Authors: Mingjun Li, Natasha Kholgade Banerjee, Sean Banerjee
Abstract: Critical VR applications in domains such as healthcare, education, and finance that use traditional credentials, such as PIN, password, or multi-factor authentication, stand the chance of being compromised if a malicious person acquires the user credentials or if the user hands over their credentials to an ally. Recently, a number of approaches on user authentication have emerged that use motions of VR head-mounted displays (HMDs) and hand controllers during user interactions in VR to represent the user's behavior as a VR biometric signature. One of the fundamental limitations of behavior-based approaches is that current on-device tracking for HMDs and controllers lacks capability to perform tracking of full-body joint articulation, losing key signature data encapsulated by the user articulation. In this paper, we propose an approach that uses 2D body joints, namely shoulder, elbow, wrist, hip, knee, and ankle, acquired from the right side of the participants using an external 2D camera. Using a Transformer-based deep neural network, our method uses the 2D data of body joints that are not tracked by the VR device to predict past and future 3D tracks of the right controller, providing the benefit of augmenting 3D knowledge in authentication. Our approach provides a minimum equal error rate (EER) of 0.025, and a maximum EER drop of 0.040 over prior work that uses single-unit 3D trajectory as the input.
Authors: Bosung Kim, Kyuhwan Lee, Isu Jeong, Jungmin Cheon, Yeojin Lee, Seulki Lee
Abstract: We present On-device Sora, a first pioneering solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. Building on Open-Sora, On-device Sora applies three novel techniques to address the challenges of diffusion-based text-to-video generation on computation- and memory-limited mobile devices. First, Linear Proportional Leap (LPL) reduces the excessive denoising steps required in video diffusion through an efficient leap-based approach. Second, Temporal Dimension Token Merging (TDTM) minimizes intensive token-processing computation in attention layers by merging consecutive tokens along the temporal dimension. Third, Concurrent Inference with Dynamic Loading (CI-DL) dynamically partitions large models into smaller blocks and loads them into memory for concurrent model inference, effectively addressing the challenges of limited device memory. We implement On-device Sora on the iPhone 15 Pro, and the experimental evaluations demonstrate that it is capable of generating high-quality videos on the device, comparable to those produced by Open-Sora running on high-end GPUs. These results show that On-device Sora enables efficient and high-quality video generation on resource-constrained mobile devices, expanding accessibility, ensuring user privacy, reducing dependence on cloud infrastructure, and lowering associated costs. We envision the proposed On-device Sora as a significant first step toward democratizing state-of-the-art generative technologies, enabling video generation capabilities on commodity mobile and embedded devices. The code implementation is publicly available at an GitHub repository: https://github.com/eai-lab/On-device-Sora.
Authors: Wenhao You, Bryan Hooi, Yiwei Wang, Euijin Choo, Ming-Hsuan Yang, Junsong Yuan, Zi Huang, Yujun Cai
Abstract: Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content. However, as these tools become increasingly accessible, they also introduce significant risks of misuse, emphasizing the critical need for robust attribution methods to ensure content authenticity and traceability. Despite the creative potential of such tools, they pose significant challenges for attribution, particularly in adversarial settings where edits can be layered to obscure an image's origins. We propose LambdaTracer, a novel latent-space attribution method that robustly identifies and differentiates authentic outputs from manipulated ones without requiring any modifications to generative or editing pipelines. By adaptively calibrating reconstruction losses, LambdaTracer remains effective across diverse iterative editing processes, whether automated through text-guided editing tools such as InstructPix2Pix and ControlNet or performed manually with editing software such as Adobe Photoshop. Extensive experiments reveal that our method consistently outperforms baseline approaches in distinguishing maliciously edited images, providing a practical solution to safeguard ownership, creativity, and credibility in the open, fast-evolving AI ecosystems.
Authors: Jorge Garc\'ia-Torres, {\O}yvind Meinich-Bache, Siren Rettedal, Kjersti Engan
Abstract: Approximately 10% of newborns need some assistance to start breathing and 5\% proper ventilation. It is crucial that interventions are initiated as soon as possible after birth. Accurate documentation of Time of Birth (ToB) is thereby essential for documenting and improving newborn resuscitation performance. However, current clinical practices rely on manual recording of ToB, typically with minute precision. In this study, we present an AI-driven, video-based system for automated ToB detection using thermal imaging, designed to preserve the privacy of healthcare providers and mothers by avoiding the use of identifiable visual data. Our approach achieves 91.4% precision and 97.4% recall in detecting ToB within thermal video clips during performance evaluation. Additionally, our system successfully identifies ToB in 96% of test cases with an absolute median deviation of 1 second compared to manual annotations. This method offers a reliable solution for improving ToB documentation and enhancing newborn resuscitation outcomes.
Authors: Shuhao Zhang, Hui Kang, Yang Liu, Fang Mei, Hongjuan Li
Abstract: Attention-based arbitrary style transfer methods have gained significant attention recently due to their impressive ability to synthesize style details. However, the point-wise matching within the attention mechanism may overly focus on local patterns such that neglect the remarkable global features of style images. Additionally, when processing large images, the quadratic complexity of the attention mechanism will bring high computational load. To alleviate above problems, we propose Holistic Style Injector (HSI), a novel attention-style transformation module to deliver artistic expression of target style. Specifically, HSI performs stylization only based on global style representation that is more in line with the characteristics of style transfer, to avoid generating local disharmonious patterns in stylized images. Moreover, we propose a dual relation learning mechanism inside the HSI to dynamically render images by leveraging semantic similarity in content and style, ensuring the stylized images preserve the original content and improve style fidelity. Note that the proposed HSI achieves linear computational complexity because it establishes feature mapping through element-wise multiplication rather than matrix multiplication. Qualitative and quantitative results demonstrate that our method outperforms state-of-the-art approaches in both effectiveness and efficiency.
Authors: Xiaoshuai Hao, Yunfeng Diao, Mengchuan Wei, Yifan Yang, Peng Hao, Rong Yin, Hui Zhang, Weiming Li, Shu Zhao, Yu Liu
Abstract: Map construction task plays a vital role in providing precise and comprehensive static environmental information essential for autonomous driving systems. Primary sensors include cameras and LiDAR, with configurations varying between camera-only, LiDAR-only, or camera-LiDAR fusion, based on cost-performance considerations. While fusion-based methods typically perform best, existing approaches often neglect modality interaction and rely on simple fusion strategies, which suffer from the problems of misalignment and information loss. To address these issues, we propose MapFusion, a novel multi-modal Bird's-Eye View (BEV) feature fusion method for map construction. Specifically, to solve the semantic misalignment problem between camera and LiDAR BEV features, we introduce the Cross-modal Interaction Transform (CIT) module, enabling interaction between two BEV feature spaces and enhancing feature representation through a self-attention mechanism. Additionally, we propose an effective Dual Dynamic Fusion (DDF) module to adaptively select valuable information from different modalities, which can take full advantage of the inherent information between different modalities. Moreover, MapFusion is designed to be simple and plug-and-play, easily integrated into existing pipelines. We evaluate MapFusion on two map construction tasks, including High-definition (HD) map and BEV map segmentation, to show its versatility and effectiveness. Compared with the state-of-the-art methods, MapFusion achieves 3.6% and 6.2% absolute improvements on the HD map construction and BEV map segmentation tasks on the nuScenes dataset, respectively, demonstrating the superiority of our approach.
Authors: Luciano Baresi, Davide Yi Xian Hu, Muhammad Irfan Mas'udi, Giovanni Quattrocchi
Abstract: Ensuring the robustness of deep learning models requires comprehensive and diverse testing. Existing approaches, often based on simple data augmentation techniques or generative adversarial networks, are limited in producing realistic and varied test cases. To address these limitations, we present a novel framework for testing vision neural networks that leverages Large Language Models and control-conditioned Diffusion Models to generate synthetic, high-fidelity test cases. Our approach begins by translating images into detailed textual descriptions using a captioning model, allowing the language model to identify modifiable aspects of the image and generate counterfactual descriptions. These descriptions are then used to produce new test images through a text-to-image diffusion process that preserves spatial consistency and maintains the critical elements of the scene. We demonstrate the effectiveness of our method using two datasets: ImageNet1K for image classification and SHIFT for semantic segmentation in autonomous driving. The results show that our approach can generate significant test cases that reveal weaknesses and improve the robustness of the model through targeted retraining. We conducted a human assessment using Mechanical Turk to validate the generated images. The responses from the participants confirmed, with high agreement among the voters, that our approach produces valid and realistic images.
Authors: David Melhart, Matthew Barthet, Georgios N. Yannakakis
Abstract: Can out-of-the-box pretrained Large Language Models (LLMs) detect human affect successfully when observing a video? To address this question, for the first time, we evaluate comprehensively the capacity of popular LLMs to annotate and successfully predict continuous affect annotations of videos when prompted by a sequence of text and video frames in a multimodal fashion. Particularly in this paper, we test LLMs' ability to correctly label changes of in-game engagement in 80 minutes of annotated videogame footage from 20 first-person shooter games of the GameVibe corpus. We run over 2,400 experiments to investigate the impact of LLM architecture, model size, input modality, prompting strategy, and ground truth processing method on engagement prediction. Our findings suggest that while LLMs rightfully claim human-like performance across multiple domains, they generally fall behind capturing continuous experience annotations provided by humans. We examine some of the underlying causes for the relatively poor overall performance, highlight the cases where LLMs exceed expectations, and draw a roadmap for the further exploration of automated emotion labelling via LLMs.
Authors: Naor Cohen, Roy Orfaig, Ben-Zion Bobrovsky
Abstract: Efforts to connect LiDAR data with text, such as LidarCLIP, have primarily focused on embedding 3D point clouds into CLIP text-image space. However, these approaches rely on 3D point clouds, which present challenges in encoding efficiency and neural network processing. With the advent of advanced LiDAR sensors like Ouster OS1, which, in addition to 3D point clouds, produce fixed resolution depth, signal, and ambient panoramic 2D images, new opportunities emerge for LiDAR based tasks. In this work, we propose an alternative approach to connect LiDAR data with text by leveraging 2D imagery generated by the OS1 sensor instead of 3D point clouds. Using the Florence 2 large model in a zero-shot setting, we perform image captioning and object detection. Our experiments demonstrate that Florence 2 generates more informative captions and achieves superior performance in object detection tasks compared to existing methods like CLIP. By combining advanced LiDAR sensor data with a large pre-trained model, our approach provides a robust and accurate solution for challenging detection scenarios, including real-time applications requiring high accuracy and robustness.
Authors: Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman, Vishwa S. Parekh
Abstract: Self-supervised learning has revolutionized medical imaging by enabling efficient and generalizable feature extraction from large-scale unlabeled datasets. Recently, self-supervised foundation models have been extended to three-dimensional (3D) computed tomography (CT) data, generating compact, information-rich embeddings with 1408 features that achieve state-of-the-art performance on downstream tasks such as intracranial hemorrhage detection and lung cancer risk forecasting. However, these embeddings have been shown to encode demographic information, such as age, sex, and race, which poses a significant risk to the fairness of clinical applications. In this work, we propose a Variation Autoencoder (VAE) based adversarial debiasing framework to transform these embeddings into a new latent space where demographic information is no longer encoded, while maintaining the performance of critical downstream tasks. We validated our approach on the NLST lung cancer screening dataset, demonstrating that the debiased embeddings effectively eliminate multiple encoded demographic information and improve fairness without compromising predictive accuracy for lung cancer risk at 1-year and 2-year intervals. Additionally, our approach ensures the embeddings are robust against adversarial bias attacks. These results highlight the potential of adversarial debiasing techniques to ensure fairness and equity in clinical applications of self-supervised 3D CT embeddings, paving the way for their broader adoption in unbiased medical decision-making.
Authors: Sophia J. Abraham, Jonathan D. Hauenstein, Walter J. Scheirer
Abstract: Face parsing is a fundamental task in computer vision, enabling applications such as identity verification, facial editing, and controllable image synthesis. However, existing face parsing models often lack fairness and robustness, leading to biased segmentation across demographic groups and errors under occlusions, noise, and domain shifts. These limitations affect downstream face synthesis, where segmentation biases can degrade generative model outputs. We propose a multi-objective learning framework that optimizes accuracy, fairness, and robustness in face parsing. Our approach introduces a homotopy-based loss function that dynamically adjusts the importance of these objectives during training. To evaluate its impact, we compare multi-objective and single-objective U-Net models in a GAN-based face synthesis pipeline (Pix2PixHD). Our results show that fairness-aware and robust segmentation improves photorealism and consistency in face generation. Additionally, we conduct preliminary experiments using ControlNet, a structured conditioning model for diffusion-based synthesis, to explore how segmentation quality influences guided image generation. Our findings demonstrate that multi-objective face parsing improves demographic consistency and robustness, leading to higher-quality GAN-based synthesis.
Authors: Wenzhang Sun, Qirui Hou, Donglin Di, Jiahui Yang, Yongjia Ma, Jianxun Cui
Abstract: Diffusion Transformers (DiT) excel in video generation but encounter significant computational challenges due to the quadratic complexity of attention. Notably, attention differences between adjacent diffusion steps follow a U-shaped pattern. Current methods leverage this property by caching attention blocks, however, they still struggle with sudden error spikes and large discrepancies. To address these issues, we propose UniCP a unified caching and pruning framework for efficient video generation. UniCP optimizes both temporal and spatial dimensions through. Error Aware Dynamic Cache Window (EDCW): Dynamically adjusts cache window sizes for different blocks at various timesteps, adapting to abrupt error changes. PCA based Slicing (PCAS) and Dynamic Weight Shift (DWS): PCAS prunes redundant attention components, and DWS integrates caching and pruning by enabling dynamic switching between pruned and cached outputs. By adjusting cache windows and pruning redundant components, UniCP enhances computational efficiency and maintains video detail fidelity. Experimental results show that UniCP outperforms existing methods in both performance and efficiency.
Authors: Siru Zhong, Weilin Ruan, Ming Jin, Huan Li, Qingsong Wen, Yuxuan Liang
Abstract: Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it often lacks fine-grained temporal details. Conversely, vision captures intricate temporal patterns but lacks semantic context, limiting the complementary potential of these modalities. To address this, we propose Time-VLM, a novel multimodal framework that leverages pre-trained Vision-Language Models (VLMs) to bridge temporal, visual, and textual modalities for enhanced forecasting. Our framework comprises three key components: (1) a Retrieval-Augmented Learner, which extracts enriched temporal features through memory bank interactions; (2) a Vision-Augmented Learner, which encodes time series as informative images; and (3) a Text-Augmented Learner, which generates contextual textual descriptions. These components collaborate with frozen pre-trained VLMs to produce multimodal embeddings, which are then fused with temporal features for final prediction. Extensive experiments across diverse datasets demonstrate that Time-VLM achieves superior performance, particularly in few-shot and zero-shot scenarios, thereby establishing a new direction for multimodal time series forecasting.
Authors: Ziyi Dong, Yao Xiao, Pengxu Wei, Liang Lin
Abstract: Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models. These models exhibit a remarkable ability to generate highly artistic and intricately detailed images based on textual prompts. However, obtaining desired generation outcomes often necessitates repetitive trials of manipulating text prompts just like casting spells on a magic mirror, and the reason behind that is the limited capability of semantic understanding inherent in current image generation models. Specifically, existing diffusion models encode the text prompt input with a pre-trained encoder structure, which is usually trained on a limited number of image-caption pairs. The state-of-the-art large language models (LLMs) based on the decoder-only structure have shown a powerful semantic understanding capability as their architectures are more suitable for training on very large-scale unlabeled data. In this work, we propose to enhance text-to-image diffusion models by borrowing the strength of semantic understanding from large language models, and devise a simple yet effective adapter to allow the diffusion models to be compatible with the decoder-only structure. Meanwhile, we also provide a supporting theoretical analysis with various architectures (e.g., encoder-only, encoder-decoder, and decoder-only), and conduct extensive empirical evaluations to verify its effectiveness. The experimental results show that the enhanced models with our adapter module are superior to the stat-of-the-art models in terms of text-to-image generation quality and reliability.
Authors: Sergios-Anestis Kefalidis, Konstantinos Plas, Manolis Koubarakis
Abstract: TerraQ is a spatiotemporal question-answering engine for satellite image archives. It is a natural language processing system that is built to process requests for satellite images satisfying certain criteria. The requests can refer to image metadata and entities from a specialized knowledge base (e.g., the Emilia-Romagna region). With it, users can make requests like "Give me a hundred images of rivers near ports in France, with less than 20% snow coverage and more than 10% cloud coverage", thus making Earth Observation data more easily accessible, in-line with the current landscape of digital assistants.
Authors: Imad Eddine Marouf, Enzo Tartaglione, Stephane Lathuiliere, Joost van de Weijer
Abstract: Continual Learning in Visual Question Answering (VQACL) requires models to learn new visual-linguistic tasks (plasticity) while retaining knowledge from previous tasks (stability). The multimodal nature of VQACL presents unique challenges, requiring models to balance stability across visual and textual domains while maintaining plasticity to adapt to novel objects and reasoning tasks. Existing methods, predominantly designed for unimodal tasks, often struggle to balance these demands effectively. In this work, we introduce QUestion-only replay with Attention Distillation (QUAD), a novel approach for VQACL that leverages only past task questions for regularisation, eliminating the need to store visual data and addressing both memory and privacy concerns. QUAD achieves stability by introducing a question-only replay mechanism that selectively uses questions from previous tasks to prevent overfitting to the current task's answer space, thereby mitigating the out-of-answer-set problem. Complementing this, we propose attention consistency distillation, which uniquely enforces both intra-modal and inter-modal attention consistency across tasks, preserving essential visual-linguistic associations. Extensive experiments on VQAv2 and NExT-QA demonstrate that QUAD significantly outperforms state-of-the-art methods, achieving robust performance in continual VQA.
Authors: Guillem Arias, Ramon Baldrich, Maria Vanrell
Abstract: This work explores how color is encoded in CLIP (Contrastive Language-Image Pre-training) which is currently the most influential VML (Visual Language model) in Artificial Intelligence. After performing different experiments on synthetic datasets created for this task, we conclude that CLIP is able to attribute correct color labels to colored visual stimulus, but, we come across two main deficiencies: (a) a clear bias on achromatic stimuli that are poorly related to the color concept, thus white, gray and black are rarely assigned as color labels; and (b) the tendency to prioritize text over other visual information. Here we prove it is highly significant in color labelling through an exhaustive Stroop-effect test. With the aim to find the causes of these color deficiencies, we analyse the internal representation at the neuron level. We conclude that CLIP presents an important amount of neurons selective to text, specially in deepest layers of the network, and a smaller amount of multi-modal color neurons which could be the key of understanding the concept of color properly. Our investigation underscores the necessity of refining color representation mechanisms in neural networks to foster a more comprehensive comprehension of colors as humans understand them, thereby advancing the efficacy and versatility of multimodal models like CLIP in real-world scenarios.
