylization of structure and appearance of 2D images. Specifically, we introduce DiffArtist, which, to the best of our knowledge, is the first stylization method to allow for dual controllability over structure and appearance. Our key insight is to represent structure and appearance as separate diffusion processes to achieve complete disentanglement without requiring any training, thereby endowing users with unprecedented controllability for both components. The evaluation of stylization of both appearance and structure, however, remains challenging as it necessitates semantic understanding. To this end, we further propose a Multimodal LLM-based style evaluator, which better aligns with human preferences than metrics lacking semantic understanding. With this powerful evaluator, we conduct extensive analysis, demonstrating that DiffArtist achieves superior style fidelity, editability, and structure-appearance disentanglement. These merits make DiffArtist a highly versatile solution for creative applications. Project homepage: https://github.com/songrise/Artist.
Authors: Alex N. Wang, Christopher Hoang, Yuwen Xiong, Yann LeCun, Mengye Ren
Abstract: Self-supervised learning has driven significant progress in learning from single-subject, iconic images. However, there are still unanswered questions about the use of minimally-curated, naturalistic video data, which contain dense scenes with many independent objects, imbalanced class distributions, and varying object sizes. In this paper, we propose PooDLe, a self-supervised learning method that combines an invariance-based objective on pooled representations with a dense SSL objective that enforces equivariance to optical flow warping. Our results show that a unified objective applied at multiple feature scales is essential for learning effective image representations from naturalistic videos. We validate our method with experiments on the BDD100K driving video dataset and the Walking Tours first-person video dataset, demonstrating its ability to capture spatial understanding from a dense objective and semantic understanding via a pooled representation objective.
Authors: Youngwan Jin, Incheol Park, Hanbin Song, Hyeongjin Ju, Yagiz Nalcakan, Shiho Kim
Abstract: This paper proposes Pix2Next, a novel image-to-image translation framework designed to address the challenge of generating high-quality Near-Infrared (NIR) images from RGB inputs. Our approach leverages a state-of-the-art Vision Foundation Model (VFM) within an encoder-decoder architecture, incorporating cross-attention mechanisms to enhance feature integration. This design captures detailed global representations and preserves essential spectral characteristics, treating RGB-to-NIR translation as more than a simple domain transfer problem. A multi-scale PatchGAN discriminator ensures realistic image generation at various detail levels, while carefully designed loss functions couple global context understanding with local feature preservation. We performed experiments on the RANUS dataset to demonstrate Pix2Next's advantages in quantitative metrics and visual quality, improving the FID score by 34.81% compared to existing methods. Furthermore, we demonstrate the practical utility of Pix2Next by showing improved performance on a downstream object detection task using generated NIR data to augment limited real NIR datasets. The proposed approach enables the scaling up of NIR datasets without additional data acquisition or annotation efforts, potentially accelerating advancements in NIR-based computer vision applications.
Authors: Zhiwu Zheng, Lauren Mentzer, Berk Iskender, Michael Price, Colm Prendergast, Audren Cloitre
Abstract: Robots operating in unstructured environments require a comprehensive understanding of their surroundings, necessitating geometric and semantic information from sensor data. Traditional RGB-D processing pipelines focus primarily on geometric reconstruction, limiting their ability to support advanced robotic perception, planning, and interaction. A key challenge is the lack of generalized methods for segmenting RGB-D data into semantically meaningful components while maintaining accurate geometric representations. We introduce a novel end-to-end modular pipeline that integrates state-of-the-art semantic segmentation, human tracking, point-cloud fusion, and scene reconstruction. Our approach improves semantic segmentation accuracy by leveraging the foundational segmentation model SAM2 with a hybrid method that combines its mask generation with a semantic classification model, resulting in sharper masks and high classification accuracy. Compared to SegFormer and OneFormer, our method achieves a similar semantic segmentation accuracy (mIoU of 47.0% vs 45.9% in the ADE20K dataset) but provides much more precise object boundaries. Additionally, our human tracking algorithm interacts with the segmentation enabling continuous tracking even when objects leave and re-enter the frame by object re-identification. Our point cloud fusion approach reduces computation time by 1.81x while maintaining a small mean reconstruction error of 25.3 mm by leveraging the semantic information. We validate our approach on benchmark datasets and real-world Kinect RGB-D data, demonstrating improved efficiency, accuracy, and usability. Our structured representation, stored in the Universal Scene Description (USD) format, supports efficient querying, visualization, and robotic simulation, making it practical for real-world deployment.
Authors: Jingkai Wang, Jue Gong, Lin Zhang, Zheng Chen, Xing Liu, Hong Gu, Yutong Liu, Yulun Zhang, Xiaokang Yang
Abstract: Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject's identity. In this work, we propose OSDFace, a novel one-step diffusion model for face restoration. Specifically, we propose a visual representation embedder (VRE) to better capture prior information and understand the input face. In VRE, low-quality faces are processed by a visual tokenizer and subsequently embedded with a vector-quantized dictionary to generate visual prompts. Additionally, we incorporate a facial identity loss derived from face recognition to further ensure identity consistency. We further employ a generative adversarial network (GAN) as a guidance model to encourage distribution alignment between the restored face and the ground truth. Experimental results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics, generating high-fidelity, natural face images with high identity consistency. The code and model will be released at https://github.com/jkwang28/OSDFace.
Authors: Di Zhang, Junxian Li, Jingdi Lei, Xunzhi Wang, Yujie Liu, Zonglin Yang, Jiatong Li, Weida Wang, Suorong Yang, Jianbo Wu, Peng Ye, Wanli Ouyang, Dongzhan Zhou
Abstract: Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined reasoning paths. To address these challenges, we introduce Critic-V, a novel framework inspired by the Actor-Critic paradigm to boost the reasoning capability of VLMs. This framework decouples the reasoning process and critic process by integrating two independent components: the Reasoner, which generates reasoning paths based on visual and textual inputs, and the Critic, which provides constructive critique to refine these paths. In this approach, the Reasoner generates reasoning responses according to text prompts, which can evolve iteratively as a policy based on feedback from the Critic. This interaction process was theoretically driven by a reinforcement learning framework where the Critic offers natural language critiques instead of scalar rewards, enabling more nuanced feedback to boost the Reasoner's capability on complex reasoning tasks. The Critic model is trained using Direct Preference Optimization (DPO), leveraging a preference dataset of critiques ranked by Rule-based Reward~(RBR) to enhance its critic capabilities. Evaluation results show that the Critic-V framework significantly outperforms existing methods, including GPT-4V, on 5 out of 8 benchmarks, especially regarding reasoning accuracy and efficiency. Combining a dynamic text-based policy for the Reasoner and constructive feedback from the preference-optimized Critic enables a more reliable and context-sensitive multimodal reasoning process. Our approach provides a promising solution to enhance the reliability of VLMs, improving their performance in real-world reasoning-heavy multimodal applications such as autonomous driving and embodied intelligence.
