Authors: Mira Adra, Simone Melcarne, Nelida Mirabet-Herranz, Jean-Luc Dugelay
Abstract: Event cameras, often referred to as dynamic vision sensors, are groundbreaking sensors capable of capturing changes in light intensity asynchronously, offering exceptional temporal resolution and energy efficiency. These attributes make them particularly suited for human-centered applications, as they capture both the most intricate details of facial expressions and the complex motion dynamics of the human body. Despite growing interest, research in human-centered applications of event cameras remains scattered, with no comprehensive overview encompassing both body and face tasks. This survey bridges that gap by being the first to unify these domains, presenting an extensive review of advancements, challenges, and opportunities. We also examine less-explored areas, including event compression techniques and simulation frameworks, which are essential for the broader adoption of event cameras. This survey is designed to serve as a foundational reference that helps both new and experienced researchers understand the current state of the field and identify promising directions for future work in human-centered event camera applications. A summary of this survey can be found at https://github.com/nmirabeth/event_human
Authors: Hongpu Huang, Wei Zhou, Chen Wang
Abstract: Early accident anticipation from dashcam videos is a highly desirable yet challenging task for improving the safety of intelligent vehicles. Existing advanced accident anticipation approaches commonly model the interaction among traffic agents (e.g., vehicles, pedestrians, etc.) in the coarse 2D image space, which may not adequately capture their true positions and interactions. To address this limitation, we propose a physical depth-aware learning framework that incorporates the monocular depth features generated by a large model named Depth-Anything to introduce more fine-grained spatial 3D information. Furthermore, the proposed framework also integrates visual interaction features and visual dynamic features from traffic scenes to provide a more comprehensive perception towards the scenes. Based on these multi-dimensional visual features, the framework captures early indicators of accidents through the analysis of interaction relationships between objects in sequential frames. Additionally, the proposed framework introduces a reconstruction adjacency matrix for key traffic participants that are occluded, mitigating the impact of occluded objects on graph learning and maintaining the spatio-temporal continuity. Experimental results on public datasets show that the proposed framework attains state-of-the-art performance, highlighting the effectiveness of incorporating visual depth features and the superiority of the proposed framework.
Authors: Chuanguang Yang, Xinqiang Yu, Han Yang, Zhulin An, Chengqing Yu, Libo Huang, Yongjun Xu
Abstract: Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods often develop weighting strategies from an individual perspective of teacher performance or teacher-student gaps, lacking comprehensive information for guidance. This paper proposes Multi-Teacher Knowledge Distillation with Reinforcement Learning (MTKD-RL) to optimize multi-teacher weights. In this framework, we construct both teacher performance and teacher-student gaps as state information to an agent. The agent outputs the teacher weight and can be updated by the return reward from the student. MTKD-RL reinforces the interaction between the student and teacher using an agent in an RL-based decision mechanism, achieving better matching capability with more meaningful weights. Experimental results on visual recognition tasks, including image classification, object detection, and semantic segmentation tasks, demonstrate that MTKD-RL achieves state-of-the-art performance compared to the existing multi-teacher KD works.
Authors: Jianjian Li, Junquan Fan, Feng Tang, Gang Huang, Shitao Zhu, Songlin Liu, Nian Xie, Wulong Liu, Yong Liao
Abstract: The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods exhibit serious performance degradation in tasks involving high-resolution, text-oriented image understanding and reasoning. In this paper, we propose an efficient visual token compression framework for text-oriented VLLMs in high-resolution scenarios. In particular, we employ a light-weight self-distillation pre-training stage to compress the visual tokens, requiring a limited numbers of image-text pairs and minimal learnable parameters. Afterwards, to mitigate potential performance degradation of token-compressed models, we construct a high-quality post-train stage. To validate the effectiveness of our method, we apply it to an advanced VLLMs, InternVL2. Experimental results show that our approach significantly reduces computational overhead while outperforming the baselines across a range of text-oriented benchmarks. We will release the models and code soon.
Authors: Mangsura Kabir Oni, Tabia Tanzin Prama
Abstract: In Bangladesh, tomatoes are a staple vegetable, prized for their versatility in various culinary applications. However, the cultivation of tomatoes is often hindered by a range of diseases that can significantly reduce crop yields and quality. Early detection of these diseases is crucial for implementing timely interventions and ensuring the sustainability of tomato production. Traditional manual inspection methods, while effective, are labor-intensive and prone to human error. To address these challenges, this research paper sought to develop an automated disease detection system using Convolutional Neural Networks (CNNs). A comprehensive dataset of tomato leaves was collected from the Brahmanbaria district, preprocessed to enhance image quality, and then applied to various deep learning models. Comparative performance analysis was conducted between YOLOv5, MobileNetV2, ResNet18, and our custom CNN model. In our study, the Custom CNN model achieved an impressive accuracy of 95.2%, significantly outperforming the other models, which achieved an accuracy of 77%, 89.38% and 71.88% respectively. While other models showed solid performance, our Custom CNN demonstrated superior results specifically tailored for the task of tomato leaf disease detection. These findings highlight the strong potential of deep learning techniques for improving early disease detection in tomato crops. By leveraging these advanced technologies, farmers can gain valuable insights to detect diseases at an early stage, allowing for more effective management practices. This approach not only promises to boost tomato yields but also contributes to the sustainability and resilience of the agricultural sector, helping to mitigate the impact of plant diseases on crop production.
Authors: Eric Xue, Zeyi Huang, Yuyang Ji, Haohan Wang
Abstract: Computer vision is a critical component in a wide range of real-world applications, including plant monitoring in agriculture and handwriting classification in digital systems. However, developing high-performance computer vision models traditionally demands both machine learning (ML) expertise and domain-specific knowledge, making the process costly, labor-intensive, and inaccessible to many. Large language model (LLM) agents have emerged as a promising solution to automate this workflow, but most existing methods share a common limitation: they attempt to optimize entire pipelines in a single step before evaluation, making it difficult to attribute improvements to specific changes. This lack of granularity leads to unstable optimization and slower convergence, limiting their effectiveness. To address this, we introduce Iterative Refinement, a novel strategy for LLM-driven ML pipeline design inspired by how human ML experts iteratively refine models, focusing on one component at a time rather than making sweeping changes all at once. By systematically updating individual components based on real training feedback, Iterative Refinement improves stability, interpretability, and overall model performance. We implement this strategy in IMPROVE, an end-to-end LLM agent framework for automating and optimizing object classification pipelines. Through extensive evaluations across datasets of varying sizes and domains, including standard benchmarks and Kaggle competition datasets, we demonstrate that Iterative Refinement enables IMPROVE to consistently achieve better performance over existing zero-shot LLM-based approaches. These findings establish Iterative Refinement as an effective new strategy for LLM-driven ML automation and position IMPROVE as an accessible solution for building high-quality computer vision models without requiring ML expertise.
Authors: Ehsan Farahbakhsh, Dakshi Goel, Dhiraj Pimparkar, R. Dietmar Muller, Rohitash Chandra
Abstract: Traditional geological mapping, based on field observations and rock sample analysis, is inefficient for continuous spatial mapping of features like alteration zones. Deep learning models, such as convolutional neural networks (CNNs), have revolutionised remote sensing data analysis by automatically extracting features for classification and regression tasks. CNNs can detect specific mineralogical changes linked to mineralisation by identifying subtle features in remote sensing data. This study uses CNNs with Landsat 8, Landsat 9, and ASTER data to map alteration zones north of Broken Hill, New South Wales, Australia. The model is trained using ground truth data and an automated approach with selective principal component analysis (PCA). We compare CNNs with traditional machine learning models, including k-nearest neighbours, support vector machines, and multilayer perceptron. Results show that ground truth-based training yields more reliable maps, with CNNs slightly outperforming conventional models in capturing spatial patterns. Landsat 9 outperforms Landsat 8 in mapping iron oxide areas using ground truth-trained CNNs, while ASTER data provides the most accurate argillic and propylitic alteration maps. This highlights CNNs' effectiveness in improving geological mapping precision, especially for identifying subtle mineralisation-related alterations.
Authors: S M Sarwar
Abstract: Visual Question Answering requires models to generate accurate answers by integrating visual and textual understanding. However, VQA models still struggle with hallucinations, producing convincing but incorrect answers, particularly in knowledge-driven and Out-of-Distribution scenarios. We introduce FilterRAG, a retrieval-augmented framework that combines BLIP-VQA with Retrieval-Augmented Generation to ground answers in external knowledge sources like Wikipedia and DBpedia. FilterRAG achieves 36.5% accuracy on the OK-VQA dataset, demonstrating its effectiveness in reducing hallucinations and improving robustness in both in-domain and Out-of-Distribution settings. These findings highlight the potential of FilterRAG to improve Visual Question Answering systems for real-world deployment.
Authors: Xuechun Li, Susu Xu
Abstract: Interferometric Synthetic Aperture Radar (InSAR) technology uses satellite radar to detect surface deformation patterns and monitor earthquake impacts on buildings. While vital for emergency response planning, extracting multi-class building damage classifications from InSAR data faces challenges: overlapping damage signatures with environmental noise, computational complexity in multi-class scenarios, and the need for rapid regional-scale processing. Our novel multi-class variational causal Bayesian inference framework with quadratic variational bounds provides rigorous approximations while ensuring efficiency. By integrating InSAR observations with USGS ground failure models and building fragility functions, our approach separates building damage signals while maintaining computational efficiency through strategic pruning. Evaluation across five major earthquakes (Haiti 2021, Puerto Rico 2020, Zagreb 2020, Italy 2016, Ridgecrest 2019) shows improved damage classification accuracy (AUC: 0.94-0.96), achieving up to 35.7% improvement over existing methods. Our approach maintains high accuracy (AUC > 0.93) across all damage categories while reducing computational overhead by over 40% without requiring extensive ground truth data.
Authors: Erick da Silva Farias, Eduardo Palhares Junior
Abstract: The automatic detection of human conflicts through videos is a crucial area in computer vision, with significant applications in monitoring and public safety policies. However, the scarcity of public datasets and the complexity of human interactions make this task challenging. This study investigates the integration of advanced deep learning techniques, including Attention Mechanism, Convolutional Neural Networks (CNNs), and Bidirectional Long ShortTerm Memory (BiLSTM), to improve the detection of violent behaviors in videos. The research explores how the use of the attention mechanism can help focus on the most relevant parts of the video, enhancing the accuracy and robustness of the model. The experiments indicate that the combination of CNNs with BiLSTM and the attention mechanism provides a promising solution for conflict monitoring, offering insights into the effectiveness of different strategies. This work opens new possibilities for the development of automated surveillance systems that can operate more efficiently in real-time detection of violent events.
Authors: Akash Vartak, Khondoker Murad Hossain, Tim Oates
Abstract: Deep neural networks (DNNs) are becoming commonplace in critical applications, making their susceptibility to backdoor (trojan) attacks a significant problem. In this paper, we introduce a novel backdoor attack detection pipeline, detecting attacked models using graph convolution networks (DeBUGCN). To the best of our knowledge, ours is the first use of GCNs for trojan detection. We use the static weights of a DNN to create a graph structure of its layers. A GCN is then used as a binary classifier on these graphs, yielding a trojan or clean determination for the DNN. To demonstrate the efficacy of our pipeline, we train hundreds of clean and trojaned CNN models on the MNIST handwritten digits and CIFAR-10 image datasets, and show the DNN classification results using DeBUGCN. For a true In-the-Wild use case, our pipeline is evaluated on the TrojAI dataset which consists of various CNN architectures, thus showing the robustness and model-agnostic behaviour of DeBUGCN. Furthermore, on comparing our results on several datasets with state-of-the-art trojan detection algorithms, DeBUGCN is faster and more accurate.
Authors: Miguel Herencia Garc\'ia del Castillo, Ricardo Moya Garcia, Manuel Jes\'us Cerezo Maz\'on, Ekaitz Arriola Garcia, Pablo Men\'endez Fern\'andez-Miranda
Abstract: In this article, we present a Latent Diffusion Model (LDM) for the generation of brain Magnetic Resonance Imaging (MRI), conditioning its generation based on pathology (Healthy, Glioblastoma, Sclerosis, Dementia) and acquisition modality (T1w, T1ce, T2w, Flair, PD). To evaluate the quality of the generated images, the Fr\'echet Inception Distance (FID) and Multi-Scale Structural Similarity Index (MS-SSIM) metrics were employed. The results indicate that the model generates images with a distribution similar to real ones, maintaining a balance between visual fidelity and diversity. Additionally, the model demonstrates extrapolation capability, enabling the generation of configurations that were not present in the training data. The results validate the potential of the model to increase in the number of samples in clinical datasets, balancing underrepresented classes, and evaluating AI models in medicine, contributing to the development of diagnostic tools in radiology without compromising patient privacy.
Authors: Saorj Kumar, Prince Asiamah, Oluwatoyin Jolaoso, Ugochukwu Esiowu
Abstract: Convolutional Neural Networks (CNNs) serve as the workhorse of deep learning, finding applications in various fields that rely on images. Given sufficient data, they exhibit the capacity to learn a wide range of concepts across diverse settings. However, a notable limitation of CNNs is their susceptibility to overfitting when trained on small datasets. The augmentation of such datasets can significantly enhance CNN performance by introducing additional data points for learning. In this study, we explore the effectiveness of 11 different sets of data augmentation techniques, which include three novel sets proposed in this work. The first set of data augmentation employs pairwise channel transfer, transferring Red, Green, Blue, Hue, and Saturation values from randomly selected images in the database to all images in the dataset. The second set introduces a novel occlusion approach, where objects in the images are occluded by randomly selected objects from the dataset. The third set involves a novel masking approach, using vertical, horizontal, circular, and checkered masks to occlude portions of the images. In addition to these novel techniques, we investigate other existing augmentation methods, including rotation, horizontal and vertical flips, resizing, translation, blur, color jitter, and random erasing, and their effects on accuracy and overfitting. We fine-tune a base EfficientNet-B0 model for each augmentation method and conduct a comparative analysis to showcase their efficacy. For the evaluation and comparison of these augmentation techniques, we utilize the Caltech-101 dataset. The ensemble of image augmentation techniques proposed emerges as the most effective on the Caltech-101 dataset. The results demonstrate that diverse data augmentation techniques present a viable means of enhancing datasets for improved image classification.
Authors: Anthony Etim, Jakub Szefer
Abstract: Adversarial attacks on deep learning models have proliferated in recent years. In many cases, a different adversarial perturbation is required to be added to each image to cause the deep learning model to misclassify it. This is ineffective as each image has to be modified in a different way. Meanwhile, research on universal perturbations focuses on designing a single perturbation that can be applied to all images in a data set, and cause a deep learning model to misclassify the images. This work advances the field of universal perturbations by exploring universal perturbations in the context of traffic signs and autonomous vehicle systems. This work introduces a novel method for generating universal perturbations that visually look like simple black and white stickers, and using them to cause incorrect street sign predictions. Unlike traditional adversarial perturbations, the adversarial universal stickers are designed to be applicable to any street sign: same sticker, or stickers, can be applied in same location to any street sign and cause it to be misclassified. Further, to enable safe experimentation with adversarial images and street signs, this work presents a virtual setting that leverages Street View images of street signs, rather than the need to physically modify street signs, to test the attacks. The experiments in the virtual setting demonstrate that these stickers can consistently mislead deep learning models used commonly in street sign recognition, and achieve high attack success rates on dataset of US traffic signs. The findings highlight the practical security risks posed by simple stickers applied to traffic signs, and the ease with which adversaries can generate adversarial universal stickers that can be applied to many street signs.
Authors: Hemanth Teja Yanambakkam, Rahul Chinthala
Abstract: Image captioning is a challenging task at the intersection of computer vision and natural language processing, requiring models to generate meaningful textual descriptions of images. Traditional approaches rely on recurrent neural networks (RNNs), but recent advancements in attention mechanisms have demonstrated significant improvements. This study benchmarks the performance of attention-based image captioning models against RNN-based approaches using the MS-COCO dataset. We evaluate the effectiveness of Bahdanau attention in enhancing the alignment between image features and generated captions. The models are assessed using natural language processing metrics such as BLEU, METEOR, GLEU, and WER. Our results show that attention-based models outperform RNNs in generating more accurate and semantically rich captions, with better alignment to human evaluation. This work provides insights into the impact of attention mechanisms in image captioning and highlights areas for future improvements.
Authors: Shaheer Mohamed, Tharindu Fernando, Sridha Sridharan, Peyman Moghadam, Clinton Fookes
Abstract: Hyperspectral object tracking using snapshot mosaic cameras is emerging as it provides enhanced spectral information alongside spatial data, contributing to a more comprehensive understanding of material properties. Using transformers, which have consistently outperformed convolutional neural networks (CNNs) in learning better feature representations, would be expected to be effective for Hyperspectral object tracking. However, training large transformers necessitates extensive datasets and prolonged training periods. This is particularly critical for complex tasks like object tracking, and the scarcity of large datasets in the hyperspectral domain acts as a bottleneck in achieving the full potential of powerful transformer models. This paper proposes an effective methodology that adapts large pretrained transformer-based foundation models for hyperspectral object tracking. We propose an adaptive, learnable spatial-spectral token fusion module that can be extended to any transformer-based backbone for learning inherent spatial-spectral features in hyperspectral data. Furthermore, our model incorporates a cross-modality training pipeline that facilitates effective learning across hyperspectral datasets collected with different sensor modalities. This enables the extraction of complementary knowledge from additional modalities, whether or not they are present during testing. Our proposed model also achieves superior performance with minimal training iterations.
Authors: Chenyang Zhao, Kun Wang, Janet H. Hsiao, Antoni B. Chan
Abstract: Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a Gradient-based visual and textual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for specific input image-text pair. By decomposing the architecture of the encoder and discovering the relationship between the matching similarity and intermediate spatial features, Grad-ECLIP produces effective heat maps that show the influence of image regions or words on the CLIP results. Different from the previous Transformer interpretation methods that focus on the utilization of self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights on token features. Qualitative and quantitative evaluations verify the effectiveness and superiority of Grad-ECLIP compared with the state-of-the-art methods. Furthermore, a series of analysis are conducted based on our visual and textual explanation results, from which we explore the working mechanism of image-text matching, the strengths and limitations in attribution identification of CLIP, and the relationship between the concreteness/abstractness of a word and its usage in CLIP. Finally, based on the ability of explanation map that indicates text-specific saliency region of input image, we also propose an application with Grad-ECLIP, which is adopted to boost the fine-grained alignment in the CLIP fine-tuning. The code of Grad-ECLIP is available here: https://github.com/Cyang-Zhao/Grad-Eclip.
Authors: Yunmei Huang, Songlin Hou, Zachary Nelson Horve, Songlin Fei
Abstract: The precise identification of tree species is fundamental to forestry, conservation, and environmental monitoring. Though many studies have demonstrated that high accuracy can be achieved using bark-based species classification, these models often function as "black boxes", limiting interpretability, trust, and adoption in critical forestry applications. Attribution-based Explainable AI (XAI) methods have been used to address this issue in related works. However, XAI applications are often dependent on local features (such as a head shape or paw in animal applications) and cannot describe global visual features (such as ruggedness or smoothness) that are present in texture-dominant images such as tree bark. Concept-based XAI methods, on the other hand, offer explanations based on global visual features with concepts, but they tend to require large overhead in building external concept image datasets and the concepts can be vague and subjective without good means of precise quantification. To address these challenges, we propose a lightweight post-hoc method to interpret visual models for tree species classification using operators and quantifiable concepts. Our approach eliminates computational overhead, enables the quantification of complex concepts, and evaluates both concept importance and the model's reasoning process. To the best of our knowledge, our work is the first study to explain bark vision models in terms of global visual features with concepts. Using a human-annotated dataset as ground truth, our experiments demonstrate that our method significantly outperforms TCAV and Llama3.2 in concept importance ranking based on Kendall's Tau, highlighting its superior alignment with human perceptions.
