Authors: Yen-Siang Wu, Chi-Pin Huang, Fu-En Yang, Yu-Chiang Frank Wang
Abstract: Text-to-video (T2V) diffusion models have shown promising capabilities in synthesizing realistic videos from input text prompts. However, the input text description alone provides limited control over the precise objects movements and camera framing. In this work, we tackle the motion customization problem, where a reference video is provided as motion guidance. While most existing methods choose to fine-tune pre-trained diffusion models to reconstruct the frame differences of the reference video, we observe that such strategy suffer from content leakage from the reference video, and they cannot capture complex motion accurately. To address this issue, we propose MotionMatcher, a motion customization framework that fine-tunes the pre-trained T2V diffusion model at the feature level. Instead of using pixel-level objectives, MotionMatcher compares high-level, spatio-temporal motion features to fine-tune diffusion models, ensuring precise motion learning. For the sake of memory efficiency and accessibility, we utilize a pre-trained T2V diffusion model, which contains considerable prior knowledge about video motion, to compute these motion features. In our experiments, we demonstrate state-of-the-art motion customization performances, validating the design of our framework.
Authors: Ahmad Salimi, Tristan Aumentado-Armstrong, Marcus A. Brubaker, Konstantinos G. Derpanis
Abstract: In this paper, we focus on 3D scene inpainting, where parts of an input image set, captured from different viewpoints, are masked out. The main challenge lies in generating plausible image completions that are geometrically consistent across views. Most recent work addresses this challenge by combining generative models with a 3D radiance field to fuse information across viewpoints. However, a major drawback of these methods is that they often produce blurry images due to the fusion of inconsistent cross-view images. To avoid blurry inpaintings, we eschew the use of an explicit or implicit radiance field altogether and instead fuse cross-view information in a learned space. In particular, we introduce a geometry-aware conditional generative model, capable of inpainting multi-view consistent images based on both geometric and appearance cues from reference images. A key advantage of our approach over existing methods is its unique ability to inpaint masked scenes with a limited number of views (i.e., few-view inpainting), whereas previous methods require relatively large image sets for their 3D model fitting step. Empirically, we evaluate and compare our scene-centric inpainting method on two datasets, SPIn-NeRF and NeRFiller, which contain images captured at narrow and wide baselines, respectively, and achieve state-of-the-art 3D inpainting performance on both. Additionally, we demonstrate the efficacy of our approach in the few-view setting compared to prior methods.
Authors: Chunhui Zhang, Yiren Jian, Zhongyu Ouyang, Soroush Vosoughi
Abstract: Developing video captioning models is computationally expensive. The dynamic nature of video also complicates the design of multimodal models that can effectively caption these sequences. However, we find that by using minimal computational resources and without complex modifications to address video dynamics, an image-based model can be repurposed to outperform several specialised video captioning systems. Our adapted model demonstrates top tier performance on major benchmarks, ranking 2nd on MSRVTT and MSVD, and 3rd on VATEX. We transform it into a competitive video captioner by post training a typical image captioning model BLIP2 with only 6,000 video text pairs and simply concatenating frames (significantly fewer data than other methods), which use 2.5 to 144 million pairs. From a resource optimization perspective, this video captioning study focuses on three fundamental factors: optimizing model scale, maximizing data efficiency, and incorporating reinforcement learning. This extensive study demonstrates that a lightweight, image based adaptation strategy can rival state-of-the-art video captioning systems, offering a practical solution for low-resource scenarios.
Authors: Naichuan Zheng, Hailun Xia
Abstract: Multimodal human action recognition based on RGB and skeleton data fusion, while effective, is constrained by significant limitations such as high computational complexity, excessive memory consumption, and substantial energy demands, particularly when implemented with Artificial Neural Networks (ANN). These limitations restrict its applicability in resource-constrained scenarios. To address these challenges, we propose a novel Spiking Neural Network (SNN)-driven framework for multimodal human action recognition, utilizing event camera and skeleton data. Our framework is centered on two key innovations: (1) a novel multimodal SNN architecture that employs distinct backbone networks for each modality-an SNN-based Mamba for event camera data and a Spiking Graph Convolutional Network (SGN) for skeleton data-combined with a spiking semantic extraction module to capture deep semantic representations; and (2) a pioneering SNN-based discretized information bottleneck mechanism for modality fusion, which effectively balances the preservation of modality-specific semantics with efficient information compression. To validate our approach, we propose a novel method for constructing a multimodal dataset that integrates event camera and skeleton data, enabling comprehensive evaluation. Extensive experiments demonstrate that our method achieves superior performance in both recognition accuracy and energy efficiency, offering a promising solution for practical applications.
Authors: Hossein Zaremehrjerdi, Lisa Coffey, Talukder Jubery, Huyu Liu, Jon Turkus, Kyle Linders, James C. Schnable, Patrick S. Schnable, Baskar Ganapathysubramanian
Abstract: Quantifying the variation in yield component traits of maize (Zea mays L.), which together determine the overall productivity of this globally important crop, plays a critical role in plant genetics research, plant breeding, and the development of improved farming practices. Grain yield per acre is calculated by multiplying the number of plants per acre, ears per plant, number of kernels per ear, and the average kernel weight. The number of kernels per ear is determined by the number of kernel rows per ear multiplied by the number of kernels per row. Traditional manual methods for measuring these two traits are time-consuming, limiting large-scale data collection. Recent automation efforts using image processing and deep learning encounter challenges such as high annotation costs and uncertain generalizability. We tackle these issues by exploring Large Vision Models for zero-shot, annotation-free maize kernel segmentation. By using an open-source large vision model, the Segment Anything Model (SAM), we segment individual kernels in RGB images of maize ears and apply a graph-based algorithm to calculate the number of kernels per row. Our approach successfully identifies the number of kernels per row across a wide range of maize ears, showing the potential of zero-shot learning with foundation vision models combined with image processing techniques to improve automation and reduce subjectivity in agronomic data collection. All our code is open-sourced to make these affordable phenotyping methods accessible to everyone.
Authors: Ziyuan Liu, Ruifei Zhu, Long Gao, Yuanxiu Zhou, Jingyu Ma, Yuantao Gu
Abstract: Deep learning has achieved significant success in the field of remote sensing image change detection (CD), yet two major challenges remain: the scarcity of sub-meter, all-inclusive open-source CD datasets, and the difficulty of achieving consistent and satisfactory detection results across images with varying change areas. To address these issues, we introduce the JL1-CD dataset, which contains 5,000 pairs of 512 x 512 pixel images with a resolution of 0.5 to 0.75 meters. Additionally, we propose a multi-teacher knowledge distillation (MTKD) framework for CD. Experimental results on the JL1-CD and SYSU-CD datasets demonstrate that the MTKD framework significantly improves the performance of CD models with various network architectures and parameter sizes, achieving new state-of-the-art results. The code is available at https://github.com/circleLZY/MTKD-CD.
Authors: Yang Yan, Bingqing Yue, Qiaxuan Li, Man Huang, Jingyu Chen, Zhenzhong Lan
Abstract: The integration of artificial intelligence in medical imaging has shown tremendous potential, yet the relationship between pre-trained knowledge and performance in cross-modality learning remains unclear. This study investigates how explicitly injecting medical knowledge into the learning process affects the performance of cross-modality classification, focusing on Chest X-ray (CXR) images. We introduce a novel Set Theory-based knowledge injection framework that generates captions for CXR images with controllable knowledge granularity. Using this framework, we fine-tune CLIP model on captions with varying levels of medical information. We evaluate the model's performance through zero-shot classification on the CheXpert dataset, a benchmark for CXR classification. Our results demonstrate that injecting fine-grained medical knowledge substantially improves classification accuracy, achieving 72.5\% compared to 49.9\% when using human-generated captions. This highlights the crucial role of domain-specific knowledge in medical cross-modality learning. Furthermore, we explore the influence of knowledge density and the use of domain-specific Large Language Models (LLMs) for caption generation, finding that denser knowledge and specialized LLMs contribute to enhanced performance. This research advances medical image analysis by demonstrating the effectiveness of knowledge injection for improving automated CXR classification, paving the way for more accurate and reliable diagnostic tools.
Authors: Yusuke Uchida, Takaaki Fukui
Abstract: Cryo-electron tomography (cryoET) is a crucial technique for unveiling the structure of protein complexes. Automatically analyzing tomograms captured by cryoET is an essential step toward understanding cellular structures. In this paper, we introduce the 4th place solution from the CZII - CryoET Object Identification competition, which was organized to advance the development of automated tomogram analysis techniques. Our solution adopted a heatmap-based keypoint detection approach, utilizing an ensemble of two different types of 2.5D U-Net models with depth reduction. Despite its highly unified and simple architecture, our method achieved 4th place, demonstrating its effectiveness.
Authors: Wei Dai, Steven Wang, Jun Liu
Abstract: Efficient evaluation of three-dimensional (3D) medical images is crucial for diagnostic and therapeutic practices in healthcare. Recent years have seen a substantial uptake in applying deep learning and computer vision to analyse and interpret medical images. Traditional approaches, such as convolutional neural networks (CNNs) and vision transformers (ViTs), face significant computational challenges, prompting the need for architectural advancements. Recent efforts have led to the introduction of novel architectures like the ``Mamba'' model as alternative solutions to traditional CNNs or ViTs. The Mamba model excels in the linear processing of one-dimensional data with low computational demands. However, Mamba's potential for 3D medical image analysis remains underexplored and could face significant computational challenges as the dimension increases. This manuscript presents MobileViM, a streamlined architecture for efficient segmentation of 3D medical images. In the MobileViM network, we invent a new dimension-independent mechanism and a dual-direction traversing approach to incorporate with a vision-Mamba-based framework. MobileViM also features a cross-scale bridging technique to improve efficiency and accuracy across various medical imaging modalities. With these enhancements, MobileViM achieves segmentation speeds exceeding 90 frames per second (FPS) on a single graphics processing unit (i.e., NVIDIA RTX 4090). This performance is over 24 FPS faster than the state-of-the-art deep learning models for processing 3D images with the same computational resources. In addition, experimental evaluations demonstrate that MobileViM delivers superior performance, with Dice similarity scores reaching 92.72%, 86.69%, 80.46%, and 77.43% for PENGWIN, BraTS2024, ATLAS, and Toothfairy2 datasets, respectively, which significantly surpasses existing models.
Authors: Zheng Wu, Yiping Xie, Bo Zhao, Jiguang He, Fei Luo, Ning Deng, Zitong Yu
Abstract: Heart rate (HR) estimation via remote photoplethysmography (rPPG) offers a non-invasive solution for health monitoring. However, traditional single-modality approaches (RGB or Radio Frequency (RF)) face challenges in balancing robustness and accuracy due to lighting variations, motion artifacts, and skin tone bias. In this paper, we propose CardiacMamba, a multimodal RGB-RF fusion framework that leverages the complementary strengths of both modalities. It introduces the Temporal Difference Mamba Module (TDMM) to capture dynamic changes in RF signals using timing differences between frames, enhancing the extraction of local and global features. Additionally, CardiacMamba employs a Bidirectional SSM for cross-modal alignment and a Channel-wise Fast Fourier Transform (CFFT) to effectively capture and refine the frequency domain characteristics of RGB and RF signals, ultimately improving heart rate estimation accuracy and periodicity detection. Extensive experiments on the EquiPleth dataset demonstrate state-of-the-art performance, achieving marked improvements in accuracy and robustness. CardiacMamba significantly mitigates skin tone bias, reducing performance disparities across demographic groups, and maintains resilience under missing-modality scenarios. By addressing critical challenges in fairness, adaptability, and precision, the framework advances rPPG technology toward reliable real-world deployment in healthcare. The codes are available at: https://github.com/WuZheng42/CardiacMamba.
Authors: Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein
Abstract: Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action within the scene. While the task is fundamental to machine perception and automated interactive navigation agents, the exponentially large number of probable pose and action variations make the problem challenging and non-trivial. However, the existing datasets and methods for human affordance prediction in 2D scenes are significantly limited in the literature. In this paper, we propose a novel cross-attention mechanism to encode the scene context for affordance prediction by mutually attending spatial feature maps from two different modalities. The proposed method is disentangled among individual subtasks to efficiently reduce the problem complexity. First, we sample a probable location for a person within the scene using a variational autoencoder (VAE) conditioned on the global scene context encoding. Next, we predict a potential pose template from a set of existing human pose candidates using a classifier on the local context encoding around the predicted location. In the subsequent steps, we use two VAEs to sample the scale and deformation parameters for the predicted pose template by conditioning on the local context and template class. Our experiments show significant improvements over the previous baseline of human affordance injection into complex 2D scenes.
Authors: Omid Nejati Manzari, Hojat Asgariandehkordi, Taha Koleilat, Yiming Xiao, Hassan Rivaz
Abstract: Convolutional networks, transformers, hybrid models, and Mamba-based architectures have demonstrated strong performance across various medical image classification tasks. However, these methods were primarily designed to classify clean images using labeled data. In contrast, real-world clinical data often involve image corruptions that are unique to multi-center studies and stem from variations in imaging equipment across manufacturers. In this paper, we introduce the Medical Vision Transformer (MedViTV2), a novel architecture incorporating Kolmogorov-Arnold Network (KAN) layers into the transformer architecture for the first time, aiming for generalized medical image classification. We have developed an efficient KAN block to reduce computational load while enhancing the accuracy of the original MedViT. Additionally, to counteract the fragility of our MedViT when scaled up, we propose an enhanced Dilated Neighborhood Attention (DiNA), an adaptation of the efficient fused dot-product attention kernel capable of capturing global context and expanding receptive fields to scale the model effectively and addressing feature collapse issues. Moreover, a hierarchical hybrid strategy is introduced to stack our Local Feature Perception and Global Feature Perception blocks in an efficient manner, which balances local and global feature perceptions to boost performance. Extensive experiments on 17 medical image classification datasets and 12 corrupted medical image datasets demonstrate that MedViTV2 achieved state-of-the-art results in 27 out of 29 experiments with reduced computational complexity. MedViTV2 is 44\% more computationally efficient than the previous version and significantly enhances accuracy, achieving improvements of 4.6\% on MedMNIST, 5.8\% on NonMNIST, and 13.4\% on the MedMNIST-C benchmark.