Authors: Xingyu Liu, Gu Wang, Chengxi Li, Yingyue Li, Chenyangguang Zhang, Ziqin Huang, Xiangyang Ji
Abstract: We present GFreeDet, an unseen object detection approach that leverages Gaussian splatting and vision Foundation models under model-free setting. Unlike existing methods that rely on predefined CAD templates, GFreeDet reconstructs objects directly from reference videos using Gaussian splatting, enabling robust detection of novel objects without prior 3D models. Evaluated on the BOP-H3 benchmark, GFreeDet achieves comparable performance to CAD-based methods, demonstrating the viability of model-free detection for mixed reality (MR) applications. Notably, GFreeDet won the best overall method and the best fast method awards in the model-free 2D detection track at BOP Challenge 2024.
Authors: Viktor Rudnev, Gereon Fox, Mohamed Elgharib, Christian Theobalt, Vladislav Golyanik
Abstract: Volumetric reconstruction of dynamic scenes is an important problem in computer vision. It is especially challenging in poor lighting and with fast motion. This is partly due to limitations of RGB cameras: To capture frames under low lighting, the exposure time needs to be increased, which leads to more motion blur. In contrast, event cameras, which record changes in pixel brightness asynchronously, are much less dependent on lighting, making them more suitable for recording fast motion. We hence propose the first method to spatiotemporally reconstruct a scene from sparse multi-view event streams and sparse RGB frames. We train a sequence of cross-faded time-conditioned NeRF models, one per short recording segment. The individual segments are supervised with a set of event- and RGB-based losses and sparse-view regularisation. We assemble a real-world multi-view camera rig with six static event cameras around the object and record a benchmark multi-view event stream dataset of challenging motions. Our work outperforms RGB-based baselines, producing state-of-the-art results, and opens up the topic of multi-view event-based reconstruction as a new path for fast scene capture beyond RGB cameras. The code and the data will be released soon at https://4dqv.mpi-inf.mpg.de/DynEventNeRF/
Authors: Baocai Yin, Ji Zhao, Huajie Jiang, Ningning Hou, Yongli Hu, Amin Beheshti, Ming-Hsuan Yang, Yuankai Qi
Abstract: Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge, which has high memory requirements. In this paper, we propose a novel lightweight CL framework, Adapter-Enhanced Semantic Prompting (AESP), which integrates prompt tuning and adapter techniques. Specifically, we design semantic-guided prompts to enhance the generalization ability of visual features and utilize adapters to efficiently fuse the semantic information, aiming to learn more adaptive features for the continual learning task. Furthermore, to choose the right task prompt for feature adaptation, we have developed a novel matching mechanism for prompt selection. Extensive experiments on three CL datasets demonstrate that our approach achieves favorable performance across multiple metrics, showing its potential for advancing CL.
Authors: Yangfan He, Sida Li, Jianhui Wang, Kun Li, Xinyuan Song, Xinhang Yuan, Keqin Li, Kuan Lu, Menghao Huo, Jiaqi Chen, Miao Zhang, Xueqian Wang
Abstract: Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating the need for resource-intensive training. However, the frame-independence of T2I generation often results in poor temporal consistency. Existing methods address this issue through temporal layer fine-tuning or inference-based temporal propagation, but these approaches suffer from high training costs or limited temporal coherence. To address these challenges, we propose a General and Efficient Adapter (GE-Adapter) that integrates temporal-spatial and semantic consistency with Baliteral DDIM inversion. This framework introduces three key components: (1) Frame-based Temporal Consistency Blocks (FTC Blocks) to capture frame-specific features and enforce smooth inter-frame transitions via temporally-aware loss functions; (2) Channel-dependent Spatial Consistency Blocks (SCD Blocks) employing bilateral filters to enhance spatial coherence by reducing noise and artifacts; and (3) Token-based Semantic Consistency Module (TSC Module) to maintain semantic alignment using shared prompt tokens and frame-specific tokens. Our method significantly improves perceptual quality, text-image alignment, and temporal coherence, as demonstrated on the MSR-VTT dataset. Additionally, it achieves enhanced fidelity and frame-to-frame coherence, offering a practical solution for T2V editing.
Authors: Hualie Jiang, Zhiqiang Lou, Laiyan Ding, Rui Xu, Minglang Tan, Wenjie Jiang, Rui Huang
Abstract: Stereo matching is a key technique for metric depth estimation in computer vision and robotics. Real-world challenges like occlusion and non-texture hinder accurate disparity estimation from binocular matching cues. Recently, monocular relative depth estimation has shown remarkable generalization using vision foundation models. Thus, to facilitate robust stereo matching with monocular depth cues, we incorporate a robust monocular relative depth model into the recurrent stereo-matching framework, building a new framework for depth foundation model-based stereo-matching, DEFOM-Stereo. In the feature extraction stage, we construct the combined context and matching feature encoder by integrating features from conventional CNNs and DEFOM. In the update stage, we use the depth predicted by DEFOM to initialize the recurrent disparity and introduce a scale update module to refine the disparity at the correct scale. DEFOM-Stereo is verified to have much stronger zero-shot generalization compared with SOTA methods. Moreover, DEFOM-Stereo achieves top performance on the KITTI 2012, KITTI 2015, Middlebury, and ETH3D benchmarks, ranking $1^{st}$ on many metrics. In the joint evaluation under the robust vision challenge, our model simultaneously outperforms previous models on the individual benchmarks, further demonstrating its outstanding capabilities.
Authors: Zixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You, Zheming Lu, Fan Zhang, Shi Guo, Tianfan Xue
Abstract: Capturing high dynamic range (HDR) scenes is one of the most important issues in camera design. Majority of cameras use exposure fusion, which fuses images captured by different exposure levels, to increase dynamic range. However, this approach can only handle images with limited exposure difference, normally 3-4 stops. When applying to very high dynamic range scenes where a large exposure difference is required, this approach often fails due to incorrect alignment or inconsistent lighting between inputs, or tone mapping artifacts. In this work, we propose \model, the first exposure fusion technique that can merge inputs with 9 stops differences. The key idea is that we model exposure fusion as a guided inpainting problem, where the under-exposed image is used as a guidance to fill the missing information of over-exposed highlights in the over-exposed region. Using an under-exposed image as a soft guidance, instead of a hard constraint, our model is robust to potential alignment issue or lighting variations. Moreover, by utilizing the image prior of the generative model, our model also generates natural tone mapping, even for very high-dynamic range scenes. Our approach outperforms HDR-Transformer on latest HDR benchmarks. Moreover, to test its performance in ultra high dynamic range scenes, we capture a new real-world exposure fusion benchmark, UltraFusion dataset, with exposure differences up to 9 stops, and experiments show that UltraFusion can generate beautiful and high-quality fusion results under various scenarios. Code and data will be available at https://openimaginglab.github.io/UltraFusion.