Authors: Junxiao Ma, Jingjing Wang, Jiamin Luo, Peiying Yu, Guodong Zhou
Abstract: Prior studies on Video Anomaly Detection (VAD) mainly focus on detecting whether each video frame is abnormal or not in the video, which largely ignore the structured video semantic information (i.e., what, when, and where does the abnormal event happen). With this in mind, we propose a new chat-paradigm \textbf{M}ulti-scene Video Abnormal Event Extraction and Localization (M-VAE) task, aiming to extract the abnormal event quadruples (i.e., subject, event type, object, scene) and localize such event. Further, this paper believes that this new task faces two key challenges, i.e., global-local spatial modeling and global-local spatial balancing. To this end, this paper proposes a Global-local Spatial-sensitive Large Language Model (LLM) named Sherlock, i.e., acting like Sherlock Holmes to track down the criminal events, for this M-VAE task. Specifically, this model designs a Global-local Spatial-enhanced MoE (GSM) module and a Spatial Imbalance Regulator (SIR) to address the two challenges respectively. Extensive experiments on our M-VAE instruction dataset show the significant advantages of Sherlock over several advanced Video-LLMs. This justifies the importance of global-local spatial information for the M-VAE task and the effectiveness of Sherlock in capturing such information.
Authors: Akhil Penta, Vaibhav Adwani, Ankush Chopra
Abstract: Accurate skier tracking is essential for performance analysis, injury prevention, and optimizing training strategies in alpine sports. Traditional tracking methods often struggle with occlusions, dynamic movements, and varying environmental conditions, limiting their effectiveness. In this work, we used STARK (Spatio-Temporal Transformer Network for Visual Tracking), a transformer-based model, to track skiers. We adapted STARK to address domain-specific challenges such as camera movements, camera changes, occlusions, etc. by optimizing the model's architecture and hyperparameters to better suit the dataset.
Authors: Youngtae Kim, Soonju Jeong, Sardar Arslan, Dhananjay Agnihotri, Yahya Ahmed, Ali Nawaz, Jinhee Song, Hyewon Kim
Abstract: This study proposes a two-phase methodology for detecting and classifying auxiliary insulation in structural components. In the detection phase, a YOLOv8x model is trained on a dataset of complete structural blueprints, each annotated with bounding boxes indicating areas that should contain insulation. In the classification phase, these detected insulation patches are cropped and categorized into two classes: present or missing. These are then used to train a YOLOv8x-CLS model that determines the presence or absence of auxiliary insulation. Preprocessing steps for both datasets included annotation, augmentation, and appropriate cropping of the insulation regions. The detection model achieved a mean average precision (mAP) score of 82%, while the classification model attained an accuracy of 98%. These findings demonstrate the effectiveness of the proposed approach in automating insulation detection and classification, providing a foundation for further advancements in this domain.
Authors: Wanyi Li, Wei Wei, Yongkang Luo, Peng Wang
Abstract: Few-shot class-incremental learning (FSCIL) poses significant challenges for artificial neural networks due to the need to efficiently learn from limited data while retaining knowledge of previously learned tasks. Inspired by the brain's mechanisms for categorization and analogical learning, we propose a novel approach called Brain-inspired Analogical Mixture Prototypes (BAMP). BAMP has three components: mixed prototypical feature learning, statistical analogy, and soft voting. Starting from a pre-trained Vision Transformer (ViT), mixed prototypical feature learning represents each class using a mixture of prototypes and fine-tunes these representations during the base session. The statistical analogy calibrates the mean and covariance matrix of prototypes for new classes according to similarity to the base classes, and computes classification score with Mahalanobis distance. Soft voting combines both merits of statistical analogy and an off-shelf FSCIL method. Our experiments on benchmark datasets demonstrate that BAMP outperforms state-of-the-art on both traditional big start FSCIL setting and challenging small start FSCIL setting. The study suggests that brain-inspired analogical mixture prototypes can alleviate catastrophic forgetting and over-fitting problems in FSCIL.
Authors: D. Hareb, J. Martinet, B. Miramond
Abstract: Achieving optimal semantic segmentation with frame-based vision sensors poses significant challenges for real-time systems like UAVs and self-driving cars, which require rapid and precise processing. Traditional frame-based methods often struggle to balance latency, accuracy, and energy efficiency. To address these challenges, we leverage event streams from event-based cameras-bio-inspired sensors that trigger events in response to changes in the scene. Specifically, we analyze the number of events triggered between successive frames, with a high number indicating significant changes and a low number indicating minimal changes. We exploit this event information to solve the semantic segmentation task by employing a Spiking Neural Network (SNN), a bio-inspired computing paradigm known for its low energy consumption. Our experiments on the DSEC dataset show that our approach significantly reduces latency with only a limited drop in accuracy. Additionally, by using SNNs, we achieve low power consumption, making our method suitable for energy-constrained real-time applications. To the best of our knowledge, our approach is the first to effectively balance reduced latency, minimal accuracy loss, and energy efficiency using events stream to enhance semantic segmentation in dynamic and resource-limited environments.
Authors: Anju Rani, Daniel O. Arroyo, Petar Durdevic
Abstract: The effectiveness of zero-shot classification in large vision-language models (VLMs), such as Contrastive Language-Image Pre-training (CLIP), depends on access to extensive, well-aligned text-image datasets. In this work, we introduce two complementary data sources, one generated by large language models (LLMs) to describe the stages of fungal growth and another comprising a diverse set of synthetic fungi images. These datasets are designed to enhance CLIPs zero-shot classification capabilities for fungi-related tasks. To ensure effective alignment between text and image data, we project them into CLIPs shared representation space, focusing on different fungal growth stages. We generate text using LLaMA3.2 to bridge modality gaps and synthetically create fungi images. Furthermore, we investigate knowledge transfer by comparing text outputs from different LLM techniques to refine classification across growth stages.
Authors: Vu Tuan Truong Long, Bao Le
Abstract: Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models generate specific, undesirable outputs called backdoor target (e.g., harmful images) when a pre-defined trigger is embedded to their inputs. In this paper, we propose PureDiffusion, a dual-purpose framework that simultaneously serves two contrasting roles: backdoor defense and backdoor attack amplification. For defense, we introduce two novel loss functions to invert backdoor triggers embedded in diffusion models. The first leverages trigger-induced distribution shifts across multiple timesteps of the diffusion process, while the second exploits the denoising consistency effect when a backdoor is activated. Once an accurate trigger inversion is achieved, we develop a backdoor detection method that analyzes both the inverted trigger and the generated backdoor targets to identify backdoor attacks. In terms of attack amplification with the role of an attacker, we describe how our trigger inversion algorithm can be used to reinforce the original trigger embedded in the backdoored diffusion model. This significantly boosts attack performance while reducing the required backdoor training time. Experimental results demonstrate that PureDiffusion achieves near-perfect detection accuracy, outperforming existing defenses by a large margin, particularly against complex trigger patterns. Additionally, in an attack scenario, our attack amplification approach elevates the attack success rate (ASR) of existing backdoor attacks to nearly 100\% while reducing training time by up to 20x.
Authors: Tresor Y. Koffi, Youssef Mourchid, Mohammed Hindawi, Yohan Dupuis
Abstract: Detecting impact where an individual makes contact with the ground within a fall event is crucial in fall detection systems, particularly for elderly care where prompt intervention can prevent serious injuries. The UP-Fall dataset, a key resource in fall detection research, has proven valuable but suffers from limitations in data accuracy and comprehensiveness. These limitations cause confusion in distinguishing between non-impact events, such as sliding, and real falls with impact, where the person actually hits the ground. This confusion compromises the effectiveness of current fall detection systems. This study presents enhancements to the UP-Fall dataset aiming at improving it for impact fall detection by incorporating 3D skeleton data. Our preprocessing techniques ensure high data accuracy and comprehensiveness, enabling a more reliable impact fall detection. Extensive experiments were conducted using various machine learning and deep learning algorithms to benchmark the improved 3D skeletons dataset. The results demonstrate substantial improvements in the performance of fall detection models trained on the enhanced dataset. This contribution aims to enhance the safety and well-being of the elderly population at risk. To support further research and development of building more reliable impact fall detection systems, we have made the improved 3D skeletons UP-Fall dataset publicly available at this link https://zenodo.org/records/12773013.
Authors: Huiqiang Wang, Mingchen Song, Guoqiang Zhong
Abstract: Currently, restoring clean images from a variety of degradation types using a single model is still a challenging task. Existing all-in-one image restoration approaches struggle with addressing complex and ambiguously defined degradation types. In this paper, we introduce a dynamic degradation decomposition network for all-in-one image restoration, named D$^3$Net. D$^3$Net achieves degradation-adaptive image restoration with guided prompt through cross-domain interaction and dynamic degradation decomposition. Concretely, in D$^3$Net, the proposed Cross-Domain Degradation Analyzer (CDDA) engages in deep interaction between frequency domain degradation characteristics and spatial domain image features to identify and model variations of different degradation types on the image manifold, generating degradation correction prompt and strategy prompt, which guide the following decomposition process. Furthermore, the prompt-based Dynamic Decomposition Mechanism (DDM) for progressive degradation decomposition, that encourages the network to adaptively select restoration strategies utilizing the two-level prompt generated by CDDA. Thanks to the synergistic cooperation between CDDA and DDM, D$^3$Net achieves superior flexibility and scalability in handling unknown degradation, while effectively reducing unnecessary computational overhead. Extensive experiments on multiple image restoration tasks demonstrate that D$^3$Net significantly outperforms the state-of-the-art approaches, especially improving PSNR by 5.47dB and 3.30dB on the SOTS-Outdoor and GoPro datasets, respectively.
Authors: Qingyao Tian, Huai Liao, Xinyan Huang, Bingyu Yang, Dongdong Lei, Sebastien Ourselin, Hongbin Liu
Abstract: Endoscopic video-based tasks, such as visual navigation and surgical phase recognition, play a crucial role in minimally invasive surgeries by providing real-time assistance. While recent video foundation models have shown promise, their applications are hindered by (1) computational inefficiencies and (2) suboptimal performance caused by limited data for pre-training in endoscopy. To address these issues, we present EndoMamba, a foundation model designed for real-time inference while learning generalized spatiotemporal representations. First, to mitigate computational inefficiencies, we propose the EndoMamba backbone, optimized for real-time inference. Inspired by recent advancements in state space models, EndoMamba integrates Bidirectional Mamba blocks for spatial modeling within individual frames and vanilla Mamba blocks for past-to-present reasoning across the temporal domain. This design enables both strong spatiotemporal modeling and efficient inference in online video streams. Second, we propose a self-supervised hierarchical pre-training diagram to enhance EndoMamba's representation learning using endoscopic videos and incorporating general video domain knowledge. Specifically, our approach combines masked reconstruction with auxiliary supervision, leveraging low-level reconstruction to capture spatial-temporal structures and high-level alignment to transfer broader knowledge from a pretrained general-video domain foundation model. Extensive experiments on four downstream tasks--classification, segmentation, surgical phase recognition, and localization--demonstrate that EndoMamba outperforms existing foundation models and task-specific methods while maintaining real-time inference speed. The source code will be released upon acceptance.
Authors: Edward G. A. Henderson, Marcel van Herk, Andrew F. Green, Eliana M. Vasquez Osorio
Abstract: We propose an anatomically-informed initialisation method for interpatient CT non-rigid registration (NRR), using a learning-based model to estimate correspondences between organ structures. A thin plate spline (TPS) deformation, set up using the correspondence predictions, is used to initialise the scans before a second NRR step. We compare two established NRR methods for the second step: a B-spline iterative optimisation-based algorithm and a deep learning-based approach. Registration performance is evaluated with and without the initialisation by assessing the similarity of propagated structures. Our proposed initialisation improved the registration performance of the learning-based method to more closely match the traditional iterative algorithm, with the mean distance-to-agreement reduced by 1.8mm for structures included in the TPS and 0.6mm for structures not included, while maintaining a substantial speed advantage (5 vs. 72 seconds).
Authors: Tianle Yang, Luyao Chang, Jiadong Yan, Juntao Li, Zhi Wang, Ke Zhang
Abstract: As industrial products become abundant and sophisticated, visual industrial defect detection receives much attention, including two-dimensional and three-dimensional visual feature modeling. Traditional methods use statistical analysis, abnormal data synthesis modeling, and generation-based models to separate product defect features and complete defect detection. Recently, the emergence of foundation models has brought visual and textual semantic prior knowledge. Many methods are based on foundation models (FM) to improve the accuracy of detection, but at the same time, increase model complexity and slow down inference speed. Some FM-based methods have begun to explore lightweight modeling ways, which have gradually attracted attention and deserve to be systematically analyzed. In this paper, we conduct a systematic survey with comparisons and discussions of foundation model methods from different aspects and briefly review non-foundation model (NFM) methods recently published. Furthermore, we discuss the differences between FM and NFM methods from training objectives, model structure and scale, model performance, and potential directions for future exploration. Through comparison, we find FM methods are more suitable for few-shot and zero-shot learning, which are more in line with actual industrial application scenarios and worthy of in-depth research.
Authors: Ziyuan Luo, Anderson Rocha, Boxin Shi, Qing Guo, Haoliang Li, Renjie Wan
Abstract: Neural Radiance Fields (NeRF) have been gaining attention as a significant form of 3D content representation. With the proliferation of NeRF-based creations, the need for copyright protection has emerged as a critical issue. Although some approaches have been proposed to embed digital watermarks into NeRF, they often neglect essential model-level considerations and incur substantial time overheads, resulting in reduced imperceptibility and robustness, along with user inconvenience. In this paper, we extend the previous criteria for image watermarking to the model level and propose NeRF Signature, a novel watermarking method for NeRF. We employ a Codebook-aided Signature Embedding (CSE) that does not alter the model structure, thereby maintaining imperceptibility and enhancing robustness at the model level. Furthermore, after optimization, any desired signatures can be embedded through the CSE, and no fine-tuning is required when NeRF owners want to use new binary signatures. Then, we introduce a joint pose-patch encryption watermarking strategy to hide signatures into patches rendered from a specific viewpoint for higher robustness. In addition, we explore a Complexity-Aware Key Selection (CAKS) scheme to embed signatures in high visual complexity patches to enhance imperceptibility. The experimental results demonstrate that our method outperforms other baseline methods in terms of imperceptibility and robustness. The source code is available at: https://github.com/luo-ziyuan/NeRF_Signature.
Authors: Junlong Ren, Hao Wu, Hui Xiong, Hao Wang
Abstract: The cross-modal 3D retrieval task aims to achieve mutual matching between text descriptions and 3D shapes. This has the potential to enhance the interaction between natural language and the 3D environment, especially within the realms of robotics and embodied artificial intelligence (AI) applications. However, the scarcity and expensiveness of 3D data constrain the performance of existing cross-modal 3D retrieval methods. These methods heavily rely on features derived from the limited number of 3D shapes, resulting in poor generalization ability across diverse scenarios. To address this challenge, we introduce SCA3D, a novel 3D shape and caption online data augmentation method for cross-modal 3D retrieval. Our approach uses the LLaVA model to create a component library, captioning each segmented part of every 3D shape within the dataset. Notably, it facilitates the generation of extensive new 3D-text pairs containing new semantic features. We employ both inter and intra distances to align various components into a new 3D shape, ensuring that the components do not overlap and are closely fitted. Further, text templates are utilized to process the captions of each component and generate new text descriptions. Besides, we use unimodal encoders to extract embeddings for 3D shapes and texts based on the enriched dataset. We then calculate fine-grained cross-modal similarity using Earth Mover's Distance (EMD) and enhance cross-modal matching with contrastive learning, enabling bidirectional retrieval between texts and 3D shapes. Extensive experiments show our SCA3D outperforms previous works on the Text2Shape dataset, raising the Shape-to-Text RR@1 score from 20.03 to 27.22 and the Text-to-Shape RR@1 score from 13.12 to 16.67. Codes can be found in https://github.com/3DAgentWorld/SCA3D.
Authors: Xuan Ding, Yao Zhu, Yunjian Zhang, Chuanlong Xie
Abstract: Compared to width-wise pruning, depth-wise pruning can significantly accelerate inference in resource-constrained scenarios. Howerver, treating the entire Transformer layer as the minimum pruning unit may degrade model performance by indiscriminately discarding the entire information of the layer. This paper reveals the "Patch-like" feature relationship between layers in large language models by analyzing the correlation of the outputs of different layers in the reproducing kernel Hilbert space. Building on this observation, we proposes a sliding layer merging method that dynamically selects and fuses consecutive layers from top to bottom according to a pre-defined similarity threshold, thereby simplifying the model structure while maintaining its performance. Extensive experiments on LLMs with various architectures and different parameter scales show that our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning. In particular, in the experiment with 35\% pruning on the Vicuna-7B model, our method achieved a 1.654\% improvement in average performance on zero-shot tasks compared to the existing method. Moreover, we further reveal the potential of combining depth pruning with width pruning to enhance the pruning effect. Our codes are available at https://github.com/920927/SLM-a-sliding-layer-merging-method.
URLs: https://github.com/920927/SLM-a-sliding-layer-merging-method.
Authors: Anton Backhaus, Thorsten Luettel, Mirko Maehlisch
Abstract: An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to inconsistency in taxonomy and/or labeling policies of different datasets. To this end, we propose a knowledge distillation approach that also serves as a label space unification method for semantic segmentation. In short, a teacher model is trained on a source dataset with a given taxonomy, then used to pseudo-label additional data for which ground truth labels of a related label space exist. By mapping the related taxonomies to the source taxonomy, we create constraints within which the model can predict pseudo-labels. Using the improved pseudo-labels we train student models that consistently outperform their teachers in two challenging domains, namely urban and off-road driving. Our ground truth-corrected pseudo-labels span over 12 and 7 public datasets with 388.230 and 18.558 images for the urban and off-road domains, respectively, creating the largest compound datasets for autonomous driving to date.
Authors: Bernardin Tamo Amougou, Marcelo Pereyra, Barbara Pascal
Abstract: Image restoration problems are often ill-posed, leading to significant uncertainty in reconstructed images. Accurately quantifying this uncertainty is essential for the reliable interpretation of reconstructed images. However, image restoration methods often lack uncertainty quantification capabilities. Conformal prediction offers a rigorous framework to augment image restoration methods with accurate uncertainty quantification estimates, but it typically requires abundant ground truth data for calibration. This paper presents a self-supervised conformal prediction method for Poisson imaging problems which leverages Poisson Unbiased Risk Estimator to eliminate the need for ground truth data. The resulting self-calibrating conformal prediction approach is applicable to any Poisson linear imaging problem that is ill-conditioned, and is particularly effective when combined with modern self-supervised image restoration techniques trained directly on measurement data. The proposed method is demonstrated through numerical experiments on image denoising and deblurring; its performance are comparable to supervised conformal prediction methods relying on ground truth data.
Authors: Linshan Jia
Abstract: Feature extraction is crucial in intelligent fault diagnosis of rotating machinery. It is easier for convolutional neural networks(CNNs) to visually recognize and learn fault features by converting the complicated one-dimensional (1D) vibrational signals into two-dimensional (2D) images with simple textures. However, the existing representation methods for encoding 1D signals as images have two main problems, including complicated computation and low separability. Meanwhile, the existing 2D-CNN fault diagnosis methods taking 2D images as the only inputs still suffer from the inevitable information loss because of the conversion process. Considering the above issues, this paper proposes a new 1D-to-2D conversion method called Embedding Gramian Representation (EGR), which is easy to calculate and shows good separability. In EGR, 1D signals are projected in the embedding space and the intrinsic periodicity of vibrational signals is captured enabling the faulty characteristics contained in raw signals to be uncovered. Second, aiming at the information loss problem of existing CNN models with the single input of converted images, a double-branch EGR-based CNN, called EGR-Net, is proposed to learn faulty features from both raw signal feature maps and their corresponding EGRs. The bridge connection is designed to improve the feature learning interaction between the two branches. Widely used open domain gearbox dataset and bearing dataset are used to verify the effectiveness and efficiency of the proposed methods. EGR-Net is compared with traditional and state-of-the-art approaches, and the results show that the proposed method can deliver enhanced performance.
