Authors: Asterios Reppas, Grigorios-Aris Cheimariotis, Panos K. Papadopoulos, Panagiotis Frasiolas, Dimitrios Zarpalas
Abstract: Precise camera localization is a critical task in XR applications and robotics. Using only the camera captures as input to a system is an inexpensive option that enables localization in large indoor and outdoor environments, but it presents challenges in achieving high accuracy. Specifically, camera relocalization methods, such as Absolute Pose Regression (APR), can localize cameras with a median translation error of more than $0.5m$ in outdoor scenes. This paper presents HAL-NeRF, a high-accuracy localization method that combines a CNN pose regressor with a refinement module based on a Monte Carlo particle filter. The Nerfacto model, an implementation of Neural Radiance Fields (NeRFs), is used to augment the data for training the pose regressor and to measure photometric loss in the particle filter refinement module. HAL-NeRF leverages Nerfacto's ability to synthesize high-quality novel views, significantly improving the performance of the localization pipeline. HAL-NeRF achieves state-of-the-art results that are conventionally measured as the average of the median per scene errors. The translation error was $0.025m$ and the rotation error was $0.59$ degrees and 0.04m and 0.58 degrees on the 7-Scenes dataset and Cambridge Landmarks datasets respectively, with the trade-off of increased computational time. This work highlights the potential of combining APR with NeRF-based refinement techniques to advance monocular camera relocalization accuracy.
Authors: Pascal Chang, Sergio Sancho, Jingwei Tang, Markus Gross, Vinicius C. Azevedo
Abstract: Anamorphosis refers to a category of images that are intentionally distorted, making them unrecognizable when viewed directly. Their true form only reveals itself when seen from a specific viewpoint, which can be through some catadioptric device like a mirror or a lens. While the construction of these mathematical devices can be traced back to as early as the 17th century, they are only interpretable when viewed from a specific vantage point and tend to lose meaning when seen normally. In this paper, we revisit these famous optical illusions with a generative twist. With the help of latent rectified flow models, we propose a method to create anamorphic images that still retain a valid interpretation when viewed directly. To this end, we introduce Laplacian Pyramid Warping, a frequency-aware image warping technique key to generating high-quality visuals. Our work extends Visual Anagrams (arXiv:2311.17919) to latent space models and to a wider range of spatial transforms, enabling the creation of novel generative perceptual illusions.
Authors: Jiahuan Long, Zhengqin Xu, Tingsong Jiang, Wen Yao, Shuai Jia, Chao Ma, Xiaoqian Chen
Abstract: The Segment Anything Model (SAM) is a widely used vision foundation model with diverse applications, including image segmentation, detection, and tracking. Given SAM's wide applications, understanding its robustness against adversarial attacks is crucial for real-world deployment. However, research on SAM's robustness is still in its early stages. Existing attacks often overlook the role of prompts in evaluating SAM's robustness, and there has been insufficient exploration of defense methods to balance the robustness and accuracy. To address these gaps, this paper proposes an adversarial robustness framework designed to evaluate and enhance the robustness of SAM. Specifically, we introduce a cross-prompt attack method to enhance the attack transferability across different prompt types. Besides attacking, we propose a few-parameter adaptation strategy to defend SAM against various adversarial attacks. To balance robustness and accuracy, we use the singular value decomposition (SVD) to constrain the space of trainable parameters, where only singular values are adaptable. Experiments demonstrate that our cross-prompt attack method outperforms previous approaches in terms of attack success rate on both SAM and SAM 2. By adapting only 512 parameters, we achieve at least a 15\% improvement in mean intersection over union (mIoU) against various adversarial attacks. Compared to previous defense methods, our approach enhances the robustness of SAM while maximally maintaining its original performance.
Authors: Jiahuan Long, Tingsong Jiang, Wen Yao, Yizhe Xiong, Zhengqin Xu, Shuai Jia, Chao Ma
Abstract: Vision foundation models (VFMs) are large pre-trained models that form the backbone of various vision tasks. Fine-tuning VFMs can further unlock their potential for downstream tasks or scenarios. However, VFMs often contain significant feature redundancy, which may limit their adaptability to new tasks. In this paper, we investigate the redundancies in the segment anything model (SAM) and then propose a parameter-free fine-tuning method to address this issue. Unlike traditional fine-tuning methods that adjust parameters, our method emphasizes selecting, reusing, and enhancing pre-trained features, offering a new perspective on model fine-tuning. Specifically, we introduce a channel selection algorithm based on the model's output difference to identify redundant and effective channels. By selectively replacing the redundant channels with more effective ones, we filter out less useful features and reuse the more relevant features to downstream tasks, thereby enhancing the task-specific feature representation. Experiments on both out-of-domain and in-domain datasets demonstrate the efficiency and effectiveness of our method. Notably, our approach can seamlessly integrate with existing fine-tuning strategies (e.g., LoRA, Adapter), further boosting the performance of already fine-tuned models. Moreover, since our channel selection involves only model inference, our method significantly reduces computational and GPU memory overhead.
Authors: Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Juwei Lu, Hai Jiang, Li Cheng
Abstract: Generative masked transformers have demonstrated remarkable success across various content generation tasks, primarily due to their ability to effectively model large-scale dataset distributions with high consistency. However, in the animation domain, large datasets are not always available. Applying generative masked modeling to generate diverse instances from a single MoCap reference may lead to overfitting, a challenge that remains unexplored. In this work, we present MotionDreamer, a localized masked modeling paradigm designed to learn internal motion patterns from a given motion with arbitrary topology and duration. By embedding the given motion into quantized tokens with a novel distribution regularization method, MotionDreamer constructs a robust and informative codebook for local motion patterns. Moreover, a sliding window local attention is introduced in our masked transformer, enabling the generation of natural yet diverse animations that closely resemble the reference motion patterns. As demonstrated through comprehensive experiments, MotionDreamer outperforms the state-of-the-art methods that are typically GAN or Diffusion-based in both faithfulness and diversity. Thanks to the consistency and robustness of the quantization-based approach, MotionDreamer can also effectively perform downstream tasks such as temporal motion editing, \textcolor{update}{crowd animation}, and beat-aligned dance generation, all using a single reference motion. Visit our project page: https://motiondreamer.github.io/
Authors: Mohamed Dhouib, Davide Buscaldi, Sonia Vanier, Aymen Shabou
Abstract: Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information. However, these visual tokens often contain redundant and unimportant information, resulting in an unnecessarily high number of tokens. To address this, we introduce PACT, a method that reduces inference time and memory usage by pruning irrelevant tokens and merging visually redundant ones at an early layer of the language model. Our approach uses a novel importance metric to identify unimportant tokens without relying on attention scores, making it compatible with FlashAttention. We also propose a novel clustering algorithm, called Distance Bounded Density Peak Clustering, which efficiently clusters visual tokens while constraining the distances between elements within a cluster by a predefined threshold. We demonstrate the effectiveness of PACT through extensive experiments.
Authors: Kyle Stein, Andrew Arash Mahyari, Guillermo Francia III, Eman El-Sheikh
Abstract: Integrating new class information without losing previously acquired knowledge remains a central challenge in artificial intelligence, often referred to as catastrophic forgetting. Few-shot class incremental learning (FSCIL) addresses this by first training a model on a robust dataset of base classes and then incrementally adapting it in successive sessions using only a few labeled examples per novel class. However, this approach is prone to overfitting on the limited new data, which can compromise overall performance and exacerbate forgetting. In this work, we propose a simple yet effective novel FSCIL framework that leverages a frozen Vision Transformer (ViT) backbone augmented with parameter-efficient additive updates. Our approach freezes the pre-trained ViT parameters and selectively injects trainable weights into the self-attention modules via an additive update mechanism. This design updates only a small subset of parameters to accommodate new classes without sacrificing the representations learned during the base session. By fine-tuning a limited number of parameters, our method preserves the generalizable features in the frozen ViT while reducing the risk of overfitting. Furthermore, as most parameters remain fixed, the model avoids overwriting previously learned knowledge when small novel data batches are introduced. Extensive experiments on benchmark datasets demonstrate that our approach yields state-of-the-art performance compared to baseline FSCIL methods.
Authors: Snigdha Agarwal, Neelam Sinha
Abstract: Deep Convolutional Neural Networks have consistently proven to achieve state-of-the-art results on a lot of imaging tasks over the past years' majority of which comprise of high-quality data. However, it is important to work on low-resolution images since it could be a cheaper alternative for remote healthcare access where the primary need of automated pathology identification models occurs. Medical diagnosis using low-resolution images is challenging since critical details may not be easily identifiable. In this paper, we report classification results by experimenting on different input image sizes of Chest X-rays to deep CNN models and discuss the feasibility of classification on varying image sizes. We also leverage the noisy labels in the dataset by proposing a Randomized Flipping of labels techniques. We use an ensemble of multi-label classification models on frontal and lateral studies. Our models are trained on 5 out of the 14 chest pathologies of the publicly available CheXpert dataset. We incorporate techniques such as augmentation, regularization for model improvement and use class activation maps to visualize the neural network's decision making. Comparison with classification results on data from 200 subjects, obtained on the corresponding high-resolution images, reported in the original CheXpert paper, has been presented. For pathologies Cardiomegaly, Consolidation and Edema, we obtain 3% higher accuracy with our model architecture.
Authors: Gen Li, Yang Xiao, Jie Ji, Kaiyuan Deng, Bo Hui, Linke Guo, Xiaolong Ma
Abstract: Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting is necessary, such as removing copyrighted content, reducing biases, or eliminating harmful concepts. While existing unlearning methods can remove certain concepts, they struggle with multi-concept forgetting due to instability, residual knowledge persistence, and generation quality degradation. To address these challenges, we propose \textbf{Dynamic Mask coupled with Concept-Aware Loss}, a novel unlearning framework designed for multi-concept forgetting in diffusion models. Our \textbf{Dynamic Mask} mechanism adaptively updates gradient masks based on current optimization states, allowing selective weight modifications that prevent interference with unrelated knowledge. Additionally, our \textbf{Concept-Aware Loss} explicitly guides the unlearning process by enforcing semantic consistency through superclass alignment, while a regularization loss based on knowledge distillation ensures that previously unlearned concepts remain forgotten during sequential unlearning. We conduct extensive experiments to evaluate our approach. Results demonstrate that our method outperforms existing unlearning techniques in forgetting effectiveness, output fidelity, and semantic coherence, particularly in multi-concept scenarios. Our work provides a principled and flexible framework for stable and high-fidelity unlearning in generative models. The code will be released publicly.
Authors: Yongchang Wu, Zipeng Qi, Zhenwei Shi, Zhengxia Zou
Abstract: The recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated remarkable potential in novel view synthesis tasks. The divide-and-conquer paradigm has enabled large-scale scene reconstruction, but significant challenges remain in scene partitioning, optimization, and merging processes. This paper introduces BlockGaussian, a novel framework incorporating a content-aware scene partition strategy and visibility-aware block optimization to achieve efficient and high-quality large-scale scene reconstruction. Specifically, our approach considers the content-complexity variation across different regions and balances computational load during scene partitioning, enabling efficient scene reconstruction. To tackle the supervision mismatch issue during independent block optimization, we introduce auxiliary points during individual block optimization to align the ground-truth supervision, which enhances the reconstruction quality. Furthermore, we propose a pseudo-view geometry constraint that effectively mitigates rendering degradation caused by airspace floaters during block merging. Extensive experiments on large-scale scenes demonstrate that our approach achieves state-of-the-art performance in both reconstruction efficiency and rendering quality, with a 5x speedup in optimization and an average PSNR improvement of 1.21 dB on multiple benchmarks. Notably, BlockGaussian significantly reduces computational requirements, enabling large-scale scene reconstruction on a single 24GB VRAM device. The project page is available at https://github.com/SunshineWYC/BlockGaussian
Authors: Zhijie Shen, Chunyu Lin, Shujuan Huang, Lang Nie, Kang Liao, Yao Zhao
Abstract: Recently, reconstructing scenes from a single panoramic image using advanced 3D Gaussian Splatting (3DGS) techniques has attracted growing interest. Panoramic images offer a 360$\times$ 180 field of view (FoV), capturing the entire scene in a single shot. However, panoramic images introduce severe distortion, making it challenging to render 3D Gaussians into 2D distorted equirectangular space directly. Converting equirectangular images to cubemap projections partially alleviates this problem but introduces new challenges, such as projection distortion and discontinuities across cube-face boundaries. To address these limitations, we present a novel framework, named TPGS, to bridge continuous panoramic 3D scene reconstruction with perspective Gaussian splatting. Firstly, we introduce a Transition Plane between adjacent cube faces to enable smoother transitions in splatting directions and mitigate optimization ambiguity in the boundary region. Moreover, an intra-to-inter face optimization strategy is proposed to enhance local details and restore visual consistency across cube-face boundaries. Specifically, we optimize 3D Gaussians within individual cube faces and then fine-tune them in the stitched panoramic space. Additionally, we introduce a spherical sampling technique to eliminate visible stitching seams. Extensive experiments on indoor and outdoor, egocentric, and roaming benchmark datasets demonstrate that our approach outperforms existing state-of-the-art methods. Code and models will be available at https://github.com/zhijieshen-bjtu/TPGS.