Authors: Taewoo Kim, Yujeong Chae, Hyun-Kurl Jang, Kuk-Jin Yoon
Abstract: Video Frame Interpolation (VFI) aims to generate intermediate video frames between consecutive input frames. Since the event cameras are bio-inspired sensors that only encode brightness changes with a micro-second temporal resolution, several works utilized the event camera to enhance the performance of VFI. However, existing methods estimate bidirectional inter-frame motion fields with only events or approximations, which can not consider the complex motion in real-world scenarios. In this paper, we propose a novel event-based VFI framework with cross-modal asymmetric bidirectional motion field estimation. In detail, our EIF-BiOFNet utilizes each valuable characteristic of the events and images for direct estimation of inter-frame motion fields without any approximation methods. Moreover, we develop an interactive attention-based frame synthesis network to efficiently leverage the complementary warping-based and synthesis-based features. Finally, we build a large-scale event-based VFI dataset, ERF-X170FPS, with a high frame rate, extreme motion, and dynamic textures to overcome the limitations of previous event-based VFI datasets. Extensive experimental results validate that our method shows significant performance improvement over the state-of-the-art VFI methods on various datasets. Our project pages are available at: https://github.com/intelpro/CBMNet
Authors: Nikolaos Dionelis, Jente Bosmans, Nicolas Long\'ep\'e
Abstract: Performing accurate confidence quantification and assessment is important for deep neural networks to predict their failures, improve their performance and enhance their capabilities in real-world applications, for their practical deployment in real life. For pixel-wise regression tasks, confidence quantification and assessment has not been well addressed in the literature, in contrast to classification tasks like semantic segmentation. The softmax output layer is not used in deep neural networks that solve pixel-wise regression problems. In this paper, to address these problems, we develop, train and evaluate the proposed model Confidence-Aware Regression Estimation (CARE). Our model CARE computes and assigns confidence to regression output results. We focus on solving regression problems as downstream tasks of an AI Foundation Model for Earth Observation (EO). We evaluate the proposed model CARE and experimental results on data from the Copernicus Sentinel-2 satellite constellation for estimating the density of buildings show that the proposed method can be successfully applied to regression problems. We also show that our approach outperforms other methods.
Authors: Miko{\l}aj Wysocki, Henryk Gierszal, Piotr Tyczka, Sophia Karagiorgou, George Pantelis
Abstract: This paper provides an analysis and comparison of the YOLOv5, YOLOv8 and YOLOv10 models for webpage CAPTCHAs detection using the datasets collected from the web and darknet as well as synthetized data of webpages. The study examines the nano (n), small (s), and medium (m) variants of YOLO architectures and use metrics such as Precision, Recall, F1 score, mAP@50 and inference speed to determine the real-life utility. Additionally, the possibility of tuning the trained model to detect new CAPTCHA patterns efficiently was examined as it is a crucial part of real-life applications. The image slicing method was proposed as a way to improve the metrics of detection on oversized input images which can be a common scenario in webpages analysis. Models in version nano achieved the best results in terms of speed, while more complexed architectures scored better in terms of other metrics.
Authors: Caihua Liu, Xu Li, Wenjing Xue, Wei Tang, Xia Feng
Abstract: Existing video captioning methods merely provide shallow or simplistic representations of object behaviors, resulting in superficial and ambiguous descriptions. However, object behavior is dynamic and complex. To comprehensively capture the essence of object behavior, we propose a dynamic action semantic-aware graph transformer. Firstly, a multi-scale temporal modeling module is designed to flexibly learn long and short-term latent action features. It not only acquires latent action features across time scales, but also considers local latent action details, enhancing the coherence and sensitiveness of latent action representations. Secondly, a visual-action semantic aware module is proposed to adaptively capture semantic representations related to object behavior, enhancing the richness and accurateness of action representations. By harnessing the collaborative efforts of these two modules,we can acquire rich behavior representations to generate human-like natural descriptions. Finally, this rich behavior representations and object representations are used to construct a temporal objects-action graph, which is fed into the graph transformer to model the complex temporal dependencies between objects and actions. To avoid adding complexity in the inference phase, the behavioral knowledge of the objects will be distilled into a simple network through knowledge distillation. The experimental results on MSVD and MSR-VTT datasets demonstrate that the proposed method achieves significant performance improvements across multiple metrics.
Authors: Zirui Song, Jingpu Yang, Yuan Huang, Jonathan Tonglet, Zeyu Zhang, Tao Cheng, Meng Fang, Iryna Gurevych, Xiuying Chen
Abstract: Geolocation, the task of identifying an image's location, requires complex reasoning and is crucial for navigation, monitoring, and cultural preservation. However, current methods often produce coarse, imprecise, and non-interpretable localization. A major challenge lies in the quality and scale of existing geolocation datasets. These datasets are typically small-scale and automatically constructed, leading to noisy data and inconsistent task difficulty, with images that either reveal answers too easily or lack sufficient clues for reliable inference. To address these challenges, we introduce a comprehensive geolocation framework with three key components: GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric, collectively designed to address critical challenges and drive advancements in geolocation research. At the core of this framework is GeoComp (Geolocation Competition Dataset), a large-scale dataset collected from a geolocation game platform involving 740K users over two years. It comprises 25 million entries of metadata and 3 million geo-tagged locations spanning much of the globe, with each location annotated thousands to tens of thousands of times by human users. The dataset offers diverse difficulty levels for detailed analysis and highlights key gaps in current models. Building on this dataset, we propose Geographical Chain-of-Thought (GeoCoT), a novel multi-step reasoning framework designed to enhance the reasoning capabilities of Large Vision Models (LVMs) in geolocation tasks. GeoCoT improves performance by integrating contextual and spatial cues through a multi-step process that mimics human geolocation reasoning. Finally, using the GeoEval metric, we demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.
Authors: Wanke Xia, Ruxin Peng, Haoqi Chu, Xinlei Zhu, Zhiyu Yang, Yaojun Wang
Abstract: Rice is one of the most widely cultivated crops globally and has been developed into numerous varieties. The quality of rice during cultivation is primarily determined by its cultivar and characteristics. Traditionally, rice classification and quality assessment rely on manual visual inspection, a process that is both time-consuming and prone to errors. However, with advancements in machine vision technology, automating rice classification and quality evaluation based on its cultivar and characteristics has become increasingly feasible, enhancing both accuracy and efficiency. This study proposes a real-time evaluation mechanism for comprehensive rice grain assessment, integrating a one-stage object detection approach, a deep convolutional neural network, and traditional machine learning techniques. The proposed framework enables rice variety identification, grain completeness grading, and grain chalkiness evaluation. The rice grain dataset used in this study comprises approximately 20,000 images from six widely cultivated rice varieties in China. Experimental results demonstrate that the proposed mechanism achieves a mean average precision (mAP) of 99.14% in the object detection task and an accuracy of 97.89% in the classification task. Furthermore, the framework attains an average accuracy of 97.56% in grain completeness grading within the same rice variety, contributing to an effective quality evaluation system.
Authors: Yi-Fan Zhang, Hang Li, Dingjie Song, Lichao Sun, Tianlong Xu, Qingsong Wen
Abstract: Large Language Models (LLMs), such as GPT-4, have demonstrated impressive mathematical reasoning capabilities, achieving near-perfect performance on benchmarks like GSM8K. However, their application in personalized education remains limited due to an overemphasis on correctness over error diagnosis and feedback generation. Current models fail to provide meaningful insights into the causes of student mistakes, limiting their utility in educational contexts. To address these challenges, we present three key contributions. First, we introduce \textbf{MathCCS} (Mathematical Classification and Constructive Suggestions), a multi-modal benchmark designed for systematic error analysis and tailored feedback. MathCCS includes real-world problems, expert-annotated error categories, and longitudinal student data. Evaluations of state-of-the-art models, including \textit{Qwen2-VL}, \textit{LLaVA-OV}, \textit{Claude-3.5-Sonnet} and \textit{GPT-4o}, reveal that none achieved classification accuracy above 30\% or generated high-quality suggestions (average scores below 4/10), highlighting a significant gap from human-level performance. Second, we develop a sequential error analysis framework that leverages historical data to track trends and improve diagnostic precision. Finally, we propose a multi-agent collaborative framework that combines a Time Series Agent for historical analysis and an MLLM Agent for real-time refinement, enhancing error classification and feedback generation. Together, these contributions provide a robust platform for advancing personalized education, bridging the gap between current AI capabilities and the demands of real-world teaching.
Authors: Vincent Ress, Jonas Meyer, Wei Zhang, David Skuddis, Uwe Soergel, Norbert Haala
Abstract: The field of visual localization has been researched for several decades and has meanwhile found many practical applications. Despite the strong progress in this field, there are still challenging situations in which established methods fail. We present an approach to significantly improve the accuracy and reliability of established visual localization methods by adding rendered images. In detail, we first use a modern visual SLAM approach that provides a 3D Gaussian Splatting (3DGS) based map to create reference data. We demonstrate that enriching reference data with images rendered from 3DGS at randomly sampled poses significantly improves the performance of both geometry-based visual localization and Scene Coordinate Regression (SCR) methods. Through comprehensive evaluation in a large industrial environment, we analyze the performance impact of incorporating these additional rendered views.
Authors: Nikolaos Dionelis, Nicolas Long\'ep\'e, Alessandra Feliciotti, Mattia Marconcini, Devis Peressutti, Nika Oman Kadunc, JaeWan Park, Hagai Raja Sinulingga, Steve Andreas Immanuel, Ba Tran, Caroline Arnold
Abstract: Estimating the construction year of buildings is of great importance for sustainability. Sustainable buildings minimize energy consumption and are a key part of responsible and sustainable urban planning and development to effectively combat climate change. By using Artificial Intelligence (AI) and recently proposed Transformer models, we are able to estimate the construction epoch of buildings from a multi-modal dataset. In this paper, we introduce a new benchmark multi-modal dataset, i.e. the Map your City Dataset (MyCD), containing top-view Very High Resolution (VHR) images, Earth Observation (EO) multi-spectral data from the Copernicus Sentinel-2 satellite constellation, and street-view images in many different cities in Europe, co-localized with respect to the building under study and labelled with the construction epoch. We assess EO generalization performance on new/ previously unseen cities that have been held-out from training and appear only during inference. In this work, we present the community-based data challenge we organized based on MyCD. The ESA AI4EO Challenge MapYourCity was opened in 2024 for 4 months. Here, we present the Top-4 performing models, and the main evaluation results. During inference, the performance of the models using both all three input modalities and only the two top-view modalities, i.e. without the street-view images, is examined. The evaluation results show that the models are effective and can achieve good performance on this difficult real-world task of estimating the age of buildings, even on previously unseen cities, as well as even using only the two top-view modalities (i.e. VHR and Sentinel-2) during inference.
Authors: Junxiao Wang, Ting Zhang, Heng Yu, Jingdong Wang, Hua Huang
Abstract: Geometric diagrams are critical in conveying mathematical and scientific concepts, yet traditional diagram generation methods are often manual and resource-intensive. While text-to-image generation has made strides in photorealistic imagery, creating accurate geometric diagrams remains a challenge due to the need for precise spatial relationships and the scarcity of geometry-specific datasets. This paper presents MagicGeo, a training-free framework for generating geometric diagrams from textual descriptions. MagicGeo formulates the diagram generation process as a coordinate optimization problem, ensuring geometric correctness through a formal language solver, and then employs coordinate-aware generation. The framework leverages the strong language translation capability of large language models, while formal mathematical solving ensures geometric correctness. We further introduce MagicGeoBench, a benchmark dataset of 220 geometric diagram descriptions, and demonstrate that MagicGeo outperforms current methods in both qualitative and quantitative evaluations. This work provides a scalable, accurate solution for automated diagram generation, with significant implications for educational and academic applications.
Authors: Shuyong Gao, Yu'ang Feng, Qishan Wang, Lingyi Hong, Xinyu Zhou, Liu Fei, Yan Wang, Wenqiang Zhang
Abstract: Video Camouflaged Object Detection (VCOD) is a challenging task which aims to identify objects that seamlessly concealed within the background in videos. The dynamic properties of video enable detection of camouflaged objects through motion cues or varied perspectives. Previous VCOD datasets primarily contain animal objects, limiting the scope of research to wildlife scenarios. However, the applications of VCOD extend beyond wildlife and have significant implications in security, art, and medical fields. Addressing this problem, we construct a new large-scale multi-domain VCOD dataset MSVCOD. To achieve high-quality annotations, we design a semi-automatic iterative annotation pipeline that reduces costs while maintaining annotation accuracy. Our MSVCOD is the largest VCOD dataset to date, introducing multiple object categories including human, animal, medical, and vehicle objects for the first time, while also expanding background diversity across various environments. This expanded scope increases the practical applicability of the VCOD task in camouflaged object detection. Alongside this dataset, we introduce a one-steam video camouflage object detection model that performs both feature extraction and information fusion without additional motion feature fusion modules. Our framework achieves state-of-the-art results on the existing VCOD animal dataset and the proposed MSVCOD. The dataset and code will be made publicly available.
Authors: Huu-Thien Tran, Phuoc-Sang Pham, Thai-Son Tran, Khoa Luu
Abstract: Referring Multi-Object Tracking (RMOT) is a relatively new concept that has rapidly gained traction as a promising research direction at the intersection of computer vision and natural language processing. Unlike traditional multi-object tracking, RMOT identifies and tracks objects and incorporates textual descriptions for object class names, making the approach more intuitive. Various techniques have been proposed to address this challenging problem; however, most require the training of the entire network due to their end-to-end nature. Among these methods, iKUN has emerged as a particularly promising solution. Therefore, we further explore its pipeline and enhance its performance. In this paper, we introduce a practical module dubbed Memory-Efficient Cross-modality -- MEX. This memory-efficient technique can be directly applied to off-the-shelf trackers like iKUN, resulting in significant architectural improvements. Our method proves effective during inference on a single GPU with 4 GB of memory. Among the various benchmarks, the Refer-KITTI dataset, which offers diverse autonomous driving scenes with relevant language expressions, is particularly useful for studying this problem. Empirically, our method demonstrates effectiveness and efficiency regarding HOTA tracking scores, substantially improving memory allocation and processing speed.
Authors: Idris Hamoud, Vinkle Srivastav, Muhammad Abdullah Jamal, Didier Mutter, Omid Mohareri, Nicolas Padoy
Abstract: Understanding the workflow of surgical procedures in complex operating rooms requires a deep understanding of the interactions between clinicians and their environment. Surgical activity recognition (SAR) is a key computer vision task that detects activities or phases from multi-view camera recordings. Existing SAR models often fail to account for fine-grained clinician movements and multi-view knowledge, or they require calibrated multi-view camera setups and advanced point-cloud processing to obtain better results. In this work, we propose a novel calibration-free multi-view multi-modal pretraining framework called Multiview Pretraining for Video-Pose Surgical Activity Recognition PreViPS, which aligns 2D pose and vision embeddings across camera views. Our model follows CLIP-style dual-encoder architecture: one encoder processes visual features, while the other encodes human pose embeddings. To handle the continuous 2D human pose coordinates, we introduce a tokenized discrete representation to convert the continuous 2D pose coordinates into discrete pose embeddings, thereby enabling efficient integration within the dual-encoder framework. To bridge the gap between these two modalities, we propose several pretraining objectives using cross- and in-modality geometric constraints within the embedding space and incorporating masked pose token prediction strategy to enhance representation learning. Extensive experiments and ablation studies demonstrate improvements over the strong baselines, while data-efficiency experiments on two distinct operating room datasets further highlight the effectiveness of our approach. We highlight the benefits of our approach for surgical activity recognition in both multi-view and single-view settings, showcasing its practical applicability in complex surgical environments. Code will be made available at: https://github.com/CAMMA-public/PreViPS.