Authors: Nektarios A. Valous, Eckhard Hitzer, Drago\c{s} Du\c{s}e, Rodrigo Rojas Moraleda, Ferdinand Popp, Meggy Suarez-Carmona, Anna Berthel, Ismini Papageorgiou, Carlo Fremd, Alexander R\"olle, Christina C. Westhoff, B\'en\'edicte Lenoir, Niels Halama, Inka Z\"ornig, Dirk J\"ager
Abstract: Hypercomplex image processing extends conventional techniques in a unified paradigm encompassing algebraic and geometric principles. This work leverages quaternions and the two-dimensional orthogonal planes split framework (splitting of a quaternion - representing a pixel - into pairs of orthogonal 2D planes) for natural/biomedical image analysis through the following computational workflows and outcomes: natural/biomedical image re-colorization, natural image de-colorization, natural/biomedical image contrast enhancement, computational re-staining and stain separation in histological images, and performance gains in machine/deep learning pipelines for histological images. The workflows are analyzed separately for natural and biomedical images to showcase the effectiveness of the proposed approaches. The proposed workflows can regulate color appearance (e.g. with alternative renditions and grayscale conversion) and image contrast, be part of automated image processing pipelines (e.g. isolating stain components, boosting learning models), and assist in digital pathology applications (e.g. enhancing biomarker visibility, enabling colorblind-friendly renditions). Employing only basic arithmetic and matrix operations, this work offers a computationally accessible methodology - in the hypercomplex domain - that showcases versatility and consistency across image processing tasks and a range of computer vision and biomedical applications. The proposed non-data-driven methods achieve comparable or better results (particularly in cases involving well-known methods) to those reported in the literature, showcasing the potential of robust theoretical frameworks with practical effectiveness. Results, methods, and limitations are detailed alongside discussion of promising extensions, emphasizing the potential of feature-rich mathematical/computational frameworks for natural and biomedical images.
Authors: Ziqi Ni, Ao Fu, Yi Zhou
Abstract: Achieving high-fidelity lip-speech synchronization in audio-driven talking portrait synthesis remains challenging. While multi-stage pipelines or diffusion models yield high-quality results, they suffer from high computational costs. Some approaches perform well on specific individuals with low resources, yet still exhibit mismatched lip movements. The aforementioned methods are modeled in the pixel domain. We observed that there are noticeable discrepancies in the frequency domain between the synthesized talking videos and natural videos. Currently, no research on talking portrait synthesis has considered this aspect. To address this, we propose a FREquency-modulated, high-fidelity, and real-time Audio-driven talKing portrait synthesis framework, named FREAK, which models talking portraits from the frequency domain perspective, enhancing the fidelity and naturalness of the synthesized portraits. FREAK introduces two novel frequency-based modules: 1) the Visual Encoding Frequency Modulator (VEFM) to couple multi-scale visual features in the frequency domain, better preserving visual frequency information and reducing the gap in the frequency spectrum between synthesized and natural frames. and 2) the Audio Visual Frequency Modulator (AVFM) to help the model learn the talking pattern in the frequency domain and improve audio-visual synchronization. Additionally, we optimize the model in both pixel domain and frequency domain jointly. Furthermore, FREAK supports seamless switching between one-shot and video dubbing settings, offering enhanced flexibility. Due to its superior performance, it can simultaneously support high-resolution video results and real-time inference. Extensive experiments demonstrate that our method synthesizes high-fidelity talking portraits with detailed facial textures and precise lip synchronization in real-time, outperforming state-of-the-art methods.
Authors: Songping Wang, Xinquan Yue, Yueming Lyu, Caifeng Shan
Abstract: Kolmogorov-Arnold Networks (KANs) have emerged as a transformative model paradigm, significantly impacting various fields. However, their adversarial robustness remains less underexplored, especially across different KAN architectures. To explore this critical safety issue, we conduct an analysis and find that due to overfitting to the specific basis functions of KANs, they possess poor adversarial transferability among different KANs. To tackle this challenge, we propose AdvKAN, the first transfer attack method for KANs. AdvKAN integrates two key components: 1) a Breakthrough-Defense Surrogate Model (BDSM), which employs a breakthrough-defense training strategy to mitigate overfitting to the specific structures of KANs. 2) a Global-Local Interaction (GLI) technique, which promotes sufficient interaction between adversarial gradients of hierarchical levels, further smoothing out loss surfaces of KANs. Both of them work together to enhance the strength of transfer attack among different KANs. Extensive experimental results on various KANs and datasets demonstrate the effectiveness of AdvKAN, which possesses notably superior attack capabilities and deeply reveals the vulnerabilities of KANs. Code will be released upon acceptance.
Authors: Peiran Wu, Yunze Liu, Miao Liu, Junxiao Shen
Abstract: Humans excel at spatial-temporal reasoning, effortlessly interpreting dynamic visual events from an egocentric viewpoint. However, whether multimodal large language models (MLLMs) can similarly understand the 4D world remains uncertain. This paper explores multimodal spatial-temporal reasoning from an egocentric perspective, aiming to equip MLLMs with human-like reasoning capabilities. To support this objective, we introduce \textbf{Ego-ST Bench}, a novel benchmark containing over 5,000 question-answer pairs across four categories, systematically evaluating spatial, temporal, and integrated spatial-temporal reasoning. Additionally, we propose \textbf{ST-R1} training paradigm, a video-based reasoning model that incorporates reverse thinking into its reinforcement learning process, significantly enhancing performance. We combine long-chain-of-thought (long-CoT) supervised fine-tuning with Group Relative Policy Optimization (GRPO) reinforcement learning, achieving notable improvements with limited high-quality data. Ego-ST Bench and ST-R1 provide valuable insights and resources for advancing video-based spatial-temporal reasoning research.
Authors: Tsu-Jui Fu, Yusu Qian, Chen Chen, Wenze Hu, Zhe Gan, Yinfei Yang
Abstract: Text-to-Image (T2I) diffusion models have shown impressive results in generating visually compelling images following user prompts. Building on this, various methods further fine-tune the pre-trained T2I model for specific tasks. However, this requires separate model architectures, training designs, and multiple parameter sets to handle different tasks. In this paper, we introduce UniVG, a generalist diffusion model capable of supporting a diverse range of image generation tasks with a single set of weights. UniVG treats multi-modal inputs as unified conditions to enable various downstream applications, ranging from T2I generation, inpainting, instruction-based editing, identity-preserving generation, and layout-guided generation, to depth estimation and referring segmentation. Through comprehensive empirical studies on data mixing and multi-task training, we provide detailed insights into the training processes and decisions that inform our final designs. For example, we show that T2I generation and other tasks, such as instruction-based editing, can coexist without performance trade-offs, while auxiliary tasks like depth estimation and referring segmentation enhance image editing. Notably, our model can even outperform some task-specific models on their respective benchmarks, marking a significant step towards a unified image generation model.
Authors: Bilal Alsallakh, Timothy Wroge, Vivek Miglani, Narine Kokhlikyan
Abstract: We explore the symmetry of the mean k x k weight kernel in each layer of various convolutional neural networks. Unlike individual neurons, the mean kernels in internal layers tend to be symmetric about their centers instead of favoring specific directions. We investigate why this symmetry emerges in various datasets and models, and how it is impacted by certain architectural choices. We show how symmetry correlates with desirable properties such as shift and flip consistency, and might constitute an inherent inductive bias in convolutional neural networks.