Authors: Yifan Yang, Lei Zou, Bing Zhou, Daoyang Li, Binbin Lin, Joynal Abedin, Mingzheng Yang
Abstract: Street-view images offer unique advantages for disaster damage estimation as they capture impacts from a visual perspective and provide detailed, on-the-ground insights. Despite several investigations attempting to analyze street-view images for damage estimation, they mainly focus on post-disaster images. The potential of time-series street-view images remains underexplored. Pre-disaster images provide valuable benchmarks for accurate damage estimations at building and street levels. These images could aid annotators in objectively labeling post-disaster impacts, improving the reliability of labeled data sets for model training, and potentially enhancing the model performance in damage evaluation. The goal of this study is to estimate hyperlocal, on-the-ground disaster damages using bi-temporal street-view images and advanced pre-trained vision models. Street-view images before and after 2024 Hurricane Milton in Horseshoe Beach, Florida, were collected for experiments. The objectives are: (1) to assess the performance gains of incorporating pre-disaster street-view images as a no-damage category in fine-tuning pre-trained models, including Swin Transformer and ConvNeXt, for damage level classification; (2) to design and evaluate a dual-channel algorithm that reads pair-wise pre- and post-disaster street-view images for hyperlocal damage assessment. The results indicate that incorporating pre-disaster street-view images and employing a dual-channel processing framework can significantly enhance damage assessment accuracy. The accuracy improves from 66.14% with the Swin Transformer baseline to 77.11% with the dual-channel Feature-Fusion ConvNeXt model. This research enables rapid, operational damage assessments at hyperlocal spatial resolutions, providing valuable insights to support effective decision-making in disaster management and resilience planning.
Authors: Shuning Sun, Yu Zhang, Chen Wu, Dianjie Lu, Dianjie Lu, Guijuan Zhan, Yang Weng, Zhuoran Zheng
Abstract: Video imaging is often affected by complex degradations such as blur, noise, and compression artifacts. Traditional restoration methods follow a "single-task single-model" paradigm, resulting in poor generalization and high computational cost, limiting their applicability in real-world scenarios with diverse degradation types. We propose UniFlowRestore, a general video restoration framework that models restoration as a time-continuous evolution under a prompt-guided and physics-informed vector field. A physics-aware backbone PhysicsUNet encodes degradation priors as potential energy, while PromptGenerator produces task-relevant prompts as momentum. These components define a Hamiltonian system whose vector field integrates inertial dynamics, decaying physical gradients, and prompt-based guidance. The system is optimized via a fixed-step ODE solver to achieve efficient and unified restoration across tasks. Experiments show that UniFlowRestore delivers stateof-the-art performance with strong generalization and efficiency. Quantitative results demonstrate that UniFlowRestore achieves state-of-the-art performance, attaining the highest PSNR (33.89 dB) and SSIM (0.97) on the video denoising task, while maintaining top or second-best scores across all evaluated tasks.
Authors: Mk Bashar, Ocean Monjur, Samia Islam, Mohammad Galib Shams, Niamul Quader
Abstract: In recent years, Convolutional Neural Networks (CNNs), MLP-mixers, and Vision Transformers have risen to prominence as leading neural architectures in image classification. Prior research has underscored the distinct advantages of each architecture, and there is growing evidence that combining modules from different architectures can boost performance. In this study, we build upon and improve previous work exploring the complementarity between different architectures. Instead of heuristically merging modules from various architectures through trial and error, we preserve the integrity of each architecture and combine them using ensemble techniques. By maintaining the distinctiveness of each architecture, we aim to explore their inherent complementarity more deeply and with implicit isolation. This approach provides a more systematic understanding of their individual strengths. In addition to uncovering insights into architectural complementarity, we showcase the effectiveness of even basic ensemble methods that combine models from diverse architectures. These methods outperform ensembles comprised of similar architectures. Our straightforward ensemble framework serves as a foundational strategy for blending complementary architectures, offering a solid starting point for further investigations into the unique strengths and synergies among different architectures and their ensembles in image classification. A direct outcome of this work is the creation of an ensemble of classification networks that surpasses the accuracy of the previous state-of-the-art single classification network on ImageNet, setting a new benchmark, all while requiring less overall latency.
Authors: Bingyu Nan, Feng Liu, Xuezhong Qian, Wei Song
Abstract: Facial expression recognition is an important research direction in the field of artificial intelligence. Although new breakthroughs have been made in recent years, the uneven distribution of datasets and the similarity between different categories of facial expressions, as well as the differences within the same category among different subjects, remain challenges. This paper proposes a visual facial expression signal feature processing network based on truncated ConvNeXt approach(Conv-cut), to improve the accuracy of FER under challenging conditions. The network uses a truncated ConvNeXt-Base as the feature extractor, and then we designed a Detail Extraction Block to extract detailed features, and introduced a Self-Attention mechanism to enable the network to learn the extracted features more effectively. To evaluate the proposed Conv-cut approach, we conducted experiments on the RAF-DB and FERPlus datasets, and the results show that our model has achieved state-of-the-art performance. Our code could be accessed at Github.
Authors: Muhammad Adil, Gaang Lee, Vicente A. Gonzalez, Qipei Mei
Abstract: Safety hazard identification and prevention are the key elements of proactive safety management. Previous research has extensively explored the applications of computer vision to automatically identify hazards from image clips collected from construction sites. However, these methods struggle to identify context-specific hazards, as they focus on detecting predefined individual entities without understanding their spatial relationships and interactions. Furthermore, their limited adaptability to varying construction site guidelines and conditions hinders their generalization across different projects. These limitations reduce their ability to assess hazards in complex construction environments and adaptability to unseen risks, leading to potential safety gaps. To address these challenges, we proposed and experimentally validated a Vision Language Model (VLM)-based framework for the identification of construction hazards. The framework incorporates a prompt engineering module that structures safety guidelines into contextual queries, allowing VLM to process visual information and generate hazard assessments aligned with the regulation guide. Within this framework, we evaluated state-of-the-art VLMs, including GPT-4o, Gemini, Llama 3.2, and InternVL2, using a custom dataset of 1100 construction site images. Experimental results show that GPT-4o and Gemini 1.5 Pro outperformed alternatives and displayed promising BERTScore of 0.906 and 0.888 respectively, highlighting their ability to identify both general and context-specific hazards. However, processing times remain a significant challenge, impacting real-time feasibility. These findings offer insights into the practical deployment of VLMs for construction site hazard detection, thereby contributing to the enhancement of proactive safety management.
Authors: Yunfei Long, Abhinav Kumar, Xiaoming Liu, Daniel Morris
Abstract: Radar hits reflect from points on both the boundary and internal to object outlines. This results in a complex distribution of radar hits that depends on factors including object category, size, and orientation. Current radar-camera fusion methods implicitly account for this with a black-box neural network. In this paper, we explicitly utilize a radar hit distribution model to assist fusion. First, we build a model to predict radar hit distributions conditioned on object properties obtained from a monocular detector. Second, we use the predicted distribution as a kernel to match actual measured radar points in the neighborhood of the monocular detections, generating matching scores at nearby positions. Finally, a fusion stage combines context with the kernel detector to refine the matching scores. Our method achieves the state-of-the-art radar-camera detection performance on nuScenes. Our source code is available at https://github.com/longyunf/riccardo.
Authors: Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, Junuk Cha, Soohyun Hwang, Hyein Hwang, Seungryul Baek
Abstract: Reconstructing 3Ds of hand-object interaction (HOI) is a fundamental problem that can find numerous applications. Despite recent advances, there is no comprehensive pipeline yet for bimanual class-agnostic interaction reconstruction from a monocular RGB video, where two hands and an unknown object are interacting with each other. Previous works tackled the limited hand-object interaction case, where object templates are pre-known or only one hand is involved in the interaction. The bimanual interaction reconstruction exhibits severe occlusions introduced by complex interactions between two hands and an object. To solve this, we first introduce BIGS (Bimanual Interaction 3D Gaussian Splatting), a method that reconstructs 3D Gaussians of hands and an unknown object from a monocular video. To robustly obtain object Gaussians avoiding severe occlusions, we leverage prior knowledge of pre-trained diffusion model with score distillation sampling (SDS) loss, to reconstruct unseen object parts. For hand Gaussians, we exploit the 3D priors of hand model (i.e., MANO) and share a single Gaussian for two hands to effectively accumulate hand 3D information, given limited views. To further consider the 3D alignment between hands and objects, we include the interacting-subjects optimization step during Gaussian optimization. Our method achieves the state-of-the-art accuracy on two challenging datasets, in terms of 3D hand pose estimation (MPJPE), 3D object reconstruction (CDh, CDo, F10), and rendering quality (PSNR, SSIM, LPIPS), respectively.
Authors: Yonghao Huang, Leiting Chen, Chuan Zhou
Abstract: The joint interpretation of multi-modal and multi-view fundus images is critical for retinopathy prevention, as different views can show the complete 3D eyeball field and different modalities can provide complementary lesion areas. Compared with single images, the sequence relationships in multi-modal and multi-view fundus images contain long-range dependencies in lesion features. By modeling the long-range dependencies in these sequences, lesion areas can be more comprehensively mined, and modality-specific lesions can be detected. To learn the long-range dependency relationship and fuse complementary multi-scale lesion features between different fundus modalities, we design a multi-modal fundus image fusion method based on multi-scale cross-attention, which solves the static receptive field problem in previous multi-modal medical fusion methods based on attention. To capture multi-view relative positional relationships between different views and fuse comprehensive lesion features between different views, we design a multi-view fundus image fusion method based on shifted window self-attention, which also solves the computational complexity of the multi-view fundus fusion method based on self-attention is quadratic to the size and number of multi-view fundus images. Finally, we design a multi-task retinopathy diagnosis framework to help ophthalmologists reduce workload and improve diagnostic accuracy by combining the proposed two fusion methods. The experimental results of retinopathy classification and report generation tasks indicate our method's potential to improve the efficiency and reliability of retinopathy diagnosis in clinical practice, achieving a classification accuracy of 82.53\% and a report generation BlEU-1 of 0.543.