Authors: Zekang Weng, Jinjin Shi, Jinwei Wang, Zeming Han
Abstract: Image anomaly detection plays a vital role in applications such as industrial quality inspection and medical imaging, where it directly contributes to improving product quality and system reliability. However, existing methods often struggle with complex and diverse anomaly patterns. In particular, the separation between generation and discrimination tasks limits the effective coordination between anomaly sample generation and anomaly region detection. To address these challenges, we propose a novel hybrid diffusion model (HDM) that integrates generation and discrimination into a unified framework. The model consists of three key modules: the Diffusion Anomaly Generation Module (DAGM), the Diffusion Discriminative Module (DDM), and the Probability Optimization Module (POM). DAGM generates realistic and diverse anomaly samples, improving their representativeness. DDM then applies a reverse diffusion process to capture the differences between generated and normal samples, enabling precise anomaly region detection and localization based on probability distributions. POM refines the probability distributions during both the generation and discrimination phases, ensuring high-quality samples are used for training. Extensive experiments on multiple industrial image datasets demonstrate that our method outperforms state-of-the-art approaches, significantly improving both image-level and pixel-level anomaly detection performance, as measured by AUROC.
Authors: Xiankang He, Dongyan Guo, Hongji Li, Ruibo Li, Ying Cui, Chi Zhang
Abstract: Monocular depth estimation (MDE) aims to predict scene depth from a single RGB image and plays a crucial role in 3D scene understanding. Recent advances in zero-shot MDE leverage normalized depth representations and distillation-based learning to improve generalization across diverse scenes. However, current depth normalization methods for distillation, relying on global normalization, can amplify noisy pseudo-labels, reducing distillation effectiveness. In this paper, we systematically analyze the impact of different depth normalization strategies on pseudo-label distillation. Based on our findings, we propose Cross-Context Distillation, which integrates global and local depth cues to enhance pseudo-label quality. Additionally, we introduce a multi-teacher distillation framework that leverages complementary strengths of different depth estimation models, leading to more robust and accurate depth predictions. Extensive experiments on benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, both quantitatively and qualitatively.
Authors: Nikita Shvetsov, Thomas K. Kilvaer, Masoud Tafavvoghi, Anders Sildnes, Kajsa M{\o}llersen, Lill-Tove Rasmussen Busund, Lars Ailo Bongo
Abstract: Developing clinically useful cell-level analysis tools in digital pathology remains challenging due to limitations in dataset granularity, inconsistent annotations, high computational demands, and difficulties integrating new technologies into workflows. To address these issues, we propose a solution that enhances data quality, model performance, and usability by creating a lightweight, extensible cell segmentation and classification model. First, we update data labels through cross-relabeling to refine annotations of PanNuke and MoNuSAC, producing a unified dataset with seven distinct cell types. Second, we leverage the H-Optimus foundation model as a fixed encoder to improve feature representation for simultaneous segmentation and classification tasks. Third, to address foundation models' computational demands, we distill knowledge to reduce model size and complexity while maintaining comparable performance. Finally, we integrate the distilled model into QuPath, a widely used open-source digital pathology platform. Results demonstrate improved segmentation and classification performance using the H-Optimus-based model compared to a CNN-based model. Specifically, average $R^2$ improved from 0.575 to 0.871, and average $PQ$ score improved from 0.450 to 0.492, indicating better alignment with actual cell counts and enhanced segmentation quality. The distilled model maintains comparable performance while reducing parameter count by a factor of 48. By reducing computational complexity and integrating into workflows, this approach may significantly impact diagnostics, reduce pathologist workload, and improve outcomes. Although the method shows promise, extensive validation is necessary prior to clinical deployment.
Authors: Tharindu Samarakoon, Kalana Abeywardena, Chamira U. S. Edussooriya
Abstract: A four-dimensional light field (LF) captures both textural and geometrical information of a scene in contrast to a two-dimensional image that captures only the textural information of a scene. Post-capture refocusing is an exciting application of LFs enabled by the geometric information captured. Previously proposed LF refocusing methods are mostly limited to the refocusing of single planar or volumetric region of a scene corresponding to a depth range and cannot simultaneously generate in-focus and out-of-focus regions having the same depth range. In this paper, we propose an end-to-end pipeline to simultaneously refocus multiple arbitrary planar or volumetric regions of a dense or a sparse LF. We employ pixel-dependent shifts with the typical shift-and-sum method to refocus an LF. The pixel-dependent shifts enables to refocus each pixel of an LF independently. For sparse LFs, the shift-and-sum method introduces ghosting artifacts due to the spatial undersampling. We employ a deep learning model based on U-Net architecture to almost completely eliminate the ghosting artifacts. The experimental results obtained with several LF datasets confirm the effectiveness of the proposed method. In particular, sparse LFs refocused with the proposed method archive structural similarity index higher than 0.9 despite having only 20% of data compared to dense LFs.
Authors: Qihang Peng, Henry Zheng, Gao Huang
Abstract: Embodied intelligence requires agents to interact with 3D environments in real time based on language instructions. A foundational task in this domain is ego-centric 3D visual grounding. However, the point clouds rendered from RGB-D images retain a large amount of redundant background data and inherent noise, both of which can interfere with the manifold structure of the target regions. Existing point cloud enhancement methods often require a tedious process to improve the manifold, which is not suitable for real-time tasks. We propose Proxy Transformation suitable for multimodal task to efficiently improve the point cloud manifold. Our method first leverages Deformable Point Clustering to identify the point cloud sub-manifolds in target regions. Then, we propose a Proxy Attention module that utilizes multimodal proxies to guide point cloud transformation. Built upon Proxy Attention, we design a submanifold transformation generation module where textual information globally guides translation vectors for different submanifolds, optimizing relative spatial relationships of target regions. Simultaneously, image information guides linear transformations within each submanifold, refining the local point cloud manifold of target regions. Extensive experiments demonstrate that Proxy Transformation significantly outperforms all existing methods, achieving an impressive improvement of 7.49% on easy targets and 4.60% on hard targets, while reducing the computational overhead of attention blocks by 40.6%. These results establish a new SOTA in ego-centric 3D visual grounding, showcasing the effectiveness and robustness of our approach.
Authors: Nadya Abdel Madjid, Murad Mebrahtu, Abdelmoamen Nasser, Bilal Hassan, Naoufel Werghi, Jorge Dias, Majid Khonji
Abstract: This paper introduces the Emirates Multi-Task (EMT) dataset - the first publicly available dataset for autonomous driving collected in the Arab Gulf region. The EMT dataset captures the unique road topology, high traffic congestion, and distinctive characteristics of the Gulf region, including variations in pedestrian clothing and weather conditions. It contains over 30,000 frames from a dash-camera perspective, along with 570,000 annotated bounding boxes, covering approximately 150 kilometers of driving routes. The EMT dataset supports three primary tasks: tracking, trajectory forecasting and intention prediction. Each benchmark dataset is complemented with corresponding evaluations: (1) multi-agent tracking experiments, focusing on multi-class scenarios and occlusion handling; (2) trajectory forecasting evaluation using deep sequential and interaction-aware models; and (3) intention benchmark experiments conducted for predicting agents intentions from observed trajectories. The dataset is publicly available at https://avlab.io/emt-dataset, and pre-processing scripts along with evaluation models can be accessed at https://github.com/AV-Lab/emt-dataset.
URLs: https://avlab.io/emt-dataset,, https://github.com/AV-Lab/emt-dataset.
Authors: Jiawei Kong, Hao Fang, Sihang Guo, Chenxi Qing, Bin Chen, Bin Wang, Shu-Tao Xia
Abstract: While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit excellent representational capabilities for multimodal data, recent studies have shown that they are vulnerable to backdoor attacks. To alleviate the threat, existing defense strategies primarily focus on fine-tuning the entire suspicious model, yet offer only marginal resistance to state-of-the-art attacks and often result in a decrease in clean accuracy, particularly in data-limited scenarios. Their failure may be attributed to the mismatch between insufficient fine-tuning data and massive parameters in VLMs. To address this challenge, we propose Class-wise Backdoor Prompt Tuning (CBPT) defense, an efficient and effective method that operates on the text prompts to indirectly purify the poisoned VLMs. Specifically, we first employ the advanced contrastive learning via our carefully crafted positive and negative samples, to effectively invert the backdoor triggers that are potentially adopted by the attacker. Once the dummy trigger is established, we utilize the efficient prompt tuning technique to optimize these class-wise text prompts for modifying the model's decision boundary to further reclassify the feature regions of backdoor triggers. Extensive experiments demonstrate that CBPT significantly mitigates backdoor threats while preserving model utility, e.g. an average Clean Accuracy (CA) of 58.86\% and an Attack Success Rate (ASR) of 0.39\% across seven mainstream backdoor attacks. These results underscore the superiority of our prompt purifying design to strengthen model robustness against backdoor attacks.
Authors: Ruben T. Lucassen, Tijn van de Luijtgaarden, Sander P. J. Moonemans, Gerben E. Breimer, Willeke A. M. Blokx, Mitko Veta
Abstract: Vision-language models in pathology enable multimodal case retrieval and automated report generation. Many of the models developed so far, however, have been trained on pathology reports that include information which cannot be inferred from paired whole slide images (e.g., patient history), potentially leading to hallucinated sentences in generated reports. To this end, we investigate how the selection of information from pathology reports for vision-language modeling affects the quality of the multimodal representations and generated reports. More concretely, we compare a model trained on full reports against a model trained on preprocessed reports that only include sentences describing the cell and tissue appearances based on the H&E-stained slides. For the experiments, we built upon the BLIP-2 framework and used a cutaneous melanocytic lesion dataset of 42,433 H&E-stained whole slide images and 19,636 corresponding pathology reports. Model performance was assessed using image-to-text and text-to-image retrieval, as well as qualitative evaluation of the generated reports by an expert pathologist. Our results demonstrate that text preprocessing prevents hallucination in report generation. Despite the improvement in the quality of the generated reports, training the vision-language model on full reports showed better cross-modal retrieval performance.
Authors: Ruben T. Lucassen, Sander P. J. Moonemans, Tijn van de Luijtgaarden, Gerben E. Breimer, Willeke A. M. Blokx, Mitko Veta
Abstract: Millions of melanocytic skin lesions are examined by pathologists each year, the majority of which concern common nevi (i.e., ordinary moles). While most of these lesions can be diagnosed in seconds, writing the corresponding pathology report is much more time-consuming. Automating part of the report writing could, therefore, alleviate the increasing workload of pathologists. In this work, we develop a vision-language model specifically for the pathology domain of cutaneous melanocytic lesions. The model follows the Contrastive Captioner framework and was trained and evaluated using a melanocytic lesion dataset of 42,512 H&E-stained whole slide images and 19,645 corresponding pathology reports. Our results show that the quality scores of model-generated reports were on par with pathologist-written reports for common nevi, assessed by an expert pathologist in a reader study. While report generation revealed to be more difficult for rare melanocytic lesion subtypes, the cross-modal retrieval performance for these cases was considerably better.
Authors: Zhe Wang, Shaocong Xu, Xucai Zhuang, Tongda Xu, Yan Wang, Jingjing Liu, Yilun Chen, Ya-Qin Zhang
Abstract: Cooperative perception enhances the individual perception capabilities of autonomous vehicles (AVs) by providing a comprehensive view of the environment. However, balancing perception performance and transmission costs remains a significant challenge. Current approaches that transmit region-level features across agents are limited in interpretability and demand substantial bandwidth, making them unsuitable for practical applications. In this work, we propose CoopDETR, a novel cooperative perception framework that introduces object-level feature cooperation via object query. Our framework consists of two key modules: single-agent query generation, which efficiently encodes raw sensor data into object queries, reducing transmission cost while preserving essential information for detection; and cross-agent query fusion, which includes Spatial Query Matching (SQM) and Object Query Aggregation (OQA) to enable effective interaction between queries. Our experiments on the OPV2V and V2XSet datasets demonstrate that CoopDETR achieves state-of-the-art performance and significantly reduces transmission costs to 1/782 of previous methods.
Authors: Rui Li, Qianfen Jiao, Wenming Cao, Hau-San Wong, Si Wu
Abstract: In this paper, we investigate a challenging unsupervised domain adaptation setting -- unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model on the target domain, since labeled source data may not be available in some real-world scenarios due to data privacy issues. For this purpose, we propose a new framework, which is referred to as collaborative class conditional generative adversarial net to bypass the dependence on the source data. Specifically, the prediction model is to be improved through generated target-style data, which provides more accurate guidance for the generator. As a result, the generator and the prediction model can collaborate with each other without source data. Furthermore, due to the lack of supervision from source data, we propose a weight constraint that encourages similarity to the source model. A clustering-based regularization is also introduced to produce more discriminative features in the target domain. Compared to conventional domain adaptation methods, our model achieves superior performance on multiple adaptation tasks with only unlabeled target data, which verifies its effectiveness in this challenging setting.
Authors: Danae S\'anchez Villegas, Ingo Ziegler, Desmond Elliott
Abstract: Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often treating images independently. This work introduces ImageChain, a framework that enhances MLLMs with sequential reasoning capabilities over image data by modeling visual sequences as a multi-turn conversation. In ImageChain, images are interleaved with corresponding textual descriptions to form a controlled dialogue that explicitly captures temporal dependencies and narrative progression. Our method optimizes for the task of next-scene description, where the model generates a context-aware description of an upcoming scene based on preceding visual and textual cues. We demonstrate that our approach improves performance on the next-scene description task -- achieving an average improvement from 3.7% to 19% in SimRate, a metric that quantifies semantic similarity to human-annotated ground truths. Moreover, ImageChain achieves robust zero-shot out-of-domain performance in applications ranging from comics to robotics. Extensive experiments validate that instruction-tuning in a multimodal, multi-turn conversation design is key to bridging the gap between static image understanding and temporally-aware reasoning.
Authors: Jiaqi Xu, Cuiling Lan, Xuejin Chen, Yan Lu
Abstract: The burgeoning growth of open-sourced vision-language models (VLMs) has catalyzed a plethora of applications across diverse domains. Ensuring the transparency and interpretability of these models is critical for fostering trustworthy and responsible AI systems. In this study, our objective is to delve into the internals of VLMs to interpret the functions of individual neurons. We observe the activations of neurons with respects to the input visual tokens and text tokens, and reveal some interesting findings. Particularly, we found that there are neurons responsible for only visual or text information, or both, respectively, which we refer to them as visual neurons, text neurons, and multi-modal neurons, respectively. We build a framework that automates the explanation of neurons with the assistant of GPT-4o. Meanwhile, for visual neurons, we propose an activation simulator to assess the reliability of the explanations for visual neurons. System statistical analyses on top of one representative VLM of LLaVA, uncover the behaviors/characteristics of different categories of neurons.
Authors: Xuemeng Song, Haoqiang Lin, Haokun Wen, Bohan Hou, Mingzhu Xu, Liqiang Nie
Abstract: Composed Image Retrieval (CIR) is an emerging yet challenging task that allows users to search for target images using a multimodal query, comprising a reference image and a modification text specifying the user's desired changes to the reference image. Given its significant academic and practical value, CIR has become a rapidly growing area of interest in the computer vision and machine learning communities, particularly with the advances in deep learning. To the best of our knowledge, there is currently no comprehensive review of CIR to provide a timely overview of this field. Therefore, we synthesize insights from over 120 publications in top conferences and journals, including ACM TOIS, SIGIR, and CVPR In particular, we systematically categorize existing supervised CIR and zero-shot CIR models using a fine-grained taxonomy. For a comprehensive review, we also briefly discuss approaches for tasks closely related to CIR, such as attribute-based CIR and dialog-based CIR. Additionally, we summarize benchmark datasets for evaluation and analyze existing supervised and zero-shot CIR methods by comparing experimental results across multiple datasets. Furthermore, we present promising future directions in this field, offering practical insights for researchers interested in further exploration.
Authors: Solha Kang, Wesley De Neve, Francois Rameau, Utku Ozbulak
Abstract: The past decade has witnessed a substantial increase in the number of startups and companies offering AI-based solutions for clinical decision support in medical institutions. However, the critical nature of medical decision-making raises several concerns about relying on external software. Key issues include potential variations in image modalities and the medical devices used to obtain these images, potential legal issues, and adversarial attacks. Fortunately, the open-source nature of machine learning research has made foundation models publicly available and straightforward to use for medical applications. This accessibility allows medical institutions to train their own AI-based models, thereby mitigating the aforementioned concerns. Given this context, an important question arises: how much data do medical institutions need to train effective AI models? In this study, we explore this question in relation to breast cancer detection, a particularly contested area due to the prevalence of this disease, which affects approximately 1 in every 8 women. Through large-scale experiments on various patient sizes in the training set, we show that medical institutions do not need a decade's worth of MRI images to train an AI model that performs competitively with the state-of-the-art, provided the model leverages foundation models. Furthermore, we observe that for patient counts greater than 50, the number of patients in the training set has a negligible impact on the performance of models and that simple ensembles further improve the results without additional complexity.
Authors: Yukun Chen, Shuo Shao, Enhao Huang, Yiming Li, Pin-Yu Chen, Zhan Qin, Kui Ren
Abstract: Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase. Pre-processing-based defense, which is one of the most important defense paradigms, typically focuses on input transformations or backdoor trigger inversion (BTI) to deactivate or eliminate embedded backdoor triggers during the inference process. However, these methods suffer from inherent limitations: transformation-based defenses often fail to balance model utility and defense performance, while BTI-based defenses struggle to accurately reconstruct trigger patterns without prior knowledge. In this paper, we propose REFINE, an inversion-free backdoor defense method based on model reprogramming. REFINE consists of two key components: \textbf{(1)} an input transformation module that disrupts both benign and backdoor patterns, generating new benign features; and \textbf{(2)} an output remapping module that redefines the model's output domain to guide the input transformations effectively. By further integrating supervised contrastive loss, REFINE enhances the defense capabilities while maintaining model utility. Extensive experiments on various benchmark datasets demonstrate the effectiveness of our REFINE and its resistance to potential adaptive attacks.
Authors: Sefik Serengil, Alper Ozpinar
Abstract: Facial recognition systems rely on embeddings to represent facial images and determine identity by verifying if the distance between embeddings is below a pre-tuned threshold. While embeddings are not reversible to original images, they still contain sensitive information, making their security critical. Traditional encryption methods like AES are limited in securely utilizing cloud computational power for distance calculations. Homomorphic Encryption, allowing calculations on encrypted data, offers a robust alternative. This paper introduces CipherFace, a homomorphic encryption-driven framework for secure cloud-based facial recognition, which we have open-sourced at http://github.com/serengil/cipherface. By leveraging FHE, CipherFace ensures the privacy of embeddings while utilizing the cloud for efficient distance computation. Furthermore, we propose a novel encrypted distance computation method for both Euclidean and Cosine distances, addressing key challenges in performing secure similarity calculations on encrypted data. We also conducted experiments with different facial recognition models, various embedding sizes, and cryptosystem configurations, demonstrating the scalability and effectiveness of CipherFace in real-world applications.
Authors: Runze Jiang, Pengjian Shang
Abstract: Information theory and Shannon entropy are essential for quantifying irregularity in complex systems or signals. Recently, two-dimensional entropy methods, such as two-dimensional sample entropy, distribution entropy, and permutation entropy, have been proposed for analyzing 2D texture or image data. This paper introduces Gradient entropy (GradEn), an extension of slope entropy to 2D, which considers both symbolic patterns and amplitude information, enabling better feature extraction from image data. We evaluate GradEn with simulated data, including 2D colored noise, 2D mixed processes, and the logistic map. Results show the ability of GradEn to distinguish images with various characteristics while maintaining low computational cost. Real-world datasets, consist of texture, fault gear, and railway corrugation signals, demonstrate the superior performance of GradEn in classification tasks compared to other 2D entropy methods. In conclusion, GradEn is an effective tool for image characterization, offering a novel approach for image processing and recognition.