Authors: Saron Samuel, Dan DeGenaro, Jimena Guallar-Blasco, Kate Sanders, Oluwaseun Eisape, 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: Ziteng Cui, Xuangeng Chu, Tatsuya Harada
Abstract: Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality. This challenge becomes more pronounced in multi-view scenarios, where variations in lighting and image signal processor (ISP) settings across viewpoints introduce photometric inconsistencies. Such lighting degradations and view-dependent variations pose substantial challenges to novel view synthesis (NVS) frameworks based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). To address this, we introduce Luminance-GS, a novel approach to achieving high-quality novel view synthesis results under diverse challenging lighting conditions using 3DGS. By adopting per-view color matrix mapping and view-adaptive curve adjustments, Luminance-GS achieves state-of-the-art (SOTA) results across various lighting conditions -- including low-light, overexposure, and varying exposure -- while not altering the original 3DGS explicit representation. Compared to previous NeRF- and 3DGS-based baselines, Luminance-GS provides real-time rendering speed with improved reconstruction quality.
Authors: Van Nguyen Nguyen, Stephen Tyree, Andrew Guo, Mederic Fourmy, Anas Gouda, Taeyeop Lee, Sungphill Moon, Hyeontae Son, Lukas Ranftl, Jonathan Tremblay, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Stan Birchfield, Jiri Matas, Yann Labbe, Martin Sundermeyer, Tomas Hodan
Abstract: We present the evaluation methodology, datasets and results of the BOP Challenge 2024, the 6th in a series of public competitions organized to capture the state of the art in 6D object pose estimation and related tasks. In 2024, our goal was to transition BOP from lab-like setups to real-world scenarios. First, we introduced new model-free tasks, where no 3D object models are available and methods need to onboard objects just from provided reference videos. Second, we defined a new, more practical 6D object detection task where identities of objects visible in a test image are not provided as input. Third, we introduced new BOP-H3 datasets recorded with high-resolution sensors and AR/VR headsets, closely resembling real-world scenarios. BOP-H3 include 3D models and onboarding videos to support both model-based and model-free tasks. Participants competed on seven challenge tracks. Notably, the best 2024 method for model-based 6D localization of unseen objects (FreeZeV2.1) achieves 22% higher accuracy on BOP-Classic-Core than the best 2023 method (GenFlow), and is only 4% behind the best 2023 method for seen objects (GPose2023) although being significantly slower (24.9 vs 2.7s per image). A more practical 2024 method for this task is Co-op which takes only 0.8s per image and is 13% more accurate than GenFlow. Methods have similar rankings on 6D detection as on 6D localization but higher run time. On model-based 2D detection of unseen objects, the best 2024 method (MUSE) achieves 21--29% relative improvement compared to the best 2023 method (CNOS). However, the 2D detection accuracy for unseen objects is still -35% behind the accuracy for seen objects (GDet2023), and the 2D detection stage is consequently the main bottleneck of existing pipelines for 6D localization/detection of unseen objects. The online evaluation system stays open and is available at http://bop.felk.cvut.cz/
URLs: http://bop.felk.cvut.cz/
Authors: Ronghui Zhang, Yuhang Ma, Tengfei Li, Ziyu Lin, Yueying Wu, Junzhou Chen, Lin Zhang, Jia Hu, Tony Z. Qiu, Konghui Guo
Abstract: Lane detection is a critical component of Advanced Driver Assistance Systems (ADAS). Existing lane detection algorithms generally perform well under favorable weather conditions. However, their performance degrades significantly in adverse conditions, such as fog, which increases the risk of traffic accidents. This challenge is compounded by the lack of specialized datasets and methods designed for foggy environments. To address this, we introduce the FoggyLane dataset, captured in real-world foggy scenarios, and synthesize two additional datasets, FoggyCULane and FoggyTusimple, from existing popular lane detection datasets. Furthermore, we propose a robust Fog-Enhanced Network for lane detection, incorporating a Global Feature Fusion Module (GFFM) to capture global relationships in foggy images, a Kernel Feature Fusion Module (KFFM) to model the structural and positional relationships of lane instances, and a Low-level Edge Enhanced Module (LEEM) to address missing edge details in foggy conditions. Comprehensive experiments demonstrate that our method achieves state-of-the-art performance, with F1-scores of 95.04 on FoggyLane, 79.85 on FoggyCULane, and 96.95 on FoggyTusimple. Additionally, with TensorRT acceleration, the method reaches a processing speed of 38.4 FPS on the NVIDIA Jetson AGX Orin, confirming its real-time capabilities and robustness in foggy environments.
Authors: Qinyue Tong, Ziqian Lu, Jun Liu, Yangming Zheng, Zheming Lu
Abstract: Despite remarkable advancements in pixel-level medical image perception, existing methods are either limited to specific tasks or heavily rely on accurate bounding boxes or text labels as input prompts. However, the medical knowledge required for input is a huge obstacle for general public, which greatly reduces the universality of these methods. Compared with these domain-specialized auxiliary information, general users tend to rely on oral queries that require logical reasoning. In this paper, we introduce a novel medical vision task: Medical Reasoning Segmentation and Detection (MedSD), which aims to comprehend implicit queries about medical images and generate the corresponding segmentation mask and bounding box for the target object. To accomplish this task, we first introduce a Multi-perspective, Logic-driven Medical Reasoning Segmentation and Detection (MLMR-SD) dataset, which encompasses a substantial collection of medical entity targets along with their corresponding reasoning. Furthermore, we propose MediSee, an effective baseline model designed for medical reasoning segmentation and detection. The experimental results indicate that the proposed method can effectively address MedSD with implicit colloquial queries and outperform traditional medical referring segmentation methods.
Authors: Songping Wang, Yueming Lyu, Shiqi Liu, Ning Li, Tong Tong, Hao Sun, Caifeng Shan
Abstract: The rise of customized diffusion models has spurred a boom in personalized visual content creation, but also poses risks of malicious misuse, severely threatening personal privacy and copyright protection. Some studies show that the aesthetic properties of images are highly positively correlated with human perception of image quality. Inspired by this, we approach the problem from a novel and intriguing aesthetic perspective to degrade the generation quality of maliciously customized models, thereby achieving better protection of facial identity. Specifically, we propose a Hierarchical Anti-Aesthetic (HAA) framework to fully explore aesthetic cues, which consists of two key branches: 1) Global Anti-Aesthetics: By establishing a global anti-aesthetic reward mechanism and a global anti-aesthetic loss, it can degrade the overall aesthetics of the generated content; 2) Local Anti-Aesthetics: A local anti-aesthetic reward mechanism and a local anti-aesthetic loss are designed to guide adversarial perturbations to disrupt local facial identity. By seamlessly integrating both branches, our HAA effectively achieves the goal of anti-aesthetics from a global to a local level during customized generation. Extensive experiments show that HAA outperforms existing SOTA methods largely in identity removal, providing a powerful tool for protecting facial privacy and copyright.