Authors: Ganxi Xu, Jinyi Long, Hanrui Wu, Jia Zhang
Abstract: Brain decoding currently faces significant challenges in individual differences, modality alignment, and high-dimensional embeddings. To address individual differences, researchers often use source subject data, which leads to issues such as privacy leakage and heavy data storage burdens. In modality alignment, current works focus on aligning the softmax probability distribution but neglect the alignment of marginal probability distributions, resulting in modality misalignment. Additionally, images and text are aligned separately with fMRI without considering the complex interplay between images and text, leading to poor image reconstruction. Finally, the enormous dimensionality of CLIP embeddings causes significant computational costs. Although the dimensionality of CLIP embeddings can be reduced by ignoring the number of patches obtained from images and the number of tokens acquired from text, this comes at the cost of a significant drop in model performance, creating a dilemma. To overcome these limitations, we propose a source-free domain adaptation-based brain decoding framework
Authors: Jizong Peng, Tze Ho Elden Tse, Kai Xu, Wenchao Gao, Angela Yao
Abstract: 3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM) algorithms; however, SfM is time-consuming and restricts the application of 3DGS in real-world scenarios and large-scale scene reconstruction. We introduce a constrained optimization method for simultaneous camera pose estimation and 3D reconstruction that does not require SfM support. Core to our approach is decomposing a camera pose into a sequence of camera-to-(device-)center and (device-)center-to-world optimizations. To facilitate, we propose two optimization constraints conditioned to the sensitivity of each parameter group and restricts each parameter's search space. In addition, as we learn the scene geometry directly from the noisy point clouds, we propose geometric constraints to improve the reconstruction quality. Experiments demonstrate that the proposed method significantly outperforms the existing (multi-modal) 3DGS baseline and methods supplemented by COLMAP on both our collected dataset and two public benchmarks.
Authors: Changhao Li, Yu Xin, Xiaowei Zhou, Ariel Shamir, Hao Zhang, Ligang Liu, Ruizhen Hu
Abstract: We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the importance of perceptual shape understanding for learning 3D shapes, MASH represents a 3D shape as a collection of observable local surface patches, each defined by a spherical distance function emanating from an anchor point. We further leverage the compactness of spherical harmonics to encode the MASH functions, combined with a generalized view cone with a parameterized base that masks the spatial extent of the spherical function to attain locality. We develop a differentiable optimization algorithm capable of converting any point cloud into a MASH representation accurately approximating ground-truth surfaces with arbitrary geometry and topology. Extensive experiments demonstrate that MASH is versatile for multiple applications including surface reconstruction, shape generation, completion, and blending, achieving superior performance thanks to its unique representation encompassing both implicit and explicit features.
Authors: Zhanzhou Feng, Shiliang Zhang
Abstract: Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those mask patterns resort to different criteria to depict image contents, sticking to a fixed pattern leads to a limited vision cues modeling capability.This paper introduces an evolved hierarchical masking method to pursue general visual cues modeling in self-supervised learning. The proposed method leverages the vision model being trained to parse the input visual cues into a hierarchy structure, which is hence adopted to generate masks accordingly. The accuracy of hierarchy is on par with the capability of the model being trained, leading to evolved mask patterns at different training stages. Initially, generated masks focus on low-level visual cues to grasp basic textures, then gradually evolve to depict higher-level cues to reinforce the learning of more complicated object semantics and contexts. Our method does not require extra pre-trained models or annotations and ensures training efficiency by evolving the training difficulty. We conduct extensive experiments on seven downstream tasks including partial-duplicate image retrieval relying on low-level details, as well as image classification and semantic segmentation that require semantic parsing capability. Experimental results demonstrate that it substantially boosts performance across these tasks. For instance, it surpasses the recent MAE by 1.1\% in imageNet-1K classification and 1.4\% in ADE20K segmentation with the same training epochs. We also align the proposed method with the current research focus on LLMs. The proposed approach bridges the gap with large-scale pre-training on semantic demanding tasks and enhances intricate detail perception in tasks requiring low-level feature recognition.
Authors: Shengyu Gong, Yueyang Li, Zijian Kang, Weiming Zeng, Hongjie Yan, Wai Ting Siok, Nizhuan Wang
Abstract: Accurate and efficient perception of emotional states in oneself and others is crucial, as emotion-related disorders are associated with severe psychosocial impairments. While electroencephalography (EEG) offers a powerful tool for emotion detection, current EEG-based emotion recognition (EER) methods face key limitations: insufficient model stability, limited accuracy in processing high-dimensional nonlinear EEG signals, and poor robustness against intra-subject variability and signal noise. To address these challenges, we propose LEREL (Lipschitz continuity-constrained Emotion Recognition Ensemble Learning), a novel framework that significantly enhances both the accuracy and robustness of emotion recognition performance. The LEREL framework employs Lipschitz continuity constraints to enhance model stability and generalization in EEG emotion recognition, reducing signal variability and noise susceptibility while maintaining strong performance on small-sample datasets. The ensemble learning strategy reduces single-model bias and variance through multi-classifier decision fusion, further optimizing overall performance. Experimental results on three public benchmark datasets (EAV, FACED and SEED) demonstrate LEREL's effectiveness, achieving average recognition accuracies of 76.43%, 83.00% and 89.22%, respectively.
Authors: Qingyuan Wang, Rui Song, Jiaojiao Li, Kerui Cheng, David Ferstl, Yinlin Hu
Abstract: We introduce SCFlow2, a plug-and-play refinement framework for 6D object pose estimation. Most recent 6D object pose methods rely on refinement to get accurate results. However, most existing refinement methods either suffer from noises in establishing correspondences, or rely on retraining for novel objects. SCFlow2 is based on the SCFlow model designed for refinement with shape constraint, but formulates the additional depth as a regularization in the iteration via 3D scene flow for RGBD frames. The key design of SCFlow2 is an introduction of geometry constraints into the training of recurrent matching network, by combining the rigid-motion embeddings in 3D scene flow and 3D shape prior of the target. We train SCFlow2 on a combination of dataset Objaverse, GSO and ShapeNet, and evaluate on BOP datasets with novel objects. After using our method as a post-processing, most state-of-the-art methods produce significantly better results, without any retraining or fine-tuning. The source code is available at https://scflow2.github.io.
Authors: Tzoulio Chamiti, Leandro Di Bella, Adrian Munteanu, Nikos Deligiannis
Abstract: Tracking multiple objects based on textual queries is a challenging task that requires linking language understanding with object association across frames. Previous works typically train the whole process end-to-end or integrate an additional referring text module into a multi-object tracker, but they both require supervised training and potentially struggle with generalization to open-set queries. In this work, we introduce ReferGPT, a novel zero-shot referring multi-object tracking framework. We provide a multi-modal large language model (MLLM) with spatial knowledge enabling it to generate 3D-aware captions. This enhances its descriptive capabilities and supports a more flexible referring vocabulary without training. We also propose a robust query-matching strategy, leveraging CLIP-based semantic encoding and fuzzy matching to associate MLLM generated captions with user queries. Extensive experiments on Refer-KITTI, Refer-KITTIv2 and Refer-KITTI+ demonstrate that ReferGPT achieves competitive performance against trained methods, showcasing its robustness and zero-shot capabilities in autonomous driving. The codes are available on https://github.com/Tzoulio/ReferGPT
Authors: Feng Lv, Chunlong Xia, Shuo Wang, Huo Cao
Abstract: Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for real-time transformer-based detectors has not yet been explored. Directly applying existing domain adaptation algorithms has proven to be suboptimal. In this paper, we propose RT-DATR, a simple and efficient real-time domain adaptive detection transformer. Building on RT-DETR as our base detector, we first introduce a local object-level feature alignment module to significantly enhance the feature representation of domain invariance during object transfer. Additionally, we introduce a scene semantic feature alignment module designed to boost cross-domain detection performance by aligning scene semantic features. Finally, we introduced a domain query and decoupled it from the object query to further align the instance feature distribution within the decoder layer, reduce the domain gap, and maintain discriminative ability. Experimental results on various benchmarks demonstrate that our method outperforms current state-of-the-art approaches. Our code will be released soon.
Authors: Tung Luu, Nam Le, Duc Le, Bac Le
Abstract: Visual counterfactual explanations are ideal hypothetical images that change the decision-making of the classifier with high confidence toward the desired class while remaining visually plausible and close to the initial image. In this paper, we propose a new approach to tackle two key challenges in recent prominent works: i) determining which specific counterfactual features are crucial for distinguishing the "concept" of the target class from the original class, and ii) supplying valuable explanations for the non-robust classifier without relying on the support of an adversarially robust model. Our method identifies the essential region for modification through algorithms that provide visual explanations, and then our framework generates realistic counterfactual explanations by combining adversarial attacks based on pruning the adversarial gradient of the target classifier and the latent diffusion model. The proposed method outperforms previous state-of-the-art results on various evaluation criteria on ImageNet and CelebA-HQ datasets. In general, our method can be applied to arbitrary classifiers, highlight the strong association between visual and counterfactual explanations, make semantically meaningful changes from the target classifier, and provide observers with subtle counterfactual images.
Authors: Saikat Dutta, Akhil Vasim, Siddhant Gole, Hamid Rezatofighi, Biplab Banerjee
Abstract: Image segmentation beyond predefined categories is a key challenge in remote sensing, where novel and unseen classes often emerge during inference. Open-vocabulary image Segmentation addresses these generalization issues in traditional supervised segmentation models while reducing reliance on extensive per-pixel annotations, which are both expensive and labor-intensive to obtain. Most Open-Vocabulary Segmentation (OVS) methods are designed for natural images but struggle with remote sensing data due to scale variations, orientation changes, and complex scene compositions. This necessitates the development of OVS approaches specifically tailored for remote sensing. In this context, we propose AerOSeg, a novel OVS approach for remote sensing data. First, we compute robust image-text correlation features using multiple rotated versions of the input image and domain-specific prompts. These features are then refined through spatial and class refinement blocks. Inspired by the success of the Segment Anything Model (SAM) in diverse domains, we leverage SAM features to guide the spatial refinement of correlation features. Additionally, we introduce a semantic back-projection module and loss to ensure the seamless propagation of SAM's semantic information throughout the segmentation pipeline. Finally, we enhance the refined correlation features using a multi-scale attention-aware decoder to produce the final segmentation map. We validate our SAM-guided Open-Vocabulary Remote Sensing Segmentation model on three benchmark remote sensing datasets: iSAID, DLRSD, and OpenEarthMap. Our model outperforms state-of-the-art open-vocabulary segmentation methods, achieving an average improvement of 2.54 h-mIoU.
Authors: Zhicheng Zhang, Hao Tang, Jinhui Tang
Abstract: Given the critical role of birds in ecosystems, Fine-Grained Bird Recognition (FGBR) has gained increasing attention, particularly in distinguishing birds within similar subcategories. Although Vision Transformer (ViT)-based methods often outperform Convolutional Neural Network (CNN)-based methods in FGBR, recent studies reveal that the limited receptive field of plain ViT model hinders representational richness and makes them vulnerable to scale variance. Thus, enhancing the multi-scale capabilities of existing ViT-based models to overcome this bottleneck in FGBR is a worthwhile pursuit. In this paper, we propose a novel framework for FGBR, namely Multi-scale Diverse Cues Modeling (MDCM), which explores diverse cues at different scales across various stages of a multi-scale Vision Transformer (MS-ViT) in an "Activation-Selection-Aggregation" paradigm. Specifically, we first propose a multi-scale cue activation module to ensure the discriminative cues learned at different stage are mutually different. Subsequently, a multi-scale token selection mechanism is proposed to remove redundant noise and highlight discriminative, scale-specific cues at each stage. Finally, the selected tokens from each stage are independently utilized for bird recognition, and the recognition results from multiple stages are adaptively fused through a multi-scale dynamic aggregation mechanism for final model decisions. Both qualitative and quantitative results demonstrate the effectiveness of our proposed MDCM, which outperforms CNN- and ViT-based models on several widely-used FGBR benchmarks.