Authors: Linshan Wu, Jiaxin Zhuang, Yanning Zhou, Sunan He, Jiabo Ma, Luyang Luo, Xi Wang, Xuefeng Ni, Xiaoling Zhong, Mingxiang Wu, Yinghua Zhao, Xiaohui Duan, Varut Vardhanabhuti, Pranav Rajpurkar, Hao Chen
Abstract: Tumor is a leading cause of death worldwide, with an estimated 10 million deaths attributed to tumor-related diseases every year. AI-driven tumor recognition unlocks new possibilities for more precise and intelligent tumor screening and diagnosis. However, the progress is heavily hampered by the scarcity of annotated datasets, which demands extensive annotation efforts by radiologists. To tackle this challenge, we introduce FreeTumor, an innovative Generative AI (GAI) framework to enable large-scale tumor synthesis for mitigating data scarcity. Specifically, FreeTumor effectively leverages a combination of limited labeled data and large-scale unlabeled data for tumor synthesis training. Unleashing the power of large-scale data, FreeTumor is capable of synthesizing a large number of realistic tumors on images for augmenting training datasets. To this end, we create the largest training dataset for tumor synthesis and recognition by curating 161,310 publicly available Computed Tomography (CT) volumes from 33 sources, with only 2.3% containing annotated tumors. To validate the fidelity of synthetic tumors, we engaged 13 board-certified radiologists in a Visual Turing Test to discern between synthetic and real tumors. Rigorous clinician evaluation validates the high quality of our synthetic tumors, as they achieved only 51.1% sensitivity and 60.8% accuracy in distinguishing our synthetic tumors from real ones. Through high-quality tumor synthesis, FreeTumor scales up the recognition training datasets by over 40 times, showcasing a notable superiority over state-of-the-art AI methods including various synthesis methods and foundation models. These findings indicate promising prospects of FreeTumor in clinical applications, potentially advancing tumor treatments and improving the survival rates of patients.
Authors: Kamyar Barakati, Yu Liu, Utkarsh Pratiush, Boris N. Slautin, Sergei V. Kalinin
Abstract: Analyzing imaging and hyperspectral data is crucial across scientific fields, including biology, medicine, chemistry, and physics. The primary goal is to transform high-resolution or high-dimensional data into an interpretable format to generate actionable insights, aiding decision-making and advancing knowledge. Currently, this task relies on complex, human-designed workflows comprising iterative steps such as denoising, spatial sampling, keypoint detection, feature generation, clustering, dimensionality reduction, and physics-based deconvolutions. The introduction of machine learning over the past decade has accelerated tasks like image segmentation and object detection via supervised learning, and dimensionality reduction via unsupervised methods. However, both classical and NN-based approaches still require human input, whether for hyperparameter tuning, data labeling, or both. The growing use of automated imaging tools, from atomically resolved imaging to biological applications, demands unsupervised methods that optimize data representation for human decision-making or autonomous experimentation. Here, we discuss advances in reward-based workflows, which adopt expert decision-making principles and demonstrate strong transfer learning across diverse tasks. We represent image analysis as a decision-making process over possible operations and identify desiderata and their mappings to classical decision-making frameworks. Reward-driven workflows enable a shift from supervised, black-box models sensitive to distribution shifts to explainable, unsupervised, and robust optimization in image analysis. They can function as wrappers over classical and DCNN-based methods, making them applicable to both unsupervised and supervised workflows (e.g., classification, regression for structure-property mapping) across imaging and hyperspectral data.
Authors: Yao Su, Keqi Han, Mingjie Zeng, Lichao Sun, Liang Zhan, Carl Yang, Lifang He, Xiangnan Kong
Abstract: Brain imaging analysis is fundamental in neuroscience, providing valuable insights into brain structure and function. Traditional workflows follow a sequential pipeline-brain extraction, registration, segmentation, parcellation, network generation, and classification-treating each step as an independent task. These methods rely heavily on task-specific training data and expert intervention to correct intermediate errors, making them particularly burdensome for high-dimensional neuroimaging data, where annotations and quality control are costly and time-consuming. We introduce UniBrain, a unified end-to-end framework that integrates all processing steps into a single optimization process, allowing tasks to interact and refine each other. Unlike traditional approaches that require extensive task-specific annotations, UniBrain operates with minimal supervision, leveraging only low-cost labels (i.e., classification and extraction) and a single labeled atlas. By jointly optimizing extraction, registration, segmentation, parcellation, network generation, and classification, UniBrain enhances both accuracy and computational efficiency while significantly reducing annotation effort. Experimental results demonstrate its superiority over existing methods across multiple tasks, offering a more scalable and reliable solution for neuroimaging analysis. Our code and data can be found at https://github.com/Anonymous7852/UniBrain
Authors: ZhenZhou Wang
Abstract: The histogram of an image is the accurate graphical representation of the numerical grayscale distribution and it is also an estimate of the probability distribution of image pixels. Therefore, histogram has been widely adopted to calculate the clustering means and partitioning thresholds for image segmentation. There have been many classical histogram-based image segmentation methods proposed and played important roles in both academics and industry. In this article, the histories and recent advances of the histogram-based image segmentation techniques are first reviewed and then they are divided into four categories: (1), the means-based method; (2), the Gaussian-mixture-model-based method; (3), the entropy-based method and (4) the feature-points-based method. The principles of the classical histogram-based image segmentation methods are described at first and then their performances are compared objectively. In addition, the histogram-based image segmentation methods are compared with the general-purpose deep learning methods in segmenting objects with uniform or simple backgrounds. The histogram-based image segmentation methods are more accurate than the universal deep-learning methods without special training in segmenting many types of images.
Authors: M. E. Smith, N. Yilmaz, T. Watts, P. M. Scheikl, J. Ge, A. Deguet, A. Kuntz, A. Krieger
Abstract: Existing tracheal tumor resection methods often lack the precision required for effective airway clearance, and robotic advancements offer new potential for autonomous resection. We present a vision-guided, autonomous approach for palliative resection of tracheal tumors. This system models the tracheal surface with a fifth-degree polynomial to plan tool trajectories, while a custom Faster R-CNN segmentation pipeline identifies the trachea and tumor boundaries. The electrocautery tool angle is optimized using handheld surgical demonstrations, and trajectories are planned to maintain a 1 mm safety clearance from the tracheal surface. We validated the workflow successfully in five consecutive experiments on ex-vivo animal tissue models, successfully clearing the airway obstruction without trachea perforation in all cases (with more than 90% volumetric tumor removal). These results support the feasibility of an autonomous resection platform, paving the way for future developments in minimally-invasive autonomous resection.
Authors: Angela Busheska, Vikram Iyer, Bruno Silva, Peder Olsen, Ranveer Chandra, Vaishnavi Ranganathan
Abstract: Understanding land use over time is critical to tracking events related to climate change, like deforestation. However, satellite-based remote sensing tools which are used for monitoring struggle to differentiate vegetation types in farms and orchards from forests. We observe that metrics such as the Normalized Difference Vegetation Index (NDVI), based on plant photosynthesis, have unique temporal signatures that reflect agricultural practices and seasonal cycles. We analyze yearly NDVI changes on 20 farms for 10 unique crops. Initial results show that NDVI curves are coherent with agricultural practices, are unique to each crop, consistent globally, and can differentiate farms from forests. We develop a novel longitudinal NDVI dataset for the state of California from 2020-2023 with 500~m resolution and over 70 million points. We use this to develop the TerraTrace platform, an end-to-end analytic tool that classifies land use using NDVI signatures and allows users to query the system through an LLM chatbot and graphical interface.
Authors: Nicolas Harvey Chapman, Feras Dayoub, Will Browne, Christopher Lehnert
Abstract: A domain shift exists between the large-scale, internet data used to train a Vision-Language Model (VLM) and the raw image streams collected by a robot. Existing adaptation strategies require the definition of a closed-set of classes, which is impractical for a robot that must respond to diverse natural language queries. In response, we present QueryAdapter; a novel framework for rapidly adapting a pre-trained VLM in response to a natural language query. QueryAdapter leverages unlabelled data collected during previous deployments to align VLM features with semantic classes related to the query. By optimising learnable prompt tokens and actively selecting objects for training, an adapted model can be produced in a matter of minutes. We also explore how objects unrelated to the query should be dealt with when using real-world data for adaptation. In turn, we propose the use of object captions as negative class labels, helping to produce better calibrated confidence scores during adaptation. Extensive experiments on ScanNet++ demonstrate that QueryAdapter significantly enhances object retrieval performance compared to state-of-the-art unsupervised VLM adapters and 3D scene graph methods. Furthermore, the approach exhibits robust generalization to abstract affordance queries and other datasets, such as Ego4D.
Authors: Gabriele Tiboni, Raffaello Camoriano, Tatiana Tommasi
Abstract: Object-Centric Motion Generation (OCMG) plays a key role in a variety of industrial applications$\unicode{x2014}$such as robotic spray painting and welding$\unicode{x2014}$requiring efficient, scalable, and generalizable algorithms to plan multiple long-horizon trajectories over free-form 3D objects. However, existing solutions rely on specialized heuristics, expensive optimization routines, or restrictive geometry assumptions that limit their adaptability to real-world scenarios. In this work, we introduce a novel, fully data-driven framework that tackles OCMG directly from 3D point clouds, learning to generalize expert path patterns across free-form surfaces. We propose MaskPlanner, a deep learning method that predicts local path segments for a given object while simultaneously inferring "path masks" to group these segments into distinct paths. This design induces the network to capture both local geometric patterns and global task requirements in a single forward pass. Extensive experimentation on a realistic robotic spray painting scenario shows that our approach attains near-complete coverage (above 99%) for unseen objects, while it remains task-agnostic and does not explicitly optimize for paint deposition. Moreover, our real-world validation on a 6-DoF specialized painting robot demonstrates that the generated trajectories are directly executable and yield expert-level painting quality. Our findings crucially highlight the potential of the proposed learning method for OCMG to reduce engineering overhead and seamlessly adapt to several industrial use cases.
Authors: Kiranmayee Janardhan, Christy Bobby Thomas
Abstract: Glioma, the prevalent primary brain tumor, exhibits diverse aggressiveness levels and prognoses. Precise classification of glioma is paramount for treatment planning and predicting prognosis. This study aims to develop an algorithm to fuse the MRI images from T1, T2, T1ce, and fluid-attenuated inversion recovery (FLAIR) sequences to enhance the efficacy of glioma subclass classification as no tumor, necrotic core, peritumoral edema, and enhancing tumor. The MRI images from BraTS datasets were used in this work. The images were pre-processed using max-min normalization to ensure consistency in pixel intensity values across different images. The segmentation of the necrotic core, peritumoral edema, and enhancing tumor was performed on 2D and 3D images separately using UNET architecture. Further, the segmented regions from multimodal MRI images were fused using the weighted averaging technique. Integrating 2D and 3D segmented outputs enhances classification accuracy by capturing detailed features like tumor shape, boundaries, and intensity distribution in slices, while also providing a comprehensive view of spatial extent, shape, texture, and localization within the brain volume. The fused images were used as input to the pre-trained ResNet50 model for glioma subclass classification. The network is trained on 80% and validated on 20% of the data. The proposed method achieved a classification of accuracy of 99.25%, precision of 99.30%, recall of 99.10, F1 score of 99.19%, Intersection Over Union of 84.49%, and specificity of 99.76, which showed a significantly higher performance than existing techniques. These findings emphasize the significance of glioma segmentation and classification in aiding accurate diagnosis.
Authors: Muhammad A. Muttaqien, Tomohiro Motoda, Ryo Hanai, Domae Yukiyasu
Abstract: This paper introduces a novel pipeline to enhance the precision of object masking for robotic manipulation within the specific domain of masking products in convenience stores. The approach integrates two advanced AI models, CLIP and SAM, focusing on their synergistic combination and the effective use of multimodal data (image and text). Emphasis is placed on utilizing gradient-based attention mechanisms and customized datasets to fine-tune performance. While CLIP, SAM, and Grad- CAM are established components, their integration within this structured pipeline represents a significant contribution to the field. The resulting segmented masks, generated through this combined approach, can be effectively utilized as inputs for robotic systems, enabling more precise and adaptive object manipulation in the context of convenience store products.
Authors: Zerui Li, Gengze Zhou, Haodong Hong, Yanyan Shao, Wenqi Lyu, Yanyuan Qiao, Qi Wu
Abstract: Vision-and-Language Navigation (VLN) empowers agents to associate time-sequenced visual observations with corresponding instructions to make sequential decisions. However, generalization remains a persistent challenge, particularly when dealing with visually diverse scenes or transitioning from simulated environments to real-world deployment. In this paper, we address the mismatch between human-centric instructions and quadruped robots with a low-height field of view, proposing a Ground-level Viewpoint Navigation (GVNav) approach to mitigate this issue. This work represents the first attempt to highlight the generalization gap in VLN across varying heights of visual observation in realistic robot deployments. Our approach leverages weighted historical observations as enriched spatiotemporal contexts for instruction following, effectively managing feature collisions within cells by assigning appropriate weights to identical features across different viewpoints. This enables low-height robots to overcome challenges such as visual obstructions and perceptual mismatches. Additionally, we transfer the connectivity graph from the HM3D and Gibson datasets as an extra resource to enhance spatial priors and a more comprehensive representation of real-world scenarios, leading to improved performance and generalizability of the waypoint predictor in real-world environments. Extensive experiments demonstrate that our Ground-level Viewpoint Navigation (GVnav) approach significantly improves performance in both simulated environments and real-world deployments with quadruped robots.
Authors: Fengbin Guan, Zihao Yu, Yiting Lu, Xin Li, Zhibo Chen
Abstract: Video quality assessment tasks rely heavily on the rich features required for video understanding, such as semantic information, texture, and temporal motion. The existing video foundational model, InternVideo2, has demonstrated strong potential in video understanding tasks due to its large parameter size and large-scale multimodal data pertaining. Building on this, we explored the transferability of InternVideo2 to video quality assessment under compression scenarios. To design a lightweight model suitable for this task, we proposed a distillation method to equip the smaller model with rich compression quality priors. Additionally, we examined the performance of different backbones during the distillation process. The results showed that, compared to other methods, our lightweight model distilled from InternVideo2 achieved excellent performance in compression video quality assessment.
Authors: Pu Wang, Huaizhi Ma, Zhihua Zhang, Zhuoran Zheng
Abstract: Accurate polyp segmentation remains challenging due to irregular lesion morphologies, ambiguous boundaries, and heterogeneous imaging conditions. While U-Net variants excel at local feature fusion, they often lack explicit mechanisms to model the dynamic evolution of segmentation confidence under uncertainty. Inspired by the interpretable nature of flow-based models, we present \textbf{PolypFLow}, a flow-matching enhanced architecture that injects physics-inspired optimization dynamics into segmentation refinement. Unlike conventional cascaded networks, our framework solves an ordinary differential equation (ODE) to progressively align coarse initial predictions with ground truth masks through learned velocity fields. This trajectory-based refinement offers two key advantages: 1) Interpretable Optimization: Intermediate flow steps visualize how the model corrects under-segmented regions and sharpens boundaries at each ODE-solver iteration, demystifying the ``black-box" refinement process; 2) Boundary-Aware Robustness: The flow dynamics explicitly model gradient directions along polyp edges, enhancing resilience to low-contrast regions and motion artifacts. Numerous experimental results show that PolypFLow achieves a state-of-the-art while maintaining consistent performance in different lighting scenarios.
Authors: Jiebin Yan, Ziwen Tan, Yuming Fang, Jiale Rao, Yifan Zuo
Abstract: Omnidirectional image, also called 360-degree image, is able to capture the entire 360-degree scene, thereby providing more realistic immersive feelings for users than general 2D image and stereoscopic image. Meanwhile, this feature brings great challenges to measuring the perceptual quality of omnidirectional images, which is closely related to users' quality of experience, especially when the omnidirectional images suffer from non-uniform distortion. In this paper, we propose a novel and effective blind omnidirectional image quality assessment (BOIQA) model with multi-axis attention (Max360IQ), which can proficiently measure not only the quality of uniformly distorted omnidirectional images but also the quality of non-uniformly distorted omnidirectional images. Specifically, the proposed Max360IQ is mainly composed of a backbone with stacked multi-axis attention modules for capturing both global and local spatial interactions of extracted viewports, a multi-scale feature integration (MSFI) module to fuse multi-scale features and a quality regression module with deep semantic guidance for predicting the quality of omnidirectional images. Experimental results demonstrate that the proposed Max360IQ outperforms the state-of-the-art Assessor360 by 3.6\% in terms of SRCC on the JUFE database with non-uniform distortion, and gains improvement of 0.4\% and 0.8\% in terms of SRCC on the OIQA and CVIQ databases, respectively. The source code is available at https://github.com/WenJuing/Max360IQ.
Authors: Behnaz Elhaminia, Abdullah Alsalemi, Esha Nasir, Mostafa Jahanifar, Ruqayya Awan, Lawrence S. Young, Nasir M. Rajpoot, Fayyaz Minhas, Shan E Ahmed Raza
Abstract: Whole slide image (WSI) registration is an essential task for analysing the tumour microenvironment (TME) in histopathology. It involves the alignment of spatial information between WSIs of the same section or serial sections of a tissue sample. The tissue sections are usually stained with single or multiple biomarkers before imaging, and the goal is to identify neighbouring nuclei along the Z-axis for creating a 3D image or identifying subclasses of cells in the TME. This task is considerably more challenging compared to radiology image registration, such as magnetic resonance imaging or computed tomography, due to various factors. These include gigapixel size of images, variations in appearance between differently stained tissues, changes in structure and morphology between non-consecutive sections, and the presence of artefacts, tears, and deformations. Currently, there is a noticeable gap in the literature regarding a review of the current approaches and their limitations, as well as the challenges and opportunities they present. We aim to provide a comprehensive understanding of the available approaches and their application for various purposes. Furthermore, we investigate current deep learning methods used for WSI registration, emphasising their diverse methodologies. We examine the available datasets and explore tools and software employed in the field. Finally, we identify open challenges and potential future trends in this area of research.
Authors: Yuhan Tang, Yudian Wang, Weizhen Li, Ye Yue, Chengchang Pan, Honggang Qi
Abstract: Fundus image quality is crucial for diagnosing eye diseases, but real-world conditions often result in blurred or unreadable images, increasing diagnostic uncertainty. To address these challenges, this study proposes RetinaRegen, a hybrid model for retinal image restoration that integrates a readability classifi-cation model, a Diffusion Model, and a Variational Autoencoder (VAE). Ex-periments on the SynFundus-1M dataset show that the proposed method achieves a PSNR of 27.4521, an SSIM of 0.9556, and an LPIPS of 0.1911 for the readability labels of the optic disc (RO) region. These results demonstrate superior performance in restoring key regions, offering an effective solution to enhance fundus image quality and support clinical diagnosis.
Authors: Jiatao Jiang, Zhen Cui, Chunyan Xu, Jian Yang
Abstract: In recent years, deep learning has achieved remarkable success in the field of image restoration. However, most convolutional neural network-based methods typically focus on a single scale, neglecting the incorporation of multi-scale information. In image restoration tasks, local features of an image are often insufficient, necessitating the integration of global features to complement them. Although recent neural network algorithms have made significant strides in feature extraction, many models do not explicitly model global features or consider the relationship between global and local features. This paper proposes multi-level attention-guided graph neural network. The proposed network explicitly constructs element block graphs and element graphs within feature maps using multi-attention mechanisms to extract both local structural features and global representation information of the image. Since the network struggles to effectively extract global information during image degradation, the structural information of local feature blocks can be used to correct and supplement the global information. Similarly, when element block information in the feature map is missing, it can be refined using global element representation information. The graph within the network learns real-time dynamic connections through the multi-attention mechanism, and information is propagated and aggregated via graph convolution algorithms. By combining local element block information and global element representation information from the feature map, the algorithm can more effectively restore missing information in the image. Experimental results on several classic image restoration tasks demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance.
Authors: Minjie Zhu, Yichen Zhu, Jinming Li, Zhongyi Zhou, Junjie Wen, Xiaoyu Liu, Chaomin Shen, Yaxin Peng, Feifei Feng
Abstract: Imitation learning has proven to be highly effective in teaching robots dexterous manipulation skills. However, it typically relies on large amounts of human demonstration data, which limits its scalability and applicability in dynamic, real-world environments. One key challenge in this context is object generalization, where a robot trained to perform a task with one object, such as "hand over the apple," struggles to transfer its skills to a semantically similar but visually different object, such as "hand over the peach." This gap in generalization to new objects beyond those in the same category has yet to be adequately addressed in previous work on end-to-end visuomotor policy learning. In this paper, we present a simple yet effective approach for achieving object generalization through Vision-Language-Action (VLA) models, referred to as \textbf{ObjectVLA}. Our model enables robots to generalize learned skills to novel objects without requiring explicit human demonstrations for each new target object. By leveraging vision-language pair data, our method provides a lightweight and scalable way to inject knowledge about the target object, establishing an implicit link between the object and the desired action. We evaluate ObjectVLA on a real robotic platform, demonstrating its ability to generalize across 100 novel objects with a 64\% success rate in selecting objects not seen during training. Furthermore, we propose a more accessible method for enhancing object generalization in VLA models, using a smartphone to capture a few images and fine-tune the pre-trained model. These results highlight the effectiveness of our approach in enabling object-level generalization and reducing the need for extensive human demonstrations, paving the way for more flexible and scalable robotic learning systems.