Authors: Daniel Gonzalez-Alvarado, Fabio Schlindwein, Jonas Cassel, Laura Steingruber, Stefania Petra, Christoph Schn\"orr
Abstract: This paper introduces patch assignment flows for metric data labeling on graphs. Labelings are determined by regularizing initial local labelings through the dynamic interaction of both labels and label assignments across the graph, entirely encoded by a dictionary of competing labeled patches and mediated by patch assignment variables. Maximal consistency of patch assignments is achieved by geometric numerical integration of a Riemannian ascent flow, as critical point of a Lagrangian action functional. Experiments illustrate properties of the approach, including uncertainty quantification of label assignments.
Authors: Hongwei Ji, Wulian Yun, Mengshi Qi, Huadong Ma
Abstract: Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL methods typically focus solely on video-level information, neglecting textual information, which can provide valuable semantic support for the localization task. Therefore, we propose a new few-shot temporal action localization method by Chain-of-Thought textual reasoning to improve localization performance. Specifically, we design a novel few-shot learning framework that leverages textual semantic information to enhance the model's ability to capture action commonalities and variations, which includes a semantic-aware text-visual alignment module designed to align the query and support videos at different levels. Meanwhile, to better express the temporal dependencies and causal relationships between actions at the textual level to assist action localization, we design a Chain of Thought (CoT)-like reasoning method that progressively guides the Vision Language Model (VLM) and Large Language Model (LLM) to generate CoT-like text descriptions for videos. The generated texts can capture more variance of action than visual features. We conduct extensive experiments on the publicly available ActivityNet1.3 and THUMOS14 datasets. We introduce the first dataset named Human-related Anomaly Localization and explore the application of the TAL task in human anomaly detection. The experimental results demonstrate that our proposed method significantly outperforms existing methods in single-instance and multi-instance scenarios. We will release our code, data and benchmark.
Authors: Ryota Takatsuki, Sonia Joseph, Ippei Fujisawa, Ryota Kanai
Abstract: Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output vocabulary space. Although applying Logit Lens to Vision Transformers (ViTs) is technically straightforward, its direct use faces limitations in capturing the richness of visual representations. Building on the work of Toker et al. (2024)~\cite{Toker2024-ve}, who introduced Diffusion Lens to visualize intermediate representations in the text encoders of text-to-image diffusion models, we demonstrate that while Diffusion Lens can effectively visualize residual stream representations in image encoders, it fails to capture the direct contributions of individual submodules. To overcome this limitation, we propose \textbf{Diffusion Steering Lens} (DSL), a novel, training-free approach that steers submodule outputs and patches subsequent indirect contributions. We validate our method through interventional studies, showing that DSL provides an intuitive and reliable interpretation of the internal processing in ViTs.
Authors: Fulong Ye, Miao Hua, Pengze Zhang, Xinghui Li, Qichao Sun, Songtao Zhao, Qian He, Xinglong Wu
Abstract: In this paper, we introduce DreamID, a diffusion-based face swapping model that achieves high levels of ID similarity, attribute preservation, image fidelity, and fast inference speed. Unlike the typical face swapping training process, which often relies on implicit supervision and struggles to achieve satisfactory results. DreamID establishes explicit supervision for face swapping by constructing Triplet ID Group data, significantly enhancing identity similarity and attribute preservation. The iterative nature of diffusion models poses challenges for utilizing efficient image-space loss functions, as performing time-consuming multi-step sampling to obtain the generated image during training is impractical. To address this issue, we leverage the accelerated diffusion model SD Turbo, reducing the inference steps to a single iteration, enabling efficient pixel-level end-to-end training with explicit Triplet ID Group supervision. Additionally, we propose an improved diffusion-based model architecture comprising SwapNet, FaceNet, and ID Adapter. This robust architecture fully unlocks the power of the Triplet ID Group explicit supervision. Finally, to further extend our method, we explicitly modify the Triplet ID Group data during training to fine-tune and preserve specific attributes, such as glasses and face shape. Extensive experiments demonstrate that DreamID outperforms state-of-the-art methods in terms of identity similarity, pose and expression preservation, and image fidelity. Overall, DreamID achieves high-quality face swapping results at 512*512 resolution in just 0.6 seconds and performs exceptionally well in challenging scenarios such as complex lighting, large angles, and occlusions.
Authors: Songping Wang, Hanqing Liu, Yueming Lyu, Xiantao Hu, Ziwen He, Wei Wang, Caifeng Shan, Liang Wang
Abstract: Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. First, fast adversarial training for video models remains largely unexplored, which severely impedes its practical applications. Specifically, most video adversarial training methods are computationally costly, with long training times and high expenses. Second, existing methods struggle with the trade-off between clean accuracy and adversarial robustness. To address these challenges, we introduce Video Fast Adversarial Training with Weak-to-Strong consistency (VFAT-WS), the first fast adversarial training method for video data. Specifically, VFAT-WS incorporates the following key designs: First, it integrates a straightforward yet effective temporal frequency augmentation (TF-AUG), and its spatial-temporal enhanced form STF-AUG, along with a single-step PGD attack to boost training efficiency and robustness. Second, it devises a weak-to-strong spatial-temporal consistency regularization, which seamlessly integrates the simpler TF-AUG and the more complex STF-AUG. Leveraging the consistency regularization, it steers the learning process from simple to complex augmentations. Both of them work together to achieve a better trade-off between clean accuracy and robustness. Extensive experiments on UCF-101 and HMDB-51 with both CNN and Transformer-based models demonstrate that VFAT-WS achieves great improvements in adversarial robustness and corruption robustness, while accelerating training by nearly 490%.
Authors: Lotfi Abdelkrim Mecharbat, Ibrahim Almakky, Martin Takac, Mohammad Yaqub
Abstract: Deep learning (DL) has achieved remarkable progress in the field of medical imaging. However, adapting DL models to medical tasks remains a significant challenge, primarily due to two key factors: (1) architecture selection, as different tasks necessitate specialized model designs, and (2) weight initialization, which directly impacts the convergence speed and final performance of the models. Although transfer learning from ImageNet is a widely adopted strategy, its effectiveness is constrained by the substantial differences between natural and medical images. To address these challenges, we introduce Medical Neural Network Search (MedNNS), the first Neural Network Search framework for medical imaging applications. MedNNS jointly optimizes architecture selection and weight initialization by constructing a meta-space that encodes datasets and models based on how well they perform together. We build this space using a Supernetwork-based approach, expanding the model zoo size by 51x times over previous state-of-the-art (SOTA) methods. Moreover, we introduce rank loss and Fr\'echet Inception Distance (FID) loss into the construction of the space to capture inter-model and inter-dataset relationships, thereby achieving more accurate alignment in the meta-space. Experimental results across multiple datasets demonstrate that MedNNS significantly outperforms both ImageNet pre-trained DL models and SOTA Neural Architecture Search (NAS) methods, achieving an average accuracy improvement of 1.7% across datasets while converging substantially faster. The code and the processed meta-space is available at https://github.com/BioMedIA-MBZUAI/MedNNS.