Authors: Wenjin Ke, Zhe Li, Dong Li, Lu Tian, Emad Barsoum
Abstract: Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream tasks. Quantization-aware Training (QAT) can alleviate this problem, but it requires significantly more computational resources. To tackle this, we introduced Weight-Decomposed Low-Rank Quantization-Aware Training (DL-QAT), which merges the advantages of QAT while training only less than 1% of the total parameters. Specifically, we introduce a group-specific quantization magnitude to adjust the overall scale of each quantization group. Within each quantization group, we use LoRA matrices to update the weight size and direction in the quantization space. We validated the effectiveness of our method on the LLaMA and LLaMA2 model families. The results show significant improvements over our baseline method across different quantization granularities. For instance, for LLaMA-7B, our approach outperforms the previous state-of-the-art method by 4.2% in MMLU on 3-bit LLaMA-7B model. Additionally, our quantization results on pre-trained models also surpass previous QAT methods, demonstrating the superior performance and efficiency of our approach.
Authors: You Wu, Xucheng Wang, Xiangyang Yang, Mengyuan Liu, Dan Zeng, Hengzhou Ye, Shuiwang Li
Abstract: Single-stream architectures using Vision Transformer (ViT) backbones show great potential for real-time UAV tracking recently. However, frequent occlusions from obstacles like buildings and trees expose a major drawback: these models often lack strategies to handle occlusions effectively. New methods are needed to enhance the occlusion resilience of single-stream ViT models in aerial tracking. In this work, we propose to learn Occlusion-Robust Representations (ORR) based on ViTs for UAV tracking by enforcing an invariance of the feature representation of a target with respect to random masking operations modeled by a spatial Cox process. Hopefully, this random masking approximately simulates target occlusions, thereby enabling us to learn ViTs that are robust to target occlusion for UAV tracking. This framework is termed ORTrack. Additionally, to facilitate real-time applications, we propose an Adaptive Feature-Based Knowledge Distillation (AFKD) method to create a more compact tracker, which adaptively mimics the behavior of the teacher model ORTrack according to the task's difficulty. This student model, dubbed ORTrack-D, retains much of ORTrack's performance while offering higher efficiency. Extensive experiments on multiple benchmarks validate the effectiveness of our method, demonstrating its state-of-the-art performance. Codes is available at https://github.com/wuyou3474/ORTrack.
Authors: Aniket Pal, Sanket Biswas, Alloy Das, Ayush Lodh, Priyanka Banerjee, Soumitri Chattopadhyay, Dimosthenis Karatzas, Josep Llados, C. V. Jawahar
Abstract: Understanding and reasoning over academic handwritten notes remains a challenge in document AI, particularly for mathematical equations, diagrams, and scientific notations. Existing visual question answering (VQA) benchmarks focus on printed or structured handwritten text, limiting generalization to real-world note-taking. To address this, we introduce NoTeS-Bank, an evaluation benchmark for Neural Transcription and Search in note-based question answering. NoTeS-Bank comprises complex notes across multiple domains, requiring models to process unstructured and multimodal content. The benchmark defines two tasks: (1) Evidence-Based VQA, where models retrieve localized answers with bounding-box evidence, and (2) Open-Domain VQA, where models classify the domain before retrieving relevant documents and answers. Unlike classical Document VQA datasets relying on optical character recognition (OCR) and structured data, NoTeS-BANK demands vision-language fusion, retrieval, and multimodal reasoning. We benchmark state-of-the-art Vision-Language Models (VLMs) and retrieval frameworks, exposing structured transcription and reasoning limitations. NoTeS-Bank provides a rigorous evaluation with NDCG@5, MRR, Recall@K, IoU, and ANLS, establishing a new standard for visual document understanding and reasoning.
Authors: Sijing Wu, Yunhao Li, Ziwen Xu, Yixuan Gao, Huiyu Duan, Wei Sun, Guangtao Zhai
Abstract: Face video quality assessment (FVQA) deserves to be explored in addition to general video quality assessment (VQA), as face videos are the primary content on social media platforms and human visual system (HVS) is particularly sensitive to human faces. However, FVQA is rarely explored due to the lack of large-scale FVQA datasets. To fill this gap, we present the first large-scale in-the-wild FVQA dataset, FVQ-20K, which contains 20,000 in-the-wild face videos together with corresponding mean opinion score (MOS) annotations. Along with the FVQ-20K dataset, we further propose a specialized FVQA method named FVQ-Rater to achieve human-like rating and scoring for face video, which is the first attempt to explore the potential of large multimodal models (LMMs) for the FVQA task. Concretely, we elaborately extract multi-dimensional features including spatial features, temporal features, and face-specific features (i.e., portrait features and face embeddings) to provide comprehensive visual information, and take advantage of the LoRA-based instruction tuning technique to achieve quality-specific fine-tuning, which shows superior performance on both FVQ-20K and CFVQA datasets. Extensive experiments and comprehensive analysis demonstrate the significant potential of the FVQ-20K dataset and FVQ-Rater method in promoting the development of FVQA.
Authors: Jianyu Wu, Hao Yang, Xinhua Zeng, Guibing He, Zhiyu Chen, Zihui Li, Xiaochuan Zhang, Yangyang Ma, Run Fang, Yang Liu
Abstract: The diagnosis of pathological images is often limited by expert availability and regional disparities, highlighting the importance of automated diagnosis using Vision-Language Models (VLMs). Traditional multimodal models typically emphasize outcomes over the reasoning process, compromising the reliability of clinical decisions. To address the weak reasoning abilities and lack of supervised processes in pathological VLMs, we have innovatively proposed PathVLM-R1, a visual language model designed specifically for pathological images. We have based our model on Qwen2.5-VL-7B-Instruct and enhanced its performance for pathological tasks through meticulously designed post-training strategies. Firstly, we conduct supervised fine-tuning guided by pathological data to imbue the model with foundational pathological knowledge, forming a new pathological base model. Subsequently, we introduce Group Relative Policy Optimization (GRPO) and propose a dual reward-driven reinforcement learning optimization, ensuring strict constraint on logical supervision of the reasoning process and accuracy of results via cross-modal process reward and outcome accuracy reward. In the pathological image question-answering tasks, the testing results of PathVLM-R1 demonstrate a 14% improvement in accuracy compared to baseline methods, and it demonstrated superior performance compared to the Qwen2.5-VL-32B version despite having a significantly smaller parameter size. Furthermore, in out-domain data evaluation involving four medical imaging modalities: Computed Tomography (CT), dermoscopy, fundus photography, and Optical Coherence Tomography (OCT) images: PathVLM-R1's transfer performance improved by an average of 17.3% compared to traditional SFT methods. These results clearly indicate that PathVLM-R1 not only enhances accuracy but also possesses broad applicability and expansion potential.
Authors: Ziran Qin, Youru Lv, Mingbao Lin, Zeren Zhang, Danping Zou, Weiyao Lin
Abstract: Visual Autoregressive (VAR) models have emerged as a powerful approach for multi-modal content creation, offering high efficiency and quality across diverse multimedia applications. However, they face significant memory bottlenecks due to extensive KV cache accumulation during inference. Existing KV cache compression techniques for large language models are suboptimal for VAR models due to, as we identify in this paper, two distinct categories of attention heads in VAR models: Structural Heads, which preserve spatial coherence through diagonal attention patterns, and Contextual Heads, which maintain semantic consistency through vertical attention patterns. These differences render single-strategy KV compression techniques ineffective for VAR models. To address this, we propose HACK, a training-free Head-Aware Compression method for KV cache. HACK allocates asymmetric cache budgets and employs pattern-specific compression strategies tailored to the essential characteristics of each head category. Experiments on Infinity-2B, Infinity-8B, and VAR-d30 demonstrate its effectiveness in text-to-image and class-conditional generation tasks. HACK can hack down up to 50\% and 70\% of cache with minimal performance degradation for VAR-d30 and Infinity-8B, respectively. Even with 70\% and 90\% KV cache compression in VAR-d30 and Infinity-8B, HACK still maintains high-quality generation while reducing memory usage by 44.2\% and 58.9\%, respectively.
Authors: Zheyuan Zhang, Monica Dou, Linkai Peng, Hongyi Pan, Ulas Bagci, Boqing Gong
Abstract: Advertisement videos serve as a rich and valuable source of purpose-driven information, encompassing high-quality visual, textual, and contextual cues designed to engage viewers. They are often more complex than general videos of similar duration due to their structured narratives and rapid scene transitions, posing significant challenges to multi-modal large language models (MLLMs). In this work, we introduce VideoAds, the first dataset tailored for benchmarking the performance of MLLMs on advertisement videos. VideoAds comprises well-curated advertisement videos with complex temporal structures, accompanied by \textbf{manually} annotated diverse questions across three core tasks: visual finding, video summary, and visual reasoning. We propose a quantitative measure to compare VideoAds against existing benchmarks in terms of video complexity. Through extensive experiments, we find that Qwen2.5-VL-72B, an opensource MLLM, achieves 73.35\% accuracy on VideoAds, outperforming GPT-4o (66.82\%) and Gemini-1.5 Pro (69.66\%); the two proprietary models especially fall behind the opensource model in video summarization and reasoning, but perform the best in visual finding. Notably, human experts easily achieve a remarkable accuracy of 94.27\%. These results underscore the necessity of advancing MLLMs' temporal modeling capabilities and highlight VideoAds as a potentially pivotal benchmark for future research in understanding video that requires high FPS sampling. The dataset and evaluation code will be publicly available at https://videoadsbenchmark.netlify.app.
Authors: Jiaying Qian, Ziheng Jia, Zicheng Zhang, Zeyu Zhang, Guangtao Zhai, Xiongkuo Min
Abstract: The rapid advancement of AI-driven visual generation technologies has catalyzed significant breakthroughs in image manipulation, particularly in achieving photorealistic localized editing effects on natural scene images (NSIs). Despite extensive research on image quality assessment (IQA) for AI-generated images (AGIs), most studies focus on fully AI-generated outputs (e.g., text-to-image generation), leaving the quality assessment of partial-AIGC images (PAIs)-images with localized AI-driven edits an almost unprecedented field. Motivated by this gap, we construct the first large-scale PAI dataset towards explainable partial-AIGC image quality assessment (EPAIQA), the EPAIQA-15K, which includes 15K images with localized AI manipulation in different regions and over 300K multi-dimensional human ratings. Based on this, we leverage large multi-modal models (LMMs) and propose a three-stage model training paradigm. This paradigm progressively trains the LMM for editing region grounding, quantitative quality scoring, and quality explanation. Finally, we develop the EPAIQA series models, which possess explainable quality feedback capabilities. Our work represents a pioneering effort in the perceptual IQA field for comprehensive PAI quality assessment.
Authors: Huu-Phong Phan-Nguyen, Anh Dao, Tien-Huy Nguyen, Tuan Quang, Huu-Loc Tran, Tinh-Anh Nguyen-Nhu, Huy-Thach Pham, Quan Nguyen, Hoang M. Le, Quang-Vinh Dinh
Abstract: Nowadays, smartphones are ubiquitous, and almost everyone owns one. At the same time, the rapid development of AI has spurred extensive research on applying deep learning techniques to image classification. However, due to the limited resources available on mobile devices, significant challenges remain in balancing accuracy with computational efficiency. In this paper, we propose a novel training framework called Cycle Training, which adopts a three-stage training process that alternates between exploration and stabilization phases to optimize model performance. Additionally, we incorporate Semi-Supervised Domain Adaptation (SSDA) to leverage the power of large models and unlabeled data, thereby effectively expanding the training dataset. Comprehensive experiments on the CamSSD dataset for mobile scene detection demonstrate that our framework not only significantly improves classification accuracy but also ensures real-time inference efficiency. Specifically, our method achieves a 94.00% in Top-1 accuracy and a 99.17% in Top-3 accuracy and runs inference in just 1.61ms using CPU, demonstrating its suitability for real-world mobile deployment.