Authors: Jiahui Chen, Amy Zhang, Adriana Romero-Soriano
Abstract: Image generation abilities of text-to-image diffusion models have significantly advanced, yielding highly photo-realistic images from descriptive text and increasing the viability of leveraging synthetic images to train computer vision models. To serve as effective training data, generated images must be highly realistic while also sufficiently diverse within the support of the target data distribution. Yet, state-of-the-art conditional image generation models have been primarily optimized for creative applications, prioritizing image realism and prompt adherence over conditional diversity. In this paper, we investigate how to improve the diversity of generated images with the goal of increasing their effectiveness to train downstream image classification models, without fine-tuning the image generation model. We find that conditioning the generation process on an augmented real image and text prompt produces generations that serve as effective synthetic datasets for downstream training. Conditioning on real training images contextualizes the generation process to produce images that are in-domain with the real image distribution, while data augmentations introduce visual diversity that improves the performance of the downstream classifier. We validate augmentation-conditioning on a total of five established long-tail and few-shot image classification benchmarks and show that leveraging augmentations to condition the generation process results in consistent improvements over the state-of-the-art on the long-tailed benchmark and remarkable gains in extreme few-shot regimes of the remaining four benchmarks. These results constitute an important step towards effectively leveraging synthetic data for downstream training.
Authors: Luiz C. S. de Araujo, Carlos M. S. Figueiredo
Abstract: Multi-Object Tracking (MOT) is a critical problem in computer vision, essential for understanding how objects move and interact in videos. This field faces significant challenges such as occlusions and complex environmental dynamics, impacting model accuracy and efficiency. While traditional approaches have relied on Convolutional Neural Networks (CNNs), introducing transformers has brought substantial advancements. This work introduces OneTrack-M, a transformer-based MOT model designed to enhance tracking computational efficiency and accuracy. Our approach simplifies the typical transformer-based architecture by eliminating the need for a decoder model for object detection and tracking. Instead, the encoder alone serves as the backbone for temporal data interpretation, significantly reducing processing time and increasing inference speed. Additionally, we employ innovative data pre-processing and multitask training techniques to address occlusion and diverse objective challenges within a single set of weights. Experimental results demonstrate that OneTrack-M achieves at least 25% faster inference times compared to state-of-the-art models in the literature while maintaining or improving tracking accuracy metrics. These improvements highlight the potential of the proposed solution for real-time applications such as autonomous vehicles, surveillance systems, and robotics, where rapid responses are crucial for system effectiveness.
Authors: Nathan Louis, Mahzad Khoshlessan, Jason J. Corso
Abstract: Modeling humans in physical scenes is vital for understanding human-environment interactions for applications involving augmented reality or assessment of human actions from video (e.g. sports or physical rehabilitation). State-of-the-art literature begins with a 3D human pose, from monocular or multiple views, and uses this representation to ground the person within a 3D world space. While standard metrics for accuracy capture joint position errors, they do not consider physical plausibility of the 3D pose. This limitation has motivated researchers to propose other metrics evaluating jitter, floor penetration, and unbalanced postures. Yet, these approaches measure independent instances of errors and are not representative of balance or stability during motion. In this work, we propose measuring physical plausibility from within physics simulation. We introduce two metrics to capture the physical plausibility and stability of predicted 3D poses from any 3D Human Pose Estimation model. Using physics simulation, we discover correlations with existing plausibility metrics and measuring stability during motion. We evaluate and compare the performances of two state-of-the-art methods, a multi-view triangulated baseline, and ground truth 3D markers from the Human3.6m dataset.
Authors: Peiyuan Zhang, Yongqi Chen, Runlong Su, Hangliang Ding, Ion Stoica, Zhenghong Liu, Hao Zhang
Abstract: Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video, attention alone takes 800 out of 945 seconds of total inference time. This paper introduces sliding tile attention (STA) to address this challenge. STA leverages the observation that attention scores in pretrained video diffusion models predominantly concentrate within localized 3D windows. By sliding and attending over the local spatial-temporal region, STA eliminates redundancy from full attention. Unlike traditional token-wise sliding window attention (SWA), STA operates tile-by-tile with a novel hardware-aware sliding window design, preserving expressiveness while being hardware-efficient. With careful kernel-level optimizations, STA offers the first efficient 2D/3D sliding-window-like attention implementation, achieving 58.79% MFU. Precisely, STA accelerates attention by 2.8-17x over FlashAttention-2 (FA2) and 1.6-10x over FlashAttention-3 (FA3). On the leading video DiT, HunyuanVideo, STA reduces end-to-end latency from 945s (FA3) to 685s without quality degradation, requiring no training. Enabling finetuning further lowers latency to 268s with only a 0.09% drop on VBench.
Authors: Roberta Hunt, Kim Steenstrup Pedersen
Abstract: Phylogenetic analysis traditionally relies on labor-intensive manual extraction of morphological traits, limiting its scalability for large datasets. Recent advances in deep learning offer the potential to automate this process, but the effectiveness of different morphological representations for phylogenetic trait extraction remains poorly understood. In this study, we compare the performance of deep learning models using three distinct morphological representations - full segmentations, binary masks, and Fourier descriptors of beetle outlines. We test this on the Rove-Tree-11 dataset, a curated collection of images from 215 rove beetle species. Our results demonstrate that the mask-based model outperformed the others, achieving a normalized Align Score of 0.33 plus/minus 0.02 on the test set, compared to 0.45 plus/minus 0.01 for the Fourier-based model and 0.39 plus/minus 0.07 for the segmentation-based model. The performance of the mask-based model likely reflects its ability to capture shape features while taking advantage of the depth and capacity of the ResNet50 architecture. These results also indicate that dorsal textural features, at least in this group of beetles, may be of lowered phylogenetic relevance, though further investigation is necessary to confirm this. In contrast, the Fourier-based model suffered from reduced capacity and occasional inaccuracies in outline approximations, particularly in fine structures like legs. These findings highlight the importance of selecting appropriate morphological representations for automated phylogenetic studies and the need for further research into explainability in automatic morphological trait extraction.
Authors: Md. Jahin Alam, Muhammad Zubair Hasan, Md Maisoon Rahman, Md Awsafur Rahman, Najibul Haque Sarker, Shariar Azad, Tasnim Nishat Islam, Bishmoy Paul, Tanvir Anjum, Barproda Halder, Shaikh Anowarul Fattah
Abstract: Real time vehicle detection is a challenging task for urban traffic surveillance. Increase in urbanization leads to increase in accidents and traffic congestion in junction areas resulting in delayed travel time. In order to solve these problems, an intelligent system utilizing automatic detection and tracking system is significant. But this becomes a challenging task at road intersection areas which require a wide range of field view. For this reason, fish eye cameras are widely used in real time vehicle detection purpose to provide large area coverage and 360 degree view at junctions. However, it introduces challenges such as light glare from vehicles and street lights, shadow, non-linear distortion, scaling issues of vehicles and proper localization of small vehicles. To overcome each of these challenges, a modified YOLOv5 object detection scheme is proposed. YOLOv5 is a deep learning oriented convolutional neural network (CNN) based object detection method. The proposed scheme for detecting vehicles in fish-eye images consists of a light-weight day-night CNN classifier so that two different solutions can be implemented to address the day-night detection issues. Furthurmore, challenging instances are upsampled in the dataset for proper localization of vehicles and later on the detection model is ensembled and trained in different combination of vehicle datasets for better generalization, detection and accuracy. For testing, a real world fisheye dataset provided by the Video and Image Processing (VIP) Cup organizer ISSD has been used which includes images from video clips of different fisheye cameras at junction of different cities during day and night time. Experimental results show that our proposed model has outperformed the YOLOv5 model on the dataset by 13.7% mAP @ 0.5.
Authors: Kunxiao Liu, Guowu Yuan, Hongyu Liu, Hao Wu
Abstract: Style transfer is adopted to synthesize appealing stylized images that preserve the structure of a content image but carry the pattern of a style image. Many recently proposed style transfer methods use only western oil paintings as style images to achieve image stylization. As a result, unnatural messy artistic effects are produced in stylized images when using these methods to directly transfer the patterns of traditional Chinese paintings, which are composed of plain colors and abstract objects. Moreover, most of them work only at the original image scale and thus ignore multiscale image information during training. In this paper, we present a novel effective multiscale style transfer method based on Laplacian pyramid decomposition and reconstruction, which can transfer unique patterns of Chinese paintings by learning different image features at different scales. In the first stage, the holistic patterns are transferred at low resolution by adopting a Style Transfer Base Network. Then, the details of the content and style are gradually enhanced at higher resolutions by a Detail Enhancement Network with an edge information selection (EIS) module in the second stage. The effectiveness of our method is demonstrated through the generation of appealing high-quality stylization results and a comparison with some state-of-the-art style transfer methods. Datasets and codes are available at https://github.com/toby-katakuri/LP_StyleTransferNet.
Authors: Seunghwan Kim, Sunha Park, Seungkyu Lee
Abstract: Prefracture method is a practical implementation for real-time object destruction that is hardly achievable within performance constraints, but can produce unrealistic results due to its heuristic nature. To mitigate it, we approach the clustering of prefractured mesh generation as an unordered segmentation on point cloud data, and propose leveraging the deep neural network trained on a physics-based dataset. Our novel paradigm successfully predicts the structural weakness of object that have been limited, exhibiting ready-to-use results with remarkable quality.
Authors: Mengting Ma, Yizhen Jiang, Mengjiao Zhao, Jiaxin Li, Wei Zhang
Abstract: Remote sensing pansharpening aims to reconstruct spatial-spectral properties during the fusion of panchromatic (PAN) images and low-resolution multi-spectral (LR-MS) images, finally generating the high-resolution multi-spectral (HR-MS) images. In the mainstream modeling strategies, i.e., CNN and Transformer, the input images are treated as the equal-sized grid of pixels in the Euclidean space. They have limitations in facing remote sensing images with irregular ground objects. Graph is the more flexible structure, however, there are two major challenges when modeling spatial-spectral properties with graph: \emph{1) constructing the customized graph structure for spatial-spectral relationship priors}; \emph{2) learning the unified spatial-spectral representation through the graph}. To address these challenges, we propose the spatial-spectral heterogeneous graph learning network, named \textbf{HetSSNet}. Specifically, HetSSNet initially constructs the heterogeneous graph structure for pansharpening, which explicitly describes pansharpening-specific relationships. Subsequently, the basic relationship pattern generation module is designed to extract the multiple relationship patterns from the heterogeneous graph. Finally, relationship pattern aggregation module is exploited to collaboratively learn unified spatial-spectral representation across different relationships among nodes with adaptive importance learning from local and global perspectives. Extensive experiments demonstrate the significant superiority and generalization of HetSSNet.
Authors: Runqing Jiang, Ye Zhang, Longguang Wang, Pengpeng Yu, Yulan Guo
Abstract: Post-training quantization (PTQ) has emerged as a promising solution for reducing the storage and computational cost of vision transformers (ViTs). Recent advances primarily target at crafting quantizers to deal with peculiar activations characterized by ViTs. However, most existing methods underestimate the information loss incurred by weight quantization, resulting in significant performance deterioration, particularly in low-bit cases. Furthermore, a common practice in quantizing post-Softmax activations of ViTs is to employ logarithmic transformations, which unfortunately prioritize less informative values around zero. This approach introduces additional redundancies, ultimately leading to suboptimal quantization efficacy. To handle these, this paper proposes an innovative PTQ method tailored for ViTs, termed AIQViT (Architecture-Informed Post-training Quantization for ViTs). First, we design an architecture-informed low rank compensation mechanism, wherein learnable low-rank weights are introduced to compensate for the degradation caused by weight quantization. Second, we design a dynamic focusing quantizer to accommodate the unbalanced distribution of post-Softmax activations, which dynamically selects the most valuable interval for higher quantization resolution. Extensive experiments on five vision tasks, including image classification, object detection, instance segmentation, point cloud classification, and point cloud part segmentation, demonstrate the superiority of AIQViT over state-of-the-art PTQ methods.
Authors: Zihao Zou, Ziyuan Qu, Xi Peng, Vivek Boominathan, Adithya Pediredla, Praneeth Chakravarthula
Abstract: Capturing and reconstructing high-speed dynamic 3D scenes has numerous applications in computer graphics, vision, and interdisciplinary fields such as robotics, aerodynamics, and evolutionary biology. However, achieving this using a single imaging modality remains challenging. For instance, traditional RGB cameras suffer from low frame rates, limited exposure times, and narrow baselines. To address this, we propose a novel sensor fusion approach using Gaussian splatting, which combines RGB, depth, and event cameras to capture and reconstruct deforming scenes at high speeds. The key insight of our method lies in leveraging the complementary strengths of these imaging modalities: RGB cameras capture detailed color information, event cameras record rapid scene changes with microsecond resolution, and depth cameras provide 3D scene geometry. To unify the underlying scene representation across these modalities, we represent the scene using deformable 3D Gaussians. To handle rapid scene movements, we jointly optimize the 3D Gaussian parameters and their temporal deformation fields by integrating data from all three sensor modalities. This fusion enables efficient, high-quality imaging of fast and complex scenes, even under challenging conditions such as low light, narrow baselines, or rapid motion. Experiments on synthetic and real datasets captured with our prototype sensor fusion setup demonstrate that our method significantly outperforms state-of-the-art techniques, achieving noticeable improvements in both rendering fidelity and structural accuracy.
Authors: Yong Li, Yingjing Huang, Gengchen Mai, Fan Zhang
Abstract: Street view imagery is extensively utilized in representation learning for urban visual environments, supporting various sustainable development tasks such as environmental perception and socio-economic assessment. However, it is challenging for existing image representations to specifically encode the dynamic urban environment (such as pedestrians, vehicles, and vegetation), the built environment (including buildings, roads, and urban infrastructure), and the environmental ambiance (such as the cultural and socioeconomic atmosphere) depicted in street view imagery to address downstream tasks related to the city. In this work, we propose an innovative self-supervised learning framework that leverages temporal and spatial attributes of street view imagery to learn image representations of the dynamic urban environment for diverse downstream tasks. By employing street view images captured at the same location over time and spatially nearby views at the same time, we construct contrastive learning tasks designed to learn the temporal-invariant characteristics of the built environment and the spatial-invariant neighborhood ambiance. Our approach significantly outperforms traditional supervised and unsupervised methods in tasks such as visual place recognition, socioeconomic estimation, and human-environment perception. Moreover, we demonstrate the varying behaviors of image representations learned through different contrastive learning objectives across various downstream tasks. This study systematically discusses representation learning strategies for urban studies based on street view images, providing a benchmark that enhances the applicability of visual data in urban science. The code is available at https://github.com/yonglleee/UrbanSTCL.
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/yang0201/MHAF-YOLO.
Authors: Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Xiuwen Liu
Abstract: While transformer-based models dominate NLP and vision applications, their underlying mechanisms to map the input space to the label space semantically are not well understood. In this paper, we study the sources of known representation vulnerabilities of vision transformers (ViT), where perceptually identical images can have very different representations and semantically unrelated images can have the same representation. Our analysis indicates that imperceptible changes to the input can result in significant representation changes, particularly in later layers, suggesting potential instabilities in the performance of ViTs. Our comprehensive study reveals that adversarial effects, while subtle in early layers, propagate and amplify through the network, becoming most pronounced in middle to late layers. This insight motivates the development of NeuroShield-ViT, a novel defense mechanism that strategically neutralizes vulnerable neurons in earlier layers to prevent the cascade of adversarial effects. We demonstrate NeuroShield-ViT's effectiveness across various attacks, particularly excelling against strong iterative attacks, and showcase its remarkable zero-shot generalization capabilities. Without fine-tuning, our method achieves a competitive accuracy of 77.8% on adversarial examples, surpassing conventional robustness methods. Our results shed new light on how adversarial effects propagate through ViT layers, while providing a promising approach to enhance the robustness of vision transformers against adversarial attacks. Additionally, they provide a promising approach to enhance the robustness of vision transformers against adversarial attacks.
Authors: S Sreehari, Dilavar P D, S M Anzar, Alavikunhu Panthakkan, Saad Ali Amin
Abstract: Fingerprint recognition remains one of the most reliable biometric technologies due to its high accuracy and uniqueness. Traditional systems rely on contact-based scanners, which are prone to issues such as image degradation from surface contamination and inconsistent user interaction. To address these limitations, contactless fingerprint recognition has emerged as a promising alternative, providing non-intrusive and hygienic authentication. This study evaluates the impact of image enhancement tech-niques on the performance of pre-trained deep learning models using transfer learning for touchless fingerprint recognition. The IIT-Bombay Touchless and Touch-Based Fingerprint Database, containing data from 200 subjects, was employed to test the per-formance of deep learning architectures such as VGG-16, VGG-19, Inception-V3, and ResNet-50. Experimental results reveal that transfer learning methods with fingerprint image enhance-ment (indirect method) significantly outperform those without enhancement (direct method). Specifically, VGG-16 achieved an accuracy of 98% in training and 93% in testing when using the enhanced images, demonstrating superior performance compared to the direct method. This paper provides a detailed comparison of the effectiveness of image enhancement in improving the accuracy of transfer learning models for touchless fingerprint recognition, offering key insights for developing more efficient biometric systems.
Authors: Alavikunhu Panthakkan, Zubair Medammal, S M Anzar, Fatma Taher, Hussain Al-Ahmad
Abstract: Falconry, an ancient practice of training and hunting with falcons, emphasizes the need for vigilant health monitoring to ensure the well-being of these highly valued birds, especially during hunting activities. This research paper introduces a cutting-edge approach, which leverages the power of Concatenated ConvNeXt and EfficientNet AI models for falcon disease classification. Focused on distinguishing 'Normal,' 'Liver,' and 'Aspergillosis' cases, the study employs a comprehensive dataset for model training and evaluation, utilizing metrics such as accuracy, precision, recall, and f1-score. Through rigorous experimentation and evaluation, we demonstrate the superior performance of the concatenated AI model compared to traditional methods and standalone architectures. This novel approach contributes to accurate falcon disease classification, laying the groundwork for further advancements in avian veterinary AI applications.
Authors: Jun Dai, Liqun Chen, Xinge Yang, Yuyao Hu, Jinwei Gu, Tianfan Xue
Abstract: Deep optics has emerged as a promising approach by co-designing optical elements with deep learning algorithms. However, current research typically overlooks the analysis and optimization of manufacturing and assembly tolerances. This oversight creates a significant performance gap between designed and fabricated optical systems. To address this challenge, we present the first end-to-end tolerance-aware optimization framework that incorporates multiple tolerance types into the deep optics design pipeline. Our method combines physics-informed modelling with data-driven training to enhance optical design by accounting for and compensating for structural deviations in manufacturing and assembly. We validate our approach through computational imaging applications, demonstrating results in both simulations and real-world experiments. We further examine how our proposed solution improves the robustness of optical systems and vision algorithms against tolerances through qualitative and quantitative analyses. Code and additional visual results are available at openimaginglab.github.io/LensTolerance.