Authors: Anyimadu Daniel Tweneboah, Suleiman Taofik Ahmed, Hossain Mohammad Imran
Abstract: Medical imaging spans diverse tasks and modalities which play a pivotal role in disease diagnosis, treatment planning, and monitoring. This study presents a novel exploration, being the first to systematically evaluate segmentation, registration, and classification tasks across multiple imaging modalities. Integrating both classical and deep learning (DL) approaches in addressing brain MRI tissue segmentation, lung CT image registration, and skin lesion classification from dermoscopic images, we demonstrate the complementary strengths of these methodologies in diverse applications. For brain tissue segmentation, 3D DL models outperformed 2D and patch-based models, specifically nnU-Net achieving Dice of 0.9397, with 3D U-Net models on ResNet34 backbone, offering competitive results with Dice 0.8946. Multi-Atlas methods provided robust alternatives for cases where DL methods are not feasible, achieving average Dice of 0.7267. In lung CT registration, classical Elastix-based methods outperformed DL models, achieving a minimum Target Registration Error (TRE) of 6.68 mm, highlighting the effectiveness of parameter tuning. HighResNet performed best among DL models with a TRE of 7.40 mm. For skin lesion classification, ensembles of DL models like InceptionResNetV2 and ResNet50 excelled, achieving up to 90.44%, and 93.62% accuracies for binary and multiclass classification respectively. Also, adopting One-vs-All method, DL attained accuracies of 94.64% (mel vs. others), 95.35% (bcc vs. others), and 96.93% (scc vs. others), while ML models specifically Multi-Layer Perceptron (MLP) on handcrafted features offered interpretable alternatives with 85.04% accuracy using SMOTE for class imbalance correction on the multi-class task and 83.27% on the binary-class task. Links to source code are available on request.
Authors: Adam Celarek, George Kopanas, George Drettakis, Michael Wimmer, Bernhard Kerbl
Abstract: Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray-marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in-depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.
Authors: Irit Chelly, Roy Uziel, Oren Freifeld, Ari Pakman
Abstract: Neural models for amortized probabilistic clustering yield samples of cluster labels given a set-structured input, while avoiding lengthy Markov chain runs and the need for explicit data likelihoods. Existing methods which label each data point sequentially, like the Neural Clustering Process, often lead to cluster assignments highly dependent on the data order. Alternatively, methods that sequentially create full clusters, do not provide assignment probabilities. In this paper, we introduce GFNCP, a novel framework for amortized clustering. GFNCP is formulated as a Generative Flow Network with a shared energy-based parametrization of policy and reward. We show that the flow matching conditions are equivalent to consistency of the clustering posterior under marginalization, which in turn implies order invariance. GFNCP also outperforms existing methods in clustering performance on both synthetic and real-world data.
Authors: Ademir G. Costa Junior, F\'abio S. da Silva, Ricardo Rios
Abstract: This paper presents a performance comparison among four Convolutional Neural Network architectures (EfficientNet-B3, InceptionV3, ResNet50, and VGG16) for classifying cassava disease images. The images were sourced from an imbalanced dataset from a competition. Appropriate metrics were employed to address class imbalance. The results indicate that EfficientNet-B3 achieved on this task accuracy of 87.7%, precision of 87.8%, revocation of 87.8% and F1-Score of 87.7%. These findings suggest that EfficientNet-B3 could be a valuable tool to support Digital Agriculture.
Authors: Minjoo Lim, Bogyeong Kang, Tae-Eui Kam
Abstract: Multi-modal magnetic resonance imaging (MRI) is essential for providing complementary information about brain anatomy and pathology, leading to more accurate diagnoses. However, obtaining high-quality multi-modal MRI in a clinical setting is difficult due to factors such as time constraints, high costs, and patient movement artifacts. To overcome this difficulty, there is increasing interest in developing generative models that can synthesize missing target modality images from the available source ones. Therefore, we design a generative model for missing MRI that integrates multi-modal contrastive learning with a focus on critical tumor regions. Specifically, we integrate multi-modal contrastive learning, tailored for multiple source modalities, and enhance its effectiveness by selecting features based on entropy during the contrastive learning process. Additionally, our network not only generates the missing target modality images but also predicts segmentation outputs, simultaneously. This approach improves the generator's capability to precisely generate tumor regions, ultimately improving performance in downstream segmentation tasks. By leveraging a combination of contrastive, segmentation, and additional self-representation losses, our model effectively reflects target-specific information and generate high-quality target images. Consequently, our results in the Brain MR Image Synthesis challenge demonstrate that the proposed model excelled in generating the missing modality.
Authors: Max Ku, Thomas Chong, Jonathan Leung, Krish Shah, Alvin Yu, Wenhu Chen
Abstract: Understanding domain-specific theorems often requires more than just text-based reasoning; effective communication through structured visual explanations is crucial for deeper comprehension. While large language models (LLMs) demonstrate strong performance in text-based theorem reasoning, their ability to generate coherent and pedagogically meaningful visual explanations remains an open challenge. In this work, we introduce TheoremExplainAgent, an agentic approach for generating long-form theorem explanation videos (over 5 minutes) using Manim animations. To systematically evaluate multimodal theorem explanations, we propose TheoremExplainBench, a benchmark covering 240 theorems across multiple STEM disciplines, along with 5 automated evaluation metrics. Our results reveal that agentic planning is essential for generating detailed long-form videos, and the o3-mini agent achieves a success rate of 93.8% and an overall score of 0.77. However, our quantitative and qualitative studies show that most of the videos produced exhibit minor issues with visual element layout. Furthermore, multimodal explanations expose deeper reasoning flaws that text-based explanations fail to reveal, highlighting the importance of multimodal explanations.
Authors: Alzayat Saleh, Marcus Sheaves, Dean Jerry, Mostafa Rahimi Azghadi
Abstract: Accurate fish segmentation in underwater videos is challenging due to low visibility, variable lighting, and dynamic backgrounds, making fully-supervised methods that require manual annotation impractical for many applications. This paper introduces a novel self-supervised learning approach for fish segmentation using Deep Learning. Our model, trained without manual annotation, learns robust and generalizable representations by aligning features across augmented views and enforcing spatial-temporal consistency. We demonstrate its effectiveness on three challenging underwater video datasets: DeepFish, Seagrass, and YouTube-VOS, surpassing existing self-supervised methods and achieving segmentation accuracy comparable to fully-supervised methods without the need for costly annotations. Trained on DeepFish, our model exhibits strong generalization, achieving high segmentation accuracy on the unseen Seagrass and YouTube-VOS datasets. Furthermore, our model is computationally efficient due to its parallel processing and efficient anchor sampling technique, making it suitable for real-time applications and potential deployment on edge devices. We present quantitative results using Jaccard Index and Dice coefficient, as well as qualitative comparisons, showcasing the accuracy, robustness, and efficiency of our approach for advancing underwater video analysis
Authors: Alzayat Saleh, Marcus Sheaves, Dean Jerry, Mostafa Rahimi Azghadi
Abstract: Tracking fish movements and sizes of fish is crucial to understanding their ecology and behaviour. Knowing where fish migrate, how they interact with their environment, and how their size affects their behaviour can help ecologists develop more effective conservation and management strategies to protect fish populations and their habitats. Deep learning is a promising tool to analyze fish ecology from underwater videos. However, training deep neural networks (DNNs) for fish tracking and segmentation requires high-quality labels, which are expensive to obtain. We propose an alternative unsupervised approach that relies on spatial and temporal variations in video data to generate noisy pseudo-ground-truth labels. We train a multitask DNN using these pseudo-labels. Our framework consists of three stages: (1) an optical flow model generates the pseudo labels using spatial and temporal consistency between frames, (2) a self-supervised model refines the pseudo-labels incrementally, and (3) a segmentation network uses the refined labels for training. Consequently, we perform extensive experiments to validate our method on three public underwater video datasets and demonstrate its effectiveness for video annotation and segmentation. We also evaluate its robustness to different imaging conditions and discuss its limitations.
Authors: Romain Thoreau, Laurent Risser, V\'eronique Achard, B\'eatrice Berthelot, Xavier Briottet
Abstract: The combination of machine learning models with physical models is a recent research path to learn robust data representations. In this paper, we introduce p$^3$VAE, a variational autoencoder that integrates prior physical knowledge about the latent factors of variation that are related to the data acquisition conditions. p$^3$VAE combines standard neural network layers with non-trainable physics layers in order to partially ground the latent space to physical variables. We introduce a semi-supervised learning algorithm that strikes a balance between the machine learning part and the physics part. Experiments on simulated and real data sets demonstrate the benefits of our framework against competing physics-informed and conventional machine learning models, in terms of extrapolation capabilities and interpretability. In particular, we show that p$^3$VAE naturally has interesting disentanglement capabilities. Our code and data have been made publicly available at https://github.com/Romain3Ch216/p3VAE.
Authors: Ayush Kumar Shah, Bryan Manrique Amador, Abhisek Dey, Ming Creekmore, Blake Ocampo, Scott Denmark, Richard Zanibbi
Abstract: Most molecular diagram parsers recover chemical structure from raster images (e.g., PNGs). However, many PDFs include commands giving explicit locations and shapes for characters, lines, and polygons. We present a new parser that uses these born-digital PDF primitives as input. The parsing model is fast and accurate, and does not require GPUs, Optical Character Recognition (OCR), or vectorization. We use the parser to annotate raster images and then train a new multi-task neural network for recognizing molecules in raster images. We evaluate our parsers using SMILES and standard benchmarks, along with a novel evaluation protocol comparing molecular graphs directly that supports automatic error compilation and reveals errors missed by SMILES-based evaluation. On the synthetic USPTO benchmark, our born-digital parser obtains a recognition rate of 98.4% (1% higher than previous models) and our relatively simple neural parser for raster images obtains a rate of 85% using less training data than existing neural approaches (thousands vs. millions of molecules).
Authors: Wei Chen, Zichen Miao, Qiang Qiu
Abstract: Efficient fine-tuning methods are critical to address the high computational and parameter complexity while adapting large pre-trained models to downstream tasks. Our study is inspired by prior research that represents each convolution filter as a linear combination of a small set of filter subspace elements, referred to as filter atoms. In this paper, we propose to fine-tune pre-trained models by adjusting only filter atoms, which are responsible for spatial-only convolution, while preserving spatially-invariant channel combination knowledge in atom coefficients. In this way, we bring a new filter subspace view for model tuning. Furthermore, each filter atom can be recursively decomposed as a combination of another set of atoms, which naturally expands the number of tunable parameters in the filter subspace. By only adapting filter atoms constructed by a small number of parameters, while maintaining the rest of model parameters constant, the proposed approach is highly parameter-efficient. It effectively preserves the capabilities of pre-trained models and prevents overfitting to downstream tasks. Extensive experiments show that such a simple scheme surpasses previous tuning baselines for both discriminate and generative tasks.
Authors: Geonho Bang, Kwangjin Choi, Jisong Kim, Dongsuk Kum, Jun Won Choi
Abstract: The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve the representation of radar data by leveraging LiDAR data. RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components: Cross-Modality Alignment (CMA), Activation-based Feature Distillation (AFD), and Proposal-based Feature Distillation (PFD). CMA enhances the density of radar features by employing multiple layers of dilation operations, effectively addressing the challenge of inefficient knowledge transfer from LiDAR to radar. AFD selectively transfers knowledge based on regions of the LiDAR features, with a specific focus on areas where activation intensity exceeds a predefined threshold. PFD similarly guides the radar network to selectively mimic features from the LiDAR network within the object proposals. Our comparative analyses conducted on the nuScenes datasets demonstrate that RadarDistill achieves state-of-the-art (SOTA) performance for radar-only object detection task, recording 20.5% in mAP and 43.7% in NDS. Also, RadarDistill significantly improves the performance of the camera-radar fusion model.
Authors: Haozhi Cao, Yuecong Xu, Pengyu Yin, Xingyu Ji, Shenghai Yuan, Jianfei Yang, Lihua Xie
Abstract: Multi-modal test-time adaptation (MM-TTA) is proposed to adapt models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. Previous MM-TTA methods for 3D segmentation rely on predictions of cross-modal information in each input frame, while they ignore the fact that predictions of geometric neighborhoods within consecutive frames are highly correlated, leading to unstable predictions across time. To fulfill this gap, we propose ReLiable Spatial-temporal Voxels (Latte), an MM-TTA method that leverages reliable cross-modal spatial-temporal correspondences for multi-modal 3D segmentation. Motivated by the fact that reliable predictions should be consistent with their spatial-temporal correspondences, Latte aggregates consecutive frames in a sliding-window manner and constructs Spatial-Temporal (ST) voxels to capture temporally local prediction consistency for each modality. After filtering out ST voxels with high ST entropy, Latte conducts cross-modal learning for each point and pixel by attending to those with reliable and consistent predictions among both spatial and temporal neighborhoods. Considering the prediction consistency might vary under different sliding windows, we further propose Latte++ which leverages ST voxels generated under various sliding windows to more thoroughly evaluate intra-modal prediction consistency before the cross-modal fusion. Experimental results show that both Latte and Latte++ achieve state-of-the-art performance on five MM-TTA benchmarks compared to previous MM-TTA or TTA methods. Code will be available at https://github.com/AronCao49/Latte-plusplus.
Authors: Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Shuaiqi Wang, Matthew B. Blaschko, Sergey Yekhanin, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
Abstract: Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate weight checkpoints are not fully utilized and only the last converged checkpoint is used. In this work, we find that high-quality model weights often lie in a basin which cannot be reached by SGD but can be obtained by proper checkpoint averaging. Based on these observations, we propose LCSC, a simple but effective and efficient method to enhance the performance of DM and CM, by combining checkpoints along the training trajectory with coefficients deduced from evolutionary search. We demonstrate the value of LCSC through two use cases: $\textbf{(a) Reducing training cost.}$ With LCSC, we only need to train DM/CM with fewer number of iterations and/or lower batch sizes to obtain comparable sample quality with the fully trained model. For example, LCSC achieves considerable training speedups for CM (23$\times$ on CIFAR-10 and 15$\times$ on ImageNet-64). $\textbf{(b) Enhancing pre-trained models.}$ Assuming full training is already done, LCSC can further improve the generation quality or speed of the final converged models. For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10. Our code is available at https://github.com/imagination-research/LCSC.
Authors: Haozhe Liu, Wentian Zhang, Jinheng Xie, Francesco Faccio, Mengmeng Xu, Tao Xiang, Mike Zheng Shou, Juan-Manuel Perez-Rua, J\"urgen Schmidhuber
Abstract: We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed point after several inference steps. The convergence time naturally divides the entire inference process into two phases: an initial phase for planning text-oriented visual semantics, which are then translated into images in a subsequent fidelity-improving phase. Cross-attention is essential in the initial phase but almost irrelevant thereafter. However, self-attention initially plays a minor role but becomes crucial in the second phase. These findings yield a simple and training-free method known as temporally gating the attention (TGATE), which efficiently generates images by caching and reusing attention outputs at scheduled time steps. Experimental results show when widely applied to various existing text-conditional diffusion models, TGATE accelerates these models by 10%-50%. The code of TGATE is available at https://github.com/HaozheLiu-ST/T-GATE.
Authors: Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang
Abstract: Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels). While Continuous Conditional Generative Adversarial Networks (CcGANs) were designed for this task, their instability during adversarial learning often leads to suboptimal results. Conditional Diffusion Models (CDMs) offer a promising alternative, generating more realistic images, but their diffusion processes, label conditioning, and model fitting procedures are either not optimized for or incompatible with CCGM, making it difficult to integrate CcGANs' vicinal approach. To address these issues, we introduce Continuous Conditional Diffusion Models (CCDMs), the first CDM specifically tailored for CCGM. CCDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, a customized label embedding method, and efficient conditional sampling procedures. Through comprehensive experiments on four datasets with resolutions ranging from 64x64 to 192x192, we demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark. Ablation studies further validate the model design and implementation, highlighting that some widely used CDM implementations are ineffective for the CCGM task. Our code is publicly available at https://github.com/UBCDingXin/CCDM.
Authors: Shengqiong Wu, Hao Fei, Xiangtai Li, Jiayi Ji, Hanwang Zhang, Tat-Seng Chua, Shuicheng Yan
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into feature representations that are most beneficial for LLMs. However, existing vision tokenizers, essential for semantic alignment between vision and language, remain problematic. Existing methods aggressively fragment visual input, corrupting the visual semantic integrity. To address this, this paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok), which groups visual features into semantic units via a dynamic clustering algorithm, flexibly determining the number of tokens based on image complexity. The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features. The proposed MLLM (Setokim) equipped with SeTok significantly demonstrates superior performance across various tasks, as evidenced by our experimental results. The project page is at https://chocowu.github.io/SeTok-web/.
Authors: Xianda Guo, Chenming Zhang, Youmin Zhang, Wenzhao Zheng, Dujun Nie, Matteo Poggi, Long Chen
Abstract: We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process. Departing from conventional methodologies that rely on aggregating computationally intensive 4D costs, LightStereo adopts the 3D cost volume as a lightweight alternative. While similar approaches have been explored previously, our breakthrough lies in enhancing performance through a dedicated focus on the channel dimension of the 3D cost volume, where the distribution of matching costs is encapsulated. Our exhaustive exploration has yielded plenty of strategies to amplify the capacity of the pivotal dimension, ensuring both precision and efficiency. We compare the proposed LightStereo with existing state-of-the-art methods across various benchmarks, which demonstrate its superior performance in speed, accuracy, and resource utilization. LightStereo achieves a competitive EPE metric in the SceneFlow datasets while demanding a minimum of only 22 GFLOPs and 17 ms of runtime, and ranks 1st on KITTI 2015 among real-time models. Our comprehensive analysis reveals the effect of 2D cost aggregation for stereo matching, paving the way for real-world applications of efficient stereo systems. Code will be available at https://github.com/XiandaGuo/OpenStereo.
Authors: Yang Liu, Zhiyong Zhang
Abstract: The current methods of video-based 3D human pose estimation have achieved significant progress.However, they still face pressing challenges, such as the underutilization of spatiotemporal bodystructure features in transformers and the inadequate granularity of spatiotemporal interaction modeling in graph convolutional networks, which leads to pervasive depth ambiguity in monocular 3D human pose estimation. To address these limitations, this paper presents the Spatio-Temporal GraphFormer framework (STGFormer) for 3D human pose estimation in videos. First, we introduce a Spatio-Temporal criss-cross Graph (STG) attention mechanism, designed to more effectively leverage the inherent graph priors of the human body within continuous sequence distributions while capturing spatiotemporal long-range dependencies. Next, we present a dual-path Modulated Hop-wise Regular GCN (MHR-GCN) to independently process temporal and spatial dimensions in parallel, preserving features rich in temporal dynamics and the original or high-dimensional representations of spatial structures. Furthermore, the module leverages modulation to optimize parameter efficiency and incorporates spatiotemporal hop-wise skip connections to capture higher-order information. Finally, we demonstrate that our method achieves state-of-the-art performance on the Human3.6M and MPIINF-3DHP datasets.
Authors: Thomas De Min, Massimiliano Mancini, St\'ephane Lathuili\`ere, Subhankar Roy, Elisa Ricci
Abstract: Machine unlearning aims to erase data from a model as if the latter never saw them during training. While existing approaches unlearn information from complete or partial access to the training data, this access can be limited over time due to privacy regulations. Currently, no setting or benchmark exists to probe the effectiveness of unlearning methods in such scenarios. To fill this gap, we propose a novel task we call One-Shot Unlearning of Personal Identities (1-SHUI) that evaluates unlearning models when the training data is not available. We focus on unlearning identity data, which is specifically relevant due to current regulations requiring personal data deletion after training. To cope with data absence, we expect users to provide a portraiting picture to aid unlearning. We design requests on CelebA, CelebA-HQ, and MUFAC with different unlearning set sizes to evaluate applicable methods in 1-SHUI. Moreover, we propose MetaUnlearn, an effective method that meta-learns to forget identities from a single image. Our findings indicate that existing approaches struggle when data availability is limited, especially when there is a dissimilarity between the provided samples and the training data. Source code available at https://github.com/tdemin16/one-shui.