Authors: Tinh-Anh Nguyen-Nhu, Huu-Loc Tran, Nguyen-Khang Le, Minh-Nhat Nguyen, Tien-Huy Nguyen, Hoang-Long Nguyen-Huu, Huu-Phong Phan-Nguyen, Huy-Thach Pham, Quan Nguyen, Hoang M. Le, Quang-Vinh Dinh
Abstract: The exponential growth of digital video content has posed critical challenges in moment-level video retrieval, where existing methodologies struggle to efficiently localize specific segments within an expansive video corpus. Current retrieval systems are constrained by computational inefficiencies, temporal context limitations, and the intrinsic complexity of navigating video content. In this paper, we address these limitations through a novel Interactive Video Corpus Moment Retrieval framework that integrates a SuperGlobal Reranking mechanism and Adaptive Bidirectional Temporal Search (ABTS), strategically optimizing query similarity, temporal stability, and computational resources. By preprocessing a large corpus of videos using a keyframe extraction model and deduplication technique through image hashing, our approach provides a scalable solution that significantly reduces storage requirements while maintaining high localization precision across diverse video repositories.
Authors: Tyler Spears, Shen Zhu, Yinzhu Jin, Aman Shrivastava, P. Thomas Fletcher
Abstract: In this work, we introduce MedIL, a first-of-its-kind autoencoder built for encoding medical images with heterogeneous sizes and resolutions for image generation. Medical images are often large and heterogeneous, where fine details are of vital clinical importance. Image properties change drastically when considering acquisition equipment, patient demographics, and pathology, making realistic medical image generation challenging. Recent work in latent diffusion models (LDMs) has shown success in generating images resampled to a fixed-size. However, this is a narrow subset of the resolutions native to image acquisition, and resampling discards fine anatomical details. MedIL utilizes implicit neural representations to treat images as continuous signals, where encoding and decoding can be performed at arbitrary resolutions without prior resampling. We quantitatively and qualitatively show how MedIL compresses and preserves clinically-relevant features over large multi-site, multi-resolution datasets of both T1w brain MRIs and lung CTs. We further demonstrate how MedIL can influence the quality of images generated with a diffusion model, and discuss how MedIL can enhance generative models to resemble raw clinical acquisitions.
Authors: Huai-Qian Khor, Yante Li, Xingxun Jiang, Guoying Zhao
Abstract: Facial micro-expressions are spontaneous, brief and subtle facial motions that unveil the underlying, suppressed emotions. Detecting Action Units (AUs) in micro-expressions is crucial because it yields a finer representation of facial motions than categorical emotions, effectively resolving the ambiguity among different expressions. One of the difficulties in micro-expression analysis is that facial motions are subtle and brief, thereby increasing the difficulty in correlating facial motion features to AU occurrence. To bridge the subtlety issue, flow-related features and motion magnification are a few common approaches as they can yield descriptive motion changes and increased motion amplitude respectively. While motion magnification can amplify the motion changes, it also accounts for illumination changes and projection errors during the amplification process, thereby creating motion artefacts that confuse the model to learn inauthentic magnified motion features. The problem is further aggravated in the context of a more complicated task where more AU classes are analyzed in cross-database settings. To address this issue, we propose InfuseNet, a layer-wise unitary feature infusion framework that leverages motion context to constrain the Action Unit (AU) learning within an informative facial movement region, thereby alleviating the influence of magnification artefacts. On top of that, we propose leveraging magnified latent features instead of reconstructing magnified samples to limit the distortion and artefacts caused by the projection inaccuracy in the motion reconstruction process. Via alleviating the magnification artefacts, InfuseNet has surpassed the state-of-the-art results in the CD6ME protocol. Further quantitative studies have also demonstrated the efficacy of motion artefacts alleviation.
Authors: Sonia Laguna, Alberto Garcia-Garcia, Marie-Julie Rakotosaona, Stylianos Moschoglou, Leonhard Helminger, Sergio Orts-Escolano
Abstract: Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system for synthetic data generation for scalable, high-quality, and customizable 3D indoor scenes. By integrating and adapting text-to-image and multi-view diffusion models with Neural Radiance Field-based meshing, this system generates highfidelity 3D object assets from text prompts and incorporates them into pre-defined floor plans using a rendering tool. By introducing novel loss functions and training strategies into existing methods, the system supports on-demand scene generation, aiming to alleviate the scarcity of current available data, generally manually crafted by artists. This system advances the role of synthetic data in addressing machine learning training limitations, enabling more robust and generalizable models for real-world applications.
Authors: Duy-Cat Can, Quang-Huy Tang, Huong Ha, Binh T. Nguyen, Oliver Y. Ch\'en
Abstract: Timely and accurate diagnosis of neurodegenerative disorders, such as Alzheimer's disease, is central to disease management. Existing deep learning models require large-scale annotated datasets and often function as "black boxes". Additionally, datasets in clinical practice are frequently small or unlabeled, restricting the full potential of deep learning methods. Here, we introduce REMEMBER -- Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning -- a new machine learning framework that facilitates zero- and few-shot Alzheimer's diagnosis using brain MRI scans through a reference-based reasoning process. Specifically, REMEMBER first trains a contrastively aligned vision-text model using expert-annotated reference data and extends pseudo-text modalities that encode abnormality types, diagnosis labels, and composite clinical descriptions. Then, at inference time, REMEMBER retrieves similar, human-validated cases from a curated dataset and integrates their contextual information through a dedicated evidence encoding module and attention-based inference head. Such an evidence-guided design enables REMEMBER to imitate real-world clinical decision-making process by grounding predictions in retrieved imaging and textual context. Specifically, REMEMBER outputs diagnostic predictions alongside an interpretable report, including reference images and explanations aligned with clinical workflows. Experimental results demonstrate that REMEMBER achieves robust zero- and few-shot performance and offers a powerful and explainable framework to neuroimaging-based diagnosis in the real world, especially under limited data.
Authors: Jiahuan Long, Tingsong Jiang, Wen Yao, Shuai Jia, Weijia Zhang, Weien Zhou, Chao Ma, Xiaoqian Chen
Abstract: Tracking multiple objects in a continuous video stream is crucial for many computer vision tasks. It involves detecting and associating objects with their respective identities across successive frames. Despite significant progress made in multiple object tracking (MOT), recent studies have revealed the vulnerability of existing MOT methods to adversarial attacks. Nevertheless, all of these attacks belong to digital attacks that inject pixel-level noise into input images, and are therefore ineffective in physical scenarios. To fill this gap, we propose PapMOT, which can generate physical adversarial patches against MOT for both digital and physical scenarios. Besides attacking the detection mechanism, PapMOT also optimizes a printable patch that can be detected as new targets to mislead the identity association process. Moreover, we introduce a patch enhancement strategy to further degrade the temporal consistency of tracking results across video frames, resulting in more aggressive attacks. We further develop new evaluation metrics to assess the robustness of MOT against such attacks. Extensive evaluations on multiple datasets demonstrate that our PapMOT can successfully attack various architectures of MOT trackers in digital scenarios. We also validate the effectiveness of PapMOT for physical attacks by deploying printed adversarial patches in the real world.
Authors: Jiawei Wu, Zhifei Yang, Zhe Wang, Zhi Jin
Abstract: All-in-one image restoration, which aims to address diverse degradations within a unified framework, is critical for practical applications. However, existing methods rely on predicting and integrating degradation conditions, which can misactivate degradation-specific features in complex scenarios, limiting their restoration performance. To address this issue, we propose a novel all-in-one image restoration framework guided by Histograms of Oriented Gradients (HOG), named HOGformer. By leveraging the degradation-discriminative capability of HOG descriptors, HOGformer employs a dynamic self-attention mechanism that adaptively attends to long-range spatial dependencies based on degradation-aware HOG cues. To enhance the degradation sensitivity of attention inputs, we design a HOG-guided local dynamic-range convolution module that captures long-range degradation similarities while maintaining awareness of global structural information. Furthermore, we propose a dynamic interaction feed-forward module, efficiently increasing the model capacity to adapt to different degradations through channel-spatial interactions. Extensive experiments across diverse benchmarks, including adverse weather and natural degradations, demonstrate that HOGformer achieves state-of-the-art performance and generalizes effectively to complex real-world degradations. Code is available at https://github.com/Fire-friend/HOGformer.
Authors: Lei Sun, Yuhan Bao, Jiajun Zhai, Jingyun Liang, Yulun Zhang, Kaiwei Wang, Danda Pani Paudel, Luc Van Gool
Abstract: Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments. Prevalent event-based solutions primarily utilize events triggered by motion, i.e., ''motion events'' to strengthen only the edge texture, while leaving the high dynamic range and excellent low-light responsiveness of event cameras largely unexplored. This paper instead opens a new avenue from the perspective of estimating the illumination using ''temporal-mapping'' events, i.e., by converting the timestamps of events triggered by a transmittance modulation into brightness values. The resulting fine-grained illumination cues facilitate a more effective decomposition and enhancement of the reflectance component in low-light images through the proposed Illumination-aided Reflectance Enhancement module. Furthermore, the degradation model of temporal-mapping events under low-light condition is investigated for realistic training data synthesizing. To address the lack of datasets under this regime, we construct a beam-splitter setup and collect EvLowLight dataset that includes images, temporal-mapping events, and motion events. Extensive experiments across 5 synthetic datasets and our real-world EvLowLight dataset substantiate that the devised pipeline, dubbed RetinEV, excels in producing well-illuminated, high dynamic range images, outperforming previous state-of-the-art event-based methods by up to 6.62 dB, while maintaining an efficient inference speed of 35.6 frame-per-second on a 640X480 image.
Authors: Shengzhe Chen, Zhaoxuan Dong, Jun Liu
Abstract: For effective image segmentation, it is crucial to employ constraints informed by prior knowledge about the characteristics of the areas to be segmented to yield favorable segmentation outcomes. However, the existing methods have primarily focused on priors of specific properties or shapes, lacking consideration of the general global shape similarity from a Contour Flow (CF) perspective. Furthermore, naturally integrating this contour flow prior image segmentation model into the activation functions of deep convolutional networks through mathematical methods is currently unexplored. In this paper, we establish a concept of global shape similarity based on the premise that two shapes exhibit comparable contours. Furthermore, we mathematically derive a contour flow constraint that ensures the preservation of global shape similarity. We propose two implementations to integrate the constraint with deep neural networks. Firstly, the constraint is converted to a shape loss, which can be seamlessly incorporated into the training phase for any learning-based segmentation framework. Secondly, we add the constraint into a variational segmentation model and derive its iterative schemes for solution. The scheme is then unrolled to get the architecture of the proposed CFSSnet. Validation experiments on diverse datasets are conducted on classic benchmark deep network segmentation models. The results indicate a great improvement in segmentation accuracy and shape similarity for the proposed shape loss, showcasing the general adaptability of the proposed loss term regardless of specific network architectures. CFSSnet shows robustness in segmenting noise-contaminated images, and inherent capability to preserve global shape similarity.
Authors: Nooshin Bahador
Abstract: This study explored whether Vision Transformers (ViTs) developed orientation and color biases similar to those observed in the human brain. Using synthetic datasets with controlled variations in noise levels, angles, lengths, widths, and colors, we analyzed the behavior of ViTs fine-tuned with LoRA. Our findings revealed four key insights: First, ViTs exhibited an oblique effect showing the lowest angle prediction errors at 180 deg (horizontal) across all conditions. Second, angle prediction errors varied by color. Errors were highest for bluish hues and lowest for yellowish ones. Additionally, clustering analysis of angle prediction errors showed that ViTs grouped colors in a way that aligned with human perceptual categories. In addition to orientation and color biases, we observed phase transition phenomena. While two phase transitions occurred consistently across all conditions, the training loss curves exhibited delayed transitions when color was incorporated as an additional data attribute. Finally, we observed that attention heads in certain layers inherently develop specialized capabilities, functioning as task-agnostic feature extractors regardless of the downstream task. These observations suggest that biases and properties arise primarily from pre-training on the original dataset which shapes the model's foundational representations and the inherent architectural constraints of the vision transformer, rather than being solely determined by downstream data statistics.
Authors: Luis Vieira
Abstract: This study compares the performance of various preprocessing techniques for Traffic Sign Recognition (TSR) using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. Techniques such as CLAHE, HUE, and YUV were evaluated for their impact on classification accuracy. Results indicate that YUV in particular significantly enhance the performance of the HOG-SVM classifier (improving accuracy from 89.65% to 91.25%), providing insights into improvements for preprocessing pipeline of TSR applications.