Authors: Daniel A. P. Oliveira, Louren\c{c}o Teodoro, David Martins de Matos
Abstract: Current image captioning systems lack the ability to link descriptive text to specific visual elements, making their outputs difficult to verify. While recent approaches offer some grounding capabilities, they cannot track object identities across multiple references or ground both actions and objects simultaneously. We propose a novel ID-based grounding system that enables consistent object reference tracking and action-object linking, and present GroundCap, a dataset containing 52,016 images from 77 movies, with 344 human-annotated and 52,016 automatically generated captions. Each caption is grounded on detected objects (132 classes) and actions (51 classes) using a tag system that maintains object identity while linking actions to the corresponding objects. Our approach features persistent object IDs for reference tracking, explicit action-object linking, and segmentation of background elements through K-means clustering. We propose gMETEOR, a metric combining caption quality with grounding accuracy, and establish baseline performance by fine-tuning Pixtral-12B. Human evaluation demonstrates our approach's effectiveness in producing verifiable descriptions with coherent object references.
Authors: Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, Junyang Lin
Abstract: We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.
Authors: Shengguang Wu, Fan-Yun Sun, Kaiyue Wen, Nick Haber
Abstract: Recent studies have shown that Large Vision-Language Models (VLMs) tend to neglect image content and over-rely on language-model priors, resulting in errors in visually grounded tasks and hallucinations. We hypothesize that this issue arises because existing VLMs are not explicitly trained to generate texts that are accurately grounded in fine-grained image details. To enhance visual feedback during VLM training, we propose S-VCO (Symmetrical Visual Contrastive Optimization), a novel finetuning objective that steers the model toward capturing important visual details and aligning them with corresponding text tokens. To further facilitate this detailed alignment, we introduce MVC, a paired image-text dataset built by automatically filtering and augmenting visual counterfactual data to challenge the model with hard contrastive cases involving Minimal Visual Contrasts. Experiments show that our method consistently improves VLM performance across diverse benchmarks covering various abilities and domains, achieving up to a 22% reduction in hallucinations, and significant gains in vision-centric and general tasks. Notably, these improvements become increasingly pronounced in benchmarks with higher visual dependency. In short, S-VCO offers a significant enhancement of VLM's visually-dependent task performance while retaining or even improving the model's general abilities. We opensource our code at https://s-vco.github.io/
URLs: https://s-vco.github.io/
Authors: Zeki Doruk Erden, Boi Faltings
Abstract: Current machine learning paradigm relies on continuous representations like neural networks, which iteratively adjust parameters to approximate outcomes rather than directly learning the structure of problem. This spreads information across the network, causing issues like information loss and incomprehensibility Building on prior work in environment dynamics modeling, we propose a method that learns visual space in a structured, continual manner. Our approach refines networks to capture the core structure of objects while representing significant subvariants in structure efficiently. We demonstrate this with 2D shape detection, showing incremental learning on MNIST without overwriting knowledge and creating compact, comprehensible representations. These results offer a promising step toward a transparent, continually learning alternative to traditional neural networks for visual processing.
Authors: Ang Jia Ning Shermaine, Michalis Lazarou, Tania Stathaki
Abstract: This paper investigates the impact of various data augmentation techniques on the performance of object detection models. Specifically, we explore classical augmentation methods, image compositing, and advanced generative models such as Stable Diffusion XL and ControlNet. The objective of this work is to enhance model robustness and improve detection accuracy, particularly when working with limited annotated data. Using YOLOv8, we fine-tune the model on a custom dataset consisting of commercial and military aircraft, applying different augmentation strategies. Our experiments show that image compositing offers the highest improvement in detection performance, as measured by precision, recall, and mean Average Precision (mAP@0.50). Other methods, including Stable Diffusion XL and ControlNet, also demonstrate significant gains, highlighting the potential of advanced data augmentation techniques for object detection tasks. The results underline the importance of dataset diversity and augmentation in achieving better generalization and performance in real-world applications. Future work will explore the integration of semi-supervised learning methods and further optimizations to enhance model performance across larger and more complex datasets.
Authors: Hao Huang, Shuaihang Yuan, Yu Hao, Congcong Wen, Yi Fang
Abstract: A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a significant domain gap between the modalities of vision and language, especially when training data is scarce in few-shot settings, where only very limited data are available for training. In order to mitigate this issue, a multi-modal meta-learning framework has been proposed to bridge the gap between two frozen pretrained large vision and language models by introducing a tunable prompt connecting these two large models. For few-shot image captioning, the existing multi-model meta-learning framework utilizes a one-step prompting scheme to accumulate the visual features of input images to guide the language model, which struggles to generate accurate image descriptions with only a few training samples. Instead, we propose a chain-of-thought (CoT) meta-learning scheme as a multi-step image captioning procedure to better imitate how humans describe images. In addition, we further propose to learn different meta-parameters of the model corresponding to each CoT step in distinct subspaces to avoid interference. We evaluated our method on three commonly used image captioning datasets, i.e., MSCOCO, Flickr8k, and Flickr30k, under few-shot settings. The results of our experiments indicate that our chain-of-thought subspace meta-learning strategy is superior to the baselines in terms of performance across different datasets measured by different metrics.
Authors: Sara Dorfman, Dana Cohen-Bar, Rinon Gal, Daniel Cohen-Or
Abstract: Content creators often draw inspiration from multiple visual sources, combining distinct elements to craft new compositions. Modern computational approaches now aim to emulate this fundamental creative process. Although recent diffusion models excel at text-guided compositional synthesis, text as a medium often lacks precise control over visual details. Image-based composition approaches can capture more nuanced features, but existing methods are typically limited in the range of concepts they can capture, and require expensive training procedures or specialized data. We present IP-Composer, a novel training-free approach for compositional image generation that leverages multiple image references simultaneously, while using natural language to describe the concept to be extracted from each image. Our method builds on IP-Adapter, which synthesizes novel images conditioned on an input image's CLIP embedding. We extend this approach to multiple visual inputs by crafting composite embeddings, stitched from the projections of multiple input images onto concept-specific CLIP-subspaces identified through text. Through comprehensive evaluation, we show that our approach enables more precise control over a larger range of visual concept compositions.
Authors: Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, O\u{g}uzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan
Abstract: Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization, recent methods like TiTok have shown that 1D tokenization can achieve high generation quality by eliminating grid redundancies. However, these methods typically use a fixed number of tokens and thus cannot adapt to an image's inherent complexity. We introduce FlexTok, a tokenizer that projects 2D images into variable-length, ordered 1D token sequences. For example, a 256x256 image can be resampled into anywhere from 1 to 256 discrete tokens, hierarchically and semantically compressing its information. By training a rectified flow model as the decoder and using nested dropout, FlexTok produces plausible reconstructions regardless of the chosen token sequence length. We evaluate our approach in an autoregressive generation setting using a simple GPT-style Transformer. On ImageNet, this approach achieves an FID<2 across 8 to 128 tokens, outperforming TiTok and matching state-of-the-art methods with far fewer tokens. We further extend the model to support to text-conditioned image generation and examine how FlexTok relates to traditional 2D tokenization. A key finding is that FlexTok enables next-token prediction to describe images in a coarse-to-fine "visual vocabulary", and that the number of tokens to generate depends on the complexity of the generation task.
Authors: Suhas Gopal, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt
Abstract: Separable 3D reconstruction of multiple objects from multi-view RGB images -- resulting in two different 3D shapes for the two objects with a clear separation between them -- remains a sparsely researched problem. It is challenging due to severe mutual occlusions and ambiguities along the objects' interaction boundaries. This paper investigates the setting and introduces a new neuro-implicit method that can reconstruct the geometry and appearance of two objects undergoing close interactions while disjoining both in 3D, avoiding surface inter-penetrations and enabling novel-view synthesis of the observed scene. The framework is end-to-end trainable and supervised using a novel alpha-blending regularisation that ensures that the two geometries are well separated even under extreme occlusions. Our reconstruction method is markerless and can be applied to rigid as well as articulated objects. We introduce a new dataset consisting of close interactions between a human and an object and also evaluate on two scenes of humans performing martial arts. The experiments confirm the effectiveness of our framework and substantial improvements using 3D and novel view synthesis metrics compared to several existing approaches applicable in our setting.
Authors: Andreas Radler, Eric Volkmann, Johannes Brandstetter, Arturs Berzins
Abstract: Topology optimization (TO) is a family of computational methods that derive near-optimal geometries from formal problem descriptions. Despite their success, established TO methods are limited to generating single solutions, restricting the exploration of alternative designs. To address this limitation, we introduce Generative Topology Optimization (GenTO) - a data-free method that trains a neural network to generate structurally compliant shapes and explores diverse solutions through an explicit diversity constraint. The network is trained with a solver-in-the-loop, optimizing the material distribution in each iteration. The trained model produces diverse shapes that closely adhere to the design requirements. We validate GenTO on 2D and 3D TO problems. Our results demonstrate that GenTO produces more diverse solutions than any prior method while maintaining near-optimality and being an order of magnitude faster due to inherent parallelism. These findings open new avenues for engineering and design, offering enhanced flexibility and innovation in structural optimization.
Authors: Danli Shi, Bowen Liu, Zhen Tian, Yue Wu, Jiancheng Yang, Ruoyu Chen, Bo Yang, Ou Xiao, Mingguang He
Abstract: Myopia, projected to affect 50% population globally by 2050, is a leading cause of vision loss. Eyes with pathological myopia exhibit distinctive shape distributions, which are closely linked to the progression of vision-threatening complications. Recent understanding of eye-shape-based biomarkers requires magnetic resonance imaging (MRI), however, it is costly and unrealistic in routine ophthalmology clinics. We present Fundus2Globe, the first AI framework that synthesizes patient-specific 3D eye globes from ubiquitous 2D color fundus photographs (CFPs) and routine metadata (axial length, spherical equivalent), bypassing MRI dependency. By integrating a 3D morphable eye model (encoding biomechanical shape priors) with a latent diffusion model, our approach achieves submillimeter accuracy in reconstructing posterior ocular anatomy efficiently. Fundus2Globe uniquely quantifies how vision-threatening lesions (e.g., staphylomas) in CFPs correlate with MRI-validated 3D shape abnormalities, enabling clinicians to simulate posterior segment changes in response to refractive shifts. External validation demonstrates its robust generation performance, ensuring fairness across underrepresented groups. By transforming 2D fundus imaging into 3D digital replicas of ocular structures, Fundus2Globe is a gateway for precision ophthalmology, laying the foundation for AI-driven, personalized myopia management.
Authors: Pedro Martin, Ant\'onio Rodrigues, Jo\~ao Ascenso, Maria Paula Queluz
Abstract: Gaussian Splatting (GS) offers a promising alternative to Neural Radiance Fields (NeRF) for real-time 3D scene rendering. Using a set of 3D Gaussians to represent complex geometry and appearance, GS achieves faster rendering times and reduced memory consumption compared to the neural network approach used in NeRF. However, quality assessment of GS-generated static content is not yet explored in-depth. This paper describes a subjective quality assessment study that aims to evaluate synthesized videos obtained with several static GS state-of-the-art methods. The methods were applied to diverse visual scenes, covering both 360-degree and forward-facing (FF) camera trajectories. Moreover, the performance of 18 objective quality metrics was analyzed using the scores resulting from the subjective study, providing insights into their strengths, limitations, and alignment with human perception. All videos and scores are made available providing a comprehensive database that can be used as benchmark on GS view synthesis and objective quality metrics.
Authors: Jiaju Ma, Maneesh Agrawala
Abstract: While large vision-language models can generate motion graphics animations from text prompts, they regularly fail to include all of spatio-temporal properties described in the prompt. We introduce MoVer, a motion verification DSL based on first-order logic that can check spatio-temporal properties of a motion graphics animation. We identify a general set of such properties that people commonly use to describe animations (e.g., the direction and timing of motions, the relative positioning of objects, etc.). We implement these properties as predicates in MoVer and provide an execution engine that can apply a MoVer program to any input SVG-based motion graphics animation. We then demonstrate how MoVer can be used in an LLM-based synthesis and verification pipeline for iteratively refining motion graphics animations. Given a text prompt, our pipeline synthesizes a motion graphics animation and a corresponding MoVer program. Executing the verification program on the animation yields a report of the predicates that failed and the report can be automatically fed back to LLM to iteratively correct the animation. To evaluate our pipeline, we build a synthetic dataset of 5600 text prompts paired with ground truth MoVer verification programs. We find that while our LLM-based pipeline is able to automatically generate a correct motion graphics animation for 58.8% of the test prompts without any iteration, this number raises to 93.6% with up to 50 correction iterations. Project website: https://mover-dsl.github.io/
Authors: Linzhuang Sun, Hao Liang, Jingxuan Wei, Bihui Yu, Tianpeng Li, Fan Yang, Zenan Zhou, Wentao Zhang
Abstract: According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we introduce MM-Verifier and MM-Reasoner to enhance multimodal reasoning through longer inference and more robust verification. First, we propose a two-step MM verification data synthesis method, which combines a simulation-based tree search with verification and uses rejection sampling to generate high-quality Chain-of-Thought (COT) data. This data is then used to fine-tune the verification model, MM-Verifier. Additionally, we present a more efficient method for synthesizing MMCOT data, bridging the gap between text-based and multimodal reasoning. The synthesized data is used to fine-tune MM-Reasoner. Our MM-Verifier outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. Moreover, MM-Reasoner demonstrates strong effectiveness and scalability, with performance improving as data size increases. Finally, our approach achieves strong performance when combining MM-Reasoner and MM-Verifier, reaching an accuracy of 65.3 on MathVista, surpassing GPT-4o (63.8) with 12 rollouts.
Authors: Simen Hexeberg, Mandar Chitre, Matthias Hoffmann-Kuhnt, Bing Wen Low
Abstract: Changes in bird populations can indicate broader changes in ecosystems, making birds one of the most important animal groups to monitor. Combining machine learning and passive acoustics enables continuous monitoring over extended periods without direct human involvement. However, most existing techniques require extensive expert-labeled datasets for training and cannot easily detect time-overlapping calls in busy soundscapes. We propose a semi-supervised acoustic bird detector designed to allow both the detection of time-overlapping calls (when separated in frequency) and the use of few labeled training samples. The classifier is trained and evaluated on a combination of community-recorded open-source data and long-duration soundscape recordings from Singapore. It achieves a mean F0.5 score of 0.701 across 315 classes from 110 bird species on a hold-out test set, with an average of 11 labeled training samples per class. It outperforms the state-of-the-art BirdNET classifier on a test set of 103 bird species despite significantly fewer labeled training samples. The detector is further tested on 144 microphone-hours of continuous soundscape data. The rich soundscape in Singapore makes suppression of false positives a challenge on raw, continuous data streams. Nevertheless, we demonstrate that achieving high precision in such environments with minimal labeled training data is possible.
Authors: Chen-An Li, Tzu-Han Lin, Yun-Nung Chen, Hung-yi Lee
Abstract: Large vision-language models (LVLMs) perform outstandingly across various multimodal tasks. However, their ability to evaluate generated content remains limited, and training vision-language reward models (VLRMs) with preference data is computationally expensive. This paper explores a training-free alternative by merging text-based reward models (RMs) with LVLMs to create VLRMs. Our approach shows that integrating these models leads to improved performance over LVLMs' scoring and text-based RMs, offering an efficient method for incorporating textual preferences into LVLMs.