Authors: Hanjun Luo, Haoyu Huang, Ziye Deng, Xinfeng Li, Hewei Wang, Yingbin Jin, Yang Liu, XiaoFeng Wang, Wenyuan Xu, Zuozhu Liu
Abstract: Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particularly in human image generation. Sociological research has established systematic classifications of bias. Yet, existing studies on bias in T2I models largely conflate different types of bias, impeding methodological progress. In this paper, we introduce BIGbench, a unified benchmark for Biases of Image Generation, featuring a carefully designed dataset. Unlike existing benchmarks, BIGbench classifies and evaluates biases across four dimensions to enable a more granular evaluation and deeper analysis. Furthermore, BIGbench applies advanced multi-modal large language models to achieve fully automated and highly accurate evaluations. We apply BIGbench to evaluate eight representative T2I models and three debiasing methods. Our human evaluation results by trained evaluators from different races underscore BIGbench's effectiveness in aligning images and identifying various biases. Moreover, our study also reveals new research directions about biases with insightful analysis of our results. Our work is openly accessible at https://github.com/BIGbench2024/BIGbench2024/.
Authors: Xinyi Zhang, Qiqi Bao, Qinpeng Cui, Wenming Yang, Qingmin Liao
Abstract: Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve the above dilemma, in this work, we leverage recent advances in state space models and utilize Mamba for high-quality and efficient long-range modeling. Nonetheless, Mamba still faces challenges in precisely exploiting local dependencies between joints. To address these issues, we propose a new attention-free hybrid spatiotemporal architecture named Hybrid Mamba-GCN (Pose Magic). This architecture introduces local enhancement with GCN by capturing relationships between neighboring joints, thus producing new representations to complement Mamba's outputs. By adaptively fusing representations from Mamba and GCN, Pose Magic demonstrates superior capability in learning the underlying 3D structure. To meet the requirements of real-time inference, we also provide a fully causal version. Extensive experiments show that Pose Magic achieves new SOTA results ($\downarrow 0.9 mm$) while saving $74.1\%$ FLOPs. In addition, Pose Magic exhibits optimal motion consistency and the ability to generalize to unseen sequence lengths.
Authors: Fanhu Zeng, Zhen Cheng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang
Abstract: Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories, has gained prominence in practical scenarios. Recently, the advent of vision-language models (VLM) has heightened interest in enhancing OOD detection for VLM through few-shot tuning. However, existing methods mainly focus on optimizing global prompts, ignoring refined utilization of local information with regard to outliers. Motivated by this, we freeze global prompts and introduce Local-Prompt, a novel coarse-to-fine tuning paradigm to emphasize regional enhancement with local prompts. Our method comprises two integral components: global prompt guided negative augmentation and local prompt enhanced regional regularization. The former utilizes frozen, coarse global prompts as guiding cues to incorporate negative augmentation, thereby leveraging local outlier knowledge. The latter employs trainable local prompts and a regional regularization to capture local information effectively, aiding in outlier identification. We also propose regional-related metric to empower the enrichment of OOD detection. Moreover, since our approach explores enhancing local prompts only, it can be seamlessly integrated with trained global prompts during inference to boost the performance. Comprehensive experiments demonstrate the effectiveness and potential of our method. Notably, our method reduces average FPR95 by 5.17% against state-of-the-art method in 4-shot tuning on challenging ImageNet-1k dataset, even outperforming 16-shot results of previous methods. Code is released at https://github.com/AuroraZengfh/Local-Prompt.
Authors: Yi-Chia Chang, Adam J. Stewart, Favyen Bastani, Piper Wolters, Shreya Kannan, George R. Huber, Jingtong Wang, Arindam Banerjee
Abstract: Foundation models pre-trained using self-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. The Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed nations not transferring well to data-scarce developing nations -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select five crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, while only 100 labeled images are sufficient for achieving high overall accuracy, 900 images are required to achieve high average accuracy due to class imbalance. All harmonized datasets and experimental code are open-source and available for download.
Authors: Minghan Chen, Guikun Chen, Wenguan Wang, Yi Yang
Abstract: DETR introduces a simplified one-stage framework for scene graph generation (SGG) but faces challenges of sparse supervision and false negative samples. The former occurs because each image typically contains fewer than 10 relation annotations, while DETR-based SGG models employ over 100 relation queries. Each ground truth relation is assigned to only one query during training. The latter arises when one ground truth relation may have multiple queries with similar matching scores, leading to suboptimally matched queries being treated as negative samples. To address these, we propose Hydra-SGG, a one-stage SGG method featuring a Hybrid Relation Assignment. This approach combines a One-to-One Relation Assignment with an IoU-based One-to-Many Relation Assignment, increasing positive training samples and mitigating sparse supervision. In addition, we empirically demonstrate that removing self-attention between relation queries leads to duplicate predictions, which actually benefits the proposed One-to-Many Relation Assignment. With this insight, we introduce Hydra Branch, an auxiliary decoder without self-attention layers, to further enhance One-to-Many Relation Assignment by promoting different queries to make the same relation prediction. Hydra-SGG achieves state-of-the-art performance on multiple datasets, including VG150 (16.0 mR@50), Open Images V6 (50.1 weighted score), and GQA (12.7 mR@50).
Authors: Victor Rong, Jingxiang Chen, Sherwin Bahmani, Kiriakos N. Kutulakos, David B. Lindell
Abstract: Gaussian splatting has demonstrated excellent performance for view synthesis and scene reconstruction. The representation achieves photorealistic quality by optimizing the position, scale, color, and opacity of thousands to millions of 2D or 3D Gaussian primitives within a scene. However, since each Gaussian primitive encodes both appearance and geometry, these attributes are strongly coupled--thus, high-fidelity appearance modeling requires a large number of Gaussian primitives, even when the scene geometry is simple (e.g., for a textured planar surface). We propose to texture each 2D Gaussian primitive so that even a single Gaussian can be used to capture appearance details. By employing per-primitive texturing, our appearance representation is agnostic to the topology and complexity of the scene's geometry. We show that our approach, GStex, yields improved visual quality over prior work in texturing Gaussian splats. Furthermore, we demonstrate that our decoupling enables improved novel view synthesis performance compared to 2D Gaussian splatting when reducing the number of Gaussian primitives, and that GStex can be used for scene appearance editing and re-texturing.
Authors: Weifeng Lin, Xinyu Wei, Renrui Zhang, Le Zhuo, Shitian Zhao, Siyuan Huang, Junlin Xie, Huan Teng, Junlin Xie, Yu Qiao, Peng Gao, Hongsheng Li
Abstract: This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable generation, inpainting/outpainting, and more. Furthermore, we adopt Diffusion Transformers (DiT) as our foundation model and extend its capabilities with a flexible any resolution mechanism, enabling the model to dynamically process images based on the aspect ratio of the input, closely aligning with human perceptual processes. The model also incorporates structure-aware and semantic-aware guidance to facilitate effective fusion of information from the input image. Our experiments demonstrate that PixWizard not only shows impressive generative and understanding abilities for images with diverse resolutions but also exhibits promising generalization capabilities with unseen tasks and human instructions. The code and related resources are available at https://github.com/AFeng-x/PixWizard
Authors: Pang-Yuan Pao, Shu-Wei Lu, Ze-Yan Lu, Yi-Ting Chen
Abstract: We study behavior change-based visual risk object identification (Visual-ROI), a critical framework designed to detect potential hazards for intelligent driving systems. Existing methods often show significant limitations in spatial accuracy and temporal consistency, stemming from an incomplete understanding of scene affordance. For example, these methods frequently misidentify vehicles that do not impact the ego vehicle as risk objects. Furthermore, existing behavior change-based methods are inefficient because they implement causal inference in the perspective image space. We propose a new framework with a Bird's Eye View (BEV) representation to overcome the above challenges. Specifically, we utilize potential fields as scene affordance, involving repulsive forces derived from road infrastructure and traffic participants, along with attractive forces sourced from target destinations. In this work, we compute potential fields by assigning different energy levels according to the semantic labels obtained from BEV semantic segmentation. We conduct thorough experiments and ablation studies, comparing the proposed method with various state-of-the-art algorithms on both synthetic and real-world datasets. Our results show a notable increase in spatial and temporal consistency, with enhancements of 20.3% and 11.6% on the RiskBench dataset, respectively. Additionally, we can improve computational efficiency by 88%. We achieve improvements of 5.4% in spatial accuracy and 7.2% in temporal consistency on the nuScenes dataset.
Authors: Fulong Ma, Peng Hou, Yuxuan Liu, Yang Liu, Ming Liu, Jun Ma
Abstract: Road curbs are considered as one of the crucial and ubiquitous traffic features, which are essential for ensuring the safety of autonomous vehicles. Current methods for detecting curbs primarily rely on camera imagery or LiDAR point clouds. Image-based methods are vulnerable to fluctuations in lighting conditions and exhibit poor robustness, while methods based on point clouds circumvent the issues associated with lighting variations. However, it is the typical case that significant processing delays are encountered due to the voluminous amount of 3D points contained in each frame of the point cloud data. Furthermore, the inherently unstructured characteristics of point clouds poses challenges for integrating the latest deep learning advancements into point cloud data applications. To address these issues, this work proposes an annotation-free curb detection method leveraging Altitude Difference Image (ADI), which effectively mitigates the aforementioned challenges. Given that methods based on deep learning generally demand extensive, manually annotated datasets, which are both expensive and labor-intensive to create, we present an Automatic Curb Annotator (ACA) module. This module utilizes a deterministic curb detection algorithm to automatically generate a vast quantity of training data. Consequently, it facilitates the training of the curb detection model without necessitating any manual annotation of data. Finally, by incorporating a post-processing module, we manage to achieve state-of-the-art results on the KITTI 3D curb dataset with considerably reduced processing delays compared to existing methods, which underscores the effectiveness of our approach in curb detection tasks.
Authors: James Baker
Abstract: In this work, we explore using the style ambiguity training objective, originally used to approximate creativity, on a diffusion model. However, this objective requires the use of a pretrained classifier and a labeled dataset. We introduce new forms of style ambiguity loss that do not require training a classifier or a labeled dataset, and show that our new methods score higher both on automated metrics and user studies to analyze novelty and appreciation. Code available at https://github.com/jamesBaker361/clipcreate
Authors: Ziqi Jiang, Zhen Wang, Long Chen
Abstract: Precise and flexible image editing remains a fundamental challenge in computer vision. Based on the modified areas, most editing methods can be divided into two main types: global editing and local editing. In this paper, we choose the two most common editing approaches (ie text-based editing and drag-based editing) and analyze their drawbacks. Specifically, text-based methods often fail to describe the desired modifications precisely, while drag-based methods suffer from ambiguity. To address these issues, we proposed \textbf{CLIPDrag}, a novel image editing method that is the first to combine text and drag signals for precise and ambiguity-free manipulations on diffusion models. To fully leverage these two signals, we treat text signals as global guidance and drag points as local information. Then we introduce a novel global-local motion supervision method to integrate text signals into existing drag-based methods by adapting a pre-trained language-vision model like CLIP. Furthermore, we also address the problem of slow convergence in CLIPDrag by presenting a fast point-tracking method that enforces drag points moving toward correct directions. Extensive experiments demonstrate that CLIPDrag outperforms existing single drag-based methods or text-based methods.
Authors: Yichu Xu, Di Wang, Lefei Zhang, Liangpei Zhang
Abstract: Transformer has achieved satisfactory results in the field of hyperspectral image (HSI) classification. However, existing Transformer models face two key challenges when dealing with HSI scenes characterized by diverse land cover types and rich spectral information: (1) A fixed receptive field overlooks the effective contextual scales required by various HSI objects; (2) invalid self-attention features in context fusion affect model performance. To address these limitations, we propose a novel Dual Selective Fusion Transformer Network (DSFormer) for HSI classification. DSFormer achieves joint spatial and spectral contextual modeling by flexibly selecting and fusing features across different receptive fields, effectively reducing unnecessary information interference by focusing on the most relevant spatial-spectral tokens. Specifically, we design a Kernel Selective Fusion Transformer Block (KSFTB) to learn an optimal receptive field by adaptively fusing spatial and spectral features across different scales, enhancing the model's ability to accurately identify diverse HSI objects. Additionally, we introduce a Token Selective Fusion Transformer Block (TSFTB), which strategically selects and combines essential tokens during the spatial-spectral self-attention fusion process to capture the most crucial contexts. Extensive experiments conducted on four benchmark HSI datasets demonstrate that the proposed DSFormer significantly improves land cover classification accuracy, outperforming existing state-of-the-art methods. Specifically, DSFormer achieves overall accuracies of 96.59%, 97.66%, 95.17%, and 94.59% in the Pavia University, Houston, Indian Pines, and Whu-HongHu datasets, respectively, reflecting improvements of 3.19%, 1.14%, 0.91%, and 2.80% over the previous model. The code will be available online at https://github.com/YichuXu/DSFormer.
Authors: Anirudh Sundara Rajan, Utkarsh Ojha, Jedidiah Schloesser, Yong Jae Lee
Abstract: As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic content, resolution, file format, etc. Fake image detectors are usually built in a data driven way, where a model is trained to separate real from fake images. Existing works primarily investigate network architecture choices and training recipes. In this work, we argue that in addition to these algorithmic choices, we also require a well aligned dataset of real/fake images to train a robust detector. For the family of LDMs, we propose a very simple way to achieve this: we reconstruct all the real images using the LDMs autoencoder, without any denoising operation. We then train a model to separate these real images from their reconstructions. The fakes created this way are extremely similar to the real ones in almost every aspect (e.g., size, aspect ratio, semantic content), which forces the model to look for the LDM decoders artifacts. We empirically show that this way of creating aligned real/fake datasets, which also sidesteps the computationally expensive denoising process, helps in building a detector that focuses less on spurious correlations, something that a very popular existing method is susceptible to. Finally, to demonstrate just how effective the alignment in a dataset can be, we build a detector using images that are not natural objects, and present promising results. Overall, our work identifies the subtle but significant issues that arise when training a fake image detector and proposes a simple and inexpensive solution to address these problems.
Authors: Adam Polyak, Amit Zohar, Andrew Brown, Andros Tjandra, Animesh Sinha, Ann Lee, Apoorv Vyas, Bowen Shi, Chih-Yao Ma, Ching-Yao Chuang, David Yan, Dhruv Choudhary, Dingkang Wang, Geet Sethi, Guan Pang, Haoyu Ma, Ishan Misra, Ji Hou, Jialiang Wang, Kiran Jagadeesh, Kunpeng Li, Luxin Zhang, Mannat Singh, Mary Williamson, Matt Le, Matthew Yu, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Quentin Duval, Rohit Girdhar, Roshan Sumbaly, Sai Saketh Rambhatla, Sam Tsai, Samaneh Azadi, Samyak Datta, Sanyuan Chen, Sean Bell, Sharadh Ramaswamy, Shelly Sheynin, Siddharth Bhattacharya, Simran Motwani, Tao Xu, Tianhe Li, Tingbo Hou, Wei-Ning Hsu, Xi Yin, Xiaoliang Dai, Yaniv Taigman, Yaqiao Luo, Yen-Cheng Liu, Yi-Chiao Wu, Yue Zhao, Yuval Kirstain, Zecheng He, Zijian He, Albert Pumarola, Ali Thabet, Artsiom Sanakoyeu, Arun Mallya, Baishan Guo, Boris Araya, Breena Kerr, Carleigh Wood, Ce Liu, Cen Peng, Dimitry Vengertsev, Edgar Schonfeld, Elliot Blanchard, Felix Juefei-Xu, Fraylie Nord, Jeff Liang, John Hoffman, Jonas Kohler, Kaolin Fire, Karthik Sivakumar, Lawrence Chen, Licheng Yu, Luya Gao, Markos Georgopoulos, Rashel Moritz, Sara K. Sampson, Shikai Li, Simone Parmeggiani, Steve Fine, Tara Fowler, Vladan Petrovic, Yuming Du
Abstract: We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.
Authors: Chaodong Xiao, Minghan Li, Zhengqiang Zhang, Deyu Meng, Lei Zhang
Abstract: Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D sequences and employ various scanning patterns to incorporate local spatial dependencies. However, these methods are limited in effectively capturing the complex image spatial structures and the increased computational cost caused by the lengthened scanning paths. To address these limitations, we propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space. Instead of relying solely on sequential state transitions, we introduce a structure-aware state fusion equation, which leverages dilated convolutions to capture image spatial structural dependencies, significantly enhancing the flow of visual contextual information. Spatial-Mamba proceeds in three stages: initial state computation in a unidirectional scan, spatial context acquisition through structure-aware state fusion, and final state computation using the observation equation. Our theoretical analysis shows that Spatial-Mamba unifies the original Mamba and linear attention under the same matrix multiplication framework, providing a deeper understanding of our method. Experimental results demonstrate that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation. Source codes and trained models can be found at https://github.com/EdwardChasel/Spatial-Mamba.
Authors: Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Min Wu, Ming-Ming Cheng, Ender Konukoglu, Serge Belongie
Abstract: Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
URLs: https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
Authors: Nidhal Jegham, Chan Young Koh, Marwan Abdelatti, Abdeltawab Hendawi
Abstract: This study presents a comprehensive benchmark analysis of various YOLO (You Only Look Once) algorithms. It represents the first comprehensive experimental evaluation of YOLOv3 to the latest version, YOLOv12, on various object detection challenges. The challenges considered include varying object sizes, diverse aspect ratios, and small-sized objects of a single class, ensuring a comprehensive assessment across datasets with distinct challenges. To ensure a robust evaluation, we employ a comprehensive set of metrics, including Precision, Recall, Mean Average Precision (mAP), Processing Time, GFLOPs count, and Model Size. Our analysis highlights the distinctive strengths and limitations of each YOLO version. For example: YOLOv9 demonstrates substantial accuracy but struggles with detecting small objects and efficiency whereas YOLOv10 exhibits relatively lower accuracy due to architectural choices that affect its performance in overlapping object detection but excels in speed and efficiency. Additionally, the YOLO11 family consistently shows superior performance maintaining a remarkable balance of accuracy and efficiency. However, YOLOv12 delivered underwhelming results, with its complex architecture introducing computational overhead without significant performance gains. These results provide critical insights for both industry and academia, facilitating the selection of the most suitable YOLO algorithm for diverse applications and guiding future enhancements.
Authors: Anthony Etim, Jakub Szefer
Abstract: Adversarial input image perturbation attacks have emerged as a significant threat to machine learning algorithms, particularly in image classification setting. These attacks involve subtle perturbations to input images that cause neural networks to misclassify the input images, even though the images remain easily recognizable to humans. One critical area where adversarial attacks have been demonstrated is in automotive systems where traffic sign classification and recognition is critical, and where misclassified images can cause autonomous systems to take wrong actions. This work presents a new class of adversarial attacks. Unlike existing work that has focused on adversarial perturbations that leverage human-made artifacts to cause the perturbations, such as adding stickers, paint, or shining flashlights at traffic signs, this work leverages nature-made artifacts: tree leaves. By leveraging nature-made artifacts, the new class of attacks has plausible deniability: a fall leaf stuck to a street sign could come from a near-by tree, rather than be placed there by an malicious human attacker. To evaluate the new class of the adversarial input image perturbation attacks, this work analyses how fall leaves can cause misclassification in street signs. The work evaluates various leaves from different species of trees, and considers various parameters such as size, color due to tree leaf type, and rotation. The work demonstrates high success rate for misclassification. The work also explores the correlation between successful attacks and how they affect the edge detection, which is critical in many image classification algorithms.
Authors: Ruibo Ming, Jingwei Wu, Zhewei Huang, Zhuoxuan Ju, Jianming HU, Lihui Peng, Shuchang Zhou
Abstract: Recent advancements in auto-regressive large language models (LLMs) have led to their application in video generation. This paper explores the use of Large Vision Models (LVMs) for video continuation, a task essential for building world models and predicting future frames. We introduce ARCON, a scheme that alternates between generating semantic and RGB tokens, allowing the LVM to explicitly learn high-level structural video information. We find high consistency in the RGB images and semantic maps generated without special design. Moreover, we employ an optical flow-based texture stitching method to enhance visual quality. Experiments in autonomous driving scenarios show that our model can consistently generate long videos.