Authors: Shengao Wang, Arjun Chandra, Aoming Liu, Venkatesh Saligrama, Boqing Gong
Abstract: Human infants rapidly develop visual reasoning skills from minimal input, suggesting that developmentally inspired pretraining could significantly enhance the efficiency of vision-language models (VLMs). Although recent efforts have leveraged infant-inspired datasets like SAYCam, existing evaluation benchmarks remain misaligned--they are either too simplistic, narrowly scoped, or tailored for large-scale pretrained models. Additionally, training exclusively on infant data overlooks the broader, diverse input from which infants naturally learn. To address these limitations, we propose BabyVLM, a novel framework comprising comprehensive in-domain evaluation benchmarks and a synthetic training dataset created via child-directed transformations of existing datasets. We demonstrate that VLMs trained with our synthetic dataset achieve superior performance on BabyVLM tasks compared to models trained solely on SAYCam or general-purpose data of the SAYCam size. BabyVLM thus provides a robust, developmentally aligned evaluation tool and illustrates how compact models trained on carefully curated data can generalize effectively, opening pathways toward data-efficient vision-language learning paradigms.
Authors: Jiahua Xu, Dawei Zhou, Lei Hu, Zaiyi Liu, Nannan Wang, Xinbo Gao
Abstract: Multimodal medical images play a crucial role in the precise and comprehensive clinical diagnosis. Diffusion model is a powerful strategy to synthesize the required medical images. However, existing approaches still suffer from the problem of anatomical structure distortion due to the overfitting of high-frequency information and the weakening of low-frequency information. Thus, we propose a novel method based on dynamic frequency balance and knowledge guidance. Specifically, we first extract the low-frequency and high-frequency components by decomposing the critical features of the model using wavelet transform. Then, a dynamic frequency balance module is designed to adaptively adjust frequency for enhancing global low-frequency features and effective high-frequency details as well as suppressing high-frequency noise. To further overcome the challenges posed by the large differences between different medical modalities, we construct a knowledge-guided mechanism that fuses the prior clinical knowledge from a visual language model with visual features, to facilitate the generation of accurate anatomical structures. Experimental evaluations on multiple datasets show the proposed method achieves significant improvements in qualitative and quantitative assessments, verifying its effectiveness and superiority.
Authors: Lincoln Linlin Xu, Yimin Zhu, Zack Dewis, Zhengsen Xu, Motasem Alkayid, Mabel Heffring, Saeid Taleghanidoozdoozan
Abstract: Although the recent Mamba models significantly improve hyperspectral image (HSI) classification, one critical challenge is caused by the difficulty to build the Mamba sequence efficiently and effectively. This paper presents a Sparse Deformable Mamba (SDMamba) approach for enhanced HSI classification, with the following contributions. First, to enhance Mamba sequence, an efficient Sparse Deformable Sequencing (SDS) approach is designed to adaptively learn the "optimal" sequence, leading to sparse and deformable Mamba sequence with increased detail preservation and decreased computations. Second, to boost spatial-spectral feature learning, based on SDS, a Sparse Deformable Spatial Mamba Module (SDSpaM) and a Sparse Deformable Spectral Mamba Module (SDSpeM) are designed for tailored modeling of the spatial information spectral information. Last, to improve the fusion of SDSpaM and SDSpeM, an attention based feature fusion approach is designed to integrate the outputs of the SDSpaM and SDSpeM. The proposed method is tested on several benchmark datasets with many state-of-the-art approaches, demonstrating that the proposed approach can achieve higher accuracy, faster speed, and better detail small-class preservation capability.
Authors: Lin Zhu, Yifeng Yang, Zichao Nie, Yuan Gao, Jiarui Li, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye
Abstract: In real-world scenarios, distribution shifts give rise to the importance of two problems: out-of-distribution (OoD) generalization, which focuses on models' generalization ability against covariate shifts (i.e., the changes of environments), and OoD detection, which aims to be aware of semantic shifts (i.e., test-time unseen classes). Real-world testing environments often involve a combination of both covariate and semantic shifts. While numerous methods have been proposed to address these critical issues, only a few works tackled them simultaneously. Moreover, prior works often improve one problem but sacrifice the other. To overcome these limitations, we delve into boosting OoD detection and OoD generalization from the perspective of information theory, which can be easily applied to existing models and different tasks. Building upon the theoretical bounds for mutual information and conditional entropy, we provide a unified approach, composed of Mutual Information Minimization (MI-Min) and Conditional Entropy Maximizing (CE-Max). Extensive experiments and comprehensive evaluations on multi-label image classification and object detection have demonstrated the superiority of our method. It successfully mitigates trade-offs between the two challenges compared to competitive baselines.
Authors: Tianyi Wang, Harry Cheng, Ming-Hui Liu, Mohan Kankanhalli
Abstract: Proactive Deepfake detection via robust watermarks has been raised ever since passive Deepfake detectors encountered challenges in identifying high-quality synthetic images. However, while demonstrating reasonable detection performance, they lack localization functionality and explainability in detection results. Additionally, the unstable robustness of watermarks can significantly affect the detection performance accordingly. In this study, we propose novel fractal watermarks for proactive Deepfake detection and localization, namely FractalForensics. Benefiting from the characteristics of fractals, we devise a parameter-driven watermark generation pipeline that derives fractal-based watermarks and conducts one-way encryption regarding the parameters selected. Subsequently, we propose a semi-fragile watermarking framework for watermark embedding and recovery, trained to be robust against benign image processing operations and fragile when facing Deepfake manipulations in a black-box setting. Meanwhile, we introduce an entry-to-patch strategy that implicitly embeds the watermark matrix entries into image patches at corresponding positions, achieving localization of Deepfake manipulations. Extensive experiments demonstrate satisfactory robustness and fragility of our approach against common image processing operations and Deepfake manipulations, outperforming state-of-the-art semi-fragile watermarking algorithms and passive detectors for Deepfake detection. Furthermore, by highlighting the areas manipulated, our method provides explainability for the proactive Deepfake detection results.
Authors: Weinan Jia, Mengqi Huang, Nan Chen, Lei Zhang, Zhendong Mao
Abstract: Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different image regions during the diffusion process, disregarding the naturally varying information densities present in these regions. However, large compression leads to limited local realism, while small compression increases computational complexity and compromises global consistency, ultimately impacting the quality of generated images. To address these limitations, we propose dynamically compressing different image regions by recognizing the importance of different regions, and introduce a novel two-stage framework designed to enhance the effectiveness and efficiency of image generation: (1) Dynamic VAE (DVAE) at first stage employs a hierarchical encoder to encode different image regions at different downsampling rates, tailored to their specific information densities, thereby providing more accurate and natural latent codes for the diffusion process. (2) Dynamic Diffusion Transformer (D$^2$iT) at second stage generates images by predicting multi-grained noise, consisting of coarse-grained (less latent code in smooth regions) and fine-grained (more latent codes in detailed regions), through an novel combination of the Dynamic Grain Transformer and the Dynamic Content Transformer. The strategy of combining rough prediction of noise with detailed regions correction achieves a unification of global consistency and local realism. Comprehensive experiments on various generation tasks validate the effectiveness of our approach. Code will be released at https://github.com/jiawn-creator/Dynamic-DiT.
Authors: Hussain Md. Safwan, Mahbub Islam Mahim, Fawwaz Mohammed Amin
Abstract: A common dilemma while photographing a scene is whether to capture it in wider angle, allowing more of the scene to be covered but in lesser details or to click in narrow angle that captures better details but leaves out portions of the scene. We propose a novel method in this paper that infuses wider shots with finer quality details that is usually associated with an image captured by the primary lens by capturing the same scene using both narrow and wide field of view (FoV) lenses. We do so by training a GAN-based model to learn to extract the visual quality parameters from a narrow angle shot and to transfer these to the corresponding wide-angle image of the scene. We have mentioned in details the proposed technique to isolate the visual essence of an image and to transfer it into another image. We have also elaborately discussed our implementation details and have presented the results of evaluation over several benchmark datasets and comparisons with contemporary advancements in the field.
Authors: Pooja Guhan, Divya Kothandaraman, Tsung-Wei Huang, Guan-Ming Su, Dinesh Manocha
Abstract: We introduce CamMimic, an innovative algorithm tailored for dynamic video editing needs. It is designed to seamlessly transfer the camera motion observed in a given reference video onto any scene of the user's choice in a zero-shot manner without requiring any additional data. Our algorithm achieves this using a two-phase strategy by leveraging a text-to-video diffusion model. In the first phase, we develop a multi-concept learning method using a combination of LoRA layers and an orthogonality loss to capture and understand the underlying spatial-temporal characteristics of the reference video as well as the spatial features of the user's desired scene. The second phase proposes a unique homography-based refinement strategy to enhance the temporal and spatial alignment of the generated video. We demonstrate the efficacy of our method through experiments conducted on a dataset containing combinations of diverse scenes and reference videos containing a variety of camera motions. In the absence of an established metric for assessing camera motion transfer between unrelated scenes, we propose CameraScore, a novel metric that utilizes homography representations to measure camera motion similarity between the reference and generated videos. Extensive quantitative and qualitative evaluations demonstrate that our approach generates high-quality, motion-enhanced videos. Additionally, a user study reveals that 70.31% of participants preferred our method for scene preservation, while 90.45% favored it for motion transfer. We hope this work lays the foundation for future advancements in camera motion transfer across different scenes.
Authors: Yongchao Feng, Yajie Liu, Shuai Yang, Wenrui Cai, Jinqing Zhang, Qiqi Zhan, Ziyue Huang, Hongxi Yan, Qiao Wan, Chenguang Liu, Junzhe Wang, Jiahui Lv, Ziqi Liu, Tengyuan Shi, Qingjie Liu, Yunhong Wang
Abstract: Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In this work, we present the systematic review of VLM-based detection and segmentation, view VLM as the foundational model and conduct comprehensive evaluations across multiple downstream tasks for the first time: 1) The evaluation spans eight detection scenarios (closed-set detection, domain adaptation, crowded objects, etc.) and eight segmentation scenarios (few-shot, open-world, small object, etc.), revealing distinct performance advantages and limitations of various VLM architectures across tasks. 2) As for detection tasks, we evaluate VLMs under three finetuning granularities: \textit{zero prediction}, \textit{visual fine-tuning}, and \textit{text prompt}, and further analyze how different finetuning strategies impact performance under varied task. 3) Based on empirical findings, we provide in-depth analysis of the correlations between task characteristics, model architectures, and training methodologies, offering insights for future VLM design. 4) We believe that this work shall be valuable to the pattern recognition experts working in the fields of computer vision, multimodal learning, and vision foundation models by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research. A project associated with this review and evaluation has been created at https://github.com/better-chao/perceptual_abilities_evaluation.
URLs: https://github.com/better-chao/perceptual_abilities_evaluation.
Authors: Yexing Xu, Longguang Wang, Minglin Chen, Sheng Ao, Li Li, Yulan Guo
Abstract: Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/.
Authors: Yue Yang, Christoph Leuze, Brian Hargreaves, Bruce Daniel, Fred Baik
Abstract: The use of Augmented Reality (AR) devices for surgical guidance has gained increasing traction in the medical field. Traditional registration methods often rely on external fiducial markers to achieve high accuracy and real-time performance. However, these markers introduce cumbersome calibration procedures and can be challenging to deploy in clinical settings. While commercial solutions have attempted real-time markerless tracking using the native RGB cameras of AR devices, their accuracy remains questionable for medical guidance, primarily due to occlusions and significant outliers between the live sensor data and the preoperative target anatomy point cloud derived from MRI or CT scans. In this work, we present a markerless framework that relies only on the depth sensor of AR devices and consists of two modules: a registration module for high-precision, outlier-robust target anatomy localization, and a tracking module for real-time pose estimation. The registration module integrates depth sensor error correction, a human-in-the-loop region filtering technique, and a robust global alignment with curvature-aware feature sampling, followed by local ICP refinement, for markerless alignment of preoperative models with patient anatomy. The tracking module employs a fast and robust registration algorithm that uses the initial pose from the registration module to estimate the target pose in real-time. We comprehensively evaluated the performance of both modules through simulation and real-world measurements. The results indicate that our markerless system achieves superior performance for registration and comparable performance for tracking to industrial solutions. The two-module design makes our system a one-stop solution for surgical procedures where the target anatomy moves or stays static during surgery.