Authors: Yujin Han, Andi Han, Wei Huang, Chaochao Lu, Difan Zou
Abstract: Despite the remarkable success of diffusion models (DMs) in data generation, they exhibit specific failure cases with unsatisfactory outputs. We focus on one such limitation: the ability of DMs to learn hidden rules between image features. Specifically, for image data with dependent features ($\mathbf{x}$) and ($\mathbf{y}$) (e.g., the height of the sun ($\mathbf{x}$) and the length of the shadow ($\mathbf{y}$)), we investigate whether DMs can accurately capture the inter-feature rule ($p(\mathbf{y}|\mathbf{x})$). Empirical evaluations on mainstream DMs (e.g., Stable Diffusion 3.5) reveal consistent failures, such as inconsistent lighting-shadow relationships and mismatched object-mirror reflections. Inspired by these findings, we design four synthetic tasks with strongly correlated features to assess DMs' rule-learning abilities. Extensive experiments show that while DMs can identify coarse-grained rules, they struggle with fine-grained ones. Our theoretical analysis demonstrates that DMs trained via denoising score matching (DSM) exhibit constant errors in learning hidden rules, as the DSM objective is not compatible with rule conformity. To mitigate this, we introduce a common technique - incorporating additional classifier guidance during sampling, which achieves (limited) improvements. Our analysis reveals that the subtle signals of fine-grained rules are challenging for the classifier to capture, providing insights for future exploration.
Authors: Huajian Huang, Yingshu Chen, Longwei Li, Hui Cheng, Tristan Braud, Yajie Zhao, Sai-Kit Yeung
Abstract: 360-degree cameras streamline data collection for radiance field 3D reconstruction by capturing comprehensive scene data. However, traditional radiance field methods do not address the specific challenges inherent to 360-degree images. We present SC-OmniGS, a novel self-calibrating omnidirectional Gaussian splatting system for fast and accurate omnidirectional radiance field reconstruction using 360-degree images. Rather than converting 360-degree images to cube maps and performing perspective image calibration, we treat 360-degree images as a whole sphere and derive a mathematical framework that enables direct omnidirectional camera pose calibration accompanied by 3D Gaussians optimization. Furthermore, we introduce a differentiable omnidirectional camera model in order to rectify the distortion of real-world data for performance enhancement. Overall, the omnidirectional camera intrinsic model, extrinsic poses, and 3D Gaussians are jointly optimized by minimizing weighted spherical photometric loss. Extensive experiments have demonstrated that our proposed SC-OmniGS is able to recover a high-quality radiance field from noisy camera poses or even no pose prior in challenging scenarios characterized by wide baselines and non-object-centric configurations. The noticeable performance gain in the real-world dataset captured by consumer-grade omnidirectional cameras verifies the effectiveness of our general omnidirectional camera model in reducing the distortion of 360-degree images.
Authors: Yijun Wang, Yong Wang, Chendong xu, Shuai Yao, Qisong Wu
Abstract: Human Activity Recognition (HAR) such as fall detection has become increasingly critical due to the aging population, necessitating effective monitoring systems to prevent serious injuries and fatalities associated with falls. This study focuses on fine-tuning the Vision Transformer (ViT) model specifically for HAR using radar-based Time-Doppler signatures. Unlike traditional image datasets, these signals present unique challenges due to their non-visual nature and the high degree of similarity among various activities. Directly fine-tuning the ViT with all parameters proves suboptimal for this application. To address this challenge, we propose a novel approach that employs Low-Rank Adaptation (LoRA) fine-tuning in the weight space to facilitate knowledge transfer from pre-trained ViT models. Additionally, to extract fine-grained features, we enhance feature representation through the integration of a serial-parallel adapter in the feature space. Our innovative joint fine-tuning method, tailored for radar-based Time-Doppler signatures, significantly improves HAR accuracy, surpassing existing state-of-the-art methodologies in this domain. Our code is released at https://github.com/wangyijunlyy/SelaFD.
Authors: Heba El-Shimy, Hind Zantout, Michael A. Lones, Neamat El Gayar
Abstract: Deep learning techniques are increasingly being adopted in diagnostic medical imaging. However, the limited availability of high-quality, large-scale medical datasets presents a significant challenge, often necessitating the use of transfer learning approaches. This study investigates self-supervised learning methods for pre-training capsule networks in polyp diagnostics for colon cancer. We used the PICCOLO dataset, comprising 3,433 samples, which exemplifies typical challenges in medical datasets: small size, class imbalance, and distribution shifts between data splits. Capsule networks offer inherent interpretability due to their architecture and inter-layer information routing mechanism. However, their limited native implementation in mainstream deep learning frameworks and the lack of pre-trained versions pose a significant challenge. This is particularly true if aiming to train them on small medical datasets, where leveraging pre-trained weights as initial parameters would be beneficial. We explored two auxiliary self-supervised learning tasks, colourisation and contrastive learning, for capsule network pre-training. We compared self-supervised pre-trained models against alternative initialisation strategies. Our findings suggest that contrastive learning and in-painting techniques are suitable auxiliary tasks for self-supervised learning in the medical domain. These techniques helped guide the model to capture important visual features that are beneficial for the downstream task of polyp classification, increasing its accuracy by 5.26% compared to other weight initialisation methods.
Authors: Wonjun Lee, Doehyeon Lee, Eugene Choi, Sangyoon Yu, Ashkan Yousefpour, Haon Park, Bumsub Ham, Suhyun Kim
Abstract: Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation methods, but these methods struggle to detect implicit harmful content or produce inaccurate evaluations. Therefore, we found that existing benchmarks have low levels of harmfulness, ambiguous data, and limited diversity in image-text pair combinations. To address these issues, we propose the ELITE {\em benchmark}, a high-quality safety evaluation benchmark for VLMs, underpinned by our enhanced evaluation method, the ELITE {\em evaluator}. The ELITE evaluator explicitly incorporates a toxicity score to accurately assess harmfulness in multimodal contexts, where VLMs often provide specific, convincing, but unharmful descriptions of images. We filter out ambiguous and low-quality image-text pairs from existing benchmarks using the ELITE evaluator and generate diverse combinations of safe and unsafe image-text pairs. Our experiments demonstrate that the ELITE evaluator achieves superior alignment with human evaluations compared to prior automated methods, and the ELITE benchmark offers enhanced benchmark quality and diversity. By introducing ELITE, we pave the way for safer, more robust VLMs, contributing essential tools for evaluating and mitigating safety risks in real-world applications.
Authors: Hanxiao Wang, Biao Zhang, Jonathan Klein, Dominik L. Michels, Dongming Yan, Peter Wonka
Abstract: We propose a transformer architecture and training strategy for tree generation. The architecture processes data at multiple resolutions and has an hourglass shape, with middle layers processing fewer tokens than outer layers. Similar to convolutional networks, we introduce longer range skip connections to completent this multi-resolution approach. The key advantage of this architecture is the faster processing speed and lower memory consumption. We are therefore able to process more complex trees than would be possible with a vanilla transformer architecture. Furthermore, we extend this approach to perform image-to-tree and point-cloud-to-tree conditional generation and to simulate the tree growth processes, generating 4D trees. Empirical results validate our approach in terms of speed, memory consumption, and generation quality.
Authors: Mingxuan Yan, Ruijie Zhang, Xuedou Xiao, Wei Wang
Abstract: While MPEG-standardized video-based point cloud compression (VPCC) achieves high compression efficiency for human perception, it struggles with a poor trade-off between bitrate savings and detection accuracy when supporting 3D object detectors. This limitation stems from VPCC's inability to prioritize regions of different importance within point clouds. To address this issue, we propose DetVPCC, a novel method integrating region-of-interest (RoI) encoding with VPCC for efficient point cloud sequence compression while preserving the 3D object detection accuracy. Specifically, we augment VPCC to support RoI-based compression by assigning spatially non-uniform quality levels. Then, we introduce a lightweight RoI detector to identify crucial regions that potentially contain objects. Experiments on the nuScenes dataset demonstrate that our approach significantly improves the detection accuracy. The code and demo video are available in supplementary materials.
Authors: Iason Ioannis Panagos, Giorgos Sfikas, Christophoros Nikou
Abstract: Visual speech recognition (VSR), which decodes spoken words from video data, offers significant benefits, particularly when audio is unavailable. However, the high dimensionality of video data leads to prohibitive computational costs that demand powerful hardware, limiting VSR deployment on resource-constrained devices. This work addresses this limitation by developing lightweight VSR architectures. Leveraging efficient operation design paradigms, we create compact yet powerful models with reduced resource requirements and minimal accuracy loss. We train and evaluate our models on a large-scale public dataset for recognition of words from video sequences, demonstrating their effectiveness for practical applications. We also conduct an extensive array of ablative experiments to thoroughly analyze the size and complexity of each model. Code and trained models will be made publicly available.
Authors: Feifei Li, Qi Song, Chi Zhang, Hui Shuai, Rui Huang
Abstract: The task of estimating camera poses can be enhanced through novel view synthesis techniques such as NeRF and Gaussian Splatting to increase the diversity and extension of training data. However, these techniques often produce rendered images with issues like blurring and ghosting, which compromise their reliability. These issues become particularly pronounced for Scene Coordinate Regression (SCR) methods, which estimate 3D coordinates at the pixel level. To mitigate the problems associated with unreliable rendered images, we introduce a novel filtering approach, which selectively extracts well-rendered pixels while discarding the inferior ones. This filter simultaneously measures the SCR model's real-time reprojection loss and gradient during training. Building on this filtering technique, we also develop a new strategy to improve scene coordinate regression using sparse inputs, drawing on successful applications of sparse input techniques in novel view synthesis. Our experimental results validate the effectiveness of our method, demonstrating state-of-the-art performance on indoor and outdoor datasets.
Authors: Qijun Gan, Yi Ren, Chen Zhang, Zhenhui Ye, Pan Xie, Xiang Yin, Zehuan Yuan, Bingyue Peng, Jianke Zhu
Abstract: Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also rely on fixed resolution and struggle to maintain visual consistency. To address these limitations, we propose HumanDiT, a pose-guided Diffusion Transformer (DiT)-based framework trained on a large and wild dataset containing 14,000 hours of high-quality video to produce high-fidelity videos with fine-grained body rendering. Specifically, (i) HumanDiT, built on DiT, supports numerous video resolutions and variable sequence lengths, facilitating learning for long-sequence video generation; (ii) we introduce a prefix-latent reference strategy to maintain personalized characteristics across extended sequences. Furthermore, during inference, HumanDiT leverages Keypoint-DiT to generate subsequent pose sequences, facilitating video continuation from static images or existing videos. It also utilizes a Pose Adapter to enable pose transfer with given sequences. Extensive experiments demonstrate its superior performance in generating long-form, pose-accurate videos across diverse scenarios.
Authors: Ran Sandhaus, Yosi Keller
Abstract: This work introduces a novel deep-learning approach for estimating age from a single facial image by refining an initial age estimate. The refinement leverages a reference face database of individuals with similar ages and appearances. We employ a network that estimates age differences between an input image and reference images with known ages, thus refining the initial estimate. Our method explicitly models age-dependent facial variations using differential regression, yielding improved accuracy compared to conventional absolute age estimation. Additionally, we introduce an age augmentation scheme that iteratively refines initial age estimates by modeling their error distribution during training. This iterative approach further enhances the initial estimates. Our approach surpasses existing methods, achieving state-of-the-art accuracy on the MORPH II and CACD datasets. Furthermore, we examine the biases inherent in contemporary state-of-the-art age estimation techniques.
Authors: Xiao Yu, Yan Fang, Yao Zhao, Yunchao Wei
Abstract: Class incremental learning aims to enable models to learn from sequential, non-stationary data streams across different tasks without catastrophic forgetting. In class incremental semantic segmentation (CISS), the semantic content of image pixels evolves over incremental phases, known as semantic drift. In this work, we identify two critical challenges in CISS that contribute to semantic drift and degrade performance. First, we highlight the issue of separate optimization, where different parts of the model are optimized in distinct incremental stages, leading to misaligned probability scales. Second, we identify noisy semantics arising from inappropriate pseudo-labeling, which results in sub-optimal results. To address these challenges, we propose a novel and effective approach, Image Posterior and Semantics Decoupling for Segmentation (IPSeg). IPSeg introduces two key mechanisms: (1) leveraging image posterior probabilities to align optimization across stages and mitigate the effects of separate optimization, and (2) employing semantics decoupling to handle noisy semantics and tailor learning strategies for different semantics. Extensive experiments on the Pascal VOC 2012 and ADE20K datasets demonstrate that IPSeg achieves superior performance compared to state-of-the-art methods, particularly in challenging long-term incremental scenarios.
Authors: Shoufa Chen, Chongjian Ge, Yuqi Zhang, Yida Zhang, Fengda Zhu, Hao Yang, Hongxiang Hao, Hui Wu, Zhichao Lai, Yifei Hu, Ting-Che Lin, Shilong Zhang, Fu Li, Chuan Li, Xing Wang, Yanghua Peng, Peize Sun, Ping Luo, Yi Jiang, Zehuan Yuan, Bingyue Peng, Xiaobing Liu
Abstract: This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We detail the foundational elements enabling high-quality visual generation, including the data curation pipeline, model architecture design, flow formulation, and advanced infrastructure for efficient and robust large-scale training. The Goku models demonstrate superior performance in both qualitative and quantitative evaluations, setting new benchmarks across major tasks. Specifically, Goku achieves 0.76 on GenEval and 83.65 on DPG-Bench for text-to-image generation, and 84.85 on VBench for text-to-video tasks. We believe that this work provides valuable insights and practical advancements for the research community in developing joint image-and-video generation models.
Authors: Xiandong Zou, Mingzhu Shen, Christos-Savvas Bouganis, Yiren Zhao
Abstract: Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and styles, in multi-concept image generation. However, current approaches face significant challenges when composing these LoRAs for multi-concept image generation, resulting in diminished generated image quality. In this paper, we initially investigate the role of LoRAs in the denoising process through the lens of the Fourier frequency domain. Based on the hypothesis that applying multiple LoRAs could lead to "semantic conflicts", we find that certain LoRAs amplify high-frequency features such as edges and textures, whereas others mainly focus on low-frequency elements, including the overall structure and smooth color gradients. Building on these insights, we devise a frequency domain based sequencing strategy to determine the optimal order in which LoRAs should be integrated during inference. This strategy offers a methodical and generalizable solution compared to the naive integration commonly found in existing LoRA fusion techniques. To fully leverage our proposed LoRA order sequence determination method in multi-LoRA composition tasks, we introduce a novel, training-free framework, Cached Multi-LoRA (CMLoRA), designed to efficiently integrate multiple LoRAs while maintaining cohesive image generation. With its flexible backbone for multi-LoRA fusion and a non-uniform caching strategy tailored to individual LoRAs, CMLoRA has the potential to reduce semantic conflicts in LoRA composition and improve computational efficiency. Our experimental evaluations demonstrate that CMLoRA outperforms state-of-the-art training-free LoRA fusion methods by a significant margin -- it achieves an average improvement of $2.19\%$ in CLIPScore, and $11.25\%$ in MLLM win rate compared to LoraHub, LoRA Composite, and LoRA Switch.
Authors: Craig Myles, In Hwa Um, Craig Marshall, David Harris-Birtill, David J. Harrison
Abstract: $\textbf{Background}$: Cancer remains one of the leading causes of morbidity and mortality worldwide. Comprehensive datasets that combine histopathological images with genetic and survival data across various tumour sites are essential for advancing computational pathology and personalised medicine. $\textbf{Results}$: We present SurGen, a dataset comprising 1,020 H&E-stained whole slide images (WSIs) from 843 colorectal cancer cases. The dataset includes detailed annotations for key genetic mutations (KRAS, NRAS, BRAF) and mismatch repair status, as well as survival data for 426 cases. To demonstrate SurGen's practical utility, we conducted a proof-of-concept machine learning experiment predicting mismatch repair status from the WSIs, achieving a test AUROC of 0.8316. These preliminary results underscore the dataset's potential to facilitate research in biomarker discovery, prognostic modelling, and advanced machine learning applications in colorectal cancer. $\textbf{Conclusions}$: SurGen offers a valuable resource for the scientific community, enabling studies that require high-quality WSIs linked with comprehensive clinical and genetic information on colorectal cancer. Our initial findings affirm the dataset's capacity to advance diagnostic precision and foster the development of personalised treatment strategies in colorectal oncology. Data available online at https://doi.org/10.6019/S-BIAD1285.
Authors: Ond\v{r}ej T\'ybl, Luk\'a\v{s} Neumann
Abstract: Deep learning has revolutionized computer vision, but it achieved its tremendous success using deep network architectures which are mostly hand-crafted and therefore likely suboptimal. Neural Architecture Search (NAS) aims to bridge this gap by following a well-defined optimization paradigm which systematically looks for the best architecture, given objective criterion such as maximal classification accuracy. The main limitation of NAS is however its astronomical computational cost, as it typically requires training each candidate network architecture from scratch. In this paper, we aim to alleviate this limitation by proposing a novel training-free proxy for image classification accuracy based on Fisher Information. The proposed proxy has a strong theoretical background in statistics and it allows estimating expected image classification accuracy of a given deep network without training the network, thus significantly reducing computational cost of standard NAS algorithms. Our training-free proxy achieves state-of-the-art results on three public datasets and in two search spaces, both when evaluated using previously proposed metrics, as well as using a new metric that we propose which we demonstrate is more informative for practical NAS applications. The source code is publicly available at http://www.github.com/ondratybl/VKDNW
Authors: Xiaoyu Zhou, Jingqi Wang, Yongtao Wang, Yufei Wei, Nan Dong, Ming-Hsuan Yang
Abstract: Obtaining semantic 3D occupancy from raw sensor data without manual annotations remains an essential yet challenging task. While prior works have approached this as a perception prediction problem, we formulate it as scene-aware 3D occupancy reconstruction with geometry and semantics. In this work, we propose OccGS, a novel 3D Occupancy reconstruction framework utilizing Semantic and Geometric-Aware Gaussian Splatting in a zero-shot manner. Leveraging semantics extracted from vision-language models and geometry guided by LiDAR points, OccGS constructs Semantic and Geometric-Aware Gaussians from raw multisensor data. We also develop a cumulative Gaussian-to-3D voxel splatting method for reconstructing occupancy from the Gaussians. OccGS performs favorably against self-supervised methods in occupancy prediction, achieving comparable performance to fully supervised approaches and achieving state-of-the-art performance on zero-shot semantic 3D occupancy estimation.
Authors: Zhuojie Wu, Yanbin Liu, Xin Shen, Xiaofeng Cao, Xin Yu
Abstract: Dataset distillation compresses a large dataset into a small synthetic subset that retains essential information. Existing methods assume that all samples are perfectly labeled, limiting their real-world applications where incorrect labels are ubiquitous. These mislabeled samples introduce untrustworthy information into the dataset, which misleads model optimization in dataset distillation. To tackle this issue, we propose a Trust-Aware Diversion (TAD) dataset distillation method. Our proposed TAD introduces an iterative dual-loop optimization framework for data-effective distillation. Specifically, the outer loop divides data into trusted and untrusted spaces, redirecting distillation toward trusted samples to guarantee trust in the distillation process. This step minimizes the impact of mislabeled samples on dataset distillation. The inner loop maximizes the distillation objective by recalibrating untrusted samples, thus transforming them into valuable ones for distillation. This dual-loop iteratively refines and compensates for each other, gradually expanding the trusted space and shrinking the untrusted space. Experiments demonstrate that our method can significantly improve the performance of existing dataset distillation methods on three widely used benchmarks (CIFAR10, CIFAR100, and Tiny ImageNet) in three challenging mislabeled settings (symmetric, asymmetric, and real-world).