Authors: Deepank Singh, Vedhus Hoskere, Pietro Milillo
Abstract: Timely and accurate assessments of building damage are crucial for effective response and recovery in the aftermath of earthquakes. Conventional preliminary damage assessments (PDA) often rely on manual door-to-door inspections, which are not only time-consuming but also pose significant safety risks. To safely expedite the PDA process, researchers have studied the applicability of satellite imagery processed with heuristic and machine learning approaches. These approaches output binary or, more recently, multiclass damage states at the scale of a block or a single building. However, the current performance of such approaches limits practical applicability. To address this limitation, we introduce a metadata-enriched, transformer based framework that combines high-resolution post-earthquake satellite imagery with building-specific metadata relevant to the seismic performance of the structure. Our model achieves state-of-the-art performance in multiclass post-earthquake damage identification for buildings from the Turkey-Syria earthquake on February 6, 2023. Specifically, we demonstrate that incorporating metadata, such as seismic intensity indicators, soil properties, and SAR damage proxy maps not only enhances the model's accuracy and ability to distinguish between damage classes, but also improves its generalizability across various regions. Furthermore, we conducted a detailed, class-wise analysis of feature importance to understand the model's decision-making across different levels of building damage. This analysis reveals how individual metadata features uniquely contribute to predictions for each damage class. By leveraging both satellite imagery and metadata, our proposed framework enables faster and more accurate damage assessments for precise, multiclass, building-level evaluations that can improve disaster response and accelerate recovery efforts for affected communities.
Authors: Sepehr Dehdashtian, Gautam Sreekumar, Vishnu Naresh Boddeti
Abstract: Images generated by text-to-image (T2I) models often exhibit visual biases and stereotypes of concepts such as culture and profession. Existing quantitative measures of stereotypes are based on statistical parity that does not align with the sociological definition of stereotypes and, therefore, incorrectly categorizes biases as stereotypes. Instead of oversimplifying stereotypes as biases, we propose a quantitative measure of stereotypes that aligns with its sociological definition. We then propose OASIS to measure the stereotypes in a generated dataset and understand their origins within the T2I model. OASIS includes two scores to measure stereotypes from a generated image dataset: (M1) Stereotype Score to measure the distributional violation of stereotypical attributes, and (M2) WALS to measure spectral variance in the images along a stereotypical attribute. OASIS also includes two methods to understand the origins of stereotypes in T2I models: (U1) StOP to discover attributes that the T2I model internally associates with a given concept, and (U2) SPI to quantify the emergence of stereotypical attributes in the latent space of the T2I model during image generation. Despite the considerable progress in image fidelity, using OASIS, we conclude that newer T2I models such as FLUX.1 and SDv3 contain strong stereotypical predispositions about concepts and still generate images with widespread stereotypical attributes. Additionally, the quantity of stereotypes worsens for nationalities with lower Internet footprints.
Authors: Tianci Wen, Zhiang Liu, Biao Lu, Yongchun Fang
Abstract: 3D Gaussian Splatting (3DGS) has recently revolutionized novel view synthesis in the Simultaneous Localization and Mapping (SLAM). However, existing SLAM methods utilizing 3DGS have failed to provide high-quality novel view rendering for monocular, stereo, and RGB-D cameras simultaneously. Notably, some methods perform well for RGB-D cameras but suffer significant degradation in rendering quality for monocular cameras. In this paper, we present Scaffold-SLAM, which delivers simultaneous localization and high-quality photorealistic mapping across monocular, stereo, and RGB-D cameras. We introduce two key innovations to achieve this state-of-the-art visual quality. First, we propose Appearance-from-Motion embedding, enabling 3D Gaussians to better model image appearance variations across different camera poses. Second, we introduce a frequency regularization pyramid to guide the distribution of Gaussians, allowing the model to effectively capture finer details in the scene. Extensive experiments on monocular, stereo, and RGB-D datasets demonstrate that Scaffold-SLAM significantly outperforms state-of-the-art methods in photorealistic mapping quality, e.g., PSNR is 16.76% higher in the TUM RGB-D datasets for monocular cameras.
Authors: Aafaf Ridouan, Amine Bohi, Youssef Mourchid
Abstract: Pain management and severity detection are crucial for effective treatment, yet traditional self-reporting methods are subjective and may be unsuitable for non-verbal individuals (people with limited speaking skills). To address this limitation, we explore automated pain detection using facial expressions. Our study leverages deep learning techniques to improve pain assessment by analyzing facial images from the Pain Emotion Faces Database (PEMF). We propose two novel approaches1: (1) a hybrid ConvNeXt model combined with Long Short-Term Memory (LSTM) blocks to analyze video frames and predict pain presence, and (2) a Spatio-Temporal Graph Convolution Network (STGCN) integrated with LSTM to process landmarks from facial images for pain detection. Our work represents the first use of the PEMF dataset for binary pain classification and demonstrates the effectiveness of these models through extensive experimentation. The results highlight the potential of combining spatial and temporal features for enhanced pain detection, offering a promising advancement in objective pain assessment methodologies.
Authors: Zibo Zhao (refer to the report for detailed contributions), Zeqiang Lai (refer to the report for detailed contributions), Qingxiang Lin (refer to the report for detailed contributions), Yunfei Zhao (refer to the report for detailed contributions), Haolin Liu (refer to the report for detailed contributions), Shuhui Yang (refer to the report for detailed contributions), Yifei Feng (refer to the report for detailed contributions), Mingxin Yang (refer to the report for detailed contributions), Sheng Zhang (refer to the report for detailed contributions), Xianghui Yang (refer to the report for detailed contributions), Huiwen Shi (refer to the report for detailed contributions), Sicong Liu (refer to the report for detailed contributions), Junta Wu (refer to the report for detailed contributions), Yihang Lian (refer to the report for detailed contributions), Fan Yang (refer to the report for detailed contributions), Ruining Tang (refer to the report for detailed contributions), Zebin He (refer to the report for detailed contributions), Xinzhou Wang (refer to the report for detailed contributions), Jian Liu (refer to the report for detailed contributions), Xuhui Zuo (refer to the report for detailed contributions), Zhuo Chen (refer to the report for detailed contributions), Biwen Lei (refer to the report for detailed contributions), Haohan Weng (refer to the report for detailed contributions), Jing Xu (refer to the report for detailed contributions), Yiling Zhu (refer to the report for detailed contributions), Xinhai Liu (refer to the report for detailed contributions), Lixin Xu (refer to the report for detailed contributions), Changrong Hu (refer to the report for detailed contributions), Shaoxiong Yang (refer to the report for detailed contributions), Song Zhang (refer to the report for detailed contributions), Yang Liu (refer to the report for detailed contributions), Tianyu Huang (refer to the report for detailed contributions), Lifu Wang (refer to the report for detailed contributions), Jihong Zhang (refer to the report for detailed contributions), Meng Chen (refer to the report for detailed contributions), Liang Dong (refer to the report for detailed contributions), Yiwen Jia (refer to the report for detailed contributions), Yulin Cai (refer to the report for detailed contributions), Jiaao Yu (refer to the report for detailed contributions), Yixuan Tang (refer to the report for detailed contributions), Hao Zhang (refer to the report for detailed contributions), Zheng Ye (refer to the report for detailed contributions), Peng He (refer to the report for detailed contributions), Runzhou Wu (refer to the report for detailed contributions), Chao Zhang (refer to the report for detailed contributions), Yonghao Tan (refer to the report for detailed contributions), Jie Xiao (refer to the report for detailed contributions), Yangyu Tao (refer to the report for detailed contributions), Jianchen Zhu (refer to the report for detailed contributions), Jinbao Xue (refer to the report for detailed contributions), Kai Liu (refer to the report for detailed contributions), Chongqing Zhao (refer to the report for detailed contributions), Xinming Wu (refer to the report for detailed contributions), Zhichao Hu (refer to the report for detailed contributions), Lei Qin (refer to the report for detailed contributions), Jianbing Peng (refer to the report for detailed contributions), Zhan Li (refer to the report for detailed contributions), Minghui Chen (refer to the report for detailed contributions), Xipeng Zhang (refer to the report for detailed contributions), Lin Niu (refer to the report for detailed contributions), Paige Wang (refer to the report for detailed contributions), Yingkai Wang (refer to the report for detailed contributions), Haozhao Kuang (refer to the report for detailed contributions), Zhongyi Fan (refer to the report for detailed contributions), Xu Zheng (refer to the report for detailed contributions), Weihao Zhuang (refer to the report for detailed contributions), YingPing He (refer to the report for detailed contributions), Tian Liu (refer to the report for detailed contributions), Yong Yang (refer to the report for detailed contributions), Di Wang (refer to the report for detailed contributions), Yuhong Liu (refer to the report for detailed contributions), Jie Jiang (refer to the report for detailed contributions), Jingwei Huang (refer to the report for detailed contributions), Chunchao Guo (refer to the report for detailed contributions)
Abstract: We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2
Authors: Dong Li, Guihong Wan, Xintao Wu, Xinyu Wu, Ajit J. Nirmal, Christine G. Lian, Peter K. Sorger, Yevgeniy R. Semenov, Chen Zhao
Abstract: Computational pathology foundation models (CPathFMs) have emerged as a powerful approach for analyzing histopathological data, leveraging self-supervised learning to extract robust feature representations from unlabeled whole-slide images. These models, categorized into uni-modal and multi-modal frameworks, have demonstrated promise in automating complex pathology tasks such as segmentation, classification, and biomarker discovery. However, the development of CPathFMs presents significant challenges, such as limited data accessibility, high variability across datasets, the necessity for domain-specific adaptation, and the lack of standardized evaluation benchmarks. This survey provides a comprehensive review of CPathFMs in computational pathology, focusing on datasets, adaptation strategies, and evaluation tasks. We analyze key techniques, such as contrastive learning and multi-modal integration, and highlight existing gaps in current research. Finally, we explore future directions from four perspectives for advancing CPathFMs. This survey serves as a valuable resource for researchers, clinicians, and AI practitioners, guiding the advancement of CPathFMs toward robust and clinically applicable AI-driven pathology solutions.
Authors: Younggun Kim, Beomsik Cho, Seonghoon Ryoo, Soomok Lee
Abstract: Point cloud representation has recently become a research hotspot in the field of computer vision and has been utilized for autonomous vehicles. However, adapting deep learning networks for point cloud data recognition is challenging due to the variability in datasets and sensor technologies. This variability underscores the necessity for adaptive techniques to maintain accuracy under different conditions. In this paper, we present the Multi-View Structural Convolution Network (MSCN) designed for domain-invariant point cloud recognition. MSCN comprises Structural Convolution Layers (SCL) that extract local context geometric features from point clouds and Structural Aggregation Layers (SAL) that extract and aggregate both local and overall context features from point clouds. Additionally, our MSCN enhances feature representation robustness by training with unseen domain point clouds derived from source domain point clouds. This method acquires domain-invariant features and exhibits robust, consistent performance across various point cloud datasets, ensuring compatibility with diverse sensor configurations without the need for parameter adjustments. This highlights MSCN's potential to significantly improve the reliability and domain invariant features in different environments. Our code is available at https://github.com/MLMLab/MSCN.
Authors: Xiaoyan Jiang, Bohan Wang, Xinlong Wan, Zhi Zhou, Hamido Fujita
Abstract: Most existing RGB-D semantic segmentation methods focus on the feature level fusion, including complex cross-modality and cross-scale fusion modules. However, these methods may cause misalignment problem in the feature fusion process and counter-intuitive patches in the segmentation results. Inspired by the popular pixel-node-pixel pipeline, we propose to 1) fuse features from two modalities in a late fusion style, during which the geometric feature injection is guided by texture feature prior; 2) employ Graph Neural Networks (GNNs) on the fused feature to alleviate the emergence of irregular patches by inferring patch relationship. At the 3D feature extraction stage, we argue that traditional CNNs are not efficient enough for depth maps. So, we encode depth map into normal map, after which CNNs can easily extract object surface tendencies.At projection matrix generation stage, we find the existence of Biased-Assignment and Ambiguous-Locality issues in the original pipeline. Therefore, we propose to 1) adopt the Kullback-Leibler Loss to ensure no missing important pixel features, which can be viewed as hard pixel mining process; 2) connect regions that are close to each other in the Euclidean space as well as in the semantic space with larger edge weights so that location informations can been considered. Extensive experiments on two public datasets, NYU-DepthV2 and SUN RGB-D, have shown that our approach can consistently boost the performance of RGB-D semantic segmentation task.
Authors: Zhiqiang Yang, Qiu Guan, Zhongwen Yu, Xinli Xu, Haixia Long, Sheng Lian, Haigen Hu, Ying Tang
Abstract: Due to the effective multi-scale feature fusion capabilities of the Path Aggregation FPN (PAFPN), it has become a widely adopted component in YOLO-based detectors. However, PAFPN struggles to integrate high-level semantic cues with low-level spatial details, limiting its performance in real-world applications, especially with significant scale variations. In this paper, we propose MHAF-YOLO, a novel detection framework featuring a versatile neck design called the Multi-Branch Auxiliary FPN (MAFPN), which consists of two key modules: the Superficial Assisted Fusion (SAF) and Advanced Assisted Fusion (AAF). The SAF bridges the backbone and the neck by fusing shallow features, effectively transferring crucial low-level spatial information with high fidelity. Meanwhile, the AAF integrates multi-scale feature information at deeper neck layers, delivering richer gradient information to the output layer and further enhancing the model learning capacity. To complement MAFPN, we introduce the Global Heterogeneous Flexible Kernel Selection (GHFKS) mechanism and the Reparameterized Heterogeneous Multi-Scale (RepHMS) module to enhance feature fusion. RepHMS is globally integrated into the network, utilizing GHFKS to select larger convolutional kernels for various feature layers, expanding the vertical receptive field and capturing contextual information across spatial hierarchies. Locally, it optimizes convolution by processing both large and small kernels within the same layer, broadening the lateral receptive field and preserving crucial details for detecting smaller targets. The source code of this work is available at: https://github.com/yang-0201/MHAF-YOLO.
Authors: Pengfei Zhou, Xukun Shen, Yong Hu
Abstract: Recent advances in Score Distillation Sampling (SDS) have improved 3D human generation from textual descriptions. However, existing methods still face challenges in accurately aligning 3D models with long and complex textual inputs. To address this challenge, we propose a novel framework that introduces contrastive preferences, where human-level preference models, guided by both positive and negative prompts, assist SDS for improved alignment. Specifically, we design a preference optimization module that integrates multiple models to comprehensively capture the full range of textual features. Furthermore, we introduce a negation preference module to mitigate over-optimization of irrelevant details by leveraging static-dynamic negation prompts, effectively preventing ``reward hacking". Extensive experiments demonstrate that our method achieves state-of-the-art results, significantly enhancing texture realism and visual alignment with textual descriptions, particularly for long and complex inputs.
Authors: Yueting Liu, Hanshi Wang, Zhengjun Zha, Weiming Hu, Jin Gao
Abstract: Recent advancements in autonomous driving perception have revealed exceptional capabilities within structured environments dominated by vehicular traffic. However, current perception models exhibit significant limitations in semi-structured environments, where dynamic pedestrians with more diverse irregular movement and occlusion prevail. We attribute this shortcoming to the scarcity of high-quality datasets in semi-structured scenes, particularly concerning pedestrian perception and prediction. In this work, we present the multi-modal Pedestrian-Focused Scene Dataset(PFSD), rigorously annotated in semi-structured scenes with the format of nuScenes. PFSD provides comprehensive multi-modal data annotations with point cloud segmentation, detection, and object IDs for tracking. It encompasses over 130,000 pedestrian instances captured across various scenarios with varying densities, movement patterns, and occlusions. Furthermore, to demonstrate the importance of addressing the challenges posed by more diverse and complex semi-structured environments, we propose a novel Hybrid Multi-Scale Fusion Network (HMFN). Specifically, to detect pedestrians in densely populated and occluded scenarios, our method effectively captures and fuses multi-scale features using a meticulously designed hybrid framework that integrates sparse and vanilla convolutions. Extensive experiments on PFSD demonstrate that HMFN attains improvement in mean Average Precision (mAP) over existing methods, thereby underscoring its efficacy in addressing the challenges of 3D pedestrian detection in complex semi-structured environments. Coding and benchmark are available.
Authors: Caixiong Li, Xiongwei Zhao, Jinhang Zhang, Xing Zhang, Qihao Sun, Zhou Wu
Abstract: Open-vocabulary detection (OVD) is a challenging task to detect and classify objects from an unrestricted set of categories, including those unseen during training. Existing open-vocabulary detectors are limited by complex visual-textual misalignment and long-tailed category imbalances, leading to suboptimal performance in challenging scenarios. To address these limitations, we introduce MQADet, a universal paradigm for enhancing existing open-vocabulary detectors by leveraging the cross-modal reasoning capabilities of multimodal large language models (MLLMs). MQADet functions as a plug-and-play solution that integrates seamlessly with pre-trained object detectors without substantial additional training costs. Specifically, we design a novel three-stage Multimodal Question Answering (MQA) pipeline to guide the MLLMs to precisely localize complex textual and visual targets while effectively enhancing the focus of existing object detectors on relevant objects. To validate our approach, we present a new benchmark for evaluating our paradigm on four challenging open-vocabulary datasets, employing three state-of-the-art object detectors as baselines. Experimental results demonstrate that our proposed paradigm significantly improves the performance of existing detectors, particularly in unseen complex categories, across diverse and challenging scenarios. To facilitate future research, we will publicly release our code.
Authors: Miaomiao Cai, Guanjie Wang, Wei Li, Zhijun Tu, Hanting Chen, Shaohui Lin, Jie Hu
Abstract: In the field of autoregressive (AR) image generation, models based on the 'next-token prediction' paradigm of LLMs have shown comparable performance to diffusion models by reducing inductive biases. However, directly applying LLMs to complex image generation can struggle with reconstructing the structure and details of the image, impacting the accuracy and stability of generation. Additionally, the 'next-token prediction' paradigm in the AR model does not align with the contextual scanning and logical reasoning processes involved in human visual perception, limiting effective image generation. Chain-of-Thought (CoT), as a key reasoning capability of LLMs, utilizes reasoning prompts to guide the model, improving reasoning performance on complex natural language process (NLP) tasks, enhancing accuracy and stability of generation, and helping the model maintain contextual coherence and logical consistency, similar to human reasoning. Inspired by CoT from the field of NLP, we propose autoregressive Image Generation with Thoughtful Reasoning (IGTR) to enhance autoregressive image generation. IGTR adds reasoning prompts without modifying the model structure or raster generation order. Specifically, we design specialized image-related reasoning prompts for AR image generation to simulate the human reasoning process, which enhances contextual reasoning by allowing the model to first perceive overall distribution information before generating the image, and improve generation stability by increasing the inference steps. Compared to the AR method without prompts, our method shows outstanding performance and achieves an approximate improvement of 20%.
Authors: Zhe Zhu, Honghua Chen, Xing He, Mingqiang Wei
Abstract: Point cloud completion is a fundamental yet not well-solved problem in 3D vision. Current approaches often rely on 3D coordinate information and/or additional data (e.g., images and scanning viewpoints) to fill in missing parts. Unlike these methods, we explore self-structure augmentation and propose PointSea for global-to-local point cloud completion. In the global stage, consider how we inspect a defective region of a physical object, we may observe it from various perspectives for a better understanding. Inspired by this, PointSea augments data representation by leveraging self-projected depth images from multiple views. To reconstruct a compact global shape from the cross-modal input, we incorporate a feature fusion module to fuse features at both intra-view and inter-view levels. In the local stage, to reveal highly detailed structures, we introduce a point generator called the self-structure dual-generator. This generator integrates both learned shape priors and geometric self-similarities for shape refinement. Unlike existing efforts that apply a unified strategy for all points, our dual-path design adapts refinement strategies conditioned on the structural type of each point, addressing the specific incompleteness of each point. Comprehensive experiments on widely-used benchmarks demonstrate that PointSea effectively understands global shapes and generates local details from incomplete input, showing clear improvements over existing methods.