Authors: Pengfei Wang (School of Computer Science,Engineering, Central South University, Changsha, China), Hao Zheng (School of Computer Science,Engineering, Central South University, Changsha, China), Zhigang Hu (School of Computer Science,Engineering, Central South University, Changsha, China), Aikun Xu (School of Computer Science,Engineering, Central South University, Changsha, China), Meiguang Zheng (School of Computer Science,Engineering, Central South University, Changsha, China), Liu Yang (School of Computer Science,Engineering, Central South University, Changsha, China)
Abstract: Existing SAR image classification methods based on Contrastive Learning often rely on sample generation strategies designed for optical images, failing to capture the distinct semantic and physical characteristics of SAR data. To address this, we propose Physics-Driven Contrastive Mutual Learning for SAR Classification (PCM-SAR), which incorporates domain-specific physical insights to improve sample generation and feature extraction. PCM-SAR utilizes the gray-level co-occurrence matrix (GLCM) to simulate realistic noise patterns and applies semantic detection for unsupervised local sampling, ensuring generated samples accurately reflect SAR imaging properties. Additionally, a multi-level feature fusion mechanism based on mutual learning enables collaborative refinement of feature representations. Notably, PCM-SAR significantly enhances smaller models by refining SAR feature representations, compensating for their limited capacity. Experimental results show that PCM-SAR consistently outperforms SOTA methods across diverse datasets and SAR classification tasks.
Authors: Yanze Jiang, Yanfeng Gu, Xian Li
Abstract: Hyperspectral point clouds (HPCs) can simultaneously characterize 3D spatial and spectral information of ground objects, offering excellent 3D perception and target recognition capabilities. Current approaches for generating HPCs often involve fusion techniques with hyperspectral images and LiDAR point clouds, which inevitably lead to geometric-spectral distortions due to fusion errors and obstacle occlusions. These adverse effects limit their performance in downstream fine-grained tasks across multiple scenarios, particularly in airborne applications. To address these issues, we propose PiV-AHPC, a 3D object detection network for airborne HPCs. To the best of our knowledge, this is the first attempt at this HPCs task. Specifically, we first develop a pillar-voxel dual-branch encoder, where the former captures spectral and vertical structural features from HPCs to overcome spectral distortion, while the latter emphasizes extracting accurate 3D spatial features from point clouds. A multi-level feature fusion mechanism is devised to enhance information interaction between the two branches, achieving neighborhood feature alignment and channel-adaptive selection, thereby organically integrating heterogeneous features and mitigating geometric distortion. Extensive experiments on two airborne HPCs datasets demonstrate that PiV-AHPC possesses state-of-the-art detection performance and high generalization capability.
Authors: Mengjiao Wang, Junpei Zhang, Xu Liu, Yuting Yang, Mengru Ma
Abstract: Video Object Segmentation (VOS) is one of the most fundamental and challenging tasks in computer vision and has a wide range of applications. Most existing methods rely on spatiotemporal memory networks to extract frame-level features and have achieved promising results on commonly used datasets. However, these methods often struggle in more complex real-world scenarios. This paper addresses this issue, aiming to achieve accurate segmentation of video objects in challenging scenes. We propose fine-tuning VOS (FVOS), optimizing existing methods for specific datasets through tailored training. Additionally, we introduce a morphological post-processing strategy to address the issue of excessively large gaps between adjacent objects in single-model predictions. Finally, we apply a voting-based fusion method on multi-scale segmentation results to generate the final output. Our approach achieves J&F scores of 76.81% and 83.92% during the validation and testing stages, respectively, securing third place overall in the MOSE Track of the 4th PVUW challenge 2025.
Authors: Puyu Han, Jiaju Kang, Yuhang Pan, Erting Pan, Zeyu Zhang, Qunchao Jin, Juntao Jiang, Zhichen Liu, Luqi Gong
Abstract: Large-scale pre-trained diffusion models have produced excellent results in the field of conditional image generation. However, restoration of ancient murals, as an important downstream task in this field, poses significant challenges to diffusion model-based restoration methods due to its large defective area and scarce training samples. Conditional restoration tasks are more concerned with whether the restored part meets the aesthetic standards of mural restoration in terms of overall style and seam detail, and such metrics for evaluating heuristic image complements are lacking in current research. We therefore propose DiffuMural, a combined Multi-scale convergence and Collaborative Diffusion mechanism with ControlNet and cyclic consistency loss to optimise the matching between the generated images and the conditional control. DiffuMural demonstrates outstanding capabilities in mural restoration, leveraging training data from 23 large-scale Dunhuang murals that exhibit consistent visual aesthetics. The model excels in restoring intricate details, achieving a coherent overall appearance, and addressing the unique challenges posed by incomplete murals lacking factual grounding. Our evaluation framework incorporates four key metrics to quantitatively assess incomplete murals: factual accuracy, textural detail, contextual semantics, and holistic visual coherence. Furthermore, we integrate humanistic value assessments to ensure the restored murals retain their cultural and artistic significance. Extensive experiments validate that our method outperforms state-of-the-art (SOTA) approaches in both qualitative and quantitative metrics.
Authors: Aisha L. Shuaibu, Kieran A. Gibb, Peter A. Wijeratne, Ivor J. A. Simpson
Abstract: Longitudinal image registration enables studying temporal changes in brain morphology which is useful in applications where monitoring the growth or atrophy of specific structures is important. However this task is challenging due to; noise/artifacts in the data and quantifying small anatomical changes between sequential scans. We propose a novel longitudinal registration method that models structural changes using temporally parameterized neural displacement fields. Specifically, we implement an implicit neural representation (INR) using a multi-layer perceptron that serves as a continuous coordinate-based approximation of the deformation field at any time point. In effect, for any N scans of a particular subject, our model takes as input a 3D spatial coordinate location x, y, z and a corresponding temporal representation t and learns to describe the continuous morphology of structures for both observed and unobserved points in time. Furthermore, we leverage the analytic derivatives of the INR to derive a new regularization function that enforces monotonic rate of change in the trajectory of the voxels, which is shown to provide more biologically plausible patterns. We demonstrate the effectiveness of our method on 4D brain MR registration.
Authors: Ting Huang, Zeyu Zhang, Yemin Wang, Hao Tang
Abstract: 3D captioning, which aims to describe the content of 3D scenes in natural language, remains highly challenging due to the inherent sparsity of point clouds and weak cross-modal alignment in existing methods. To address these challenges, we propose 3D CoCa, a novel unified framework that seamlessly combines contrastive vision-language learning with 3D caption generation in a single architecture. Our approach leverages a frozen CLIP vision-language backbone to provide rich semantic priors, a spatially-aware 3D scene encoder to capture geometric context, and a multi-modal decoder to generate descriptive captions. Unlike prior two-stage methods that rely on explicit object proposals, 3D CoCa jointly optimizes contrastive and captioning objectives in a shared feature space, eliminating the need for external detectors or handcrafted proposals. This joint training paradigm yields stronger spatial reasoning and richer semantic grounding by aligning 3D and textual representations. Extensive experiments on the ScanRefer and Nr3D benchmarks demonstrate that 3D CoCa significantly outperforms current state-of-the-arts by 10.2% and 5.76% in CIDEr at 0.5IoU, respectively. Code will be available at https://github.com/AIGeeksGroup/3DCoCa.
Authors: Xing Zi, Tengjun Ni, Xianjing Fan, Xian Tao, Jun Li, Ali Braytee, Mukesh Prasad
Abstract: Accurate and automated captioning of aerial imagery is crucial for applications like environmental monitoring, urban planning, and disaster management. However, this task remains challenging due to complex spatial semantics and domain variability. To address these issues, we introduce \textbf{AeroLite}, a lightweight, tag-guided captioning framework designed to equip small-scale language models (1--3B parameters) with robust and interpretable captioning capabilities specifically for remote sensing images. \textbf{AeroLite} leverages GPT-4o to generate a large-scale, semantically rich pseudo-caption dataset by integrating multiple remote sensing benchmarks, including DLRSD, iSAID, LoveDA, WHU, and RSSCN7. To explicitly capture key semantic elements such as orientation and land-use types, AeroLite employs natural language processing techniques to extract relevant semantic tags. These tags are then learned by a dedicated multi-label CLIP encoder, ensuring precise semantic predictions. To effectively fuse visual and semantic information, we propose a novel bridging multilayer perceptron (MLP) architecture, aligning semantic tags with visual embeddings while maintaining minimal computational overhead. AeroLite's flexible design also enables seamless integration with various pretrained large language models. We adopt a two-stage LoRA-based training approach: the initial stage leverages our pseudo-caption dataset to capture broad remote sensing semantics, followed by fine-tuning on smaller, curated datasets like UCM and Sydney Captions to refine domain-specific alignment. Experimental evaluations demonstrate that AeroLite surpasses significantly larger models (e.g., 13B parameters) in standard captioning metrics, including BLEU and METEOR, while maintaining substantially lower computational costs.
Authors: Shuchao Duan, Amirhossein Dadashzadeh, Alan Whone, Majid Mirmehdi
Abstract: Automated facial expression quality assessment (FEQA) in neurological disorders is critical for enhancing diagnostic accuracy and improving patient care, yet effectively capturing the subtle motions and nuances of facial muscle movements remains a challenge. We propose to analyse facial landmark trajectories, a compact yet informative representation, that encodes these subtle motions from a high-level structural perspective. Hence, we introduce Trajectory-guided Motion Perception Transformer (TraMP-Former), a novel FEQA framework that fuses landmark trajectory features for fine-grained motion capture with visual semantic cues from RGB frames, ultimately regressing the combined features into a quality score. Extensive experiments demonstrate that TraMP-Former achieves new state-of-the-art performance on benchmark datasets with neurological disorders, including PFED5 (up by 6.51%) and an augmented Toronto NeuroFace (up by 7.62%). Our ablation studies further validate the efficiency and effectiveness of landmark trajectories in FEQA. Our code is available at https://github.com/shuchaoduan/TraMP-Former.
Authors: Yuting Zhao, Yuheng Ji, Xiaoshuai Hao, Shuxiao Li
Abstract: Road Surface Reconstruction (RSR) is crucial for autonomous driving, enabling the understanding of road surface conditions. Recently, RSR from the Bird's Eye View (BEV) has gained attention for its potential to enhance performance. However, existing methods for transforming perspective views to BEV face challenges such as information loss and representation sparsity. Moreover, stereo matching in BEV is limited by the need to balance accuracy with inference speed. To address these challenges, we propose two efficient and accurate BEV-based RSR models: FastRSR-mono and FastRSR-stereo. Specifically, we first introduce Depth-Aware Projection (DAP), an efficient view transformation strategy designed to mitigate information loss and sparsity by querying depth and image features to aggregate BEV data within specific road surface regions using a pre-computed look-up table. To optimize accuracy and speed in stereo matching, we design the Spatial Attention Enhancement (SAE) and Confidence Attention Generation (CAG) modules. SAE adaptively highlights important regions, while CAG focuses on high-confidence predictions and filters out irrelevant information. FastRSR achieves state-of-the-art performance, exceeding monocular competitors by over 6.0% in elevation absolute error and providing at least a 3.0x speedup by stereo methods on the RSRD dataset. The source code will be released.