Authors: Shiwei Lian, Feitian Zhang
Abstract: The object goal visual navigation is the task of navigating to a specific target object using egocentric visual observations. Recent end-to-end navigation models based on deep reinforcement learning have achieved remarkable performance in finding and reaching target objects. However, the collision problem of these models during navigation remains unresolved, since the collision is typically neglected when evaluating the success. Although incorporating a negative reward for collision during training appears straightforward, it results in a more conservative policy, thereby limiting the agent's ability to reach targets. In addition, many of these models utilize only RGB observations, further increasing the difficulty of collision avoidance without depth information. To address these limitations, a new concept -- collision-free success is introduced to evaluate the ability of navigation models to find a collision-free path towards the target object. A two-stage training method with collision prediction is proposed to improve the collision-free success rate of the existing navigation models using RGB observations. In the first training stage, the collision prediction module supervises the agent's collision states during exploration to learn to predict the possible collision. In the second stage, leveraging the trained collision prediction, the agent learns to navigate to the target without collision. The experimental results in the AI2-THOR environment demonstrate that the proposed method greatly improves the collision-free success rate of different navigation models and outperforms other comparable collision-avoidance methods.
Authors: Ziming Hong, Yongli Xiang, Tongliang Liu
Abstract: Over the past decades, researchers have primarily focused on improving the generalization abilities of models, with limited attention given to regulating such generalization. However, the ability of models to generalize to unintended data (e.g., harmful or unauthorized data) can be exploited by malicious adversaries in unforeseen ways, potentially resulting in violations of model ethics. Non-transferable learning (NTL), a task aimed at reshaping the generalization abilities of deep learning models, was proposed to address these challenges. While numerous methods have been proposed in this field, a comprehensive review of existing progress and a thorough analysis of current limitations remain lacking. In this paper, we bridge this gap by presenting the first comprehensive survey on NTL and introducing NTLBench, the first benchmark to evaluate NTL performance and robustness within a unified framework. Specifically, we first introduce the task settings, general framework, and criteria of NTL, followed by a summary of NTL approaches. Furthermore, we emphasize the often-overlooked issue of robustness against various attacks that can destroy the non-transferable mechanism established by NTL. Experiments conducted via NTLBench verify the limitations of existing NTL methods in robustness. Finally, we discuss the practical applications of NTL, along with its future directions and associated challenges.
Authors: Takuya Matsuyama, Shinji Nishimoto, Yu Takagi
Abstract: Understanding the property of neural populations (or voxels) in the human brain can advance our comprehension of human perceptual and cognitive processing capabilities and contribute to developing brain-inspired computer models. Recent encoding models using deep neural networks (DNNs) have successfully predicted voxel-wise activity. However, interpreting the properties that explain voxel responses remains challenging because of the black-box nature of DNNs. As a solution, we propose LLM-assisted Visual Cortex Captioning (LaVCa), a data-driven approach that uses large language models (LLMs) to generate natural-language captions for images to which voxels are selective. By applying LaVCa for image-evoked brain activity, we demonstrate that LaVCa generates captions that describe voxel selectivity more accurately than the previously proposed method. Furthermore, the captions generated by LaVCa quantitatively capture more detailed properties than the existing method at both the inter-voxel and intra-voxel levels. Furthermore, a more detailed analysis of the voxel-specific properties generated by LaVCa reveals fine-grained functional differentiation within regions of interest (ROIs) in the visual cortex and voxels that simultaneously represent multiple distinct concepts. These findings offer profound insights into human visual representations by assigning detailed captions throughout the visual cortex while highlighting the potential of LLM-based methods in understanding brain representations. Please check out our webpage at https://sites.google.com/view/lavca-llm/
Authors: Yucheng Zeng
Abstract: Medical image segmentation plays a crucial role in various clinical applications. A major challenge in medical image segmentation is achieving accurate delineation of regions of interest in the presence of noise, low contrast, or complex anatomical structures. Existing segmentation models often neglect the integration of multi-grained information and fail to preserve edge details, which are critical for precise segmentation. To address these challenges, we propose a novel image semantic segmentation model called the Multi-Grained Feature Integration Network (MGFI-Net). Our MGFI-Net is designed with two dedicated modules to tackle these issues. First, to enhance segmentation accuracy, we introduce a Multi-Grained Feature Extraction Module, which leverages hierarchical relationships between different feature scales to selectively focus on the most relevant information. Second, to preserve edge details, we incorporate an Edge Enhancement Module that effectively retains and integrates boundary information to refine segmentation results. Extensive experiments demonstrate that MGFI-Net not only outperforms state-of-the-art methods in terms of segmentation accuracy but also achieves superior time efficiency, establishing it as a leading solution for real-time medical image segmentation.
Authors: Hang Yin, Li Qiao, Yu Ma, Shuo Sun, Kan Li, Zhen Gao, Dusit Niyato
Abstract: Despite significant advancements in traditional syntactic communications based on Shannon's theory, these methods struggle to meet the requirements of 6G immersive communications, especially under challenging transmission conditions. With the development of generative artificial intelligence (GenAI), progress has been made in reconstructing videos using high-level semantic information. In this paper, we propose a scalable generative video semantic communication framework that extracts and transmits semantic information to achieve high-quality video reconstruction. Specifically, at the transmitter, description and other condition signals (e.g., first frame, sketches, etc.) are extracted from the source video, functioning as text and structural semantics, respectively. At the receiver, the diffusion-based GenAI large models are utilized to fuse the semantics of the multiple modalities for reconstructing the video. Simulation results demonstrate that, at an ultra-low channel bandwidth ratio (CBR), our scheme effectively captures semantic information to reconstruct videos aligned with human perception under different signal-to-noise ratios. Notably, the proposed ``First Frame+Desc." scheme consistently achieves CLIP score exceeding 0.92 at CBR = 0.0057 for SNR > 0 dB. This demonstrates its robust performance even under low SNR conditions.
Authors: Yiran Qin, Ao Sun, Yuze Hong, Benyou Wang, Ruimao Zhang
Abstract: Navigating unfamiliar environments presents significant challenges for household robots, requiring the ability to recognize and reason about novel decoration and layout. Existing reinforcement learning methods cannot be directly transferred to new environments, as they typically rely on extensive mapping and exploration, leading to time-consuming and inefficient. To address these challenges, we try to transfer the logical knowledge and the generalization ability of pre-trained foundation models to zero-shot navigation. By integrating a large vision-language model with a diffusion network, our approach named \mname ~constructs a visual predictor that continuously predicts the agent's potential observations in the next step which can assist robots generate robust actions. Furthermore, to adapt the temporal property of navigation, we introduce temporal historical information to ensure that the predicted image is aligned with the navigation scene. We then carefully designed an information fusion framework that embeds the predicted future frames as guidance into goal-reaching policy to solve downstream image navigation tasks. This approach enhances navigation control and generalization across both simulated and real-world environments. Through extensive experimentation, we demonstrate the robustness and versatility of our method, showcasing its potential to improve the efficiency and effectiveness of robotic navigation in diverse settings.
Authors: Bartlomiej Wronski
Abstract: Texture and material blending is one of the leading methods for adding variety to rendered virtual worlds, creating composite materials, and generating procedural content. When done naively, it can introduce either visible seams or contrast loss, leading to an unnatural look not representative of blended textures. Earlier work proposed addressing this problem through careful manual parameter tuning, lengthy per-texture statistics precomputation, look-up tables, or training deep neural networks. In this work, we propose an alternative approach based on insights from image processing and Laplacian pyramid blending. Our approach does not require any precomputation or increased memory usage (other than the presence of a regular, non-Laplacian, texture mipmap chain), does not produce ghosting, preserves sharp local features, and can run in real time on the GPU at the cost of a few additional lower mipmap texture taps.
Authors: Arjun Gupta, Rishik Sathua, Saurabh Gupta
Abstract: Many everyday mobile manipulation tasks require precise interaction with small objects, such as grasping a knob to open a cabinet or pressing a light switch. In this paper, we develop Servoing with Vision Models (SVM), a closed-loop training-free framework that enables a mobile manipulator to tackle such precise tasks involving the manipulation of small objects. SVM employs an RGB-D wrist camera and uses visual servoing for control. Our novelty lies in the use of state-of-the-art vision models to reliably compute 3D targets from the wrist image for diverse tasks and under occlusion due to the end-effector. To mitigate occlusion artifacts, we employ vision models to out-paint the end-effector thereby significantly enhancing target localization. We demonstrate that aided by out-painting methods, open-vocabulary object detectors can serve as a drop-in module to identify semantic targets (e.g. knobs) and point tracking methods can reliably track interaction sites indicated by user clicks. This training-free method obtains an 85% zero-shot success rate on manipulating unseen objects in novel environments in the real world, outperforming an open-loop control method and an imitation learning baseline trained on 1000+ demonstrations by an absolute success rate of 50%.
Authors: Emanuele Ballarin, Alessio Ansuini, Luca Bortolussi
Abstract: In this work, we propose a novel adversarial defence mechanism for image classification - CARSO - blending the paradigms of adversarial training and adversarial purification in a synergistic robustness-enhancing way. The method builds upon an adversarially-trained classifier, and learns to map its internal representation associated with a potentially perturbed input onto a distribution of tentative clean reconstructions. Multiple samples from such distribution are classified by the same adversarially-trained model, and a carefully chosen aggregation of its outputs finally constitutes the robust prediction of interest. Experimental evaluation by a well-established benchmark of strong adaptive attacks, across different image datasets, shows that CARSO is able to defend itself against adaptive end-to-end white-box attacks devised for stochastic defences. Paying a modest clean accuracy toll, our method improves by a significant margin the state-of-the-art for Cifar-10, Cifar-100, and TinyImageNet-200 $\ell_\infty$ robust classification accuracy against AutoAttack. Code, and instructions to obtain pre-trained models are available at: https://github.com/emaballarin/CARSO .
Authors: Guoyao Shen, Yancheng Zhu, Mengyu Li, Ryan McNaughton, Hernan Jara, Sean B. Andersson, Chad W. Farris, Stephan Anderson, Xin Zhang
Abstract: Recent advances in MRI reconstruction have demonstrated remarkable success through deep learning-based models. However, most existing methods rely heavily on large-scale, task-specific datasets, making reconstruction in data-limited settings a critical yet underexplored challenge. While regularization by denoising (RED) leverages denoisers as priors for reconstruction, we propose Regularization by Neural Style Transfer (RNST), a novel framework that integrates a neural style transfer (NST) engine with a denoiser to enable magnetic field-transfer reconstruction. RNST generates high-field-quality images from low-field inputs without requiring paired training data, leveraging style priors to address limited-data settings. Our experiment results demonstrate RNST's ability to reconstruct high-quality images across diverse anatomical planes (axial, coronal, sagittal) and noise levels, achieving superior clarity, contrast, and structural fidelity compared to lower-field references. Crucially, RNST maintains robustness even when style and content images lack exact alignment, broadening its applicability in clinical environments where precise reference matches are unavailable. By combining the strengths of NST and denoising, RNST offers a scalable, data-efficient solution for MRI field-transfer reconstruction, demonstrating significant potential for resource-limited settings.
Authors: Kangcheng Liu, Yong-Jin Liu, Baoquan Chen
Abstract: Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize any unseen novel classes beyond the training categories in diverse real-world applications. Therefore, we are in urgent need of a framework that can simultaneously be applicable to both 3D point cloud segmentation and detection, particularly in the circumstances where the labels are rather scarce. This work presents a generalized and straightforward framework for dealing with 3D scene understanding when the labeled scenes are quite limited. To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy to extract and distill meaningful information from large-scale vision-language models, which helps benefit the open-vocabulary scene understanding tasks. To encourage latent instance discrimination and to guarantee efficiency, we propose the unsupervised region-level semantic contrastive learning scheme for point clouds, using confident predictions of the neural network to discriminate the intermediate feature embeddings at multiple stages. In the limited reconstruction case, our proposed approach, termed WS3D++, ranks 1st on the large-scale ScanNet benchmark on both the task of semantic segmentation and instance segmentation. Extensive experiments with both indoor and outdoor scenes demonstrated the effectiveness of our approach in both data-efficient learning and open-world few-shot learning. The code is made publicly available at: https://drive.google.com/drive/folders/1M58V-PtR8DBEwD296zJkNg_m2qq-MTAP?usp=sharing.
URLs: https://drive.google.com/drive/folders/1M58V-PtR8DBEwD296zJkNg_m2qq-MTAP?usp=sharing.
Authors: Boqian Wu, Qiao Xiao, Shiwei Liu, Lu Yin, Mykola Pechenizkiy, Decebal Constantin Mocanu, Maurice Van Keulen, Elena Mocanu
Abstract: Deep neural networks have evolved as the leading approach in 3D medical image segmentation due to their outstanding performance. However, the ever-increasing model size and computation cost of deep neural networks have become the primary barrier to deploying them on real-world resource-limited hardware. In pursuit of improving performance and efficiency, we propose a 3D medical image segmentation model, named Efficient to Efficient Network (E2ENet), incorporating two parametrically and computationally efficient designs. i. Dynamic sparse feature fusion (DSFF) mechanism: it adaptively learns to fuse informative multi-scale features while reducing redundancy. ii. Restricted depth-shift in 3D convolution: it leverages the 3D spatial information while keeping the model and computational complexity as 2D-based methods. We conduct extensive experiments on BTCV, AMOS-CT and Brain Tumor Segmentation Challenge, demonstrating that E2ENet consistently achieves a superior trade-off between accuracy and efficiency than prior arts across various resource constraints. E2ENet achieves comparable accuracy on the large-scale challenge AMOS-CT, while saving over 68\% parameter count and 29\% FLOPs in the inference phase, compared with the previous best-performing method. Our code has been made available at: https://github.com/boqian333/E2ENet-Medical.
Authors: Nan Huang, Ting Zhang, Yuhui Yuan, Dong Chen, Shanghang Zhang
Abstract: In this paper, we address the critical bottleneck in robotics caused by the scarcity of diverse 3D data by presenting a novel two-stage approach for generating high-quality 3D models from a single image. This method is motivated by the need to efficiently expand 3D asset creation, particularly for robotics datasets, where the variety of object types is currently limited compared to general image datasets. Unlike previous methods that primarily rely on general diffusion priors, which often struggle to align with the reference image, our approach leverages subject-specific prior knowledge. By incorporating subject-specific priors in both geometry and texture, we ensure precise alignment between the generated 3D content and the reference object. Specifically, we introduce a shading mode-aware prior into the NeRF optimization process, enhancing the geometry and refining texture in the coarse outputs to achieve superior quality. Extensive experiments demonstrate that our method significantly outperforms prior approaches.
Authors: Ilyass Abouelaziz, Youssef Mourchid
Abstract: This paper presents a framework to address the challenges involved in building point cloud cleaning, plane detection, and semantic segmentation, with the ultimate goal of enhancing building modeling. We focus in the cleaning stage on removing outliers from the acquired point cloud data by employing an adaptive threshold technique based on z-score measure. Following the cleaning process, we perform plane detection using the robust RANSAC paradigm. The goal is to carry out multiple plane segmentations, and to classify segments into distinct categories, such as floors, ceilings, and walls. The resulting segments can generate accurate and detailed point clouds representing the building's architectural elements. Moreover, we address the problem of semantic segmentation, which plays a vital role in the identification and classification of different components within the building, such as walls, windows, doors, roofs, and objects. Inspired by the PointNet architecture, we propose a deep learning architecture for efficient semantic segmentation in buildings. The results demonstrate the effectiveness of the proposed framework in handling building modeling tasks, paving the way for improved accuracy and efficiency in the field of building modelization.