Authors: Chang Zong, Bin Li, Shoujun Zhou, Jian Wan, Lei Zhang
Abstract: Locating specific segments within an instructional video is an efficient way to acquire guiding knowledge. Generally, the task of obtaining video segments for both verbal explanations and visual demonstrations is known as visual answer localization (VAL). However, users often need multiple interactions to obtain answers that align with their expectations when using the system. During these interactions, humans deepen their understanding of the video content by asking themselves questions, thereby accurately identifying the location. Therefore, we propose a new task, named In-VAL, to simulate the multiple interactions between humans and videos in the procedure of obtaining visual answers. The In-VAL task requires interactively addressing several semantic gap issues, including 1) the ambiguity of user intent in the input questions, 2) the incompleteness of language in video subtitles, and 3) the fragmentation of content in video segments. To address these issues, we propose Ask2Loc, a framework for resolving In-VAL by asking questions. It includes three key modules: 1) a chatting module to refine initial questions and uncover clear intentions, 2) a rewriting module to generate fluent language and create complete descriptions, and 3) a searching module to broaden local context and provide integrated content. We conduct extensive experiments on three reconstructed In-VAL datasets. Compared to traditional end-to-end and two-stage methods, our proposed Ask2Loc can improve performance by up to 14.91 (mIoU) on the In-VAL task. Our code and datasets can be accessed at https://github.com/changzong/Ask2Loc.
Authors: Francesco Santini, Jakob Wasserthal, Abramo Agosti, Xeni Deligianni, Kevin R. Keene, Hermien E. Kan, Stefan Sommer, Fengdan Wang, Claudia Weidensteiner, Giulia Manco, Matteo Paoletti, Valentina Mazzoli, Arjun Desai, Anna Pichiecchio
Abstract: Purpose: To present and evaluate Dafne (deep anatomical federated network), a freely available decentralized, collaborative deep learning system for the semantic segmentation of radiological images through federated incremental learning. Materials and Methods: Dafne is free software with a client-server architecture. The client side is an advanced user interface that applies the deep learning models stored on the server to the user's data and allows the user to check and refine the prediction. Incremental learning is then performed at the client's side and sent back to the server, where it is integrated into the root model. Dafne was evaluated locally, by assessing the performance gain across model generations on 38 MRI datasets of the lower legs, and through the analysis of real-world usage statistics (n = 639 use-cases). Results: Dafne demonstrated a statistically improvement in the accuracy of semantic segmentation over time (average increase of the Dice Similarity Coefficient by 0.007 points/generation on the local validation set, p < 0.001). Qualitatively, the models showed enhanced performance on various radiologic image types, including those not present in the initial training sets, indicating good model generalizability. Conclusion: Dafne showed improvement in segmentation quality over time, demonstrating potential for learning and generalization.
Authors: Yujian Hu, Yilang Xiang, Yan-Jie Zhou, Yangyan He, Dehai Lang, Shifeng Yang, Xiaolong Du, Chunlan Den, Youyao Xu, Gaofeng Wang, Zhengyao Ding, Jingyong Huang, Wenjun Zhao, Xuejun Wu, Donglin Li, Qianqian Zhu, Zhenjiang Li, Chenyang Qiu, Ziheng Wu, Yunjun He, Chen Tian, Yihui Qiu, Zuodong Lin, Xiaolong Zhang, Yuan He, Zhenpeng Yuan, Xiaoxiang Zhou, Rong Fan, Ruihan Chen, Wenchao Guo, Jianpeng Zhang, Tony C. W. Mok, Zi Li, Mannudeep K. Kalra, Le Lu, Wenbo Xiao, Xiaoqiang Li, Yun Bian, Chengwei Shao, Guofu Wang, Wei Lu, Zhengxing Huang, Minfeng Xu, Hongkun Zhang
Abstract: The accurate and timely diagnosis of acute aortic syndromes (AAS) in patients presenting with acute chest pain remains a clinical challenge. Aortic CT angiography (CTA) is the imaging protocol of choice in patients with suspected AAS. However, due to economic and workflow constraints in China, the majority of suspected patients initially undergo non-contrast CT as the initial imaging testing, and CTA is reserved for those at higher risk. In this work, we present an artificial intelligence-based warning system, iAorta, using non-contrast CT for AAS identification in China, which demonstrates remarkably high accuracy and provides clinicians with interpretable warnings. iAorta was evaluated through a comprehensive step-wise study. In the multi-center retrospective study (n = 20,750), iAorta achieved a mean area under the receiver operating curve (AUC) of 0.958 (95% CI 0.950-0.967). In the large-scale real-world study (n = 137,525), iAorta demonstrated consistently high performance across various non-contrast CT protocols, achieving a sensitivity of 0.913-0.942 and a specificity of 0.991-0.993. In the prospective comparative study (n = 13,846), iAorta demonstrated the capability to significantly shorten the time to correct diagnostic pathway. For the prospective pilot deployment that we conducted, iAorta correctly identified 21 out of 22 patients with AAS among 15,584 consecutive patients presenting with acute chest pain and under non-contrast CT protocol in the emergency department (ED) and enabled the average diagnostic time of these 21 AAS positive patients to be 102.1 (75-133) mins. Last, the iAorta can help avoid delayed or missed diagnosis of AAS in settings where non-contrast CT remains the unavoidable the initial or only imaging test in resource-constrained regions and in patients who cannot or did not receive intravenous contrast.
Authors: Xin Jin, Hongyu Zhu, Siyuan Li, Zedong Wang, Zicheng Liu, Juanxi Tian, Chang Yu, Huafeng Qin, Stan Z. Li
Abstract: As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at https://github.com/Westlake-AI/Awesome-Mixup.
Authors: Santhosh Malarvannan, Pandiyaraju V, Shravan Venkatraman, Abeshek A, Priyadarshini B, Kannan A
Abstract: Diabetic retinopathy is a leading cause of blindness around the world and demands precise AI-based diagnostic tools. Traditional loss functions in multi-class classification, such as Categorical Cross-Entropy (CCE), are very common but break down with class imbalance, especially in cases with inherently challenging or overlapping classes, which leads to biased and less sensitive models. Since a heavy imbalance exists in the number of examples for higher severity stage 4 diabetic retinopathy, etc., classes compared to those very early stages like class 0, achieving class balance is key. For this purpose, we propose the Adaptive Hybrid Focal-Entropy Loss which combines the ideas of focal loss and entropy loss with adaptive weighting in order to focus on minority classes and highlight the challenging samples. The state-of-the art models applied for diabetic retinopathy detection with AHFE revealed good performance improvements, indicating the top performances of ResNet50 at 99.79%, DenseNet121 at 98.86%, Xception at 98.92%, MobileNetV2 at 97.84%, and InceptionV3 at 93.62% accuracy. This sheds light into how AHFE promotes enhancement in AI-driven diagnostics for complex and imbalanced medical datasets.