Authors: Yuqin Dai, Zhouheng Yao, Chunfeng Song, Qihao Zheng, Weijian Mai, Kunyu Peng, Shuai Lu, Wanli Ouyang, Jian Yang, Jiamin Wu
Abstract: Brain decoding aims to reconstruct visual perception of human subject from fMRI signals, which is crucial for understanding brain's perception mechanisms. Existing methods are confined to the single-subject paradigm due to substantial brain variability, which leads to weak generalization across individuals and incurs high training costs, exacerbated by limited availability of fMRI data. To address these challenges, we propose MindAligner, an explicit functional alignment framework for cross-subject brain decoding from limited fMRI data. The proposed MindAligner enjoys several merits. First, we learn a Brain Transfer Matrix (BTM) that projects the brain signals of an arbitrary new subject to one of the known subjects, enabling seamless use of pre-trained decoding models. Second, to facilitate reliable BTM learning, a Brain Functional Alignment module is proposed to perform soft cross-subject brain alignment under different visual stimuli with a multi-level brain alignment loss, uncovering fine-grained functional correspondences with high interpretability. Experiments indicate that MindAligner not only outperforms existing methods in visual decoding under data-limited conditions, but also provides valuable neuroscience insights in cross-subject functional analysis. The code will be made publicly available.
Authors: Loick Chambon, Eloi Zablocki, Alexandre Boulch, Mickael Chen, Matthieu Cord
Abstract: Understanding the 3D geometry and semantics of driving scenes is critical for developing of safe autonomous vehicles. While 3D occupancy models are typically trained using voxel-based supervision with standard losses (e.g., cross-entropy, Lovasz, dice), these approaches treat voxel predictions independently, neglecting their spatial relationships. In this paper, we propose GaussRender, a plug-and-play 3D-to-2D reprojection loss that enhances voxel-based supervision. Our method projects 3D voxel representations into arbitrary 2D perspectives and leverages Gaussian splatting as an efficient, differentiable rendering proxy of voxels, introducing spatial dependencies across projected elements. This approach improves semantic and geometric consistency, handles occlusions more efficiently, and requires no architectural modifications. Extensive experiments on multiple benchmarks (SurroundOcc-nuScenes, Occ3D-nuScenes, SSCBench-KITTI360) demonstrate consistent performance gains across various 3D occupancy models (TPVFormer, SurroundOcc, Symphonies), highlighting the robustness and versatility of our framework. The code is available at https://github.com/valeoai/GaussRender.
Authors: Gawoon Ban, Hyeongjun Kim, Seokjun Choi, Seungwoo Yoon, Seung-Hwan Baek
Abstract: Display photometric stereo uses a display as a programmable light source to illuminate a scene with diverse illumination conditions. Recently, differentiable display photometric stereo (DDPS) demonstrated improved normal reconstruction accuracy by using learned display patterns. However, DDPS faced limitations in practicality, requiring a fixed desktop imaging setup using a polarization camera and a desktop-scale monitor. In this paper, we propose a more practical physics-based photometric stereo, differentiable mobile display photometric stereo (DMDPS), that leverages a mobile phone consisting of a display and a camera. We overcome the limitations of using a mobile device by developing a mobile app and method that simultaneously displays patterns and captures high-quality HDR images. Using this technique, we capture real-world 3D-printed objects and learn display patterns via a differentiable learning process. We demonstrate the effectiveness of DMDPS on both a 3D printed dataset and a first dataset of fallen leaves. The leaf dataset contains reconstructed surface normals and albedos of fallen leaves that may enable future research beyond computer graphics and vision. We believe that DMDPS takes a step forward for practical physics-based photometric stereo.
Authors: Aditya Kumar, Tom Blanchard, Adam Dziedzic, Franziska Boenisch
Abstract: State-of-the-art visual generation models, such as Diffusion Models (DMs) and Vision Auto-Regressive Models (VARs), produce highly realistic images. While prior work has successfully mitigated Not Safe For Work (NSFW) content in the visual domain, we identify a novel threat: the generation of NSFW text embedded within images. This includes offensive language, such as insults, racial slurs, and sexually explicit terms, posing significant risks to users. We show that all state-of-the-art DMs (e.g., SD3, Flux, DeepFloyd IF) and VARs (e.g., Infinity) are vulnerable to this issue. Through extensive experiments, we demonstrate that existing mitigation techniques, effective for visual content, fail to prevent harmful text generation while substantially degrading benign text generation. As an initial step toward addressing this threat, we explore safety fine-tuning of the text encoder underlying major DM architectures using a customized dataset. Thereby, we suppress NSFW generation while preserving overall image and text generation quality. Finally, to advance research in this area, we introduce ToxicBench, an open-source benchmark for evaluating NSFW text generation in images. ToxicBench provides a curated dataset of harmful prompts, new metrics, and an evaluation pipeline assessing both NSFW-ness and generation quality. Our benchmark aims to guide future efforts in mitigating NSFW text generation in text-to-image models and is available at https://github.com/sprintml/ToxicBench
Authors: Gorkem Can Ates, Kuang Gong, Wei Shao
Abstract: Vision-language models (VLMs) align visual and textual representations, enabling high-performance zero-shot classification and image-text retrieval in 2D medical imaging. However, extending VLMs to 3D medical imaging remains computationally challenging. Existing 3D VLMs rely on Vision Transformers (ViTs), which are computationally expensive due to self-attention's quadratic complexity, or 3D convolutions, which demand excessive parameters and FLOPs as kernel size increases. We introduce DCFormer, an efficient 3D medical image encoder that factorizes 3D convolutions into three parallel 1D convolutions along depth, height, and width. This design preserves spatial information while significantly reducing computational cost. Integrated into a CLIP-based vision-language framework, DCFormer is evaluated on CT-RATE, a dataset of 50,188 paired 3D chest CT volumes and radiology reports, for zero-shot multi-abnormality detection across 18 pathologies. Compared to ViT, ConvNeXt, PoolFormer, and TransUNet, DCFormer achieves superior efficiency and accuracy, with DCFormer-Tiny reaching 62.0% accuracy and a 46.3% F1-score while using significantly fewer parameters. These results highlight DCFormer's potential for scalable, clinically deployable 3D medical VLMs. Our codes will be publicly available.
Authors: Rohit Saxena, Aryo Pradipta Gema, Pasquale Minervini
Abstract: Understanding time from visual representations is a fundamental cognitive skill, yet it remains a challenge for multimodal large language models (MLLMs). In this work, we investigate the capabilities of MLLMs in interpreting time and date through analogue clocks and yearly calendars. To facilitate this, we curated a structured dataset comprising two subsets: 1) $\textit{ClockQA}$, which comprises various types of clock styles$-$standard, black-dial, no-second-hand, Roman numeral, and arrow-hand clocks$-$paired with time related questions; and 2) $\textit{CalendarQA}$, which consists of yearly calendar images with questions ranging from commonly known dates (e.g., Christmas, New Year's Day) to computationally derived ones (e.g., the 100th or 153rd day of the year). We aim to analyse how MLLMs can perform visual recognition, numerical reasoning, and temporal inference when presented with time-related visual data. Our evaluations show that despite recent advancements, reliably understanding time remains a significant challenge for MLLMs.
Authors: Jasper M. Everink, Bernardin Tamo Amougou, Marcelo Pereyra
Abstract: Most image restoration problems are ill-conditioned or ill-posed and hence involve significant uncertainty. Quantifying this uncertainty is crucial for reliably interpreting experimental results, particularly when reconstructed images inform critical decisions and science. However, most existing image restoration methods either fail to quantify uncertainty or provide estimates that are highly inaccurate. Conformal prediction has recently emerged as a flexible framework to equip any estimator with uncertainty quantification capabilities that, by construction, have nearly exact marginal coverage. To achieve this, conformal prediction relies on abundant ground truth data for calibration. However, in image restoration problems, reliable ground truth data is often expensive or not possible to acquire. Also, reliance on ground truth data can introduce large biases in situations of distribution shift between calibration and deployment. This paper seeks to develop a more robust approach to conformal prediction for image restoration problems by proposing a self-supervised conformal prediction method that leverages Stein's Unbiased Risk Estimator (SURE) to self-calibrate itself directly from the observed noisy measurements, bypassing the need for ground truth. The method is suitable for any linear imaging inverse problem that is ill-conditioned, and it is especially powerful when used with modern self-supervised image restoration techniques that can also be trained directly from measurement data. The proposed approach is demonstrated through numerical experiments on image denoising and deblurring, where it delivers results that are remarkably accurate and comparable to those obtained by supervised conformal prediction with ground truth data.
Authors: Kai Van Brunt, Justin Kay, Timm Haucke, Pietro Perona, Grant Van Horn, Sara Beery
Abstract: Accurate estimates of salmon escapement - the number of fish migrating upstream to spawn - are key data for conservation and fishery management. Existing methods for salmon counting using high-resolution imaging sonar hardware are non-invasive and compatible with computer vision processing. Prior work in this area has utilized object detection and tracking based methods for automated salmon counting. However, these techniques remain inaccessible to many sonar deployment sites due to limited compute and connectivity in the field. We propose an alternative lightweight computer vision method for fish counting based on analyzing echograms - temporal representations that compress several hundred frames of imaging sonar video into a single image. We predict upstream and downstream counts within 200-frame time windows directly from echograms using a ResNet-18 model, and propose a set of domain-specific image augmentations and a weakly-supervised training protocol to further improve results. We achieve a count error of 23% on representative data from the Kenai River in Alaska, demonstrating the feasibility of our approach.
Authors: Zhengjian Kang, Ye Zhang, Xiaoyu Deng, Xintao Li, Yongzhe Zhang
Abstract: This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces learnable spatial relationships between object queries through a relation-aware self-attention mechanism, which adaptively learns to balance different scales of relations (local, medium and global) across decoder layers. This progressive design enables the model to effectively capture evolving spatial dependencies throughout the detection pipeline. Extensive experiments on COCO 2017 dataset demonstrate that our method improves both convergence speed and detection accuracy compared to standard self-attention module. The proposed method achieves competitive results, reaching 52.3\% AP with 12 epochs and 52.5\% AP with 24 epochs using ResNet-50 backbone, and further improving to 58.0\% AP with Swin-L backbone. Furthermore, our analysis reveals an interesting pattern: the model naturally learns to prioritize local spatial relations in early decoder layers while gradually shifting attention to broader contexts in deeper layers, providing valuable insights for future research in object detection.
Authors: Minh-Quan Le, Gaurav Mittal, Tianjian Meng, A S M Iftekhar, Vishwas Suryanarayanan, Barun Patra, Dimitris Samaras, Mei Chen
Abstract: While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i.e. a reference image with accompanying text guidance query. To address this, we introduce Hummingbird, the first diffusion-based image generator which, given a multimodal context, generates highly diverse images w.r.t. the reference image while ensuring high fidelity by accurately preserving scene attributes, such as object interactions and spatial relationships from the text guidance. Hummingbird employs a novel Multimodal Context Evaluator that simultaneously optimizes our formulated Global Semantic and Fine-grained Consistency Rewards to ensure generated images preserve the scene attributes of reference images in relation to the text guidance while maintaining diversity. As the first model to address the task of maintaining both diversity and fidelity given a multimodal context, we introduce a new benchmark formulation incorporating MME Perception and Bongard HOI datasets. Benchmark experiments show Hummingbird outperforms all existing methods by achieving superior fidelity while maintaining diversity, validating Hummingbird's potential as a robust multimodal context-aligned image generator in complex visual tasks.
Authors: Gemma Canet Tarr\'es, Zhe Lin, Zhifei Zhang, He Zhang, Andrew Gilbert, John Collomosse, Soo Ye Kim
Abstract: We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex actions requiring reposing (e.g., hugging, playing guitar). When an interaction implies additional props, like `taking a selfie', our model autonomously generates these supporting objects. By jointly training for compositing and subject-driven generation, also known as customization, we achieve a more balanced integration of textual and visual inputs for text-driven object compositing. As a result, we obtain a versatile model with state-of-the-art performance in both tasks. We further present a data generation pipeline leveraging visual and language models to effortlessly synthesize multimodal, aligned training data.
Authors: Georg B\"okman, David Nordstr\"om, Fredrik Kahl
Abstract: Incorporating geometric invariance into neural networks enhances parameter efficiency but typically increases computational costs. This paper introduces new equivariant neural networks that preserve symmetry while maintaining a comparable number of floating-point operations (FLOPs) per parameter to standard non-equivariant networks. We focus on horizontal mirroring (flopping) invariance, common in many computer vision tasks. The main idea is to parametrize the feature spaces in terms of mirror-symmetric and mirror-antisymmetric features, i.e., irreps of the flopping group. This decomposes the linear layers to be block-diagonal, requiring half the number of FLOPs. Our approach reduces both FLOPs and wall-clock time, providing a practical solution for efficient, scalable symmetry-aware architectures.
Authors: Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Jian Tong, Haodong Duan, Qipeng Guo, Jiaqi Wang, Xipeng Qiu, Dahua Lin
Abstract: While Rotary Position Embedding (RoPE) and its variants are widely adopted for their long-context capabilities, the extension of the 1D RoPE to video, with its complex spatio-temporal structure, remains an open challenge. This work first introduces a comprehensive analysis that identifies four key characteristics essential for the effective adaptation of RoPE to video, which have not been fully considered in prior work. As part of our analysis, we introduce a challenging V-NIAH-D (Visual Needle-In-A-Haystack with Distractors) task, which adds periodic distractors into V-NIAH. The V-NIAH-D task demonstrates that previous RoPE variants, lacking appropriate temporal dimension allocation, are easily misled by distractors. Based on our analysis, we introduce \textbf{VideoRoPE}, with a \textit{3D structure} designed to preserve spatio-temporal relationships. VideoRoPE features \textit{low-frequency temporal allocation} to mitigate periodic oscillations, a \textit{diagonal layout} to maintain spatial symmetry, and \textit{adjustable temporal spacing} to decouple temporal and spatial indexing. VideoRoPE consistently surpasses previous RoPE variants, across diverse downstream tasks such as long video retrieval, video understanding, and video hallucination. Our code will be available at \href{https://github.com/Wiselnn570/VideoRoPE}{https://github.com/Wiselnn570/VideoRoPE}.
URLs: https://github.com/Wiselnn570/VideoRoPE, https://github.com/Wiselnn570/VideoRoPE
Authors: Ethan Weber, Norman M\"uller, Yash Kant, Vasu Agrawal, Michael Zollh\"ofer, Angjoo Kanazawa, Christian Richardt
Abstract: We present Fillerbuster, a method that completes unknown regions of a 3D scene by utilizing a novel large-scale multi-view latent diffusion transformer. Casual captures are often sparse and miss surrounding content behind objects or above the scene. Existing methods are not suitable for handling this challenge as they focus on making the known pixels look good with sparse-view priors, or on creating the missing sides of objects from just one or two photos. In reality, we often have hundreds of input frames and want to complete areas that are missing and unobserved from the input frames. Additionally, the images often do not have known camera parameters. Our solution is to train a generative model that can consume a large context of input frames while generating unknown target views and recovering image poses when desired. We show results where we complete partial captures on two existing datasets. We also present an uncalibrated scene completion task where our unified model predicts both poses and creates new content. Our model is the first to predict many images and poses together for scene completion.
Authors: Chung-Ho Wu, Yang-Jung Chen, Ying-Huan Chen, Jie-Ying Lee, Bo-Hsu Ke, Chun-Wei Tuan Mu, Yi-Chuan Huang, Chin-Yang Lin, Min-Hung Chen, Yen-Yu Lin, Yu-Lun Liu
Abstract: Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometric accuracy in 360{\deg} unbounded scenes. We present AuraFusion360, a novel reference-based method that enables high-quality object removal and hole filling in 3D scenes represented by Gaussian Splatting. Our approach introduces (1) depth-aware unseen mask generation for accurate occlusion identification, (2) Adaptive Guided Depth Diffusion, a zero-shot method for accurate initial point placement without requiring additional training, and (3) SDEdit-based detail enhancement for multi-view coherence. We also introduce 360-USID, the first comprehensive dataset for 360{\deg} unbounded scene inpainting with ground truth. Extensive experiments demonstrate that AuraFusion360 significantly outperforms existing methods, achieving superior perceptual quality while maintaining geometric accuracy across dramatic viewpoint changes. See our project page for video results and the dataset at https://kkennethwu.github.io/aurafusion360/.
Authors: Yunhang Shen, Chaoyou Fu, Shaoqi Dong, Xiong Wang, Peixian Chen, Mengdan Zhang, Haoyu Cao, Ke Li, Xiawu Zheng, Yan Zhang, Yiyi Zhou, Rongrong Ji, Xing Sun
Abstract: Establishing the long-context capability of large vision-language models is crucial for video understanding, high-resolution image understanding, multi-modal agents and reasoning. We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M tokens while delivering advanced performances on short-context multi-modal tasks. We propose an effective multi-modal training schema that starts with large language models and proceeds through vision-language alignment, general knowledge learning, and two sequential stages of long-sequence fine-tuning. We further implement context-parallelism distributed inference and logits-masked language modeling head to scale Long-VITA to infinitely long inputs of images and texts during model inference. Regarding training data, Long-VITA is built on a mix of $17$M samples from public datasets only and demonstrates the state-of-the-art performance on various multi-modal benchmarks, compared against recent cutting-edge models with internal data. Long-VITA is fully reproducible and supports both NPU and GPU platforms for training and testing. We hope Long-VITA can serve as a competitive baseline and offer valuable insights for the open-source community in advancing long-context multi-modal understanding.
Authors: Yue Zhao, Fuzhao Xue, Scott Reed, Linxi Fan, Yuke Zhu, Jan Kautz, Zhiding Yu, Philipp Kr\"ahenb\"uhl, De-An Huang
Abstract: We introduce Quantized Language-Image Pretraining (QLIP), a visual tokenization method that combines state-of-the-art reconstruction quality with state-of-the-art zero-shot image understanding. QLIP trains a binary-spherical-quantization-based autoencoder with reconstruction and language-image alignment objectives. We are the first to show that the two objectives do not need to be at odds. We balance the two loss terms dynamically during training and show that a two-stage training pipeline effectively mixes the large-batch requirements of image-language pre-training with the memory bottleneck imposed by the reconstruction objective. We validate the effectiveness of QLIP for multimodal understanding and text-conditioned image generation with a single model. Specifically, QLIP serves as a drop-in replacement for the visual encoder for LLaVA and the image tokenizer for LlamaGen with comparable or even better performance. Finally, we demonstrate that QLIP enables a unified mixed-modality auto-regressive model for understanding and generation.
Authors: Shilong Zhang, Wenbo Li, Shoufa Chen, Chongjian Ge, Peize Sun, Yida Zhang, Yi Jiang, Zehuan Yuan, Binyue Peng, Ping Luo
Abstract: DiT diffusion models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale. High content and motion fidelity aligned with text prompts, however, often require large model parameters and a substantial number of function evaluations (NFEs). Realistic and visually appealing details are typically reflected in high resolution outputs, further amplifying computational demands especially for single stage DiT models. To address these challenges, we propose a novel two stage framework, FlashVideo, which strategically allocates model capacity and NFEs across stages to balance generation fidelity and quality. In the first stage, prompt fidelity is prioritized through a low resolution generation process utilizing large parameters and sufficient NFEs to enhance computational efficiency. The second stage establishes flow matching between low and high resolutions, effectively generating fine details with minimal NFEs. Quantitative and visual results demonstrate that FlashVideo achieves state-of-the-art high resolution video generation with superior computational efficiency. Additionally, the two-stage design enables users to preview the initial output before committing to full resolution generation, thereby significantly reducing computational costs and wait times as well as enhancing commercial viability .