Authors: Yuli Wu, Fucheng Liu, R\"uveyda Yilmaz, Henning Konermann, Peter Walter, Johannes Stegmaier
Abstract: Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-v3 follow a multivariate Gaussian distribution and calculates the 2-Wasserstein distance based on their means and covariances. While FID effectively measures how closely synthetic data match real data in many image synthesis tasks, the primary goal in biomedical generative models is often to enrich training datasets ideally with corresponding annotations. For this purpose, the gold standard for evaluating generative models is to incorporate synthetic data into downstream task training, such as classification and segmentation, to pragmatically assess its performance. In this paper, we examine cases from retinal imaging modalities, including color fundus photography and optical coherence tomography, where FID and its related metrics misalign with task-specific evaluation goals in classification and segmentation. We highlight the limitations of using various metrics, represented by FID and its variants, as evaluation criteria for these applications and address their potential caveats in broader biomedical imaging modalities and downstream tasks.
Authors: Robyn Larracy, Angkoon Phinyomark, Ala Salehi, Eve MacDonald, Saeed Kazemi, Shikder Shafiul Bashar, Aaron Tabor, Erik Scheme
Abstract: Gait refers to the patterns of limb movement generated during walking, which are unique to each individual due to both physical and behavioural traits. Walking patterns have been widely studied in biometrics, biomechanics, sports, and rehabilitation. While traditional methods rely on video and motion capture, advances in underfoot pressure sensing technology now offer deeper insights into gait. However, underfoot pressures during walking remain underexplored due to the lack of large, publicly accessible datasets. To address this, the UNB StepUP database was created, featuring gait pressure data collected with high-resolution pressure sensing tiles (4 sensors/cm$^2$, 1.2m by 3.6m). Its first release, UNB StepUP-P150, includes over 200,000 footsteps from 150 individuals across various walking speeds (preferred, slow-to-stop, fast, and slow) and footwear types (barefoot, standard shoes, and two personal shoes). As the largest and most comprehensive dataset of its kind, it supports biometric gait recognition while presenting new research opportunities in biomechanics and deep learning. The UNB StepUP-P150 dataset sets a new benchmark for pressure-based gait analysis and recognition. Please note that the hypertext links to the dataset on FigShare remain dormant while the document is under review.
Authors: Lei Cheng, Lihao Guo, Tianya Zhang, Tam Bang, Austin Harris, Mustafa Hajij, Mina Sartipi, Siyang Cao
Abstract: Accurate multi-sensor calibration is essential for deploying robust perception systems in applications such as autonomous driving, robotics, and intelligent transportation. Existing LiDAR-camera calibration methods often rely on manually placed targets, preliminary parameter estimates, or intensive data preprocessing, limiting their scalability and adaptability in real-world settings. In this work, we propose a fully automatic, targetless, and online calibration framework, CalibRefine, which directly processes raw LiDAR point clouds and camera images. Our approach is divided into four stages: (1) a Common Feature Discriminator that trains on automatically detected objects--using relative positions, appearance embeddings, and semantic classes--to generate reliable LiDAR-camera correspondences, (2) a coarse homography-based calibration, (3) an iterative refinement to incrementally improve alignment as additional data frames become available, and (4) an attention-based refinement that addresses non-planar distortions by leveraging a Vision Transformer and cross-attention mechanisms. Through extensive experiments on two urban traffic datasets, we show that CalibRefine delivers high-precision calibration results with minimal human involvement, outperforming state-of-the-art targetless methods and remaining competitive with, or surpassing, manually tuned baselines. Our findings highlight how robust object-level feature matching, together with iterative and self-supervised attention-based adjustments, enables consistent sensor fusion in complex, real-world conditions without requiring ground-truth calibration matrices or elaborate data preprocessing.
Authors: Luigi Seminara, Giovanni Maria Farinella, Antonino Furnari
Abstract: We introduce a gradient-based approach for learning task graphs from procedural activities, improving over hand-crafted methods. Our method directly optimizes edge weights via maximum likelihood, enabling integration into neural architectures. We validate our approach on CaptainCook4D, EgoPER, and EgoProceL, achieving +14.5%, +10.2%, and +13.6% F1-score improvements. Our feature-based approach for predicting task graphs from textual/video embeddings demonstrates emerging video understanding abilities. We also achieved top performance on the procedure understanding benchmark on Ego-Exo4D and significantly improved online mistake detection (+19.8% on Assembly101-O, +6.4% on EPIC-Tent-O). Code: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.
URLs: https://github.com/fpv-iplab/Differentiable-Task-Graph-Learning.
Authors: Peng Zhang, Xin Li, Xin Lin, Liang He
Abstract: Recent advancements in 3D multi-object tracking (3D MOT) have predominantly relied on tracking-by-detection pipelines. However, these approaches often neglect potential enhancements in 3D detection processes, leading to high false positives (FP), missed detections (FN), and identity switches (IDS), particularly in challenging scenarios such as crowded scenes, small-object configurations, and adverse weather conditions. Furthermore, limitations in data preprocessing, association mechanisms, motion modeling, and life-cycle management hinder overall tracking robustness. To address these issues, we present Easy-Poly, a real-time, filter-based 3D MOT framework for multiple object categories. Our contributions include: (1) An Augmented Proposal Generator utilizing multi-modal data augmentation and refined SpConv operations, significantly improving mAP and NDS on nuScenes; (2) A Dynamic Track-Oriented (DTO) data association algorithm that effectively manages uncertainties and occlusions through optimal assignment and multiple hypothesis handling; (3) A Dynamic Motion Modeling (DMM) incorporating a confidence-weighted Kalman filter and adaptive noise covariances, enhancing MOTA and AMOTA in challenging conditions; and (4) An extended life-cycle management system with adjustive thresholds to reduce ID switches and false terminations. Experimental results show that Easy-Poly outperforms state-of-the-art methods such as Poly-MOT and Fast-Poly, achieving notable gains in mAP (e.g., from 63.30% to 64.96% with LargeKernel3D) and AMOTA (e.g., from 73.1% to 74.5%), while also running in real-time. These findings highlight Easy-Poly's adaptability and robustness in diverse scenarios, making it a compelling choice for autonomous driving and related 3D MOT applications. The source code of this paper will be published upon acceptance.
Authors: Zhenyu Wang, Heng Song
Abstract: The identification of art authors is crucial in areas like cultural heritage protection, art market analysis, and historical research. With the advancement of deep learning, Convolutional Neural Networks (CNNs) and Transformer models have become key tools for image classification. While CNNs excel in local feature extraction, they struggle with global context, and Transformers are strong in capturing global dependencies but weak in fine-grained local details. To address these challenges, this paper proposes a fusion model combining CNNs and Transformers for art author identification. The model first extracts local features using CNNs, then captures global context with a Transformer, followed by a feature fusion mechanism to enhance classification accuracy. Experiments on Chinese and oil painting datasets show the fusion model outperforms individual CNN and Transformer models, improving classification accuracy by 9.7\% and 7.1\%, respectively, and increasing F1 scores by 0.06 and 0.05. The results demonstrate the model's effectiveness and potential for future improvements, such as multimodal integration and architecture optimization.
Authors: Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Serge Belongie, Lei Li
Abstract: In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. To address these challenges, we propose BayesGenie, an off-the-shelf approach that integrates Large Language Models (LLMs) with Bayesian Optimization to facilitate precise and user-friendly image editing. Our method enables users to modify images through natural language descriptions without manual area marking, while preserving the original image's semantic integrity. Unlike existing techniques that require extensive pre-training or fine-tuning, our approach demonstrates remarkable adaptability across various LLMs through its model-agnostic design. BayesGenie employs an adapted Bayesian optimization strategy to automatically refine the inference process parameters, achieving high-precision image editing with minimal user intervention. Through extensive experiments across diverse scenarios, we demonstrate that our framework significantly outperforms existing methods in both editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4.
Authors: Alexander Groshev, Anastasiia Iashchenko, Pavel Paramonov, Denis Dimitrov, Andrey Kuznetsov
Abstract: While the task of face swapping has recently gained attention in the research community, a related problem of head swapping remains largely unexplored. In addition to skin color transfer, head swap poses extra challenges, such as the need to preserve structural information of the whole head during synthesis and inpaint gaps between swapped head and background. In this paper, we address these concerns with GHOST 2.0, which consists of two problem-specific modules. First, we introduce enhanced Aligner model for head reenactment, which preserves identity information at multiple scales and is robust to extreme pose variations. Secondly, we use a Blender module that seamlessly integrates the reenacted head into the target background by transferring skin color and inpainting mismatched regions. Both modules outperform the baselines on the corresponding tasks, allowing to achieve state of the art results in head swapping. We also tackle complex cases, such as large difference in hair styles of source and target. Code is available at https://github.com/ai-forever/ghost-2.0
Authors: Xin Wang, Yineng Chen, Shu Hu, Heng Fan, Hongtu Zhu, Xin Li
Abstract: Neural Radiance Fields (NeRF), as a pioneering technique in computer vision, offer great potential to revolutionize medical imaging by synthesizing three-dimensional representations from the projected two-dimensional image data. However, they face unique challenges when applied to medical applications. This paper presents a comprehensive examination of applications of NeRFs in medical imaging, highlighting four imminent challenges, including fundamental imaging principles, inner structure requirement, object boundary definition, and color density significance. We discuss current methods on different organs and discuss related limitations. We also review several datasets and evaluation metrics and propose several promising directions for future research.
Authors: Philipp Hess, Michael Aich, Baoxiang Pan, Niklas Boers
Abstract: Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high spatial resolution. Recent machine learning approaches have shown promising results in downscaling ESM simulations, outperforming state-of-the-art statistical approaches. However, existing methods require computationally costly retraining for each ESM and extrapolate poorly to climates unseen during training. We address these shortcomings by learning a consistency model (CM) that efficiently and accurately downscales arbitrary ESM simulations without retraining in a zero-shot manner. Our approach yields probabilistic downscaled fields at a resolution only limited by the observational reference data. We show that the CM outperforms state-of-the-art diffusion models at a fraction of computational cost while maintaining high controllability on the downscaling task. Further, our method generalizes to climate states unseen during training without explicitly formulated physical constraints.
Authors: K. Aditya Mohan, Massimiliano Ferrucci, Chuck Divin, Garrett A. Stevenson, Hyojin Kim
Abstract: 4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an important inverse problem in non-destructive evaluation. Conventional back-projection based reconstruction methods assume that the object remains static for the duration of several tens or hundreds of X-ray projection measurement images (reconstruction of consecutive limited-angle CT scans). However, this is an unrealistic assumption for many in-situ experiments that causes spurious artifacts and inaccurate morphological reconstructions of the object. To solve this problem, we propose to perform a 4D time-space reconstruction using a distributed implicit neural representation (DINR) network that is trained using a novel distributed stochastic training algorithm. Our DINR network learns to reconstruct the object at its output by iterative optimization of its network parameters such that the measured projection images best match the output of the CT forward measurement model. We use a forward measurement model that is a function of the DINR outputs at a sparsely sampled set of continuous valued 4D object coordinates. Unlike previous neural representation architectures that forward and back propagate through dense voxel grids that sample the object's entire time-space coordinates, we only propagate through the DINR at a small subset of object coordinates in each iteration resulting in an order-of-magnitude reduction in memory and compute for training. DINR leverages distributed computation across several compute nodes and GPUs to produce high-fidelity 4D time-space reconstructions. We use both simulated parallel-beam and experimental cone-beam X-ray CT datasets to demonstrate the superior performance of our approach.
Authors: Tugba Akinci D'Antonoli, Lucas K. Berger, Ashraya K. Indrakanti, Nathan Vishwanathan, Jakob Wei{\ss}, Matthias Jung, Zeynep Berkarda, Alexander Rau, Marco Reisert, Thomas K\"ustner, Alexandra Walter, Elmar M. Merkle, Daniel Boll, Hanns-Christian Breit, Andrew Phillip Nicoli, Martin Segeroth, Joshy Cyriac, Shan Yang, Jakob Wasserthal
Abstract: Since the introduction of TotalSegmentator CT, there is demand for a similar robust automated MRI segmentation tool that can be applied across all MRI sequences and anatomic structures. In this retrospective study, a nnU-Net model (TotalSegmentator) was trained on MRI and CT examinations to segment 80 anatomic structures relevant for use cases such as organ volumetry, disease characterization, surgical planning and opportunistic screening. Examinations were randomly sampled from routine clinical studies to represent real-world examples. Dice scores were calculated between the predicted segmentations and expert radiologist reference standard segmentations to evaluate model performance on an internal test set, two external test sets and against two publicly available models, and TotalSegmentator CT. The model was applied to an internal dataset containing abdominal MRIs to investigate age-dependent volume changes. A total of 1143 examinations (616 MRIs, 527 CTs) (median age 61 years, IQR 50-72) were split into training (n=1088, CT and MRI) and an internal test set (n=55; only MRI), two external test sets (AMOS, n=20; CHAOS, n=20; only MRI), and an internal aging-study dataset of 8672 abdominal MRIs (median age 59 years, IQR 45-70) were included. The model showed a Dice Score of 0.839 on the internal test set and outperformed two other models (Dice Score, 0.862 versus 0.759; and 0.838 versus 0.560; p<.001 for both). The proposed open-source, easy-to-use model allows for automatic, robust segmentation of 80 structures, extending the capabilities of TotalSegmentator to MRIs of any sequence. The ready-to-use online tool is available at https://totalsegmentator.com, the model at https://github.com/wasserth/TotalSegmentator, and the dataset at https://zenodo.org/records/14710732.
URLs: https://totalsegmentator.com,, https://github.com/wasserth/TotalSegmentator,, https://zenodo.org/records/14710732.
Authors: Jakub Gregorek, Lazaros Nalpantidis
Abstract: Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods still assumes depth values covering all areas of the scene. To address this limitation, we introduce SteeredMarigold, a training-free, zero-shot depth completion method capable of producing metric dense depth, even for largely incomplete depth maps. SteeredMarigold achieves this by using the available sparse depth points as conditions to steer a denoising diffusion probabilistic model. Our method outperforms relevant top-performing methods on the NYUv2 dataset, in tests where no depth was provided for a large area, achieving state-of-art performance and exhibiting remarkable robustness against depth map incompleteness. Our source code is publicly available at https://steeredmarigold.github.io.
Authors: Anthony Etim, Jakub Szefer
Abstract: Adversarial example attacks have emerged as a critical threat to machine learning. Adversarial attacks in image classification abuse various, minor modifications to the image that confuse the image classification neural network -- while the image still remains recognizable to humans. One important domain where the attacks have been applied is in the automotive setting with traffic sign classification. Researchers have demonstrated that adding stickers, shining light, or adding shadows are all different means to make machine learning inference algorithms mis-classify the traffic signs. This can cause potentially dangerous situations as a stop sign is recognized as a speed limit sign causing vehicles to ignore it and potentially leading to accidents. To address these attacks, this work focuses on enhancing defenses against such adversarial attacks. This work shifts the advantage to the user by introducing the idea of leveraging historical images and majority voting. While the attacker modifies a traffic sign that is currently being processed by the victim's machine learning inference, the victim can gain advantage by examining past images of the same traffic sign. This work introduces the notion of ''time traveling'' and uses historical Street View images accessible to anybody to perform inference on different, past versions of the same traffic sign. In the evaluation, the proposed defense has 100% effectiveness against latest adversarial example attack on traffic sign classification algorithm.
Authors: Suraj Pai, Ibrahim Hadzic, Dennis Bontempi, Keno Bressem, Benjamin H. Kann, Andriy Fedorov, Raymond H. Mak, Hugo J. W. L. Aerts
Abstract: Foundation models (FMs) have shown transformative potential in radiology by performing diverse, complex tasks across imaging modalities. Here, we developed CT-FM, a large-scale 3D image-based pre-trained model designed explicitly for various radiological tasks. CT-FM was pre-trained using 148,000 computed tomography (CT) scans from the Imaging Data Commons through label-agnostic contrastive learning. We evaluated CT-FM across four categories of tasks, namely, whole-body and tumor segmentation, head CT triage, medical image retrieval, and semantic understanding, showing superior performance against state-of-the-art models. Beyond quantitative success, CT-FM demonstrated the ability to cluster regions anatomically and identify similar anatomical and structural concepts across scans. Furthermore, it remained robust across test-retest settings and indicated reasonable salient regions attached to its embeddings. This study demonstrates the value of large-scale medical imaging foundation models and by open-sourcing the model weights, code, and data, aims to support more adaptable, reliable, and interpretable AI solutions in radiology.
Authors: Dongqi Liu, Chenxi Whitehouse, Xi Yu, Louis Mahon, Rohit Saxena, Zheng Zhao, Yifu Qiu, Mirella Lapata, Vera Demberg
Abstract: Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains. VISTA contains 18,599 recorded AI conference presentations paired with their corresponding paper abstracts. We benchmark the performance of state-of-the-art large models and apply a plan-based framework to better capture the structured nature of abstracts. Both human and automated evaluations confirm that explicit planning enhances summary quality and factual consistency. However, a considerable gap remains between models and human performance, highlighting the challenges of scientific video summarization.
Authors: Austin C. Houston, Sumner B. Harris, Hao Wang, Yu-Chuan Lin, David B. Geohegan, Kai Xiao, Gerd Duscher
Abstract: Moire patterns in van der Waals bilayer materials complicate the analysis of atomic-resolution images, hindering the atomic-scale insight typically attainable with scanning transmission electron microscopy. Here, we report a method to detect the positions and identities of atoms in each of the individual layers that compose twisted bilayer heterostructures. We developed a deep learning model, Gomb-Net, which identifies the coordinates and atomic species in each layer, effectively deconvoluting the moire pattern. This enables layer-specific mapping of quantities like strain and dopant distributions, unlike other commonly used segmentation models which struggle with moire-induced complexity. Using this approach, we explored the Se atom substitutional site distribution in a twisted fractional Janus WS2-WS2(1-x)Se2x heterostructure and found that layer-specific implantation sites are unaffected by the moire pattern's local energetic or electronic modulation. This advancement enables atom identification within material regimes where it was not possible before, opening new insights into previously inaccessible material physics.
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: Melane Navaratnarajah, Sophie A. Martin, David A. Kelly, Nathan Blake, Hana Chockler
Abstract: Explainability remains a significant problem for AI models in medical imaging, making it challenging for clinicians to trust AI-driven predictions. We introduce 3D ReX, the first causality-based post-hoc explainability tool for 3D models. 3D ReX uses the theory of actual causality to generate responsibility maps which highlight the regions most crucial to the model's decision. We test 3D ReX on a stroke detection model, providing insight into the spatial distribution of features relevant to stroke.
Authors: Eldad Haber, Shadab Ahamed, Md. Shahriar Rahim Siddiqui, Niloufar Zakariaei, Moshe Eliasof
Abstract: Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems. Nonetheless, training a generator is a non-trivial feat that requires fine-tuning and can lead to so-called hallucinations, that is, the generation of images that are unrealistic. In this work, we explore image generation using flow matching. We explain and demonstrate why flow matching can generate hallucinations, and propose an iterative process to improve the generation process. Our iterative process can be integrated into virtually $\textit{any}$ generative modeling technique, thereby enhancing the performance and robustness of image synthesis systems.
Authors: Ryo Takizawa, Izumi Karino, Koki Nakagawa, Yoshiyuki Ohmura, Yasuo Kuniyoshi
Abstract: Autonomous agents capable of diverse object manipulations should be able to acquire a wide range of manipulation skills with high reusability. Although advances in deep learning have made it increasingly feasible to replicate the dexterity of human teleoperation in robots, generalizing these acquired skills to previously unseen scenarios remains a significant challenge. In this study, we propose a novel algorithm, Gaze-based Bottleneck-aware Robot Manipulation (GazeBot), which enables high reusability of the learned motions even when the object positions and end-effector poses differ from those in the provided demonstrations. By leveraging gaze information and motion bottlenecks, both crucial features for object manipulation, GazeBot achieves high generalization performance compared with state-of-the-art imitation learning methods, without sacrificing its dexterity and reactivity. Furthermore, the training process of GazeBot is entirely data-driven once a demonstration dataset with gaze data is provided. Videos and code are available at https://crumbyrobotics.github.io/gazebot.