Authors: Asad Aali, Marius Arvinte, Sidharth Kumar, Yamin I. Arefeen, Jonathan I. Tamir
Abstract: We study the effect of incorporating self-supervised denoising as a pre-processing step for training deep learning (DL) based reconstruction methods on data corrupted by Gaussian noise. K-space data employed for training are typically multi-coil and inherently noisy. Although DL-based reconstruction methods trained on fully sampled data can enable high reconstruction quality, obtaining large, noise-free datasets is impractical. We leverage Generalized Stein's Unbiased Risk Estimate (GSURE) for denoising. We evaluate two DL-based reconstruction methods: Diffusion Probabilistic Models (DPMs) and Model-Based Deep Learning (MoDL). We evaluate the impact of denoising on the performance of these DL-based methods in solving accelerated multi-coil magnetic resonance imaging (MRI) reconstruction. The experiments were carried out on T2-weighted brain and fat-suppressed proton-density knee scans. We observed that self-supervised denoising enhances the quality and efficiency of MRI reconstructions across various scenarios. Specifically, employing denoised images rather than noisy counterparts when training DL networks results in lower normalized root mean squared error (NRMSE), higher structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) across different SNR levels, including 32dB, 22dB, and 12dB for T2-weighted brain data, and 24dB, 14dB, and 4dB for fat-suppressed knee data. Overall, we showed that denoising is an essential pre-processing technique capable of improving the efficacy of DL-based MRI reconstruction methods under diverse conditions. By refining the quality of input data, denoising enables training more effective DL networks, potentially bypassing the need for noise-free reference MRI scans.
Authors: Kaizhen Sun, Jinghang Li, Kuan Dai, Bangyan Liao, Wei Xiong, Yi Zhou
Abstract: Time-to-Collision (TTC) estimation lies in the core of the forward collision warning (FCW) functionality, which is key to all Automatic Emergency Braking (AEB) systems. Although the success of solutions using frame-based cameras (e.g., Mobileye's solutions) has been witnessed in normal situations, some extreme cases, such as the sudden variation in the relative speed of leading vehicles and the sudden appearance of pedestrians, still pose significant risks that cannot be handled. This is due to the inherent imaging principles of frame-based cameras, where the time interval between adjacent exposures introduces considerable system latency to AEB. Event cameras, as a novel bio-inspired sensor, offer ultra-high temporal resolution and can asynchronously report brightness changes at the microsecond level. To explore the potential of event cameras in the above-mentioned challenging cases, we propose EvTTC, which is, to the best of our knowledge, the first multi-sensor dataset focusing on TTC tasks under high-relative-speed scenarios. EvTTC consists of data collected using standard cameras and event cameras, covering various potential collision scenarios in daily driving and involving multiple collision objects. Additionally, LiDAR and GNSS/INS measurements are provided for the calculation of ground-truth TTC. Considering the high cost of testing TTC algorithms on full-scale mobile platforms, we also provide a small-scale TTC testbed for experimental validation and data augmentation. All the data and the design of the testbed are open sourced, and they can serve as a benchmark that will facilitate the development of vision-based TTC techniques.
Authors: Hritik Bansal, Daniel Israel, Siyan Zhao, Shufan Li, Tung Nguyen, Aditya Grover
Abstract: Recent advancements in mixed-modal generative have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and generating multimodal patient reports. However, existing datasets face challenges such as small sizes, limited coverage of biomedical tasks and domains, and a reliance on narrow sources. To address these gaps, we present MedMax, a large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, including interleaved image-text generation, biomedical image captioning and generation, visual chat, and report understanding. These tasks span knowledge across diverse biomedical domains, including radiology and histopathology, grounded in medical papers and YouTube videos. Subsequently, we fine-tune a mixed-modal foundation model on the MedMax dataset, achieving significant performance improvements: a 26% gain over the Chameleon model and an 18.3% improvement over GPT-4o across 12 downstream biomedical visual question-answering tasks. Finally, we introduce a unified evaluation suite for biomedical tasks to guide the development of mixed-modal biomedical AI assistants. The data, model, and code is available at https://mint-medmax.github.io/.
Authors: Zihang Cheng, Huiping Zhuang, Chun Li, Xin Meng, Ming Li, Fei Richard Yu, Liqiang Nie
Abstract: 3D Gaussian Splatting (3DGS) has been widely used in 3D reconstruction and 3D generation. Training to get a 3DGS scene often takes a lot of time and resources and even valuable inspiration. The increasing amount of 3DGS digital asset have brought great challenges to the copyright protection. However, it still lacks profound exploration targeted at 3DGS. In this paper, we propose a new framework X-SG$^2$S which can simultaneously watermark 1 to 3D messages while keeping the original 3DGS scene almost unchanged. Generally, we have a X-SG$^2$S injector for adding multi-modal messages simultaneously and an extractor for extract them. Specifically, we first split the watermarks into message patches in a fixed manner and sort the 3DGS points. A self-adaption gate is used to pick out suitable location for watermarking. Then use a XD(multi-dimension)-injection heads to add multi-modal messages into sorted 3DGS points. A learnable gate can recognize the location with extra messages and XD-extraction heads can restore hidden messages from the location recommended by the learnable gate. Extensive experiments demonstrated that the proposed X-SG$^2$S can effectively conceal multi modal messages without changing pretrained 3DGS pipeline or the original form of 3DGS parameters. Meanwhile, with simple and efficient model structure and high practicality, X-SG$^2$S still shows good performance in hiding and extracting multi-modal inner structured or unstructured messages. X-SG$^2$S is the first to unify 1 to 3D watermarking model for 3DGS and the first framework to add multi-modal watermarks simultaneous in one 3DGS which pave the wave for later researches.
Authors: Zeyue Tian, Yizhu Jin, Zhaoyang Liu, Ruibin Yuan, Xu Tan, Qifeng Chen, Wei Xue, Yike Guo
Abstract: Audio and music generation have emerged as crucial tasks in many applications, yet existing approaches face significant limitations: they operate in isolation without unified capabilities across modalities, suffer from scarce high-quality, multi-modal training data, and struggle to effectively integrate diverse inputs. In this work, we propose AudioX, a unified Diffusion Transformer model for Anything-to-Audio and Music Generation. Unlike previous domain-specific models, AudioX can generate both general audio and music with high quality, while offering flexible natural language control and seamless processing of various modalities including text, video, image, music, and audio. Its key innovation is a multi-modal masked training strategy that masks inputs across modalities and forces the model to learn from masked inputs, yielding robust and unified cross-modal representations. To address data scarcity, we curate two comprehensive datasets: vggsound-caps with 190K audio captions based on the VGGSound dataset, and V2M-caps with 6 million music captions derived from the V2M dataset. Extensive experiments demonstrate that AudioX not only matches or outperforms state-of-the-art specialized models, but also offers remarkable versatility in handling diverse input modalities and generation tasks within a unified architecture. The code and datasets will be available at https://zeyuet.github.io/AudioX/
Authors: Hongjie He, Xu Pan, Yudong Yao
Abstract: As deep learning continues to advance, the transparency of neural network decision-making remains a critical challenge, limiting trust and applicability in high-stakes domains. Class Activation Mapping (CAM) techniques have emerged as a key approach toward visualizing model decisions, yet existing methods face inherent trade-offs. Gradient-based CAM variants suffer from sensitivity to gradient perturbations due to gradient noise, leading to unstable and unreliable explanations. Conversely, gradient-free approaches mitigate gradient instability but incur significant computational overhead and inference latency. To address these limitations, we propose a Cluster Filter Class Activation Map (CF-CAM) technique, a novel framework that reintroduces gradient-based weighting while enhancing robustness against gradient noise. CF-CAM utilizes hierarchical importance weighting strategy to balance discriminative feature preservation and noise elimination. A density-aware channel clustering method via Density-Based Spatial Clustering of Applications with Noise (DBSCAN) groups semantically relevant feature channels and discard noise-prone activations. Additionally, cluster-conditioned gradient filtering leverages Gaussian filters to refine gradient signals, preserving edge-aware localization while suppressing noise impact. Experiment results demonstrate that CF-CAM achieves superior interpretability performance while enhancing computational efficiency, outperforming state-of-the-art CAM methods in faithfulness and robustness. By effectively mitigating gradient instability without excessive computational cost, CF-CAM provides a competitive solution for enhancing the interpretability of deep neural networks in critical applications such as autonomous driving and medical diagnosis.