Authors: Wanqing Cui, Rui Cheng, Jiafeng Guo, Xueqi Cheng
Abstract: Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single representation often struggles to capture complex content fully. Such models may ignore fine-grained information during matching, resulting in suboptimal retrieval results. To overcome this limitation and enhance the performance of two-stream models, we propose a Multi-view Attention Method (MVAM) for image-text matching. This approach leverages diverse attention heads with unique view codes to learn multiple representations for images and text, which are then concatenated for matching. We also incorporate a diversity objective to explicitly encourage attention heads to focus on distinct aspects of the input data, capturing complementary fine-grained details. This diversity enables the model to represent image-text pairs from multiple perspectives, ensuring a more comprehensive understanding and alignment of critical content. Our method allows models to encode images and text from different perspectives and focus on more critical details, leading to better matching performance. Our experiments on MSCOCO and Flickr30K demonstrate enhancements over existing models, and further case studies reveal that different attention heads can focus on distinct content, achieving more comprehensive representations.
Authors: Nicholas Bai, Rahul A. Iyer, Tuomas Oikarinen, Akshay Kulkarni, Tsui-Wei Weng
Abstract: In this paper, we propose Describe-and-Dissect (DnD), a novel method to describe the roles of hidden neurons in vision networks. DnD utilizes recent advancements in multimodal deep learning to produce complex natural language descriptions, without the need for labeled training data or a predefined set of concepts to choose from. Additionally, DnD is training-free, meaning we don't train any new models and can easily leverage more capable general purpose models in the future. We have conducted extensive qualitative and quantitative analysis to show that DnD outperforms prior work by providing higher quality neuron descriptions. Specifically, our method on average provides the highest quality labels and is more than 2$\times$ as likely to be selected as the best explanation for a neuron than the best baseline. Finally, we present a use case providing critical insights into land cover prediction models for sustainability applications. Our code and data are available at https://github.com/Trustworthy-ML-Lab/Describe-and-Dissect.
URLs: https://github.com/Trustworthy-ML-Lab/Describe-and-Dissect.
Authors: Ruyi Lian, Yuewei Lin, Longin Jan Latecki, Haibin Ling
Abstract: Localizing predefined 3D keypoints in a 2D image is an effective way to establish 3D-2D correspondences for 6DoF object pose estimation. However, unreliable localization results of invisible keypoints degrade the quality of correspondences. In this paper, we address this issue by localizing the important keypoints in terms of visibility. Since keypoint visibility information is currently missing in the dataset collection process, we propose an efficient way to generate binary visibility labels from available object-level annotations, for keypoints of both asymmetric objects and symmetric objects. We further derive real-valued visibility-aware importance from binary labels based on the PageRank algorithm. Taking advantage of the flexibility of our visibility-aware importance, we construct VAPO (Visibility-Aware POse estimator) by integrating the visibility-aware importance with a state-of-the-art pose estimation algorithm, along with additional positional encoding. VAPO can work in both CAD-based and CAD-free settings. Extensive experiments are conducted on popular pose estimation benchmarks including Linemod, Linemod-Occlusion, and YCB-V, demonstrating that VAPO clearly achieves state-of-the-art performances. Our code is available at https://github.com/RuyiLian/VAPO.
Authors: Yu Cai, Weiwen Zhang, Hao Chen, Kwang-Ting Cheng
Abstract: Anomaly detection (AD) aims at detecting abnormal samples that deviate from the expected normal patterns. Generally, it can be trained merely on normal data, without a requirement for abnormal samples, and thereby plays an important role in rare disease recognition and health screening in the medical domain. Despite the emergence of numerous methods for medical AD, the lack of a fair and comprehensive evaluation causes ambiguous conclusions and hinders the development of this field. To address this problem, this paper builds a benchmark with unified comparison. Seven medical datasets with five image modalities, including chest X-rays, brain MRIs, retinal fundus images, dermatoscopic images, and histopathology images, are curated for extensive evaluation. Thirty typical AD methods, including reconstruction and self-supervised learning-based methods, are involved in comparison of image-level anomaly classification and pixel-level anomaly segmentation. Furthermore, for the first time, we systematically investigate the effect of key components in existing methods, revealing unresolved challenges and potential future directions. The datasets and code are available at https://github.com/caiyu6666/MedIAnomaly.
Authors: Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kaji\'c, Su Wang, Emanuele Bugliarello, Yasumasa Onoe, Chris Knutsen, Cyrus Rashtchian, Jordi Pont-Tuset, Aida Nematzadeh
Abstract: While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for collecting human judgements, the quality of these components is not systematically measured. Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated. We address this gap by performing an extensive study evaluating auto-eval metrics and human templates. We provide three main contributions: (1) We introduce a comprehensive skills-based benchmark that can discriminate models across different human templates. This skills-based benchmark categorises prompts into sub-skills, allowing a practitioner to pinpoint not only which skills are challenging, but at what level of complexity a skill becomes challenging. (2) We gather human ratings across four templates and four T2I models for a total of >100K annotations. This allows us to understand where differences arise due to inherent ambiguity in the prompt and where they arise due to differences in metric and model quality. (3) Finally, we introduce a new QA-based auto-eval metric that is better correlated with human ratings than existing metrics for our new dataset, across different human templates, and on TIFA160.
Authors: Yizhuo Lu, Changde Du, Chong Wang, Xuanliu Zhu, Liuyun Jiang, Xujin Li, Huiguang He
Abstract: Reconstructing human dynamic vision from brain activity is a challenging task with great scientific significance. Although prior video reconstruction methods have made substantial progress, they still suffer from several limitations, including: (1) difficulty in simultaneously reconciling semantic (e.g. categorical descriptions), structure (e.g. size and color), and consistent motion information (e.g. order of frames); (2) low temporal resolution of fMRI, which poses a challenge in decoding multiple frames of video dynamics from a single fMRI frame; (3) reliance on video generation models, which introduces ambiguity regarding whether the dynamics observed in the reconstructed videos are genuinely derived from fMRI data or are hallucinations from generative model. To overcome these limitations, we propose a two-stage model named Mind-Animator. During the fMRI-to-feature stage, we decouple semantic, structure, and motion features from fMRI. Specifically, we employ fMRI-vision-language tri-modal contrastive learning to decode semantic feature from fMRI and design a sparse causal attention mechanism for decoding multi-frame video motion features through a next-frame-prediction task. In the feature-to-video stage, these features are integrated into videos using an inflated Stable Diffusion, effectively eliminating external video data interference. Extensive experiments on multiple video-fMRI datasets demonstrate that our model achieves state-of-the-art performance. Comprehensive visualization analyses further elucidate the interpretability of our model from a neurobiological perspective. Project page: https://mind-animator-design.github.io/.
Authors: Ted Lentsch, Holger Caesar, Dariu M. Gavrila
Abstract: Unsupervised 3D object detection methods have emerged to leverage vast amounts of data without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect mobile objects but penalize the detections of static instances during training. Multiple rounds of self-training are used to add detected static instances to the set of training targets; this procedure to improve performance is computationally expensive. To address this, we propose the method UNION. We use spatial clustering and self-supervised scene flow to obtain a set of static and dynamic object proposals from LiDAR. Subsequently, object proposals' visual appearances are encoded to distinguish static objects in the foreground and background by selecting static instances that are visually similar to dynamic objects. As a result, static and dynamic mobile objects are obtained together, and existing detectors can be trained with a single training. In addition, we extend 3D object discovery to detection by using object appearance-based cluster labels as pseudo-class labels for training object classification. We conduct extensive experiments on the nuScenes dataset and increase the state-of-the-art performance for unsupervised 3D object discovery, i.e. UNION more than doubles the average precision to 39.5. The code is available at github.com/TedLentsch/UNION.
Authors: Xiaoxiao Ma, Mohan Zhou, Tao Liang, Yalong Bai, Tiejun Zhao, Biye Li, Huaian Chen, Yi Jin
Abstract: We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm. Unlike VAR, which is constrained to class-conditioned synthesis for images up to 256$\times$256, STAR enables text-driven image generation up to 1024$\times$1024 through three key designs. First, we introduce a pre-trained text encoder to extract and adopt representations for textual constraints, enhancing details and generalizability. Second, given the inherent structural correlation across different scales, we leverage 2D Rotary Positional Encoding (RoPE) and tweak it into a normalized version, ensuring consistent interpretation of relative positions across token maps and stabilizing the training process. Third, we observe that simultaneously sampling all tokens within a single scale can disrupt inter-token relationships, leading to structural instability, particularly in high-resolution generation. To address this, we propose a novel stable sampling method that incorporates causal relationships into the sampling process, ensuring both rich details and stable structures. Compared to previous diffusion models and auto-regressive models, STAR surpasses existing benchmarks in fidelity, text-image consistency, and aesthetic quality, requiring just 2.21s for 1024$\times$1024 images on A100. This highlights the potential of auto-regressive methods in high-quality image synthesis, offering new directions for the text-to-image generation.
Authors: Kang Liao, Zongsheng Yue, Zhouxia Wang, Chen Change Loy
Abstract: Although learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing methods address this issue by improving data synthesis pipelines, estimating degradation kernels, employing deep internal learning, and performing domain adaptation and regularization. Previous domain adaptation methods have sought to bridge the domain gap by learning domain-invariant knowledge in either feature or pixel space. However, these techniques often struggle to extend to low-level vision tasks within a stable and compact framework. In this paper, we show that it is possible to perform domain adaptation via the noise space using diffusion models. In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful diffusion loss that guides the restoration model in progressively aligning both restored synthetic and real-world outputs with a target clean distribution. We refer to this method as denoising as adaptation. To prevent shortcuts during joint training, we present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model. They implicitly blur the boundaries between conditioned synthetic and real data and prevent the reliance of the model on easily distinguishable features. Experimental results on three classical image restoration tasks, namely denoising, deblurring, and deraining, demonstrate the effectiveness of the proposed method.
Authors: Haotian Sun, Tao Lei, Bowen Zhang, Yanghao Li, Haoshuo Huang, Ruoming Pang, Bo Dai, Nan Du
Abstract: Diffusion transformers have been widely adopted for text-to-image synthesis. While scaling these models up to billions of parameters shows promise, the effectiveness of scaling beyond current sizes remains underexplored and challenging. By explicitly exploiting the computational heterogeneity of image generations, we develop a new family of Mixture-of-Experts (MoE) models (EC-DIT) for diffusion transformers with expert-choice routing. EC-DIT learns to adaptively optimize the compute allocated to understand the input texts and generate the respective image patches, enabling heterogeneous computation aligned with varying text-image complexities. This heterogeneity provides an efficient way of scaling EC-DIT up to 97 billion parameters and achieving significant improvements in training convergence, text-to-image alignment, and overall generation quality over dense models and conventional MoE models. Through extensive ablations, we show that EC-DIT demonstrates superior scalability and adaptive compute allocation by recognizing varying textual importance through end-to-end training. Notably, in text-to-image alignment evaluation, our largest models achieve a state-of-the-art GenEval score of 71.68% and still maintain competitive inference speed with intuitive interpretability.
Authors: Hong-You Chen, Zhengfeng Lai, Haotian Zhang, Xinze Wang, Marcin Eichner, Keen You, Meng Cao, Bowen Zhang, Yinfei Yang, Zhe Gan
Abstract: Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone of multimodal large language models (MLLMs) to connect image inputs for language interactions. The success of CLIP as a vision-language foundation model relies on aligning web-crawled noisy text annotations at image levels. Nevertheless, such criteria may become insufficient for downstream tasks in need of fine-grained vision representations, especially when region-level understanding is demanding for MLLMs. In this paper, we improve the localization capability of CLIP with several advances. We propose a pre-training method called Contrastive Localized Language-Image Pre-training (CLOC) by complementing CLIP with region-text contrastive loss and modules. We formulate a new concept, promptable embeddings, of which the encoder produces image embeddings easy to transform into region representations given spatial hints. To support large-scale pre-training, we design a visually-enriched and spatially-localized captioning framework to effectively generate region-text pseudo-labels at scale. By scaling up to billions of annotated images, CLOC enables high-quality regional embeddings for image region recognition and retrieval tasks, and can be a drop-in replacement of CLIP to enhance MLLMs, especially on referring and grounding tasks.
Authors: Luca Barsellotti, Roberto Bigazzi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Abstract: In the last years, the research interest in visual navigation towards objects in indoor environments has grown significantly. This growth can be attributed to the recent availability of large navigation datasets in photo-realistic simulated environments, like Gibson and Matterport3D. However, the navigation tasks supported by these datasets are often restricted to the objects present in the environment at acquisition time. Also, they fail to account for the realistic scenario in which the target object is a user-specific instance that can be easily confused with similar objects and may be found in multiple locations within the environment. To address these limitations, we propose a new task denominated Personalized Instance-based Navigation (PIN), in which an embodied agent is tasked with locating and reaching a specific personal object by distinguishing it among multiple instances of the same category. The task is accompanied by PInNED, a dedicated new dataset composed of photo-realistic scenes augmented with additional 3D objects. In each episode, the target object is presented to the agent using two modalities: a set of visual reference images on a neutral background and manually annotated textual descriptions. Through comprehensive evaluations and analyses, we showcase the challenges of the PIN task as well as the performance and shortcomings of currently available methods designed for object-driven navigation, considering modular and end-to-end agents.
Authors: Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari Taghanaki, Andrea Tagliasacchi, Ghassan Hamarneh, Ali Mahdavi Amiri
Abstract: Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty increases when the segmentation is with arbitrary granularity, meaning the number of segments can vary arbitrarily, and masks are defined based on only one or a few sample images. In this paper, we address this issue by employing a pre-trained text to image diffusion model supplemented with an additional tracking mechanism. We demonstrate that our approach can effectively manage various segmentation scenarios and outperforms state-of-the-art alternatives.
Authors: Hongyu Chen, Chengcheng Chen, Fei Wang, Yuhu Shi, Weiming Zeng
Abstract: Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in complex backgrounds with fewer parameters remains a challenge. This letter introduces RSNet, a lightweight framework constructed to enhance ship detection in SAR imagery. To ensure accuracy with fewer parameters, we proposed Waveletpool-ContextGuided (WCG) as its backbone, guiding global context understanding through multi-scale wavelet features for effective detection in complex scenes. Additionally, Waveletpool-StarFusion (WSF) is introduced as the neck, employing a residual wavelet element-wise multiplication structure to achieve higher dimensional nonlinear features without increasing network width. The Lightweight-Shared (LS) module is designed as detect components to achieve efficient detection through lightweight shared convolutional structure and multi-format compatibility. Experiments on the SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Image Dataset (HRSID) demonstrate that RSNet achieves a strong balance between lightweight design and detection performance, surpassing many state-of-the-art detectors, reaching 72.5\% and 67.6\% in \textbf{\(\mathbf{mAP_{.50:.95}}\) }respectively with 1.49M parameters. Our code will be released soon.