Authors: Afshin Khadangi, Amir Sartipi, Igor Tchappi, Gilbert Fridgen
Abstract: Art, as a universal language, can be interpreted in diverse ways, with artworks embodying profound meanings and nuances. The advent of Large Language Models (LLMs) and the availability of Multimodal Large Language Models (MLLMs) raise the question of how these transformative models can be used to assess and interpret the artistic elements of artworks. While research has been conducted in this domain, to the best of our knowledge, a deep and detailed understanding of the technical and expressive features of artworks using LLMs has not been explored. In this study, we investigate the automation of a formal art analysis framework to analyze a high-throughput number of artworks rapidly and examine how their patterns evolve over time. We explore how LLMs can decode artistic expressions, visual elements, composition, and techniques, revealing emerging patterns that develop across periods. Finally, we discuss the strengths and limitations of LLMs in this context, emphasizing their ability to process vast quantities of art-related data and generate insightful interpretations. Due to the exhaustive and granular nature of the results, we have developed interactive data visualizations, available online https://cognartive.github.io/, to enhance understanding and accessibility.
Authors: Akshar Tumu, Parisa Kordjamshidi
Abstract: Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works use image captioning tasks and visual question answering. In this work, we propose using the Referring Expression Comprehension task instead as a platform for the evaluation of spatial reasoning by VLMs. This platform provides the opportunity for a deeper analysis of spatial comprehension and grounding abilities when there is 1) ambiguity in object detection, 2) complex spatial expressions with a longer sentence structure and multiple spatial relations, and 3) expressions with negation ('not'). In our analysis, we use task-specific architectures as well as large VLMs and highlight their strengths and weaknesses in dealing with these specific situations. While all these models face challenges with the task at hand, the relative behaviors depend on the underlying models and the specific categories of spatial semantics (topological, directional, proximal, etc.). Our results highlight these challenges and behaviors and provide insight into research gaps and future directions.
Authors: Kiran Sharma, Ziya Uddin, Adarsh Wadal, Dhruv Gupta
Abstract: Medical image classification is a vital research area that utilizes advanced computational techniques to improve disease diagnosis and treatment planning. Deep learning models, especially Convolutional Neural Networks (CNNs), have transformed this field by providing automated and precise analysis of complex medical images. This study introduces a hybrid deep learning model that integrates a pre-trained ResNet101 with a custom CNN to classify kidney CT images into four categories: normal, stone, cyst, and tumor. The proposed model leverages feature fusion to enhance classification accuracy, achieving 99.73% training accuracy and 100% testing accuracy. Using a dataset of 12,446 CT images and advanced feature mapping techniques, the hybrid CNN model outperforms standalone ResNet101. This architecture delivers a robust and efficient solution for automated kidney disease diagnosis, providing improved precision, recall, and reduced testing time, making it highly suitable for clinical applications.
Authors: Viktor Rogowski, Lars E Olsson, Jonas Scherman, Emilia Persson, Mustafa Kadhim, Sacha af Wetterstedt, Adalsteinn Gunnlaugsson, Martin P. Nilsson, Nandor Vass, Mathieu Moreau, Maria Gebre Medhin, Sven B\"ack, Per Munck af Rosensch\"old, Silke Engelholm, Christian Jamtheim Gustafsson
Abstract: Radiotherapy treatment for prostate cancer relies on computed tomography (CT) and/or magnetic resonance imaging (MRI) for segmentation of target volumes and organs at risk (OARs). Manual segmentation of these volumes is regarded as the gold standard for ground truth in machine learning applications but to acquire such data is tedious and time-consuming. A publicly available clinical dataset is presented, comprising MRI- and synthetic CT (sCT) images, target and OARs segmentations, and radiotherapy dose distributions for 432 prostate cancer patients treated with MRI-guided radiotherapy. An extended dataset with 35 patients is also included, with the addition of deep learning (DL)-generated segmentations, DL segmentation uncertainty maps, and DL segmentations manually adjusted by four radiation oncologists. The publication of these resources aims to aid research within the fields of automated radiotherapy treatment planning, segmentation, inter-observer analyses, and DL model uncertainty investigation. The dataset is hosted on the AIDA Data Hub and offers a free-to-use resource for the scientific community, valuable for the advancement of medical imaging and prostate cancer radiotherapy research.
Authors: Valiyeh A. Nezhad, Gokberk Elmas, Bilal Kabas, Fuat Arslan, Tolga \c{C}ukur
Abstract: Although learning-based models hold great promise for MRI reconstruction, single-site models built on limited local datasets often suffer from poor generalization. This challenge has spurred interest in collaborative model training on multi-site datasets via federated learning (FL) -- a privacy-preserving framework that aggregates model updates instead of sharing imaging data. Conventional FL builds a global model by aggregating locally trained model weights, inherently constraining all sites to a homogeneous model architecture. This rigid homogeneity requirement forces sites to forgo architectures tailored to their compute infrastructure and application-specific demands. Consequently, existing FL methods for MRI reconstruction fail to support model-heterogeneous settings, where individual sites are allowed to use distinct architectures. To overcome this fundamental limitation, here we introduce FedGAT, a novel model-agnostic FL technique based on generative autoregressive transformers. FedGAT decentralizes the training of a global generative prior that captures the distribution of multi-site MR images. For enhanced fidelity, we propose a novel site-prompted GAT prior that controllably synthesizes MR images from desired sites via autoregressive prediction across spatial scales. Each site then trains its site-specific reconstruction model -- using its preferred architecture -- on a hybrid dataset comprising the local MRI dataset and GAT-generated synthetic MRI datasets for other sites. Comprehensive experiments on multi-institutional datasets demonstrate that FedGAT supports flexible collaborations while enjoying superior within-site and across-site reconstruction performance compared to state-of-the-art FL baselines.
Authors: Artughrul Gayibov (Baku Engineering University)
Abstract: Efficient use of cultivated areas is a necessary factor for sustainable development of agriculture and ensuring food security. Along with the rapid development of satellite technologies in developed countries, new methods are being searched for accurate and operational identification of cultivated areas. In this context, identification of cropland boundaries based on spectral analysis of data obtained from satellite images is considered one of the most optimal and accurate methods in modern agriculture. This article proposes a new approach to determine the suitability and green index of cultivated areas using satellite data obtained through the "Google Earth Engine" (GEE) platform. In this approach, two powerful algorithms, "SNIC (Simple Non-Iterative Clustering) Super Pixels" and "Canny Edge Detection Method", are combined. The SNIC algorithm combines pixels in a satellite image into larger regions (super pixels) with similar characteristics, thereby providing better image analysis. The Canny Edge Detection Method detects sharp changes (edges) in the image to determine the precise boundaries of agricultural fields. This study, carried out using high-resolution multispectral data from the Sentinel-2 satellite and the Google Earth Engine JavaScript API, has shown that the proposed method is effective in accurately and reliably classifying randomly selected agricultural fields. The combined use of these two tools allows for more accurate determination of the boundaries of agricultural fields by minimizing the effects of outliers in satellite images. As a result, more accurate and reliable maps can be created for agricultural monitoring and resource management over large areas based on the obtained data. By expanding the application capabilities of cloud-based platforms and artificial intelligence methods in the agricultural field.
Authors: Yuchi Zhao, Miroslav Bogdanovic, Chengyuan Luo, Steven Tohme, Kourosh Darvish, Al\'an Aspuru-Guzik, Florian Shkurti, Animesh Garg
Abstract: Object placement in robotic tasks is inherently challenging due to the diversity of object geometries and placement configurations. To address this, we propose AnyPlace, a two-stage method trained entirely on synthetic data, capable of predicting a wide range of feasible placement poses for real-world tasks. Our key insight is that by leveraging a Vision-Language Model (VLM) to identify rough placement locations, we focus only on the relevant regions for local placement, which enables us to train the low-level placement-pose-prediction model to capture diverse placements efficiently. For training, we generate a fully synthetic dataset of randomly generated objects in different placement configurations (insertion, stacking, hanging) and train local placement-prediction models. We conduct extensive evaluations in simulation, demonstrating that our method outperforms baselines in terms of success rate, coverage of possible placement modes, and precision. In real-world experiments, we show how our approach directly transfers models trained purely on synthetic data to the real world, where it successfully performs placements in scenarios where other models struggle -- such as with varying object geometries, diverse placement modes, and achieving high precision for fine placement. More at: https://any-place.github.io.
Authors: Haoyu Han, Heng Yang
Abstract: Global bundle adjustment is made easy by depth prediction and convex optimization. We (i) propose a scaled bundle adjustment (SBA) formulation that lifts 2D keypoint measurements to 3D with learned depth, (ii) design an empirically tight convex semidfinite program (SDP) relaxation that solves SBA to certfiable global optimality, (iii) solve the SDP relaxations at extreme scale with Burer-Monteiro factorization and a CUDA-based trust-region Riemannian optimizer (dubbed XM), (iv) build a structure from motion (SfM) pipeline with XM as the optimization engine and show that XM-SfM dominates or compares favorably with existing SfM pipelines in terms of reconstruction quality while being faster, more scalable, and initialization-free.
Authors: Sadia Hussain, Brejesh Lall
Abstract: Hyperspectral imaging (HSI) is a powerful earth observation technology that captures and processes information across a wide spectrum of wavelengths. Hyperspectral imaging provides comprehensive and detailed spectral data that is invaluable for a wide range of reconstruction problems. However due to complexity in analysis it often becomes difficult to handle this data. To address the challenge of handling large number of bands in reconstructing high quality HSI, we propose to form groups of bands. In this position paper we propose a method of selecting diverse bands using determinantal point processes in correlated bands. To address the issue of overlapping bands that may arise from grouping, we use spectral angle mapper analysis. This analysis can be fed to any Machine learning model to enable detailed analysis and monitoring with high precision and accuracy.
Authors: Minrui Chen, Yi Zhou, Huidong Jiang, Yuhan Zhu, Guanjie Zou, Minqi Chen, Rong Tian, Hiroto Saigo
Abstract: Fever of unknown origin FUO remains a diagnostic challenge. MedMimic is introduced as a multimodal framework inspired by real-world diagnostic processes. It uses pretrained models such as DINOv2, Vision Transformer, and ResNet-18 to convert high-dimensional 18F-FDG PET/CT imaging into low-dimensional, semantically meaningful features. A learnable self-attention-based fusion network then integrates these imaging features with clinical data for classification. Using 416 FUO patient cases from Sichuan University West China Hospital from 2017 to 2023, the multimodal fusion classification network MFCN achieved macro-AUROC scores ranging from 0.8654 to 0.9291 across seven tasks, outperforming conventional machine learning and single-modality deep learning methods. Ablation studies and five-fold cross-validation further validated its effectiveness. By combining the strengths of pretrained large models and deep learning, MedMimic offers a promising solution for disease classification.
Authors: Ricardo Coimbra Brioso, Leonardo Crespi, Andrea Seghetto, Damiano Dei, Nicola Lambri, Pietro Mancosu, Marta Scorsetti, Daniele Loiacono
Abstract: A key step in Adaptive Radiation Therapy (ART) workflows is the evaluation of the patient's anatomy at treatment time to ensure the accuracy of the delivery. To this end, Cone Beam Computerized Tomography (CBCT) is widely used being cost-effective and easy to integrate into the treatment process. Nonetheless, CBCT images have lower resolution and more artifacts than CT scans, making them less reliable for precise treatment validation. Moreover, in complex treatments such as Total Marrow and Lymph Node Irradiation (TMLI), where full-body visualization of the patient is critical for accurate dose delivery, the CBCT images are often discontinuous, leaving gaps that could contain relevant anatomical information. To address these limitations, we propose ARTInp (Adaptive Radiation Therapy Inpainting), a novel deep-learning framework combining image inpainting and CBCT-to-CT translation. ARTInp employs a dual-network approach: a completion network that fills anatomical gaps in CBCT volumes and a custom Generative Adversarial Network (GAN) to generate high-quality synthetic CT (sCT) images. We trained ARTInp on a dataset of paired CBCT and CT images from the SynthRad 2023 challenge, and the performance achieved on a test set of 18 patients demonstrates its potential for enhancing CBCT-based workflows in radiotherapy.
Authors: Jie Huang, Rui Huang, Jinghao Xu, Siran Pen, Yule Duan, Liangjian Deng
Abstract: Pansharpening aims to combine a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. Although pansharpening in the frequency domain offers clear advantages, most existing methods either continue to operate solely in the spatial domain or fail to fully exploit the benefits of the frequency domain. To address this issue, we innovatively propose Multi-Frequency Fusion Attention (MFFA), which leverages wavelet transforms to cleanly separate frequencies and enable lossless reconstruction across different frequency domains. Then, we generate Frequency-Query, Spatial-Key, and Fusion-Value based on the physical meanings represented by different features, which enables a more effective capture of specific information in the frequency domain. Additionally, we focus on the preservation of frequency features across different operations. On a broader level, our network employs a wavelet pyramid to progressively fuse information across multiple scales. Compared to previous frequency domain approaches, our network better prevents confusion and loss of different frequency features during the fusion process. Quantitative and qualitative experiments on multiple datasets demonstrate that our method outperforms existing approaches and shows significant generalization capabilities for real-world scenarios.
Authors: Zhuojie Wu, Heming Du, Shuyun Wang, Ming Lu, Haiyang Sun, Yandong Guo, Xin Yu
Abstract: Learned Image Compression (LIC) has explored various architectures, such as Convolutional Neural Networks (CNNs) and transformers, in modeling image content distributions in order to achieve compression effectiveness. However, achieving high rate-distortion performance while maintaining low computational complexity (\ie, parameters, FLOPs, and latency) remains challenging. In this paper, we propose a hybrid Convolution and State Space Models (SSMs) based image compression framework, termed \textit{CMamba}, to achieve superior rate-distortion performance with low computational complexity. Specifically, CMamba introduces two key components: a Content-Adaptive SSM (CA-SSM) module and a Context-Aware Entropy (CAE) module. First, we observed that SSMs excel in modeling overall content but tend to lose high-frequency details. In contrast, CNNs are proficient at capturing local details. Motivated by this, we propose the CA-SSM module that can dynamically fuse global content extracted by SSM blocks and local details captured by CNN blocks in both encoding and decoding stages. As a result, important image content is well preserved during compression. Second, our proposed CAE module is designed to reduce spatial and channel redundancies in latent representations after encoding. Specifically, our CAE leverages SSMs to parameterize the spatial content in latent representations. Benefiting from SSMs, CAE significantly improves spatial compression efficiency while reducing spatial content redundancies. Moreover, along the channel dimension, CAE reduces inter-channel redundancies of latent representations via an autoregressive manner, which can fully exploit prior knowledge from previous channels without sacrificing efficiency. Experimental results demonstrate that CMamba achieves superior rate-distortion performance.
Authors: Chenxing Sun, Yongyang Xu, Xuwei Xu, Xixi Fan, Jing Bai, Xiechun Lu, Zhanlong Chen
Abstract: Multi-scale maps are essential representations of surveying and cartographic results, serving as fundamental components of geographic services. Current image generation networks can quickly produce map tiles from remote-sensing images. However, generative models designed for natural images often focus on texture features, neglecting the unique characteristics of remote-sensing features and the scale attributes of tile maps. This limitation in generative models impairs the accurate representation of geographic information, and the quality of tile map generation still needs improvement. Diffusion models have demonstrated remarkable success in various image generation tasks, highlighting their potential to address this challenge. This paper presents C2GM, a novel framework for generating multi-scale tile maps through conditional guided diffusion and multi-scale cascade generation. Specifically, we implement a conditional feature fusion encoder to extract object priors from remote sensing images and cascade reference double branch input, ensuring an accurate representation of complex features. Low-level generated tiles act as constraints for high-level map generation, enhancing visual continuity. Moreover, we incorporate map scale modality information using CLIP to simulate the relationship between map scale and cartographic generalization in tile maps. Extensive experimental evaluations demonstrate that C2GM consistently achieves the state-of-the-art (SOTA) performance on all metrics, facilitating the rapid and effective generation of multi-scale large-format maps for emergency response and remote mapping applications.
Authors: David \v{C}apek, Jan Hrn\v{c}\'i\v{r}, Tom\'a\v{s} B\'a\v{c}a, Jakub Jirkal, Vojt\v{e}ch Von\'asek, Robert P\v{e}ni\v{c}ka, Martin Saska
Abstract: Robotic simulators play a crucial role in the development and testing of autonomous systems, particularly in the realm of Uncrewed Aerial Vehicles (UAV). However, existing simulators often lack high-level autonomy, hindering their immediate applicability to complex tasks such as autonomous navigation in unknown environments. This limitation stems from the challenge of integrating realistic physics, photorealistic rendering, and diverse sensor modalities into a single simulation environment. At the same time, the existing photorealistic UAV simulators use mostly hand-crafted environments with limited environment sizes, which prevents the testing of long-range missions. This restricts the usage of existing simulators to only low-level tasks such as control and collision avoidance. To this end, we propose the novel FlightForge UAV open-source simulator. FlightForge offers advanced rendering capabilities, diverse control modalities, and, foremost, procedural generation of environments. Moreover, the simulator is already integrated with a fully autonomous UAV system capable of long-range flights in cluttered unknown environments. The key innovation lies in novel procedural environment generation and seamless integration of high-level autonomy into the simulation environment. Experimental results demonstrate superior sensor rendering capability compared to existing simulators, and also the ability of autonomous navigation in almost infinite environments.
Authors: Aravind R. Krishnan, Yihao Liu, Kaiwen Xu, Michael E. Kim, Lucas W. Remedios, Gaurav Rudravaram, Adam M. Saunders, Bradley W. Richmond, Kim L. Sandler, Fabien Maldonado, Bennett A. Landman, Lianrui Zuo
Abstract: Paired inspiratory-expiratory CT scans enable the quantification of gas trapping due to small airway disease and emphysema by analyzing lung tissue motion in COPD patients. Deformable image registration of these scans assesses regional lung volumetric changes. However, variations in reconstruction kernels between paired scans introduce errors in quantitative analysis. This work proposes a two-stage pipeline to harmonize reconstruction kernels and perform deformable image registration using data acquired from the COPDGene study. We use a cycle generative adversarial network (GAN) to harmonize inspiratory scans reconstructed with a hard kernel (BONE) to match expiratory scans reconstructed with a soft kernel (STANDARD). We then deformably register the expiratory scans to inspiratory scans. We validate harmonization by measuring emphysema using a publicly available segmentation algorithm before and after harmonization. Results show harmonization significantly reduces emphysema measurement inconsistencies, decreasing median emphysema scores from 10.479% to 3.039%, with a reference median score of 1.305% from the STANDARD kernel as the target. Registration accuracy is evaluated via Dice overlap between emphysema regions on inspiratory, expiratory, and deformed images. The Dice coefficient between inspiratory emphysema masks and deformably registered emphysema masks increases significantly across registration stages (p<0.001). Additionally, we demonstrate that deformable registration is robust to kernel variations.