Authors: Zhenyu Yang, Haiming Zhu, Rihui Zhang, Haipeng Zhang, Jianliang Wang, Chunhao Wang, Minbin Chen, Fang-Fang Yin
Abstract: Background: Deep learning has significantly advanced medical image analysis, with Vision Transformers (ViTs) offering a powerful alternative to convolutional models by modeling long-range dependencies through self-attention. However, ViTs are inherently data-intensive and lack domain-specific inductive biases, limiting their applicability in medical imaging. In contrast, radiomics provides interpretable, handcrafted descriptors of tissue heterogeneity but suffers from limited scalability and integration into end-to-end learning frameworks. In this work, we propose the Radiomics-Embedded Vision Transformer (RE-ViT) that combines radiomic features with data-driven visual embeddings within a ViT backbone. Purpose: To develop a hybrid RE-ViT framework that integrates radiomics and patch-wise ViT embeddings through early fusion, enhancing robustness and performance in medical image classification. Methods: Following the standard ViT pipeline, images were divided into patches. For each patch, handcrafted radiomic features were extracted and fused with linearly projected pixel embeddings. The fused representations were normalized, positionally encoded, and passed to the ViT encoder. A learnable [CLS] token aggregated patch-level information for classification. We evaluated RE-ViT on three public datasets (including BUSI, ChestXray2017, and Retinal OCT) using accuracy, macro AUC, sensitivity, and specificity. RE-ViT was benchmarked against CNN-based (VGG-16, ResNet) and hybrid (TransMed) models. Results: RE-ViT achieved state-of-the-art results: on BUSI, AUC=0.950+/-0.011; on ChestXray2017, AUC=0.989+/-0.004; on Retinal OCT, AUC=0.986+/-0.001, which outperforms other comparison models. Conclusions: The RE-ViT framework effectively integrates radiomics with ViT architectures, demonstrating improved performance and generalizability across multimodal medical image classification tasks.
Authors: Oliver Mills, Philip Conaghan, Nishant Ravikumar, Samuel Relton
Abstract: Menisci are cartilaginous tissue found within the knee that contribute to joint lubrication and weight dispersal. Damage to menisci can lead to onset and progression of knee osteoarthritis (OA), a condition that is a leading cause of disability, and for which there are few effective therapies. Accurate automated segmentation of menisci would allow for earlier detection and treatment of meniscal abnormalities, as well as shedding more light on the role the menisci play in OA pathogenesis. Focus in this area has mainly used variants of convolutional networks, but there has been no attempt to utilise recent large vision transformer segmentation models. The Segment Anything Model (SAM) is a so-called foundation segmentation model, which has been found useful across a range of different tasks due to the large volume of data used for training the model. In this study, SAM was adapted to perform fully-automated segmentation of menisci from 3D knee magnetic resonance images. A 3D U-Net was also trained as a baseline. It was found that, when fine-tuning only the decoder, SAM was unable to compete with 3D U-Net, achieving a Dice score of $0.81\pm0.03$, compared to $0.87\pm0.03$, on a held-out test set. When fine-tuning SAM end-to-end, a Dice score of $0.87\pm0.03$ was achieved. The performance of both the end-to-end trained SAM configuration and the 3D U-Net were comparable to the winning Dice score ($0.88\pm0.03$) in the IWOAI Knee MRI Segmentation Challenge 2019. Performance in terms of the Hausdorff Distance showed that both configurations of SAM were inferior to 3D U-Net in matching the meniscus morphology. Results demonstrated that, despite its generalisability, SAM was unable to outperform a basic 3D U-Net in meniscus segmentation, and may not be suitable for similar 3D medical image segmentation tasks also involving fine anatomical structures with low contrast and poorly-defined boundaries.
Authors: Chen Guo, Zhuo Su, Jian Wang, Shuang Li, Xu Chang, Zhaohu Li, Yang Zhao, Guidong Wang, Ruqi Huang
Abstract: Creating photorealistic 3D head avatars from limited input has become increasingly important for applications in virtual reality, telepresence, and digital entertainment. While recent advances like neural rendering and 3D Gaussian splatting have enabled high-quality digital human avatar creation and animation, most methods rely on multiple images or multi-view inputs, limiting their practicality for real-world use. In this paper, we propose SEGA, a novel approach for Single-imagE-based 3D drivable Gaussian head Avatar creation that combines generalized prior models with a new hierarchical UV-space Gaussian Splatting framework. SEGA seamlessly combines priors derived from large-scale 2D datasets with 3D priors learned from multi-view, multi-expression, and multi-ID data, achieving robust generalization to unseen identities while ensuring 3D consistency across novel viewpoints and expressions. We further present a hierarchical UV-space Gaussian Splatting framework that leverages FLAME-based structural priors and employs a dual-branch architecture to disentangle dynamic and static facial components effectively. The dynamic branch encodes expression-driven fine details, while the static branch focuses on expression-invariant regions, enabling efficient parameter inference and precomputation. This design maximizes the utility of limited 3D data and achieves real-time performance for animation and rendering. Additionally, SEGA performs person-specific fine-tuning to further enhance the fidelity and realism of the generated avatars. Experiments show our method outperforms state-of-the-art approaches in generalization ability, identity preservation, and expression realism, advancing one-shot avatar creation for practical applications.
Authors: Abhishek Tyagi, Charu Gaur
Abstract: We present an autonomous aerial surveillance platform, Veg, designed as a fault-tolerant quadcopter system that integrates visual SLAM for GPS-independent navigation, advanced control architecture for dynamic stability, and embedded vision modules for real-time object and face recognition. The platform features a cascaded control design with an LQR inner-loop and PD outer-loop trajectory control. It leverages ORB-SLAM3 for 6-DoF localization and loop closure, and supports waypoint-based navigation through Dijkstra path planning over SLAM-derived maps. A real-time Failure Detection and Identification (FDI) system detects rotor faults and executes emergency landing through re-routing. The embedded vision system, based on a lightweight CNN and PCA, enables onboard object detection and face recognition with high precision. The drone operates fully onboard using a Raspberry Pi 4 and Arduino Nano, validated through simulations and real-world testing. This work consolidates real-time localization, fault recovery, and embedded AI on a single platform suitable for constrained environments.