Authors: Max Bengtsson, Elif Keles, Gorkem Durak, Syed Anwar, Yuri S. Velichko, Marius G. Linguraru, Angela J. Waanders, Ulas Bagci
Abstract: In this paper, we present a novel approach for segmenting pediatric brain tumors using a deep learning architecture, inspired by expert radiologists' segmentation strategies. Our model delineates four distinct tumor labels and is benchmarked on a held-out PED BraTS 2024 test set (i.e., pediatric brain tumor datasets introduced by BraTS). Furthermore, we evaluate our model's performance against the state-of-the-art (SOTA) model using a new external dataset of 30 patients from CBTN (Children's Brain Tumor Network), labeled in accordance with the PED BraTS 2024 guidelines and 2023 BraTS Adult Glioma dataset. We compare segmentation outcomes with the winning algorithm from the PED BraTS 2023 challenge as the SOTA model. Our proposed algorithm achieved an average Dice score of 0.642 and an HD95 of 73.0 mm on the CBTN test data, outperforming the SOTA model, which achieved a Dice score of 0.626 and an HD95 of 84.0 mm. Moreover, our model exhibits strong generalizability, attaining a 0.877 Dice score in whole tumor segmentation on the BraTS 2023 Adult Glioma dataset, surpassing existing SOTA. Our results indicate that the proposed model is a step towards providing more accurate segmentation for pediatric brain tumors, which is essential for evaluating therapy response and monitoring patient progress. Our source code is available at https://github.com/NUBagciLab/Pediatric-Brain-Tumor-Segmentation-Model.
URLs: https://github.com/NUBagciLab/Pediatric-Brain-Tumor-Segmentation-Model.
Authors: Yansong Qu, Zixuan Xu, Zilin Huang, Zihao Sheng, Tiantian Chen, Sikai Chen
Abstract: Semantic scene completion (SSC) is essential for achieving comprehensive perception in autonomous driving systems. However, existing SSC methods often overlook the high deployment costs in real-world applications. Traditional architectures, such as 3D Convolutional Neural Networks (3D CNNs) and self-attention mechanisms, face challenges in efficiently capturing long-range dependencies within 3D voxel grids, limiting their effectiveness. To address these issues, we introduce MetaSSC, a novel meta-learning-based framework for SSC that leverages deformable convolution, large-kernel attention, and the Mamba (D-LKA-M) model. Our approach begins with a voxel-based semantic segmentation (SS) pretraining task, aimed at exploring the semantics and geometry of incomplete regions while acquiring transferable meta-knowledge. Using simulated cooperative perception datasets, we supervise the perception training of a single vehicle using aggregated sensor data from multiple nearby connected autonomous vehicles (CAVs), generating richer and more comprehensive labels. This meta-knowledge is then adapted to the target domain through a dual-phase training strategy that does not add extra model parameters, enabling efficient deployment. To further enhance the model's capability in capturing long-sequence relationships within 3D voxel grids, we integrate Mamba blocks with deformable convolution and large-kernel attention into the backbone network. Extensive experiments demonstrate that MetaSSC achieves state-of-the-art performance, significantly outperforming competing models while also reducing deployment costs.
Authors: Yang You, Yixin Li, Congyue Deng, Yue Wang, Leonidas Guibas
Abstract: Vision foundation models, particularly the ViT family, have revolutionized image understanding by providing rich semantic features. However, despite their success in 2D comprehension, their abilities on grasping 3D spatial relationships are still unclear. In this work, we evaluate and enhance the 3D awareness of ViT-based models. We begin by systematically assessing their ability to learn 3D equivariant features, specifically examining the consistency of semantic embeddings across different viewpoints. Our findings indicate that improved 3D equivariance leads to better performance on various downstream tasks, including pose estimation, tracking, and semantic transfer. Building on this insight, we propose a simple yet effective finetuning strategy based on 3D correspondences, which significantly enhances the 3D correspondence understanding of existing vision models. Remarkably, finetuning on a single object for one iteration results in substantial gains. Our code is available at https://github.com/qq456cvb/3DCorrEnhance.
Authors: Ahc\`ene Boubekki, Samuel G. Fadel, Sebastian Mair
Abstract: Recent developments in the field of explainable artificial intelligence (XAI) for vision models investigate the information extracted by their feature encoder. We contribute to this effort and propose Neuro-Activated Vision Explanations (NAVE), which extracts the information captured by the encoder by clustering the feature activations of the frozen network to be explained. The method does not aim to explain the model's prediction but to answer questions such as which parts of the image are processed similarly or which information is kept in deeper layers. Experimentally, we leverage NAVE to show that the training dataset and the level of supervision affect which concepts are captured. In addition, our method reveals the impact of registers on vision transformers (ViT) and the information saturation caused by the watermark Clever Hans effect in the training set.
Authors: Massine El Khader, Elias Al Bouzidi, Abdellah Oumida, Mohammed Sbaihi, Eliott Binard, Jean-Philippe Poli, Wassila Ouerdane, Boussad Addad, Katarzyna Kapusta
Abstract: Recent advances in Diffusion Models have enabled the generation of images from text, with powerful closed-source models like DALL-E and Midjourney leading the way. However, open-source alternatives, such as StabilityAI's Stable Diffusion, offer comparable capabilities. These open-source models, hosted on Hugging Face, come equipped with ethical filter protections designed to prevent the generation of explicit images. This paper reveals first their limitations and then presents a novel text-based safety filter that outperforms existing solutions. Our research is driven by the critical need to address the misuse of AI-generated content, especially in the context of information warfare. DiffGuard enhances filtering efficacy, achieving a performance that surpasses the best existing filters by over 14%.
Authors: Jun Ye
Abstract: We propose a method to improve the generalization of skin lesion classification models by combining self-supervised learning (SSL) and active domain adaptation (ADA). The main steps of the approach include selection of an SSL pre-trained model on natural image datasets, subsequent SSL retraining on all available skin-lesion datasets, fine-tuning of the model on source domain data with labels, and application of ADA methods on target domain data. The efficacy of the proposed approach is assessed in ten skin lesion datasets with five different ADA methods, demonstrating its potential to improve generalization in settings with different amounts of domain shifts.
Authors: Michal Shlapentokh-Rothman, Yu-Xiong Wang, Derek Hoiem
Abstract: For users with limited computational resources, visual programming or prompting large language models (LLMs) to generate executable code for visual tasks, like visual question answering (VQA), remains largely inaccessible. Even with techniques such as distillation, adapting visual programming to smaller models or specific datasets is still quite challenging due to high annotation costs. We propose a low-cost visual program distillation method that can be used for models with fewer than 1 billion parameters and requires no human-generated program annotations. We achieve this through synthetic data augmentation based on decoupling programs into higher-level skills, called templates, and their corresponding arguments. Experimental results show that, with a relatively small amount of question/answer data, small language models can generate high-quality visual programs with the added benefit of much faster inference.
Authors: Xinhao Zhong, Shuoyang Sun, Xulin Gu, Zhaoyang Xu, Yaowei Wang, Jianlong Wu, Bin Chen
Abstract: Dataset distillation offers an efficient way to reduce memory and computational costs by optimizing a smaller dataset with performance comparable to the full-scale original. However, for large datasets and complex deep networks (e.g., ImageNet-1K with ResNet-101), the extensive optimization space limits performance, reducing its practicality. Recent approaches employ pre-trained diffusion models to generate informative images directly, avoiding pixel-level optimization and achieving notable results. However, these methods often face challenges due to distribution shifts between pre-trained models and target datasets, along with the need for multiple distillation steps across varying settings. To address these issues, we propose a novel framework orthogonal to existing diffusion-based distillation methods, leveraging diffusion models for selection rather than generation. Our method starts by predicting noise generated by the diffusion model based on input images and text prompts (with or without label text), then calculates the corresponding loss for each pair. With the loss differences, we identify distinctive regions of the original images. Additionally, we perform intra-class clustering and ranking on selected patches to maintain diversity constraints. This streamlined framework enables a single-step distillation process, and extensive experiments demonstrate that our approach outperforms state-of-the-art methods across various metrics.
Authors: Jiajia Liang
Abstract: Image shadow removal is a crucial task in computer vision. In real-world scenes, shadows alter image color and brightness, posing challenges for perception and texture recognition. Traditional and deep learning methods often overlook the distinct needs for handling hard and soft shadows, thereby lacking detailed processing to specifically address each type of shadow in images.We propose a dual-path model that processes these shadows separately using specially designed loss functions to accomplish the hard and soft shadow removal. The model classifies shadow types and processes them through appropriate paths to produce shadow-free outputs, integrating a Vision Transformer with UNet++ for enhanced edge detail and feature fusion. Our model outperforms state-of-the-art methods and achieves 2.905 RMSE value on the ISTD dataset, which demonstrates greater effectiveness than typical single-path approaches.
Authors: Lizhi Chen, Zhong Qian, Peifeng Li, Qiaoming Zhu
Abstract: Although existing methods have addressed fake news video detection as a classification problem, it is not clear why certain news content is identified as fake. Without proper explanation, end users may not be able to understand the potential meaning of fake news. Therefore, we propose a novel task, Fake News Video Explanation (FNVE), to generate natural language explanations that reveal the falseness of news videos. To this end, we first developed ONVE and VTSE, two new datasets to explain fake news video posts. Then, we propose a Multimodal Relation Graph Transformer (MRGT) model to benchmark ONVE and VTSE. MRGT introduces a multimodal relation graph to comprehensively represent multimodal relations and then introduces a BART-based decoder to explain generations. The experimental results show that the proposed MRGT outperforms the strong baselines. In addition, the human evaluation on the annotated ONVE and VTSE also achieves high scores in terms of adequacy rating.
Authors: Miguel L\'opez-P\'erez, S{\o}ren Hauberg, Aasa Feragen
Abstract: Racial bias in medicine, such as in dermatology, presents significant ethical and clinical challenges. This is likely to happen because there is a significant underrepresentation of darker skin tones in training datasets for machine learning models. While efforts to address bias in dermatology have focused on improving dataset diversity and mitigating disparities in discriminative models, the impact of racial bias on generative models remains underexplored. Generative models, such as Variational Autoencoders (VAEs), are increasingly used in healthcare applications, yet their fairness across diverse skin tones is currently not well understood. In this study, we evaluate the fairness of generative models in clinical dermatology with respect to racial bias. For this purpose, we first train a VAE with a perceptual loss to generate and reconstruct high-quality skin images across different skin tones. We utilize the Fitzpatrick17k dataset to examine how racial bias influences the representation and performance of these models. Our findings indicate that VAE performance is, as expected, influenced by representation, i.e. increased skin tone representation comes with increased performance on the given skin tone. However, we also observe, even independently of representation, that the VAE performs better for lighter skin tones. Additionally, the uncertainty estimates produced by the VAE are ineffective in assessing the model's fairness. These results highlight the need for more representative dermatological datasets, but also a need for better understanding the sources of bias in such model, as well as improved uncertainty quantification mechanisms to detect and address racial bias in generative models for trustworthy healthcare technologies.
Authors: Luqi Zhang, Haiping Wang, Chong Liu, Zhen Dong, Bisheng Yang
Abstract: The point clouds collected by the Airborne Laser Scanning (ALS) system provide accurate 3D information of urban land covers. By utilizing multi-temporal ALS point clouds, semantic changes in urban area can be captured, demonstrating significant potential in urban planning, emergency management, and infrastructure maintenance. Existing 3D change detection methods struggle to efficiently extract multi-class semantic information and change features, still facing the following challenges: (1) the difficulty of accurately modeling cross-temporal point clouds spatial relationships for effective change feature extraction; (2) class imbalance of change samples which hinders distinguishability of semantic features; (3) the lack of real-world datasets for 3D semantic change detection. To resolve these challenges, we propose the Multi-task Enhanced Cross-temporal Point Transformer (ME-CPT) network. ME-CPT establishes spatiotemporal correspondences between point cloud across different epochs and employs attention mechanisms to jointly extract semantic change features, facilitating information exchange and change comparison. Additionally, we incorporate a semantic segmentation task and through the multi-task training strategy, further enhance the distinguishability of semantic features, reducing the impact of class imbalance in change types. Moreover, we release a 22.5 $km^2$ 3D semantic change detection dataset, offering diverse scenes for comprehensive evaluation. Experiments on multiple datasets show that the proposed MT-CPT achieves superior performance compared to existing state-of-the-art methods. The source code and dataset will be released upon acceptance at https://github.com/zhangluqi0209/ME-CPT.
Authors: Dazhou Yu, Genpei Zhang, Liang Zhao
Abstract: Ubiquitous geometric objects can be precisely and efficiently represented as polyhedra. The transformation of a polyhedron into a vector, known as polyhedra representation learning, is crucial for manipulating these shapes with mathematical and statistical tools for tasks like classification, clustering, and generation. Recent years have witnessed significant strides in this domain, yet most efforts focus on the vertex sequence of a polyhedron, neglecting the complex surface modeling crucial in real-world polyhedral objects. This study proposes \textbf{PolyhedronNet}, a general framework tailored for learning representations of 3D polyhedral objects. We propose the concept of the surface-attributed graph to seamlessly model the vertices, edges, faces, and their geometric interrelationships within a polyhedron. To effectively learn the representation of the entire surface-attributed graph, we first propose to break it down into local rigid representations to effectively learn each local region's relative positions against the remaining regions without geometric information loss. Subsequently, we propose PolyhedronGNN to hierarchically aggregate the local rigid representation via intra-face and inter-face geometric message passing modules, to obtain a global representation that minimizes information loss while maintaining rotation and translation invariance. Our experimental evaluations on four distinct datasets, encompassing both classification and retrieval tasks, substantiate PolyhedronNet's efficacy in capturing comprehensive and informative representations of 3D polyhedral objects. Code and data are available at {https://github.com/dyu62/3D_polyhedron}.
Authors: Yunhang Shen, Chaoyou Fu, Shaoqi Dong, Xiong Wang, Yi-Fan Zhang, Peixian Chen, Mengdan Zhang, Haoyu Cao, Ke Li, Xiawu Zheng, Yan Zhang, Yiyi Zhou, Ran He, Caifeng Shan, Rongrong Ji, Xing Sun
Abstract: We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M tokens while delivering advanced performances on short-context multi-modal tasks. We propose an effective multi-modal training schema that starts with large language models and proceeds through vision-language alignment, general knowledge learning, and two sequential stages of long-sequence fine-tuning. We further implement context-parallelism distributed inference and logits-masked language modeling head to scale Long-VITA to infinitely long inputs of images and texts during model inference. Regarding training data, Long-VITA is built on a mix of 17M samples from public datasets only and demonstrates the state-of-the-art performance on various multi-modal benchmarks, compared against recent cutting-edge models with internal data. Long-VITA is fully reproducible and supports both NPU and GPU platforms for training and testing. By leveraging our inference designs, Long-VITA models achieve a remarkable 2x prefill speedup and 4x context length extension in single node with 8 GPUs. We hope Long-VITA can serve as a competitive baseline and offer valuable insights for the open-source community in advancing long-context multi-modal understanding.