Authors: Yusheng Dai, Chenxi Wang, Chang Li, Chen Wang, Jun Du, Kewei Li, Ruoyu Wang, Jiefeng Ma, Lei Sun, Jianqing Gao
Abstract: Previous work on long-form audio generation using global-view diffusion or iterative generation demands significant training or inference costs. While recent advancements in multi-view joint diffusion for panoramic generation provide an efficient option, they struggle with spectrum generation with severe overlap distortions and high cross-view consistency costs. We initially explore this phenomenon through the connectivity inheritance of latent maps and uncover that averaging operations excessively smooth the high-frequency components of the latent map. To address these issues, we propose Swap Forward (SaFa), a frame-level latent swap framework that synchronizes multiple diffusions to produce a globally coherent long audio with more spectrum details in a forward-only manner. At its core, the bidirectional Self-Loop Latent Swap is applied between adjacent views, leveraging stepwise diffusion trajectory to adaptively enhance high-frequency components without disrupting low-frequency components. Furthermore, to ensure cross-view consistency, the unidirectional Reference-Guided Latent Swap is applied between the reference and the non-overlap regions of each subview during the early stages, providing centralized trajectory guidance. Quantitative and qualitative experiments demonstrate that SaFa significantly outperforms existing joint diffusion methods and even training-based long audio generation models. Moreover, we find that it also adapts well to panoramic generation, achieving comparable state-of-the-art performance with greater efficiency and model generalizability. Project page is available at https://swapforward.github.io/.
Authors: Zefan Yang, Xuanang Xu, Jiajin Zhang, Ge Wang, Mannudeep K. Kalra, Pingkun Yan
Abstract: Chest X-ray (CXR) is the most frequently ordered imaging test, supporting diverse clinical tasks from thoracic disease detection to postoperative monitoring. However, task-specific classification models are limited in scope, require costly labeled data, and lack generalizability to out-of-distribution datasets. To address these challenges, we introduce CheXFound, a self-supervised vision foundation model that learns robust CXR representations and generalizes effectively across a wide range of downstream tasks. We pretrain CheXFound on a curated CXR-1M dataset, comprising over one million unique CXRs from publicly available sources. We propose a Global and Local Representations Integration (GLoRI) module for downstream adaptations, by incorporating disease-specific local features with global image features for enhanced performance in multilabel classification. Our experimental results show that CheXFound outperforms state-of-the-art models in classifying 40 disease findings across different prevalence levels on the CXR-LT 24 dataset and exhibits superior label efficiency on downstream tasks with limited training data. Additionally, CheXFound achieved significant improvements on new tasks with out-of-distribution datasets, including opportunistic cardiovascular disease risk estimation and mortality prediction. These results highlight CheXFound's strong generalization capabilities, enabling diverse adaptations with improved label efficiency. The project source code is publicly available at https://github.com/RPIDIAL/CheXFound.
Authors: Steffen Eger, Yong Cao, Jennifer D'Souza, Andreas Geiger, Christian Greisinger, Stephanie Gross, Yufang Hou, Brigitte Krenn, Anne Lauscher, Yizhi Li, Chenghua Lin, Nafise Sadat Moosavi, Wei Zhao, Tristan Miller
Abstract: With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. Recently, a plethora of new AI models and tools has been proposed, promising to empower researchers and academics worldwide to conduct their research more effectively and efficiently. This includes all aspects of the research cycle, especially (1) searching for relevant literature; (2) generating research ideas and conducting experimentation; generating (3) text-based and (4) multimodal content (e.g., scientific figures and diagrams); and (5) AI-based automatic peer review. In this survey, we provide an in-depth overview over these exciting recent developments, which promise to fundamentally alter the scientific research process for good. Our survey covers the five aspects outlined above, indicating relevant datasets, methods and results (including evaluation) as well as limitations and scope for future research. Ethical concerns regarding shortcomings of these tools and potential for misuse (fake science, plagiarism, harms to research integrity) take a particularly prominent place in our discussion. We hope that our survey will not only become a reference guide for newcomers to the field but also a catalyst for new AI-based initiatives in the area of "AI4Science".
Authors: Nathan Louis, Luowei Zhou, Steven J. Yule, Roger D. Dias, Milisa Manojlovich, Francis D. Pagani, Donald S. Likosky, Jason J. Corso
Abstract: Articulated hand pose tracking is an under-explored problem that carries the potential for use in an extensive number of applications, especially in the medical domain. With a robust and accurate tracking system on surgical videos, the motion dynamics and movement patterns of the hands can be captured and analyzed for many rich tasks. In this work, we propose a novel hand pose estimation model, CondPose, which improves detection and tracking accuracy by incorporating a pose prior into its prediction. We show improvements over state-of-the-art methods which provide frame-wise independent predictions, by following a temporally guided approach that effectively leverages past predictions. We collect Surgical Hands, the first dataset that provides multi-instance articulated hand pose annotations for videos. Our dataset provides over 8.1k annotated hand poses from publicly available surgical videos and bounding boxes, pose annotations, and tracking IDs to enable multi-instance tracking. When evaluated on Surgical Hands, we show our method outperforms the state-of-the-art approach using mean Average Precision (mAP), to measure pose estimation accuracy, and Multiple Object Tracking Accuracy (MOTA), to assess pose tracking performance. In comparison to a frame-wise independent strategy, we show greater performance in detecting and tracking hand poses and more substantial impact on localization accuracy. This has positive implications in generating more accurate representations of hands in the scene to be used for targeted downstream tasks.
Authors: Mingjian Li, Mingyuan Meng, Michael Fulham, David Dagan Feng, Lei Bi, Jinman Kim
Abstract: Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities.
Authors: Fernando P\'erez-Garc\'ia, Harshita Sharma, Sam Bond-Taylor, Kenza Bouzid, Valentina Salvatelli, Maximilian Ilse, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Matthew P. Lungren, Maria Teodora Wetscherek, Noel Codella, Stephanie L. Hyland, Javier Alvarez-Valle, Ozan Oktay
Abstract: Language-supervised pre-training has proven to be a valuable method for extracting semantically meaningful features from images, serving as a foundational element in multimodal systems within the computer vision and medical imaging domains. However, the computed features are limited by the information contained in the text, which is particularly problematic in medical imaging, where the findings described by radiologists focus on specific observations. This challenge is compounded by the scarcity of paired imaging-text data due to concerns over leakage of personal health information. In this work, we fundamentally challenge the prevailing reliance on language supervision for learning general-purpose biomedical imaging encoders. We introduce RAD-DINO, a biomedical image encoder pre-trained solely on unimodal biomedical imaging data that obtains similar or greater performance than state-of-the-art biomedical language-supervised models on a diverse range of benchmarks. Specifically, the quality of learned representations is evaluated on standard imaging tasks (classification and semantic segmentation), and a vision-language alignment task (text report generation from images). To further demonstrate the drawback of language supervision, we show that features from RAD-DINO correlate with other medical records (e.g., sex or age) better than language-supervised models, which are generally not mentioned in radiology reports. Finally, we conduct a series of ablations determining the factors in RAD-DINO's performance; notably, we observe that RAD-DINO's downstream performance scales well with the quantity and diversity of training data, demonstrating that image-only supervision is a scalable approach for training a foundational biomedical image encoder. Model weights of RAD-DINO trained on publicly available datasets are available at https://huggingface.co/microsoft/rad-dino.
Authors: Kexin Li, Tao Jiang, Zongxin Yang, Yi Yang, Yueting Zhuang, Jun Xiao
Abstract: Interactive Video Object Segmentation (iVOS) is a challenging task that requires real-time human-computer interaction. To improve the user experience, it is important to consider the user's input habits, segmentation quality, running time and memory consumption.However, existing methods compromise user experience with single input mode and slow running speed. Specifically, these methods only allow the user to interact with one single frame, which limits the expression of the user's intent.To overcome these limitations and better align with people's usage habits, we propose a framework that can accept multiple frames simultaneously and explore synergistic interaction across frames (SIAF). Concretely, we designed the Across-Frame Interaction Module that enables users to annotate different objects freely on multiple frames. The AFI module will migrate scribble information among multiple interactive frames and generate multi-frame masks. Additionally, we employ the id-queried mechanism to process multiple objects in batches. Furthermore, for a more efficient propagation and lightweight model, we design a truncated re-propagation strategy to replace the previous multi-round fusion module, which employs an across-round memory that stores important interaction information. Our SwinB-SIAF achieves new state-of-the-art performance on DAVIS 2017 (89.6%, J&F@60). Moreover, our R50-SIAF is more than 3 faster than the state-of-the-art competitor under challenging multi-object scenarios.
Authors: Prakhar Kaushik, Adam Kortylewski, Alan Yuille
Abstract: An important and unsolved problem in computer vision is to ensure that the algorithms are robust to changes in image domains. We address this problem in the scenario where we have access to images from the target domains but no annotations. Motivated by the challenges of the OOD-CV benchmark where we encounter real world Out-of-Domain (OOD) nuisances and occlusion, we introduce a novel Bayesian approach to OOD robustness for object classification. Our work extends Compositional Neural Networks (CompNets), which have been shown to be robust to occlusion but degrade badly when tested on OOD data. We exploit the fact that CompNets contain a generative head defined over feature vectors represented by von Mises-Fisher (vMF) kernels, which correspond roughly to object parts, and can be learned without supervision. We obverse that some vMF kernels are similar between different domains, while others are not. This enables us to learn a transitional dictionary of vMF kernels that are intermediate between the source and target domains and train the generative model on this dictionary using the annotations on the source domain, followed by iterative refinement. This approach, termed Unsupervised Generative Transition (UGT), performs very well in OOD scenarios even when occlusion is present. UGT is evaluated on different OOD benchmarks including the OOD-CV dataset, several popular datasets (e.g., ImageNet-C [9]), artificial image corruptions (including adding occluders), and synthetic-to-real domain transfer, and does well in all scenarios outperforming SOTA alternatives (e.g. up to 10% top-1 accuracy on Occluded OOD-CV dataset).
Authors: Guoyang Zhao, Fulong Ma, Weiqing Qi, Yuxuan Liu, Ming Liu, Jun Ma
Abstract: Curb detection is a crucial function in intelligent driving, essential for determining drivable areas on the road. However, the complexity of road environments makes curb detection challenging. This paper introduces CurbNet, a novel framework for curb detection utilizing point cloud segmentation. To address the lack of comprehensive curb datasets with 3D annotations, we have developed the 3D-Curb dataset based on SemanticKITTI, currently the largest and most diverse collection of curb point clouds. Recognizing that the primary characteristic of curbs is height variation, our approach leverages spatially rich 3D point clouds for training. To tackle the challenges posed by the uneven distribution of curb features on the xy-plane and their dependence on high-frequency features along the z-axis, we introduce the Multi-Scale and Channel Attention (MSCA) module, a customized solution designed to optimize detection performance. Additionally, we propose an adaptive weighted loss function group specifically formulated to counteract the imbalance in the distribution of curb point clouds relative to other categories. Extensive experiments conducted on 2 major datasets demonstrate that our method surpasses existing benchmarks set by leading curb detection and point cloud segmentation models. Through the post-processing refinement of the detection results, we have significantly reduced noise in curb detection, thereby improving precision by 4.5 points. Similarly, our tolerance experiments also achieve state-of-the-art results. Furthermore, real-world experiments and dataset analyses mutually validate each other, reinforcing CurbNet's superior detection capability and robust generalizability. The project website is available at: https://github.com/guoyangzhao/CurbNet/.
Authors: Joseph Cho, Mrudang Mathur, Cyril Zakka, Dhamanpreet Kaur, Matthew Leipzig, Alex Dalal, Aravind Krishnan, Eubee Koo, Karen Wai, Cindy S. Zhao, Rohan Shad, Robyn Fong, Ross Wightman, Akshay Chaudhari, William Hiesinger
Abstract: Deep learning algorithms require extensive data to achieve robust performance. However, data availability is often restricted in the medical domain due to patient privacy concerns. Synthetic data presents a possible solution to these challenges. Recently, image generative models have found increasing use for medical applications but are often designed for singular medical specialties and imaging modalities, thus limiting their broader utility. To address this, we introduce MediSyn: a text-guided, latent diffusion model capable of generating synthetic images from 6 medical specialties and 10 image types. The synthetic images are validated by expert clinicians for alignment with their corresponding text prompts. Furthermore, a direct comparison of the synthetic images against the real images confirms that our model synthesizes novel images and, crucially, may preserve patient privacy. Finally, classifiers trained on a mixture of synthetic and real data achieve similar performance to those trained on twice the amount of real data. Our findings highlight the immense potential for generalist image generative models to accelerate algorithmic research and development in medicine.
Authors: Tom Burgert, Kai Norman Clasen, Jonas Klotz, Tim Siebert, Beg\"um Demir
Abstract: The development of supervised deep learning-based methods for multi-label scene classification (MLC) is one of the prominent research directions in remote sensing (RS). Yet, collecting annotations for large RS image archives is time-consuming and costly. To address this issue, several data augmentation methods have been introduced in RS. Among others, the data augmentation technique CutMix, which combines parts of two existing training images to generate an augmented image, stands out as a particularly effective approach. However, the direct application of CutMix in RS MLC can lead to the erasure or addition of class labels (i.e., label noise) in the augmented (i.e., combined) training image. To address this problem, we introduce a label propagation (LP) strategy that allows the effective application of CutMix in the context of MLC problems in RS without being affected by label noise. To this end, our proposed LP strategy exploits pixel-level class positional information to update the multi-label of the augmented training image. We propose to access such class positional information from reference maps associated to each training image (e.g., thematic products) or from class explanation masks provided by an explanation method if no reference maps are available. Similarly to pairing two training images, our LP strategy carries out a pairing operation on the associated pixel-level class positional information to derive the updated multi-label for the augmented image. Experimental results show the effectiveness of our LP strategy in general and its robustness in the case of various simulated and real scenarios with noisy class positional information in particular.
Authors: Zicheng Zhang, Haoning Wu, Chunyi Li, Yingjie Zhou, Wei Sun, Xiongkuo Min, Zijian Chen, Xiaohong Liu, Weisi Lin, Guangtao Zhai
Abstract: How to accurately and efficiently assess AI-generated images (AIGIs) remains a critical challenge for generative models. Given the high costs and extensive time commitments required for user studies, many researchers have turned towards employing large multi-modal models (LMMs) as AIGI evaluators, the precision and validity of which are still questionable. Furthermore, traditional benchmarks often utilize mostly natural-captured content rather than AIGIs to test the abilities of LMMs, leading to a noticeable gap for AIGIs. Therefore, we introduce A-Bench in this paper, a benchmark designed to diagnose whether LMMs are masters at evaluating AIGIs. Specifically, A-Bench is organized under two key principles: 1) Emphasizing both high-level semantic understanding and low-level visual quality perception to address the intricate demands of AIGIs. 2) Various generative models are utilized for AIGI creation, and various LMMs are employed for evaluation, which ensures a comprehensive validation scope. Ultimately, 2,864 AIGIs from 16 text-to-image models are sampled, each paired with question-answers annotated by human experts, and tested across 18 leading LMMs. We hope that A-Bench will significantly enhance the evaluation process and promote the generation quality for AIGIs. The benchmark is available at https://github.com/Q-Future/A-Bench.
Authors: Jia Syuen Lim, Zhuoxiao Chen, Mahsa Baktashmotlagh, Zhi Chen, Xin Yu, Zi Huang, Yadan Luo
Abstract: Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discovery methods that leverage basic visual cues to identify salient objects, consistently achieving a high recall rate remains difficult due to the diversity of object types and their contextual complexity. In this work, we investigate using vision-language models (VLMs) to enhance object detection via a self-supervised prompt learning strategy. Our initial findings indicate that manually crafted text queries often result in undetected objects, primarily because detection confidence diminishes when the query words exhibit semantic overlap. To address this, we propose a Dispersing Prompt Expansion (DiPEx) approach. DiPEx progressively learns to expand a set of distinct, non-overlapping hyperspherical prompts to enhance recall rates, thereby improving performance in downstream tasks such as out-of-distribution OD. Specifically, DiPEx initiates the process by self-training generic parent prompts and selecting the one with the highest semantic uncertainty for further expansion. The resulting child prompts are expected to inherit semantics from their parent prompts while capturing more fine-grained semantics. We apply dispersion losses to ensure high inter-class discrepancy among child prompts while preserving semantic consistency between parent-child prompt pairs. To prevent excessive growth of the prompt sets, we utilize the maximum angular coverage (MAC) of the semantic space as a criterion for early termination. We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20.1\% in AR and achieving a 21.3\% AP improvement over SAM. The code is available at https://github.com/jason-lim26/DiPEx.
Authors: Nan Xu, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen
Abstract: Motivated by in-context learning (ICL) capabilities of Large Language Models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provided as demonstrations. However, relatively less work has been done to investigate the principles behind how and why multimodal ICL works. We conduct a systematic and principled evaluation of multimodal ICL for models of different scales on a broad spectrum of new yet critical tasks. Through perturbations over different modality information, we show that modalities matter differently across tasks in multimodal ICL. Guided by task-specific modality impact, we recommend modality-driven demonstration strategies to boost ICL performance. We also find that models may follow inductive biases from multimodal ICL even if they are rarely seen in or contradict semantic priors from pretraining data. Our principled analysis provides a comprehensive way of understanding the role of demonstrations in multimodal in-context learning, and sheds light on effectively improving multimodal ICL on a wide range of tasks.
Authors: Muchammad Daniyal Kautsar, Afra Majida Hariono, Ridwan Akmal
Abstract: Indonesia ranks fourth globally in the number of deaf cases. Individuals with hearing impairments often find communication challenging, necessitating the use of sign language. However, there are limited public services that offer such inclusivity. On the other hand, advancements in artificial intelligence (AI) present promising solutions to overcome communication barriers faced by the deaf. This study aims to explore the application of AI in developing models for a simplified sign language translation app and dictionary, designed for integration into public service facilities, to facilitate communication for individuals with hearing impairments, thereby enhancing inclusivity in public services. The researchers compared the performance of LSTM and 1D CNN + Transformer (1DCNNTrans) models for sign language recognition. Through rigorous testing and validation, it was found that the LSTM model achieved an accuracy of 94.67%, while the 1DCNNTrans model achieved an accuracy of 96.12%. Model performance evaluation indicated that although the LSTM exhibited lower inference latency, it showed weaknesses in classifying classes with similar keypoints. In contrast, the 1DCNNTrans model demonstrated greater stability and higher F1 scores for classes with varying levels of complexity compared to the LSTM model. Both models showed excellent performance, exceeding 90% validation accuracy and demonstrating rapid classification of 50 sign language gestures.
Authors: Haiyu Wu, Jaskirat Singh, Sicong Tian, Liang Zheng, Kevin W. Bowyer
Abstract: This paper studies how to synthesize face images of non-existent persons, to create a dataset that allows effective training of face recognition (FR) models. Besides generating realistic face images, two other important goals are: 1) the ability to generate a large number of distinct identities (inter-class separation), and 2) a proper variation in appearance of the images for each identity (intra-class variation). However, existing works 1) are typically limited in how many well-separated identities can be generated and 2) either neglect or use an external model for attribute augmentation. We propose Vec2Face, a holistic model that uses only a sampled vector as input and can flexibly generate and control the identity of face images and their attributes. Composed of a feature masked autoencoder and an image decoder, Vec2Face is supervised by face image reconstruction and can be conveniently used in inference. Using vectors with low similarity among themselves as inputs, Vec2Face generates well-separated identities. Randomly perturbing an input identity vector within a small range allows Vec2Face to generate faces of the same identity with proper variation in face attributes. It is also possible to generate images with designated attributes by adjusting vector values with a gradient descent method. Vec2Face has efficiently synthesized as many as 300K identities, whereas 60K is the largest number of identities created in the previous works. As for performance, FR models trained with the generated HSFace datasets, from 10k to 300k identities, achieve state-of-the-art accuracy, from 92% to 93.52%, on five real-world test sets (\emph{i.e.}, LFW, CFP-FP, AgeDB-30, CALFW, and CPLFW). For the first time, the FR model trained using our synthetic training set achieves higher accuracy than that trained using a same-scale training set of real face images on the CALFW, IJBB, and IJBC test sets.
Authors: Hua Yan, Heng Tan, Yi Ding, Pengfei Zhou, Vinod Namboodiri, Yu Yang
Abstract: Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements create distribution gaps across datasets, reducing the performance of HAR models. To address this, we propose LanHAR, a novel system that leverages Large Language Models (LLMs) to generate semantic interpretations of sensor readings and activity labels for cross-dataset HAR. This approach not only mitigates cross-dataset heterogeneity but also enhances the recognition of new activities. LanHAR employs an iterative re-generation method to produce high-quality semantic interpretations with LLMs and a two-stage training framework that bridges the semantic interpretations of sensor readings and activity labels. This ultimately leads to a lightweight sensor encoder suitable for mobile deployment, enabling any sensor reading to be mapped into the semantic interpretation space. Experiments on five public datasets demonstrate that our approach significantly outperforms state-of-the-art methods in both cross-dataset HAR and new activity recognition. The source code will be made publicly available.
Authors: Jingnan Gao, Zhuo Chen, Xiaokang Yang, Yichao Yan
Abstract: Neural radiance fields have recently revolutionized novel-view synthesis and achieved high-fidelity renderings. However, these methods sacrifice the geometry for the rendering quality, limiting their further applications including relighting and deformation. How to synthesize photo-realistic rendering while reconstructing accurate geometry remains an unsolved problem. In this work, we present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction. Different from previous neural surfaces, our fused-granularity geometry structure balances the overall structures and fine geometric details, producing accurate geometry reconstruction. To disambiguate geometry from reflective appearance, we introduce blended radiance fields to model diffuse and specularity following the anisotropic spherical Gaussian encoding, a physics-based rendering pipeline. With these designs, AniSDF can reconstruct objects with complex structures and produce high-quality renderings. Furthermore, our method is a unified model that does not require complex hyperparameter tuning for specific objects. Extensive experiments demonstrate that our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.
Authors: Bin Wang, Anwesa Choudhuri, Meng Zheng, Zhongpai Gao, Benjamin Planche, Andong Deng, Qin Liu, Terrence Chen, Ulas Bagci, Ziyan Wu
Abstract: Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative depth between objects in a scene. To address this issue, we propose OIS: order-aware interactive segmentation, where we explicitly encode the relative depth between objects into order maps. We introduce a novel order-aware attention, where the order maps seamlessly guide the user interactions (in the form of clicks) to attend to the image features. We further present an object-aware attention module to incorporate a strong object-level understanding to better differentiate objects with similar order. Our approach allows both dense and sparse integration of user clicks, enhancing both accuracy and efficiency as compared to prior works. Experimental results demonstrate that OIS achieves state-of-the-art performance, improving mIoU after one click by 7.61 on the HQSeg44K dataset and 1.32 on the DAVIS dataset as compared to the previous state-of-the-art SegNext, while also doubling inference speed compared to current leading methods. The project page is https://ukaukaaaa.github.io/projects/OIS/index.html
Authors: Xupeng Chen, Zhixin Lai, Kangrui Ruan, Shichu Chen, Jiaxiang Liu, Zuozhu Liu
Abstract: Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries. Experimental evaluation on four standard Med-VQA datasets demonstrates R-LLaVA's superiority over existing state-of-the-art (SoTA) methods. Additionally, to verify the model's capability in visual comprehension, a novel multiple-choice medical visual understanding dataset is introduced, confirming the positive impact of focusing on visual regions of interest in advancing biomedical VQA understanding.
Authors: Tahar Chettaoui, Naser Damer, Fadi Boutros
Abstract: Foundation models are predominantly trained in an unsupervised or self-supervised manner on highly diverse and large-scale datasets, making them broadly applicable to various downstream tasks. In this work, we investigate for the first time whether such models are suitable for the specific domain of face recognition (FR). We further propose and demonstrate the adaptation of these models for FR across different levels of data availability, including synthetic data. Extensive experiments are conducted on multiple foundation models and datasets of varying scales for training and fine-tuning, with evaluation on a wide range of benchmarks. Our results indicate that, despite their versatility, pre-trained foundation models tend to underperform in FR in comparison with similar architectures trained specifically for this task. However, fine-tuning foundation models yields promising results, often surpassing models trained from scratch, particularly when training data is limited. For example, after fine-tuning only on 1K identities, DINOv2 ViT-S achieved average verification accuracy on LFW, CALFW, CPLFW, CFP-FP, and AgeDB30 benchmarks of 87.10%, compared to 64.70% achieved by the same model and without fine-tuning. While training the same model architecture, ViT-S, from scratch on 1k identities reached 69.96%. With access to larger-scale FR training datasets, these performances reach 96.03% and 95.59% for the DINOv2 and CLIP ViT-L models, respectively. In comparison to the ViT-based architectures trained from scratch for FR, fine-tuned same architectures of foundation models achieve similar performance while requiring lower training computational costs and not relying on the assumption of extensive data availability. We further demonstrated the use of synthetic face data, showing improved performances over both pre-trained foundation and ViT models.
Authors: Hao Phung, Quan Dao, Trung Dao, Hoang Phan, Dimitris Metaxas, Anh Tran
Abstract: We introduce a novel state-space architecture for diffusion models, effectively harnessing spatial and frequency information to enhance the inductive bias towards local features in input images for image generation tasks. While state-space networks, including Mamba, a revolutionary advancement in recurrent neural networks, typically scan input sequences from left to right, they face difficulties in designing effective scanning strategies, especially in the processing of image data. Our method demonstrates that integrating wavelet transformation into Mamba enhances the local structure awareness of visual inputs and better captures long-range relations of frequencies by disentangling them into wavelet subbands, representing both low- and high-frequency components. These wavelet-based outputs are then processed and seamlessly fused with the original Mamba outputs through a cross-attention fusion layer, combining both spatial and frequency information to optimize the order awareness of state-space models which is essential for the details and overall quality of image generation. Besides, we introduce a globally-shared transformer to supercharge the performance of Mamba, harnessing its exceptional power to capture global relationships. Through extensive experiments on standard benchmarks, our method demonstrates superior results compared to DiT and DIFFUSSM, achieving faster training convergence and delivering high-quality outputs. The codes and pretrained models are released at https://github.com/VinAIResearch/DiMSUM.git.
Authors: Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann
Abstract: Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin on the right of a bowl". Understanding these inconsistencies is crucial for reliable image generation. In this paper, we highlight the significant role of initial noise in these inconsistencies, where certain noise patterns are more reliable for compositional prompts than others. Our analyses reveal that different initial random seeds tend to guide the model to place objects in distinct image areas, potentially adhering to specific patterns of camera angles and image composition associated with the seed. To improve the model's compositional ability, we propose a method for mining these reliable cases, resulting in a curated training set of generated images without requiring any manual annotation. By fine-tuning text-to-image models on these generated images, we significantly enhance their compositional capabilities. For numerical composition, we observe relative increases of 29.3% and 19.5% for Stable Diffusion and PixArt-{\alpha}, respectively. Spatial composition sees even larger gains, with 60.7% for Stable Diffusion and 21.1% for PixArt-{\alpha}.
Authors: Ram Zaveri, Shivang Patel, Yu Gu, Gianfranco Doretto
Abstract: Efficient visual trackers overfit to their training distributions and lack generalization abilities, resulting in them performing well on their respective in-distribution (ID) test sets and not as well on out-of-distribution (OOD) sequences, imposing limitations to their deployment in-the-wild under constrained resources. We introduce SiamABC, a highly efficient Siamese tracker that significantly improves tracking performance, even on OOD sequences. SiamABC takes advantage of new architectural designs in the way it bridges the dynamic variability of the target, and of new losses for training. Also, it directly addresses OOD tracking generalization by including a fast backward-free dynamic test-time adaptation method that continuously adapts the model according to the dynamic visual changes of the target. Our extensive experiments suggest that SiamABC shows remarkable performance gains in OOD sets while maintaining accurate performance on the ID benchmarks. SiamABC outperforms MixFormerV2-S by 7.6\% on the OOD AVisT benchmark while being 3x faster (100 FPS) on a CPU. Our code and models are available at https://wvuvl.github.io/SiamABC/.
Authors: Xiao Fu, Xian Liu, Xintao Wang, Sida Peng, Menghan Xia, Xiaoyu Shi, Ziyang Yuan, Pengfei Wan, Di Zhang, Dahua Lin
Abstract: This paper aims to manipulate multi-entity 3D motions in video generation. Previous methods on controllable video generation primarily leverage 2D control signals to manipulate object motions and have achieved remarkable synthesis results. However, 2D control signals are inherently limited in expressing the 3D nature of object motions. To overcome this problem, we introduce 3DTrajMaster, a robust controller that regulates multi-entity dynamics in 3D space, given user-desired 6DoF pose (location and rotation) sequences of entities. At the core of our approach is a plug-and-play 3D-motion grounded object injector that fuses multiple input entities with their respective 3D trajectories through a gated self-attention mechanism. In addition, we exploit an injector architecture to preserve the video diffusion prior, which is crucial for generalization ability. To mitigate video quality degradation, we introduce a domain adaptor during training and employ an annealed sampling strategy during inference. To address the lack of suitable training data, we construct a 360-Motion Dataset, which first correlates collected 3D human and animal assets with GPT-generated trajectory and then captures their motion with 12 evenly-surround cameras on diverse 3D UE platforms. Extensive experiments show that 3DTrajMaster sets a new state-of-the-art in both accuracy and generalization for controlling multi-entity 3D motions. Project page: http://fuxiao0719.github.io/projects/3dtrajmaster
Authors: Yuchen Su, Zhineng Chen, Yongkun Du, Zhilong Ji, Kai Hu, Jinfeng Bai, Xieping Gao
Abstract: Connected component (CC) is a proper text shape representation that aligns with human reading intuition. However, CC-based text detection methods have recently faced a developmental bottleneck that their time-consuming post-processing is difficult to eliminate. To address this issue, we introduce an explicit relational reasoning network (ERRNet) to elegantly model the component relationships without post-processing. Concretely, we first represent each text instance as multiple ordered text components, and then treat these components as objects in sequential movement. In this way, scene text detection can be innovatively viewed as a tracking problem. From this perspective, we design an end-to-end tracking decoder to achieve a CC-based method dispensing with post-processing entirely. Additionally, we observe that there is an inconsistency between classification confidence and localization quality, so we propose a Polygon Monte-Carlo method to quickly and accurately evaluate the localization quality. Based on this, we introduce a position-supervised classification loss to guide the task-aligned learning of ERRNet. Experiments on challenging benchmarks demonstrate the effectiveness of our ERRNet. It consistently achieves state-of-the-art accuracy while holding highly competitive inference speed.
Authors: Xiyue Zhu, Dou Hoon Kwark, Ruike Zhu, Kaiwen Hong, Yiqi Tao, Shirui Luo, Yudu Li, Zhi-Pei Liang, Volodymyr Kindratenko
Abstract: In volume-to-volume translations in medical images, existing models often struggle to capture the inherent volumetric distribution using 3D voxelspace representations, due to high computational dataset demands. We present Score-Fusion, a novel volumetric translation model that effectively learns 3D representations by ensembling perpendicularly trained 2D diffusion models in score function space. By carefully initializing our model to start with an average of 2D models as in TPDM, we reduce 3D training to a fine-tuning process and thereby mitigate both computational and data demands. Furthermore, we explicitly design the 3D model's hierarchical layers to learn ensembles of 2D features, further enhancing efficiency and performance. Moreover, Score-Fusion naturally extends to multi-modality settings, by fusing diffusion models conditioned on different inputs for flexible, accurate integration. We demonstrate that 3D representation is essential for better performance in downstream recognition tasks, such as tumor segmentation, where most segmentation models are based on 3D representation. Extensive experiments demonstrate that Score-Fusion achieves superior accuracy and volumetric fidelity in 3D medical image super-resolution and modality translation. Beyond these improvements, our work also provides broader insight into learning-based approaches for score function fusion.
Authors: Adam Goodge, Wee Siong Ng, Bryan Hooi, See Kiong Ng
Abstract: Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and language tasks. However, despite the prevalence of spatio-temporal data in critical domains such as transportation, public health, and environmental monitoring, spatio-temporal foundation models (STFMs) have not yet achieved comparable success. In this paper, we articulate a vision for the future of STFMs, outlining their essential characteristics and the generalization capabilities necessary for broad applicability. We critically assess the current state of research, identifying gaps relative to these ideal traits, and highlight key challenges that impede their progress. Finally, we explore potential opportunities and directions to advance research towards the aim of effective and broadly applicable STFMs.
Authors: Yihang Chen, Qianyi Wu, Weiyao Lin, Mehrtash Harandi, Jianfei Cai
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additionally, HAC++ captures intra-anchor contextual relationships to further enhance compression performance. To facilitate entropy coding, we utilize Gaussian distributions to precisely estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Moreover, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Overall, HAC++ achieves a remarkable size reduction of over 100X compared to vanilla 3DGS when averaged on all datasets, while simultaneously improving fidelity. It also delivers more than 20X size reduction compared to Scaffold-GS. Our code is available at https://github.com/YihangChen-ee/HAC-plus.
Authors: Shilong Hong, Yanzhou Zhou, Weichao Xu
Abstract: With the rapid development of modern transportation systems and the exponential growth of logistics volumes, intelligent X-ray-based security inspection systems play a crucial role in public safety. Although single-view X-ray equipment is widely deployed, it struggles to accurately identify contraband in complex stacking scenarios due to strong viewpoint dependency and inadequate feature representation. To address this, we propose an innovative multi-scale interactive feature fusion framework tailored for dual-view X-ray security inspection image classification. The framework comprises three core modules: the Frequency Domain Interaction Module (FDIM) enhances frequency-domain features through Fourier transform; the Multi-Scale Cross-View Feature Enhancement (MSCFE) leverages cross-view attention mechanisms to strengthen feature interactions; and the Convolutional Attention Fusion Module (CAFM) efficiently fuses features by integrating channel attention with depthwise-separable convolutions. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches across multiple backbone architectures, particularly excelling in complex scenarios with occlusions and object stacking.
Authors: Haibo Tong, Zhaoyang Wang, Zhaorun Chen, Haonian Ji, Shi Qiu, Siwei Han, Kexin Geng, Zhongkai Xue, Yiyang Zhou, Peng Xia, Mingyu Ding, Rafael Rafailov, Chelsea Finn, Huaxiu Yao
Abstract: Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challenges such as instruction misalignment, content hallucination, safety concerns, and bias. Addressing these limitations, we introduce MJ-BENCH-VIDEO, a large-scale video preference benchmark designed to evaluate video generation across five critical aspects: Alignment, Safety, Fineness, Coherence & Consistency, and Bias & Fairness. This benchmark incorporates 28 fine-grained criteria to provide a comprehensive evaluation of video preference. Building upon this dataset, we propose MJ-VIDEO, a Mixture-of-Experts (MoE)-based video reward model designed to deliver fine-grained reward. MJ-VIDEO can dynamically select relevant experts to accurately judge the preference based on the input text-video pair. This architecture enables more precise and adaptable preference judgments. Through extensive benchmarking on MJ-BENCH-VIDEO, we analyze the limitations of existing video reward models and demonstrate the superior performance of MJ-VIDEO in video preference assessment, achieving 17.58% and 15.87% improvements in overall and fine-grained preference judgments, respectively. Additionally, introducing MJ-VIDEO for preference tuning in video generation enhances the alignment performance. All our code, data, and models are available at https://aiming-lab.github.io/MJ-VIDEO.github.io/.
Authors: Tzu-Tao Chang, Shivaram Venkataraman
Abstract: Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a large number of visual tokens in cross-attention layers leads to high memory demands and often necessitates distributed computation across multiple GPUs. Existing distributed attention mechanisms face significant communication overheads, making cross-attention layers a critical bottleneck for efficient training and inference of MLLMs. To address this, we propose LV-XAttn, a distributed, exact cross-attention mechanism with minimal communication overhead. We observe that in applications involving large visual inputs the size of the query block is typically much smaller than that of the key-value blocks. Thus, in LV-XAttn we keep the large key-value blocks locally on each GPU and exchange smaller query blocks across GPUs. We also introduce an efficient activation recomputation technique enabling support for longer visual context. We theoretically analyze the communication benefits of LV-XAttn and show that it can achieve speedups for a wide range of models. Our evaluations with mPLUG-Owl3 and OpenFlamingo models find that LV-XAttn achieves up to 5.58$\times$ end-to-end speedup compared to existing approaches.
Authors: Shuyang Wu, Yifu Qiu, Ines P. Nearchou, Sandrine Prost, Jonathan A. Fallowfield, Hakan Bilen, Timothy J. Kendall
Abstract: Multiple Instance Learning (MIL) for whole slide image (WSI) analysis in computational pathology often neglects instance-level learning as supervision is typically provided only at the bag level. In this work, we present PathMIL, a framework designed to improve MIL through two perspectives: (1) employing instance-level supervision and (2) learning inter-instance contextual information on bag level. Firstly, we propose a novel Coarse-to-Fine Self-Distillation (CFSD) paradigm, to probe and distil a classifier trained with bag-level information to obtain instance-level labels which could effectively provide the supervision for the same classifier in a finer way. Secondly, to capture inter-instance contextual information in WSI, we propose Two-Dimensional Positional Encoding (2DPE), which encodes the spatial appearance of instances within a bag. We also theoretically and empirically prove the instance-level learnability of CFSD. PathMIL is evaluated on multiple benchmarking tasks, including subtype classification (TCGA-NSCLC), tumour classification (CAMELYON16), and an internal benchmark for breast cancer receptor status classification. Our method achieves state-of-the-art performance, with AUC scores of 0.9152 and 0.8524 for estrogen and progesterone receptor status classification, respectively, an AUC of 0.9618 for subtype classification, and 0.8634 for tumour classification, surpassing existing methods.