Authors: Lei Lu, Yize Li, Yanzhi Wang, Wei Wang, Wei Jiang
Abstract: Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling. Conventional LIC suffers from severe artifacts due to heavy quantization, while generative VQ modeling gives poor fidelity due to the mismatch between learned generative priors and specific inputs. In this work, we propose Hybrid-Diffusion Image Compression (HDCompression), a dual-stream framework that utilizes both generative VQ-modeling and diffusion models, as well as conventional LIC, to achieve both high fidelity and high perceptual quality. Different from previous hybrid methods that directly use pre-trained LIC models to generate low-quality fidelity-preserving information from heavily quantized latent, we use diffusion models to extract high-quality complimentary fidelity information from the ground-truth input, which can enhance the system performance in several aspects: improving indices map prediction, enhancing the fidelity-preserving output of the LIC stream, and refining conditioned image reconstruction with VQ-latent correction. In addition, our diffusion model is based on a dense representative vector (DRV), which is lightweight with very simple sampling schedulers. Extensive experiments demonstrate that our HDCompression outperforms the previous conventional LIC, generative VQ-modeling, and hybrid frameworks in both quantitative metrics and qualitative visualization, providing balanced robust compression performance at ultra-low bitrates.
Authors: Kehua Chen, Haoyang Shen
Abstract: In this paper, we study semi-supervised Handwritten Mathematical Expression Recognition (HMER) via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization framework, termed SemiHMER, which introduces dual-branch semi-supervised learning. Specifically, we enforce consistency between the two networks for the same input image. The pseudo-label, generated by one perturbed recognition network, is utilized to supervise the other network using the standard cross-entropy loss. The SemiHMER consistency encourages high similarity between the predictions of the two perturbed networks for the same input image and expands the training data by leveraging unlabeled data with pseudo-labels. We further introduce a weak-to-strong strategy by applying different levels of augmentation to each branch, effectively expanding the training data and enhancing the quality of network training. Additionally, we propose a novel module, the Global Dynamic Counting Module (GDCM), to enhance the performance of the HMER decoder by alleviating recognition inaccuracies in long-distance formula recognition and reducing the occurrence of repeated characters. The experimental results demonstrate that our work achieves significant performance improvements, with an average accuracy increase of 5.47% on CROHME14, 4.87% on CROHME16, and 5.25% on CROHME19, compared to our baselines.
Authors: Ao Li, Wei Fang, Hongbo Zhao, Le Lu, Ge Yang, Minfeng Xu
Abstract: In applications of diffusion models, controllable generation is of practical significance, but is also challenging. Current methods for controllable generation primarily focus on modifying the score function of diffusion models, while Mean Reverting (MR) Diffusion directly modifies the structure of the stochastic differential equation (SDE), making the incorporation of image conditions simpler and more natural. However, current training-free fast samplers are not directly applicable to MR Diffusion. And thus MR Diffusion requires hundreds of NFEs (number of function evaluations) to obtain high-quality samples. In this paper, we propose a new algorithm named MRS (MR Sampler) to reduce the sampling NFEs of MR Diffusion. We solve the reverse-time SDE and the probability flow ordinary differential equation (PF-ODE) associated with MR Diffusion, and derive semi-analytical solutions. The solutions consist of an analytical function and an integral parameterized by a neural network. Based on this solution, we can generate high-quality samples in fewer steps. Our approach does not require training and supports all mainstream parameterizations, including noise prediction, data prediction and velocity prediction. Extensive experiments demonstrate that MR Sampler maintains high sampling quality with a speedup of 10 to 20 times across ten different image restoration tasks. Our algorithm accelerates the sampling procedure of MR Diffusion, making it more practical in controllable generation.
Authors: Ilmari Vahteristo, Zhi-Song Liu, Andreas Rupp
Abstract: Reconstructing an image from its Radon transform is a fundamental computed tomography (CT) task arising in applications such as X-ray scans. In many practical scenarios, a full 180-degree scan is not feasible, or there is a desire to reduce radiation exposure. In these limited-angle settings, the problem becomes ill-posed, and methods designed for full-view data often leave significant artifacts. We propose a very low-data approach to reconstruct the original image from its Radon transform under severe angle limitations. Because the inverse problem is ill-posed, we combine multiple regularization methods, including Total Variation, a sinogram filter, Deep Image Prior, and a patch-level autoencoder. We use a differentiable implementation of the Radon transform, which allows us to use gradient-based techniques to solve the inverse problem. Our method is evaluated on a dataset from the Helsinki Tomography Challenge 2022, where the goal is to reconstruct a binary disk from its limited-angle sinogram. We only use a total of 12 data points--eight for learning a prior and four for hyperparameter selection--and achieve results comparable to the best synthetic data-driven approaches.
Authors: Zhen Li, Weiwei Sun, Shrisudhan Govindarajan, Shaobo Xia, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
Abstract: We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based architectures (i.e., PointTransformerV3), that serializes the point cloud into a locality-preserving sequence of tokens. We efficiently predict the SDF value at a point by aggregating nearby tokens, where fast approximate neighbors can be retrieved thanks to the serialization. We serialize the point cloud at different levels/scales, and non-linearly aggregate a feature to predict the SDF value. We show that aggregating across multiple scales is critical to overcome the approximations introduced by the serialization (i.e. false negatives in the neighborhood). Our frameworks sets the new state-of-the-art in terms of accuracy and efficiency (better or similar performance with half the latency of the best prior method, coupled with a simpler implementation), particularly on outdoor datasets where sparse-grid methods have shown limited performance.
Authors: Dongki Jung, Jaehoon Choi, Yonghan Lee, Dinesh Manocha
Abstract: We present a novel 3D reconstruction pipeline for 360$^\circ$ cameras for 3D mapping and rendering of indoor environments. Traditional Structure-from-Motion (SfM) methods may not work well in large-scale indoor scenes due to the prevalence of textureless and repetitive regions. To overcome these challenges, our approach (IM360) leverages the wide field of view of omnidirectional images and integrates the spherical camera model into every core component of the SfM pipeline. In order to develop a comprehensive 3D reconstruction solution, we integrate a neural implicit surface reconstruction technique to generate high-quality surfaces from sparse input data. Additionally, we utilize a mesh-based neural rendering approach to refine texture maps and accurately capture view-dependent properties by combining diffuse and specular components. We evaluate our pipeline on large-scale indoor scenes from the Matterport3D and Stanford2D3D datasets. In practice, IM360 demonstrate superior performance in terms of textured mesh reconstruction over SOTA. We observe accuracy improvements in terms of camera localization and registration as well as rendering high frequency details.
Authors: Timon Winter, Stanislav Frolov, Brian Bernhard Moser, Andreas Dengel
Abstract: Recent advancements in text-to-image (T2I) have improved synthesis results, but challenges remain in layout control and generating omnidirectional panoramic images. Dense T2I (DT2I) and spherical T2I (ST2I) models address these issues, but so far no unified approach exists. Trivial approaches, like prompting a DT2I model to generate panoramas can not generate proper spherical distortions and seamless transitions at the borders. Our work shows that spherical dense text-to-image (SDT2I) can be achieved by integrating training-free DT2I approaches into finetuned panorama models. Specifically, we propose MultiStitchDiffusion (MSTD) and MultiPanFusion (MPF) by integrating MultiDiffusion into StitchDiffusion and PanFusion, respectively. Since no benchmark for SDT2I exists, we further construct Dense-Synthetic-View (DSynView), a new synthetic dataset containing spherical layouts to evaluate our models. Our results show that MSTD outperforms MPF across image quality as well as prompt- and layout adherence. MultiPanFusion generates more diverse images but struggles to synthesize flawless foreground objects. We propose bootstrap-coupling and turning off equirectangular perspective-projection attention in the foreground as an improvement of MPF.
Authors: Kihyuk Yoon, Chiehyeon Lim
Abstract: In this work, we propose a novel activation mechanism called LayerAct for CNNs. This approach is motivated by our theoretical and experimental analyses, which demonstrate that Layer Normalization (LN) can mitigate a limitation of existing activation functions regarding noise robustness. However, LN is known to be disadvantageous in CNNs due to its tendency to make activation outputs homogeneous. The proposed method is designed to be more robust than existing activation functions by reducing the upper bound of influence caused by input shifts without inheriting LN's limitation. We provide analyses and experiments showing that LayerAct functions exhibit superior robustness compared to ElementAct functions. Experimental results on three clean and noisy benchmark datasets for image classification tasks indicate that LayerAct functions outperform other activation functions in handling noisy datasets while achieving superior performance on clean datasets in most cases.
Authors: Hai-Long Sun, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Abstract: While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, incremental learning emerges to address real-world scenarios involving new data's arrival. Recently, pre-training has made significant advancements and garnered the attention of numerous researchers. The strong performance of these pre-trained models (PTMs) presents a promising avenue for developing continual learning algorithms that can effectively adapt to real-world scenarios. Consequently, exploring the utilization of PTMs in incremental learning has become essential. This paper introduces a pre-trained model-based continual learning toolbox known as PILOT. On the one hand, PILOT implements some state-of-the-art class-incremental learning algorithms based on pre-trained models, such as L2P, DualPrompt, and CODA-Prompt. On the other hand, PILOT also fits typical class-incremental learning algorithms (e.g., DER, FOSTER, and MEMO) within the context of pre-trained models to evaluate their effectiveness.
Authors: Jie Chen, Hua Mao, Wai Lok Woo, Chuanbin Liu, Xi Peng
Abstract: Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representation learning methods. In this paper, we propose a cross-view graph consistency learning (CGCL) method that learns invariant graph representations for link prediction. First, two complementary augmented views are derived from an incomplete graph structure through a coupled graph structure augmentation scheme. This augmentation scheme mitigates the potential information loss that is commonly associated with various data augmentation techniques involving raw graph data, such as edge perturbation, node removal, and attribute masking. Second, we propose a CGCL model that can learn invariant graph representations. A cross-view training scheme is proposed to train the proposed CGCL model. This scheme attempts to maximize the consistency information between one augmented view and the graph structure reconstructed from the other augmented view. Furthermore, we offer a comprehensive theoretical CGCL analysis. This paper empirically and experimentally demonstrates the effectiveness of the proposed CGCL method, achieving competitive results on graph datasets in comparisons with several state-of-the-art algorithms.
Authors: Fabian Bongratz, Jan Fecht, Anne-Marie Rickmann, Christian Wachinger
Abstract: Reconstructing the cortex from longitudinal magnetic resonance imaging (MRI) is indispensable for analyzing morphological alterations in the human brain. Despite the recent advancement of cortical surface reconstruction with deep learning, challenges arising from longitudinal data are still persistent. Especially the lack of strong spatiotemporal point correspondence between highly convoluted brain surfaces hinders downstream analyses, as local morphology is not directly comparable if the anatomical location is not matched precisely. To address this issue, we present V2C-Long, the first dedicated deep learning-based cortex reconstruction method for longitudinal MRI. V2C-Long exhibits strong inherent spatiotemporal correspondence across subjects and visits, thereby reducing the need for surface-based post-processing. We establish this correspondence directly during the reconstruction via the composition of two deep template-deformation networks and innovative aggregation of within-subject templates in mesh space. We validate V2C-Long on two large neuroimaging studies, focusing on surface accuracy, consistency, generalization, test-retest reliability, and sensitivity. The results reveal a substantial improvement in longitudinal consistency and accuracy compared to existing methods. In addition, we demonstrate stronger evidence for longitudinal cortical atrophy in Alzheimer's disease than longitudinal FreeSurfer.
Authors: Hongrui Cai, Yuting Xiao, Xuan Wang, Jiafei Li, Yudong Guo, Yanbo Fan, Shenghua Gao, Juyong Zhang
Abstract: We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time (>30fps at $2048 \times 1334$ resolution). First, we propose a hybrid explicit representation that combines the advantages of two primitive-based efficient rendering techniques. UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures. In the pipeline of modeling an avatar, after tracking parametric models based on captured multi-view RGB videos, our goal is to simultaneously optimize the texture and opacity map of mesh, as well as a set of 3D Gaussian splats localized and rigged onto the mesh facets. Specifically, we perform $\alpha$-blending on the color and opacity values based on the merged and re-ordered z-buffer from the rasterization results of mesh and 3DGS. This process involves the mesh and 3DGS adaptively fitting the captured visual information to outline a high-fidelity digital avatar. To avoid artifacts caused by Gaussian splats crossing the mesh facets, we design a stable hybrid depth sorting strategy. Experiments illustrate that our modeled results exceed those of state-of-the-art approaches.
Authors: Joe Dhanith P R, Shravan Venkatraman, Vigya Sharma, Santhosh Malarvannan, Modigari Narendra
Abstract: Understanding emotions is a fundamental aspect of human communication. Integrating audio and video signals offers a more comprehensive understanding of emotional states compared to traditional methods that rely on a single data source, such as speech or facial expressions. Despite its potential, multimodal emotion recognition faces significant challenges, particularly in synchronization, feature extraction, and fusion of diverse data sources. To address these issues, this paper introduces a novel transformer-based model named Audio-Video Transformer Fusion with Cross Attention (AVT-CA). The AVT-CA model employs a transformer fusion approach to effectively capture and synchronize interlinked features from both audio and video inputs, thereby resolving synchronization problems. Additionally, the Cross Attention mechanism within AVT-CA selectively extracts and emphasizes critical features while discarding irrelevant ones from both modalities, addressing feature extraction and fusion challenges. Extensive experimental analysis conducted on the CMU-MOSEI, RAVDESS and CREMA-D datasets demonstrates the efficacy of the proposed model. The results underscore the importance of AVT-CA in developing precise and reliable multimodal emotion recognition systems for practical applications.
Authors: Gaia Fior, Carlo Fonda, Enrique Canessa
Abstract: The facilitation of STEM education can be enhanced by the provision of opportunities for learners to gain a better understanding of science through the utilization of tangible and visual examples. The objective of this work is to present an account of our experiences and activities carried out in Italian schools with this novel approach. The selection of projects and experiences discussed --in which students develop a range of core competencies such as collaboration, creativity, critical thinking, experimentation, prototyping, communication and problem-solving; include tangible complex 3D printed structures, large micro-controller board replicas and the visualization of wind dynamics and tiny invisible elementary particles among others. These hands-on experiences demonstrate the benefits on the use of digital fabrication technologies implemented within a FabLab for STEM learning.
Authors: Xiaohua Feng, Yuyuan Li, Chaochao Chen, Li Zhang, Longfei Li, Jun Zhou, Xiaolin Zheng
Abstract: While generative models have made significant advancements in recent years, they also raise concerns such as privacy breaches and biases. Machine unlearning has emerged as a viable solution, aiming to remove specific training data, e.g., containing private information and bias, from models. In this paper, we study the machine unlearning problem in Image-to-Image (I2I) generative models. Previous studies mainly treat it as a single objective optimization problem, offering a solitary solution, thereby neglecting the varied user expectations towards the trade-off between complete unlearning and model utility. To address this issue, we propose a controllable unlearning framework that uses a control coefficient $\varepsilon$ to control the trade-off. We reformulate the I2I generative model unlearning problem into a $\varepsilon$-constrained optimization problem and solve it with a gradient-based method to find optimal solutions for unlearning boundaries. These boundaries define the valid range for the control coefficient. Within this range, every yielded solution is theoretically guaranteed with Pareto optimality. We also analyze the convergence rate of our framework under various control functions. Extensive experiments on two benchmark datasets across three mainstream I2I models demonstrate the effectiveness of our controllable unlearning framework.