Authors: Li Pan, Yupei Zhang, Qiushi Yang, Tan Li, Zhen Chen
Abstract: Recently computer-aided diagnosis has demonstrated promising performance, effectively alleviating the workload of clinicians. However, the inherent sample imbalance among different diseases leads algorithms biased to the majority categories, leading to poor performance for rare categories. Existing works formulated this challenge as a long-tailed problem and attempted to tackle it by decoupling the feature representation and classification. Yet, due to the imbalanced distribution and limited samples from tail classes, these works are prone to biased representation learning and insufficient classifier calibration. To tackle these problems, we propose a new Long-tailed Medical Diagnosis (LMD) framework for balanced medical image classification on long-tailed datasets. In the initial stage, we develop a Relation-aware Representation Learning (RRL) scheme to boost the representation ability by encouraging the encoder to capture intrinsic semantic features through different data augmentations. In the subsequent stage, we propose an Iterative Classifier Calibration (ICC) scheme to calibrate the classifier iteratively. This is achieved by generating a large number of balanced virtual features and fine-tuning the encoder using an Expectation-Maximization manner. The proposed ICC compensates for minority categories to facilitate unbiased classifier optimization while maintaining the diagnostic knowledge in majority classes. Comprehensive experiments on three public long-tailed medical datasets demonstrate that our LMD framework significantly surpasses state-of-the-art approaches. The source code can be accessed at https://github.com/peterlipan/LMD.
Authors: Jingyi Yang, Zitong Yu, Xiuming Ni, Jia He, Hui Li
Abstract: Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose \textbf{CLAVER}: a \textbf{C}ontrastive \textbf{L}anguage-\textbf{A}ction \textbf{V}ideo Learn\textbf{er}, designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to the alignment of dynamic action behaviors and abstract verbs. Specifically, we introduce a novel Kronecker mask attention for temporal modeling. Our tailored Kronecker mask offers three benefits 1) it expands the temporal receptive field for each token, 2) it serves as an effective spatiotemporal heterogeneity inductive bias, mitigating the issue of spatiotemporal homogenization, and 3) it can be seamlessly plugged into transformer-based models. Regarding the textual branch, we leverage large language models to generate diverse, sentence-level and semantically rich interpretive prompts of actions, which shift the model's focus towards the verb comprehension. Extensive experiments on various benchmarks and learning scenarios demonstrate the superiority and generality of our approach. The code will be available soon.
Authors: Priyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S Rawat
Abstract: Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization across diverse tasks, largely attributed to extensive pre-training on largescale datasets. However, their robustness on low-resolution/pixelated (LR) images, a common challenge in real-world scenarios, remains underexplored. We introduce LR0.FM, a comprehensive benchmark evaluating the impact of low resolution on the zero-shot classification performance of 10 FM(s) across 66 backbones and 15 datasets. We propose a novel metric, Weighted Aggregated Robustness, to address the limitations of existing metrics and better evaluate model performance across resolutions and datasets. Our key findings show that: (i) model size positively correlates with robustness to resolution degradation, (ii) pre-training dataset quality is more important than its size, and (iii) fine-tuned and higher resolution models are less robust against LR. Our analysis further reveals that the model makes semantically reasonable predictions at LR, and the lack of fine-grained details in input adversely impacts the model's initial layers more than the deeper layers. We use these insights and introduce a simple strategy, LR-TK0, to enhance the robustness of models without compromising their pre-trained weights. We demonstrate the effectiveness of LR-TK0 for robustness against low-resolution across several datasets and its generalization capability across backbones and other approaches. Code is available at https://github.com/shyammarjit/LR0.FM
Authors: Aristeidis Panos, Rahaf Aljundi, Daniel Olmeda Reino, Richard E. Turner
Abstract: Vision-language models (VLMs) excel in tasks such as visual question answering and image captioning. However, VLMs are often limited by their use of pretrained image encoders, like CLIP, leading to image understanding errors that hinder overall performance. On top of that, real-world applications often require the model to be continuously adapted as new and often limited data continuously arrive. To address this, we propose LoRSU (Low-Rank Adaptation with Structured Updates), a robust and computationally efficient method for selectively updating image encoders within VLMs. LoRSU introduces structured and localized parameter updates, effectively correcting performance on previously error-prone data while preserving the model's general robustness. Our approach leverages theoretical insights to identify and update only the most critical parameters, achieving significant resource efficiency. Specifically, we demonstrate that LoRSU reduces computational overhead by over 25x compared to full VLM updates, without sacrificing performance. Experimental results on VQA tasks in the few-shot continual learning setting, validate LoRSU's scalability, efficiency, and effectiveness, making it a compelling solution for image encoder adaptation in resource-constrained environments.
Authors: Yi Yu, Botao Ren, Peiyuan Zhang, Mingxin Liu, Junwei Luo, Shaofeng Zhang, Feipeng Da, Junchi Yan, Xue Yang
Abstract: With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning OOD from point annotations has gained great attention. In this paper, we rethink this challenging task setting with the layout among instances and present Point2RBox-v2. At the core are three principles: 1) Gaussian overlap loss. It learns an upper bound for each instance by treating objects as 2D Gaussian distributions and minimizing their overlap. 2) Voronoi watershed loss. It learns a lower bound for each instance through watershed on Voronoi tessellation. 3) Consistency loss. It learns the size/rotation variation between two output sets with respect to an input image and its augmented view. Supplemented by a few devised techniques, e.g. edge loss and copy-paste, the detector is further enhanced. To our best knowledge, Point2RBox-v2 is the first approach to explore the spatial layout among instances for learning point-supervised OOD. Our solution is elegant and lightweight, yet it is expected to give a competitive performance especially in densely packed scenes: 62.61%/86.15%/34.71% on DOTA/HRSC/FAIR1M. Code is available at https://github.com/VisionXLab/point2rbox-v2.
Authors: Masih Eskandar, Tooba Imtiaz, Zifeng Wang, Jennifer Dy
Abstract: The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks. Many existing defenses against these attacks, such as adversarial training, rely on full-model fine-tuning to induce robustness in the models. These defenses require storing a copy of the entire model, that can have billions of parameters, for each task. At the same time, parameter-efficient prompt tuning is used to adapt large transformer-based models to downstream tasks without the need to save large copies. In this paper, we examine parameter-efficient prompt tuning of Vision Transformers for downstream tasks under the lens of robustness. We show that previous adversarial defense methods, when applied to the prompt tuning paradigm, suffer from gradient obfuscation and are vulnerable to adaptive attacks. We introduce ADAPT, a novel framework for performing adaptive adversarial training in the prompt tuning paradigm. Our method achieves competitive robust accuracy of ~40% w.r.t. SOTA robustness methods using full-model fine-tuning, by tuning only ~1% of the number of parameters.
Authors: Kirill Muravyev, Alexander Melekhin, Dmitry Yudin, Konstantin Yakovlev
Abstract: Mapping is one of the crucial tasks enabling autonomous navigation of a mobile robot. Conventional mapping methods output a dense geometric map representation, e.g. an occupancy grid, which is not trivial to keep consistent for prolonged runs covering large environments. Meanwhile, capturing the topological structure of the workspace enables fast path planning, is typically less prone to odometry error accumulation, and does not consume much memory. Following this idea, this paper introduces PRISM-TopoMap -- a topological mapping method that maintains a graph of locally aligned locations not relying on global metric coordinates. The proposed method involves original learnable multimodal place recognition paired with the scan matching pipeline for localization and loop closure in the graph of locations. The latter is updated online, and the robot is localized in a proper node at each time step. We conduct a broad experimental evaluation of the suggested approach in a range of photo-realistic environments and on a real robot, and compare it to state of the art. The results of the empirical evaluation confirm that PRISM-Topomap consistently outperforms competitors computationally-wise, achieves high mapping quality and performs well on a real robot. The code of PRISM-Topomap is open-sourced and is available at: https://github.com/kirillMouraviev/prism-topomap.
Authors: David R Wessels, David M Knigge, Samuele Papa, Riccardo Valperga, Sharvaree Vadgama, Efstratios Gavves, Erik J Bekkers
Abstract: Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone Neural Field (NeF) to reconstruct the sample. However, existing CNF architectures face limitations when using this latent downstream in tasks requiring fine-grained geometric reasoning, such as classification and segmentation. We posit that this results from lack of explicit modelling of geometric information (e.g., locality in the signal or the orientation of a feature) in the latent space of CNFs. As such, we propose Equivariant Neural Fields (ENFs), a novel CNF architecture which uses a geometry-informed cross-attention to condition the NeF on a geometric variable--a latent point cloud of features--that enables an equivariant decoding from latent to field. We show that this approach induces a steerability property by which both field and latent are grounded in geometry and amenable to transformation laws: if the field transforms, the latent representation transforms accordingly--and vice versa. Crucially, this equivariance relation ensures that the latent is capable of (1) representing geometric patterns faithfully, allowing for geometric reasoning in latent space, and (2) weight-sharing over similar local patterns, allowing for efficient learning of datasets of fields. We validate these main properties in a range of tasks including classification, segmentation, forecasting, reconstruction and generative modelling, showing clear improvement over baselines with a geometry-free latent space. Code attached to submission https://github.com/Dafidofff/enf-jax. Code for a clean and minimal repo https://github.com/david-knigge/enf-min-jax.
URLs: https://github.com/Dafidofff/enf-jax., https://github.com/david-knigge/enf-min-jax.
Authors: Xiang Cao, Qiaoqiao Ding, Xiaoqun Zhang
Abstract: The regularized D-bar method is a popular method for solving Electrical Impedance Tomography (EIT) problems due to its efficiency and simplicity. It utilizes the low-pass truncated scattering data in the non-linear Fourier domain to solve the associated D-bar integral equations, yielding a smooth conductivity approximation. However, the D-bar reconstruction often presents low contrast and resolution due to the absence of accurate high-frequency information and the ill-posedness of the problem. In this paper, we propose a deep learning-based supervised approach for real-time EIT reconstruction. Based on the D-bar method, we propose to utilize both multi-scale frequency enhancement and spatial consistency for a high image quality reconstruction. Additionally, we propose a fixed-point iteration for solving discrete D-bar systems on GPUs for fast computation. Numerical results are performed for both the continuum model and complete electrode model simulation on KIT4 and ACT4 datasets to demonstrate notable improvements in absolute EIT imaging quality.
Authors: Lin Zhang, Wenbo Gao, Jie Yi, Yunyun Yang
Abstract: Multi-organ segmentation in medical image analysis is crucial for diagnosis and treatment planning. However, many factors complicate the task, including variability in different target categories and interference from complex backgrounds. In this paper, we utilize the knowledge of Deformable Convolution V3 (DCNv3) and multi-object segmentation to optimize our Spatially Adaptive Convolution Network (SACNet) in three aspects: feature extraction, model architecture, and loss constraint, simultaneously enhancing the perception of different segmentation targets. Firstly, we propose the Adaptive Receptive Field Module (ARFM), which combines DCNv3 with a series of customized block-level and architecture-level designs similar to transformers. This module can capture the unique features of different organs by adaptively adjusting the receptive field according to various targets. Secondly, we utilize ARFM as building blocks to construct the encoder-decoder of SACNet and partially share parameters between the encoder and decoder, making the network wider rather than deeper. This design achieves a shared lightweight decoder and a more parameter-efficient and effective framework. Lastly, we propose a novel continuity dynamic adjustment loss function, based on t-vMF dice loss and cross-entropy loss, to better balance easy and complex classes in segmentation. Experiments on 3D slice datasets from ACDC and Synapse demonstrate that SACNet delivers superior segmentation performance in multi-organ segmentation tasks compared to several existing methods.
Authors: Lining Yu, Mengmeng Yin, Ruining Deng, Quan Liu, Tianyuan Yao, Can Cui, Yitian Long, Yu Wang, Yaohong Wang, Shilin Zhao, Haichun Yang, Yuankai Huo
Abstract: Moving from animal models to human applications in preclinical research encompasses a broad spectrum of disciplines in medical science. A fundamental element in the development of new drugs, treatments, diagnostic methods, and in deepening our understanding of disease processes is the accurate measurement of kidney tissues. Past studies have demonstrated the viability of translating glomeruli segmentation techniques from mouse models to human applications. Yet, these investigations tend to neglect the complexities involved in segmenting pathological glomeruli affected by different lesions. Such lesions present a wider range of morphological variations compared to healthy glomerular tissue, which are arguably more valuable than normal glomeruli in clinical practice. Furthermore, data on lesions from animal models can be more readily scaled up from disease models and whole kidney biopsies. This brings up a question: ``\textit{Can a pathological segmentation model trained on mouse models be effectively applied to human patients?}" To answer this question, we introduced GLAM, a deep learning study for fine-grained segmentation of human kidney lesions using a mouse model, addressing mouse-to-human transfer learning, by evaluating different learning strategies for segmenting human pathological lesions using zero-shot transfer learning and hybrid learning by leveraging mouse samples. From the results, the hybrid learning model achieved superior performance.
Authors: Basar Demir, Lin Tian, Thomas Hastings Greer, Roland Kwitt, Francois-Xavier Vialard, Raul San Jose Estepar, Sylvain Bouix, Richard Jarrett Rushmore, Ebrahim Ebrahim, Marc Niethammer
Abstract: Modern medical image registration approaches predict deformations using deep networks. These approaches achieve state-of-the-art (SOTA) registration accuracy and are generally fast. However, deep learning (DL) approaches are, in contrast to conventional non-deep-learning-based approaches, anatomy-specific. Recently, a universal deep registration approach, uniGradICON, has been proposed. However, uniGradICON focuses on monomodal image registration. In this work, we therefore develop multiGradICON as a first step towards universal *multimodal* medical image registration. Specifically, we show that 1) we can train a DL registration model that is suitable for monomodal *and* multimodal registration; 2) loss function randomization can increase multimodal registration accuracy; and 3) training a model with multimodal data helps multimodal generalization. Our code and the multiGradICON model are available at https://github.com/uncbiag/uniGradICON.
Authors: Junlin Guo, Siqi Lu, Can Cui, Ruining Deng, Tianyuan Yao, Zhewen Tao, Yizhe Lin, Marilyn Lionts, Quan Liu, Juming Xiong, Yu Wang, Shilin Zhao, Catie Chang, Mitchell Wilkes, Mengmeng Yin, Haichun Yang, Yuankai Huo
Abstract: Cell nuclei instance segmentation is a crucial task in digital kidney pathology. Traditional automatic segmentation methods often lack generalizability when applied to unseen datasets. Recently, the success of foundation models (FMs) has provided a more generalizable solution, potentially enabling the segmentation of any cell type. In this study, we perform a large-scale evaluation of three widely used state-of-the-art (SOTA) cell nuclei foundation models (Cellpose, StarDist, and CellViT). Specifically, we created a highly diverse evaluation dataset consisting of 2,542 kidney whole slide images (WSIs) collected from both human and rodent sources, encompassing various tissue types, sizes, and staining methods. To our knowledge, this is the largest-scale evaluation of its kind to date. Our quantitative analysis of the prediction distribution reveals a persistent performance gap in kidney pathology. Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology. However, none of the foundation models are perfect; a performance gap remains in general nuclei segmentation for kidney pathology.
Authors: Junyang Zhang, Mu Yuan, Ruiguang Zhong, Puhan Luo, Huiyou Zhan, Ningkang Zhang, Chengchen Hu, Xiangyang Li
Abstract: The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention techniques can dynamically reduce computational redundancy and thus improve efficiency. Although current adaptive attention methods significantly reduce the memory requirements of Transformer-based language models, they are not tailored for LVLMs. We observe that LVLMs generate responses from both remote image tokens and local text tokens, and different modalities have different attention patterns. This observation inspires us to manage the attention for each modality separately. Specifically, for visual input, we store the cache of potentially useful information but only compute the most critical parts. For language input, we care more about local information. Based on our observation and analysis of vision-language attention patterns, we develop A-VL, a plug-and-play adaptive attention tailored for LVLM inference. Extensive evaluations on three vision-language tasks and five datasets show the effectiveness of our designs. Our approach A-VL outperforms existing adaptive attention methods in reducing memory usage and computational load without compromising performance.
Authors: Jun-En Ding, Chien-Chin Hsu, Chi-Hsiang Chu, Shuqiang Wang, Feng Liu
Abstract: The classification of medical images is a pivotal aspect of disease diagnosis, often enhanced by deep learning techniques. However, traditional approaches typically focus on unimodal medical image data, neglecting the integration of diverse non-image patient data. This paper proposes a novel Cross-Graph Modal Contrastive Learning (CGMCL) framework for multimodal structured data from different data domains to improve medical image classification. The model effectively integrates both image and non-image data by constructing cross-modality graphs and leveraging contrastive learning to align multimodal features in a shared latent space. An inter-modality feature scaling module further optimizes the representation learning process by reducing the gap between heterogeneous modalities. The proposed approach is evaluated on two datasets: a Parkinson's disease (PD) dataset and a public melanoma dataset. Results demonstrate that CGMCL outperforms conventional unimodal methods in accuracy, interpretability, and early disease prediction. Additionally, the method shows superior performance in multi-class melanoma classification. The CGMCL framework provides valuable insights into medical image classification while offering improved disease interpretability and predictive capabilities.
Authors: Lokendra Poudel, Sushant Jha, Ryan Meeker, Duy-Nhat Phan, Rahul Bhowmik
Abstract: Ultrasonic Additive Manufacturing (UAM) employs ultrasonic welding to bond similar or dissimilar metal foils to a substrate, resulting in solid, consolidated metal components. However, certain processing conditions can lead to inter-layer defects, affecting the final product's quality. This study develops a method to monitor in-process quality using deep learning-based convolutional neural networks (CNNs). The CNN models were evaluated on their ability to classify samples with and without embedded thermocouples across five power levels (300W, 600W, 900W, 1200W, 1500W) using thermal images with supervised labeling. Four distinct CNN classification models were created for different scenarios including without (baseline) and with thermocouples, only without thermocouples across power levels, only with thermocouples across power levels, and combined without and with thermocouples across power levels. The models achieved 98.29% accuracy on combined baseline and thermocouple images, 97.10% for baseline images across power levels, 97.43% for thermocouple images, and 97.27% for both types across power levels. The high accuracy, above 97%, demonstrates the system's effectiveness in identifying and classifying conditions within the UAM process, providing a reliable tool for quality assurance and process control in manufacturing environments.
Authors: Yansong Qu, Dian Chen, Xinyang Li, Xiaofan Li, Shengchuan Zhang, Liujuan Cao, Rongrong Ji
Abstract: Recent advancements in 3D scene editing have been propelled by the rapid development of generative models. Existing methods typically utilize generative models to perform text-guided editing on 3D representations, such as 3D Gaussian Splatting (3DGS). However, these methods are often limited to texture modifications and fail when addressing geometric changes, such as editing a character's head to turn around. Moreover, such methods lack accurate control over the spatial position of editing results, as language struggles to precisely describe the extent of edits. To overcome these limitations, we introduce DYG, an effective 3D drag-based editing method for 3D Gaussian Splatting. It enables users to conveniently specify the desired editing region and the desired dragging direction through the input of 3D masks and pairs of control points, thereby enabling precise control over the extent of editing. DYG integrates the strengths of the implicit triplane representation to establish the geometric scaffold of the editing results, effectively overcoming suboptimal editing outcomes caused by the sparsity of 3DGS in the desired editing regions. Additionally, we incorporate a drag-based Latent Diffusion Model into our method through the proposed Drag-SDS loss function, enabling flexible, multi-view consistent, and fine-grained editing. Extensive experiments demonstrate that DYG conducts effective drag-based editing guided by control point prompts, surpassing other baselines in terms of editing effect and quality, both qualitatively and quantitatively. Visit our project page at https://quyans.github.io/Drag-Your-Gaussian.