Authors: Nikolaos Stathoulopoulos, Vidya Sumathy, Christoforos Kanellakis, George Nikolakopoulos
Abstract: Recent advances in robotics are driving real-world autonomy for long-term and large-scale missions, where loop closures via place recognition are vital for mitigating pose estimation drift. However, achieving real-time performance remains challenging for resource-constrained mobile robots and multi-robot systems due to the computational burden of high-density sampling, which increases the complexity of comparing and verifying query samples against a growing map database. Conventional methods often retain redundant information or miss critical data by relying on fixed sampling intervals or operating in 3-D space instead of the descriptor feature space. To address these challenges, we introduce the concept of sample space and propose a novel keyframe sampling approach for LiDAR-based place recognition. Our method minimizes redundancy while preserving essential information in the hyper-dimensional descriptor space, supporting both learning-based and handcrafted descriptors. The proposed approach incorporates a sliding window optimization strategy to ensure efficient keyframe selection and real-time performance, enabling seamless integration into robotic pipelines. In sum, our approach demonstrates robust performance across diverse datasets, with the ability to adapt seamlessly from indoor to outdoor scenarios without parameter tuning, reducing loop closure detection times and memory requirements.
Authors: Chang Zou, Xuyang Liu, Ting Liu, Siteng Huang, Linfeng Zhang
Abstract: Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion transformers by caching the features in previous timesteps and reusing them in the following timesteps. However, previous caching methods ignore that different tokens exhibit different sensitivities to feature caching, and feature caching on some tokens may lead to 10$\times$ more destruction to the overall generation quality compared with other tokens. In this paper, we introduce token-wise feature caching, allowing us to adaptively select the most suitable tokens for caching, and further enable us to apply different caching ratios to neural layers in different types and depths. Extensive experiments on PixArt-$\alpha$, OpenSora, and DiT demonstrate our effectiveness in both image and video generation with no requirements for training. For instance, 2.36$\times$ and 1.93$\times$ acceleration are achieved on OpenSora and PixArt-$\alpha$ with almost no drop in generation quality.
Authors: Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong
Abstract: The rapid advancement of scientific progress requires innovative tools that can accelerate knowledge discovery. Although recent AI methods, particularly large language models (LLMs), have shown promise in tasks such as hypothesis generation and experimental design, they fall short of replicating the collaborative nature of real-world scientific practices, where diverse experts work together in teams to tackle complex problems. To address the limitations, we propose an LLM-based multi-agent system, i.e., Virtual Scientists (VirSci), designed to mimic the teamwork inherent in scientific research. VirSci organizes a team of agents to collaboratively generate, evaluate, and refine research ideas. Through comprehensive experiments, we demonstrate that this multi-agent approach outperforms the state-of-the-art method in producing novel scientific ideas. We further investigate the collaboration mechanisms that contribute to its tendency to produce ideas with higher novelty, offering valuable insights to guide future research and illuminating pathways toward building a robust system for autonomous scientific discovery. The code is available at https://github.com/open-sciencelab/Virtual-Scientists.
URLs: https://github.com/open-sciencelab/Virtual-Scientists.
Authors: Yanjie Ze, Zixuan Chen, Wenhao Wang, Tianyi Chen, Xialin He, Ying Yuan, Xue Bin Peng, Jiajun Wu
Abstract: Humanoid robots capable of autonomous operation in diverse environments have long been a goal for roboticists. However, autonomous manipulation by humanoid robots has largely been restricted to one specific scene, primarily due to the difficulty of acquiring generalizable skills and the expensiveness of in-the-wild humanoid robot data. In this work, we build a real-world robotic system to address this challenging problem. Our system is mainly an integration of 1) a whole-upper-body robotic teleoperation system to acquire human-like robot data, 2) a 25-DoF humanoid robot platform with a height-adjustable cart and a 3D LiDAR sensor, and 3) an improved 3D Diffusion Policy learning algorithm for humanoid robots to learn from noisy human data. We run more than 2000 episodes of policy rollouts on the real robot for rigorous policy evaluation. Empowered by this system, we show that using only data collected in one single scene and with only onboard computing, a full-sized humanoid robot can autonomously perform skills in diverse real-world scenarios. Videos are available at \href{https://humanoid-manipulation.github.io}{humanoid-manipulation.github.io}.
Authors: Kyungmin Min, Minbeom Kim, Kang-il Lee, Dongryeol Lee, Kyomin Jung
Abstract: Large Vision-Language Models (LVLMs) demonstrate impressive capabilities in generating detailed and coherent responses from visual inputs. However, they are prone to generate hallucinations due to an over-reliance on language priors. To address this issue, we investigate the language priors in LVLMs and make two key observations: (1) Even when predicting the tokens associated with image-related part-of-speech (POS), models increasingly rely on linguistic priors as the token sequences grow, thereby amplifying hallucinations. (2) Methods that directly calibrate LVLM's output distribution to mitigate language priors can lead to a degradation in text quality or even exacerbate hallucinations. Based on these findings, we propose a novel method, Summary-Guided Decoding (SumGD). This method naturally encourages the model to focus more on image information by reducing the text context through summaries, while controlling only the image-related POS tokens to maintain text quality. Through experiments, we demonstrate that SumGD achieves state-of-the-art performance on object hallucination benchmarks. Furthermore, in terms of the trade-off between precision and recall, SumGD achieves Pareto optimality among the existing methods. Lastly, we observe that although existing methods struggle to balance the reduction of object hallucinations with maintaining text quality, SumGD demonstrates robustness in handling this challenge.
Authors: Brian Hsuan-Cheng Liao, Yingjie Xu, Chih-Hong Cheng, Hasan Esen, Alois Knoll
Abstract: This paper presents a novel monitoring framework that infers the level of collision risk for autonomous vehicles (AVs) based on their object detection performance. The framework takes two sets of predictions from different algorithms and associates their inconsistencies with the collision risk via fuzzy inference. The first set of predictions is obtained by retrieving safety-critical 2.5D objects from a depth map, and the second set comes from the ordinary AV's 3D object detector. We experimentally validate that, based on Intersection-over-Union (IoU) and a depth discrepancy measure, the inconsistencies between the two sets of predictions strongly correlate to the error of the 3D object detector against ground truths. This correlation allows us to construct a fuzzy inference system and map the inconsistency measures to an AV collision risk indicator. In particular, we optimize the fuzzy inference system towards an existing offline metric that matches AV collision rates well. Lastly, we validate our monitor's capability to produce relevant risk estimates with the large-scale nuScenes dataset and demonstrate that it can safeguard an AV in closed-loop simulations.
Authors: Ziyan Wang, Sizhe Wei, Xiaoming Huo, Hao Wang
Abstract: Diffusion models have made significant advancements in recent years. However, their performance often deteriorates when trained or fine-tuned on imbalanced datasets. This degradation is largely due to the disproportionate representation of majority and minority data in image-text pairs. In this paper, we propose a general fine-tuning approach, dubbed PoGDiff, to address this challenge. Rather than directly minimizing the KL divergence between the predicted and ground-truth distributions, PoGDiff replaces the ground-truth distribution with a Product of Gaussians (PoG), which is constructed by combining the original ground-truth targets with the predicted distribution conditioned on a neighboring text embedding. Experiments on real-world datasets demonstrate that our method effectively addresses the imbalance problem in diffusion models, improving both generation accuracy and quality.
Authors: Mantas Mazeika, Xuwang Yin, Rishub Tamirisa, Jaehyuk Lim, Bruce W. Lee, Richard Ren, Long Phan, Norman Mu, Adam Khoja, Oliver Zhang, Dan Hendrycks
Abstract: As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values. Tracking the emergence of goals and values has proven a longstanding problem, and despite much interest over the years it remains unclear whether current AIs have meaningful values. We propose a solution to this problem, leveraging the framework of utility functions to study the internal coherence of AI preferences. Surprisingly, we find that independently-sampled preferences in current LLMs exhibit high degrees of structural coherence, and moreover that this emerges with scale. These findings suggest that value systems emerge in LLMs in a meaningful sense, a finding with broad implications. To study these emergent value systems, we propose utility engineering as a research agenda, comprising both the analysis and control of AI utilities. We uncover problematic and often shocking values in LLM assistants despite existing control measures. These include cases where AIs value themselves over humans and are anti-aligned with specific individuals. To constrain these emergent value systems, we propose methods of utility control. As a case study, we show how aligning utilities with a citizen assembly reduces political biases and generalizes to new scenarios. Whether we like it or not, value systems have already emerged in AIs, and much work remains to fully understand and control these emergent representations.
Authors: Ruslan Agishev, Karel Zimmermann
Abstract: We propose a novel model for the prediction of robot trajectories on rough offroad terrain from the onboard camera images. This model enforces the laws of classical mechanics through a physics-aware neural symbolic layer while preserving the ability to learn from large-scale data as it is end-to-end differentiable. The proposed hybrid model integrates a black-box component that predicts robot-terrain interaction forces with a neural-symbolic layer. This layer includes a differentiable physics engine that computes the robot's trajectory by querying these forces at the points of contact with the terrain. As the proposed architecture comprises substantial geometrical and physics priors, the resulting model can also be seen as a learnable physics engine conditioned on real images that delivers $10^4$ trajectories per second. We argue and empirically demonstrate that this architecture reduces the sim-to-real gap and mitigates out-of-distribution sensitivity. The differentiability, in conjunction with the rapid simulation speed, makes the model well-suited for various applications including model predictive control, trajectory shooting, supervised and reinforcement learning or SLAM. The codes and data are publicly available.
Authors: Zihan Lan, Weixin Mao, Haosheng Li, Le Wang, Tiancai Wang, Haoqiang Fan, Osamu Yoshie
Abstract: In real-world scenarios, multi-view cameras are typically employed for fine-grained manipulation tasks. Existing approaches (e.g., ACT) tend to treat multi-view features equally and directly concatenate them for policy learning. However, it will introduce redundant visual information and bring higher computational costs, leading to ineffective manipulation. For a fine-grained manipulation task, it tends to involve multiple stages while the most contributed view for different stages is varied over time. In this paper, we propose a plug-and-play best-feature-aware (BFA) fusion strategy for multi-view manipulation tasks, which is adaptable to various policies. Built upon the visual backbone of the policy network, we design a lightweight network to predict the importance score of each view. Based on the predicted importance scores, the reweighted multi-view features are subsequently fused and input into the end-to-end policy network, enabling seamless integration. Notably, our method demonstrates outstanding performance in fine-grained manipulations. Experimental results show that our approach outperforms multiple baselines by 22-46% success rate on different tasks. Our work provides new insights and inspiration for tackling key challenges in fine-grained manipulations.
Authors: Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Zhicheng Zheng, Xiaoyong Zhu, Bo Zheng
Abstract: The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability. In this paper, we introduce the first factuality-based visual question-answering benchmark in Chinese, named ChineseSimpleVQA, aimed at assessing the visual factuality of LVLMs across 8 major topics and 56 subtopics. The key features of this benchmark include a focus on the Chinese language, diverse knowledge types, a multi-hop question construction, high-quality data, static consistency, and easy-to-evaluate through short answers. Moreover, we contribute a rigorous data construction pipeline and decouple the visual factuality into two parts: seeing the world (i.e., object recognition) and discovering knowledge. This decoupling allows us to analyze the capability boundaries and execution mechanisms of LVLMs. Subsequently, we evaluate 34 advanced open-source and closed-source models, revealing critical performance gaps within this field.
Authors: Zeliang Zhang, Susan Liang, Daiki Shimada, Chenliang Xu
Abstract: While audio-visual learning equips models with a richer understanding of the real world by leveraging multiple sensory modalities, this integration also introduces new vulnerabilities to adversarial attacks. In this paper, we present a comprehensive study of the adversarial robustness of audio-visual models, considering both temporal and modality-specific vulnerabilities. We propose two powerful adversarial attacks: 1) a temporal invariance attack that exploits the inherent temporal redundancy across consecutive time segments and 2) a modality misalignment attack that introduces incongruence between the audio and visual modalities. These attacks are designed to thoroughly assess the robustness of audio-visual models against diverse threats. Furthermore, to defend against such attacks, we introduce a novel audio-visual adversarial training framework. This framework addresses key challenges in vanilla adversarial training by incorporating efficient adversarial perturbation crafting tailored to multi-modal data and an adversarial curriculum strategy. Extensive experiments in the Kinetics-Sounds dataset demonstrate that our proposed temporal and modality-based attacks in degrading model performance can achieve state-of-the-art performance, while our adversarial training defense largely improves the adversarial robustness as well as the adversarial training efficiency.
Authors: Luigi Freda
Abstract: pySLAM is an open-source Python framework for Visual SLAM, supporting monocular, stereo, and RGB-D cameras. It provides a flexible interface for integrating both classical and modern local features, making it adaptable to various SLAM tasks. The framework includes different loop closure methods, a volumetric reconstruction pipeline, and support for depth prediction models. Additionally, it offers a suite of tools for visual odometry and SLAM applications. Designed for both beginners and experienced researchers, pySLAM encourages community contributions, fostering collaborative development in the field of Visual SLAM.
Authors: Atalay Donat, Xiaogang Jia, Xi Huang, Aleksandar Taranovic, Denis Blessing, Ge Li, Hongyi Zhou, Hanyi Zhang, Rudolf Lioutikov, Gerhard Neumann
Abstract: Learning for manipulation requires using policies that have access to rich sensory information such as point clouds or RGB images. Point clouds efficiently capture geometric structures, making them essential for manipulation tasks in imitation learning. In contrast, RGB images provide rich texture and semantic information that can be crucial for certain tasks. Existing approaches for fusing both modalities assign 2D image features to point clouds. However, such approaches often lose global contextual information from the original images. In this work, we propose FPV-Net, a novel imitation learning method that effectively combines the strengths of both point cloud and RGB modalities. Our method conditions the point-cloud encoder on global and local image tokens using adaptive layer norm conditioning, leveraging the beneficial properties of both modalities. Through extensive experiments on the challenging RoboCasa benchmark, we demonstrate the limitations of relying on either modality alone and show that our method achieves state-of-the-art performance across all tasks.
Authors: Junchen Fu, Xuri Ge, Kaiwen Zheng, Ioannis Arapakis, Xin Xin, Joemon M. Jose
Abstract: Popular Micro-videos, dominant on platforms like TikTok and YouTube, hold significant commercial value. The rise of high-quality AI-generated content has spurred interest in AI-driven micro-video creation. However, despite the advanced capabilities of large language models (LLMs) like ChatGPT and DeepSeek in text generation and reasoning, their potential to assist the creation of popular micro-videos remains largely unexplored. In this paper, we conduct an empirical study on LLM-assisted popular micro-video generation (LLMPopcorn). Specifically, we investigate the following research questions: (i) How can LLMs be effectively utilized to assist popular micro-video generation? (ii) To what extent can prompt-based enhancements optimize the LLM-generated content for higher popularity? (iii) How well do various LLMs and video generators perform in the popular micro-video generation task? By exploring these questions, we show that advanced LLMs like DeepSeek-V3 enable micro-video generation to achieve popularity comparable to human-created content. Prompt enhancements further boost popularity, and benchmarking highlights DeepSeek-V3 and DeepSeek-R1 among LLMs, while LTX-Video and HunyuanVideo lead in video generation. This pioneering work advances AI-assisted micro-video creation, uncovering new research opportunities. We will release the code and datasets to support future studies.