Authors: Hao Wang, Xiaobao Wei, Xiaoan Zhang, Jianing Li, Chengyu Bai, Ying Li, Ming Lu, Wenzhao Zheng, Shanghang Zhang
Abstract: Online 3D occupancy prediction provides a comprehensive spatial understanding of embodied environments. While the innovative EmbodiedOcc framework utilizes 3D semantic Gaussians for progressive indoor occupancy prediction, it overlooks the geometric characteristics of indoor environments, which are primarily characterized by planar structures. This paper introduces EmbodiedOcc++, enhancing the original framework with two key innovations: a Geometry-guided Refinement Module (GRM) that constrains Gaussian updates through plane regularization, along with a Semantic-aware Uncertainty Sampler (SUS) that enables more effective updates in overlapping regions between consecutive frames. GRM regularizes the position update to align with surface normals. It determines the adaptive regularization weight using curvature-based and depth-based constraints, allowing semantic Gaussians to align accurately with planar surfaces while adapting in complex regions. To effectively improve geometric consistency from different views, SUS adaptively selects proper Gaussians to update. Comprehensive experiments on the EmbodiedOcc-ScanNet benchmark demonstrate that EmbodiedOcc++ achieves state-of-the-art performance across different settings. Our method demonstrates improved edge accuracy and retains more geometric details while ensuring computational efficiency, which is essential for online embodied perception. The code will be released at: https://github.com/PKUHaoWang/EmbodiedOcc2.
Authors: Xiang Hu, Pingping Zhang, Yuhao Wang, Bin Yan, Huchuan Lu
Abstract: Aerial-Ground Person Re-IDentification (AG-ReID) aims to retrieve specific persons across cameras with different viewpoints. Previous works focus on designing discriminative ReID models to maintain identity consistency despite drastic changes in camera viewpoints. The core idea behind these methods is quite natural, but designing a view-robust network is a very challenging task. Moreover, they overlook the contribution of view-specific features in enhancing the model's capability to represent persons. To address these issues, we propose a novel two-stage feature learning framework named SD-ReID for AG-ReID, which takes advantage of the powerful understanding capacity of generative models, e.g., Stable Diffusion (SD), to generate view-specific features between different viewpoints. In the first stage, we train a simple ViT-based model to extract coarse-grained representations and controllable conditions. Then, in the second stage, we fine-tune the SD model to learn complementary representations guided by the controllable conditions. Furthermore, we propose the View-Refine Decoder (VRD) to obtain additional controllable conditions to generate missing cross-view features. Finally, we use the coarse-grained representations and all-view features generated by SD to retrieve target persons. Extensive experiments on the AG-ReID benchmarks demonstrate the effectiveness of our proposed SD-ReID. The source code will be available upon acceptance.
Authors: Jinhao Li, Zijian Chen, Runze Dong, Tingzhu Chen, Changbo Wang, Guangtao Zhai
Abstract: The oracle bone inscription (OBI) recognition plays a significant role in understanding the history and culture of ancient China. However, the existing OBI datasets suffer from a long-tail distribution problem, leading to biased performance of OBI recognition models across majority and minority classes. With recent advancements in generative models, OBI synthesis-based data augmentation has become a promising avenue to expand the sample size of minority classes. Unfortunately, current OBI datasets lack large-scale structure-aligned image pairs for generative model training. To address these problems, we first present the Oracle-P15K, a structure-aligned OBI dataset for OBI generation and denoising, consisting of 14,542 images infused with domain knowledge from OBI experts. Second, we propose a diffusion model-based pseudo OBI generator, called OBIDiff, to achieve realistic and controllable OBI generation. Given a clean glyph image and a target rubbing-style image, it can effectively transfer the noise style of the original rubbing to the glyph image. Extensive experiments on OBI downstream tasks and user preference studies show the effectiveness of the proposed Oracle-P15K dataset and demonstrate that OBIDiff can accurately preserve inherent glyph structures while transferring authentic rubbing styles effectively.
Authors: Zhicong Wu, Hongbin Xu, Gang Xu, Ping Nie, Zhixin Yan, Jinkai Zheng, Liangqiong Qu, Ming Li, Liqiang Nie
Abstract: Recent advancements in Generalizable Gaussian Splatting have enabled robust 3D reconstruction from sparse input views by utilizing feed-forward Gaussian Splatting models, achieving superior cross-scene generalization. However, while many methods focus on geometric consistency, they often neglect the potential of text-driven guidance to enhance semantic understanding, which is crucial for accurately reconstructing fine-grained details in complex scenes. To address this limitation, we propose TextSplat--the first text-driven Generalizable Gaussian Splatting framework. By employing a text-guided fusion of diverse semantic cues, our framework learns robust cross-modal feature representations that improve the alignment of geometric and semantic information, producing high-fidelity 3D reconstructions. Specifically, our framework employs three parallel modules to obtain complementary representations: the Diffusion Prior Depth Estimator for accurate depth information, the Semantic Aware Segmentation Network for detailed semantic information, and the Multi-View Interaction Network for refined cross-view features. Then, in the Text-Guided Semantic Fusion Module, these representations are integrated via the text-guided and attention-based feature aggregation mechanism, resulting in enhanced 3D Gaussian parameters enriched with detailed semantic cues. Experimental results on various benchmark datasets demonstrate improved performance compared to existing methods across multiple evaluation metrics, validating the effectiveness of our framework. The code will be publicly available.
Authors: Yining Zhao, Ali Braytee, Mukesh Prasad
Abstract: Medical image captioning via vision-language models has shown promising potential for clinical diagnosis assistance. However, generating contextually relevant descriptions with accurate modality recognition remains challenging. We present DualPrompt-MedCap, a novel dual-prompt enhancement framework that augments Large Vision-Language Models (LVLMs) through two specialized components: (1) a modality-aware prompt derived from a semi-supervised classification model pretrained on medical question-answer pairs, and (2) a question-guided prompt leveraging biomedical language model embeddings. To address the lack of captioning ground truth, we also propose an evaluation framework that jointly considers spatial-semantic relevance and medical narrative quality. Experiments on multiple medical datasets demonstrate that DualPrompt-MedCap outperforms the baseline BLIP-3 by achieving a 22% improvement in modality recognition accuracy while generating more comprehensive and question-aligned descriptions. Our method enables the generation of clinically accurate reports that can serve as medical experts' prior knowledge and automatic annotations for downstream vision-language tasks.
Authors: Jia Wei, Xiaoqi Zhao, Jonghye Woo, Jinsong Ouyang, Georges El Fakhri, Qingyu Chen, Xiaofeng Liu
Abstract: Single domain generalization (SDG) has recently attracted growing attention in medical image segmentation. One promising strategy for SDG is to leverage consistent semantic shape priors across different imaging protocols, scanner vendors, and clinical sites. However, existing dictionary learning methods that encode shape priors often suffer from limited representational power with a small set of offline computed shape elements, or overfitting when the dictionary size grows. Moreover, they are not readily compatible with large foundation models such as the Segment Anything Model (SAM). In this paper, we propose a novel Mixture-of-Shape-Experts (MoSE) framework that seamlessly integrates the idea of mixture-of-experts (MoE) training into dictionary learning to efficiently capture diverse and robust shape priors. Our method conceptualizes each dictionary atom as a shape expert, which specializes in encoding distinct semantic shape information. A gating network dynamically fuses these shape experts into a robust shape map, with sparse activation guided by SAM encoding to prevent overfitting. We further provide this shape map as a prompt to SAM, utilizing the powerful generalization capability of SAM through bidirectional integration. All modules, including the shape dictionary, are trained in an end-to-end manner. Extensive experiments on multiple public datasets demonstrate its effectiveness.
Authors: Lexington Whalen (Celine), Zhenbang Du (Celine), Haoran You (Celine), Chaojian Li (Celine), Sixu Li (Celine), Yingyan (Celine), Lin
Abstract: Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose EB-Diff-Train, a new efficient DM training approach that is orthogonal to other methods of accelerating DM training, by investigating and leveraging Early-Bird (EB) tickets -- sparse subnetworks that manifest early in the training process and maintain high generation quality. We first investigate the existence of traditional EB tickets in DMs, enabling competitive generation quality without fully training a dense model. Then, we delve into the concept of diffusion-dedicated EB tickets, drawing on insights from varying importance of different timestep regions. These tickets adapt their sparsity levels according to the importance of corresponding timestep regions, allowing for aggressive sparsity during non-critical regions while conserving computational resources for crucial timestep regions. Building on this, we develop an efficient DM training technique that derives timestep-aware EB tickets, trains them in parallel, and combines them during inference for image generation. Extensive experiments validate the existence of both traditional and timestep-aware EB tickets, as well as the effectiveness of our proposed EB-Diff-Train method. This approach can significantly reduce training time both spatially and temporally -- achieving 2.9$\times$ to 5.8$\times$ speedups over training unpruned dense models, and up to 10.3$\times$ faster training compared to standard train-prune-finetune pipelines -- without compromising generative quality. Our code is available at https://github.com/GATECH-EIC/Early-Bird-Diffusion.
Authors: Xingke Song, Xiaoying Yang, Chenglin Yao, Jianfeng Ren, Ruibin Bai, Xin Chen, Xudong Jiang
Abstract: Solving jigsaw puzzles has been extensively studied. While most existing models focus on solving either small-scale puzzles or puzzles with no gap between fragments, solving large-scale puzzles with gaps presents distinctive challenges in both image understanding and combinatorial optimization. To tackle these challenges, we propose a framework of Evolutionary Reinforcement Learning with Multi-head Puzzle Perception (ERL-MPP) to derive a better set of swapping actions for solving the puzzles. Specifically, to tackle the challenges of perceiving the puzzle with gaps, a Multi-head Puzzle Perception Network (MPPN) with a shared encoder is designed, where multiple puzzlet heads comprehensively perceive the local assembly status, and a discriminator head provides a global assessment of the puzzle. To explore the large swapping action space efficiently, an Evolutionary Reinforcement Learning (EvoRL) agent is designed, where an actor recommends a set of suitable swapping actions from a large action space based on the perceived puzzle status, a critic updates the actor using the estimated rewards and the puzzle status, and an evaluator coupled with evolutionary strategies evolves the actions aligning with the historical assembly experience. The proposed ERL-MPP is comprehensively evaluated on the JPLEG-5 dataset with large gaps and the MIT dataset with large-scale puzzles. It significantly outperforms all state-of-the-art models on both datasets.
Authors: Jiuchen Chen, Xinyu Yan, Qizhi Xu, Kaiqi Li
Abstract: Global contextual information and local detail features are essential for haze removal tasks. Deep learning models perform well on small, low-resolution images, but they encounter difficulties with large, high-resolution ones due to GPU memory limitations. As a compromise, they often resort to image slicing or downsampling. The former diminishes global information, while the latter discards high-frequency details. To address these challenges, we propose DehazeXL, a haze removal method that effectively balances global context and local feature extraction, enabling end-to-end modeling of large images on mainstream GPU hardware. Additionally, to evaluate the efficiency of global context utilization in haze removal performance, we design a visual attribution method tailored to the characteristics of haze removal tasks. Finally, recognizing the lack of benchmark datasets for haze removal in large images, we have developed an ultra-high-resolution haze removal dataset (8KDehaze) to support model training and testing. It includes 10000 pairs of clear and hazy remote sensing images, each sized at 8192 $\times$ 8192 pixels. Extensive experiments demonstrate that DehazeXL can infer images up to 10240 $\times$ 10240 pixels with only 21 GB of memory, achieving state-of-the-art results among all evaluated methods. The source code and experimental dataset are available at https://github.com/CastleChen339/DehazeXL.
Authors: Atharv Mahesh Mane, Dulanga Weerakoon, Vigneshwaran Subbaraju, Sougata Sen, Sanjay E. Sarma, Archan Misra
Abstract: 3-Dimensional Embodied Reference Understanding (3D-ERU) combines a language description and an accompanying pointing gesture to identify the most relevant target object in a 3D scene. Although prior work has explored pure language-based 3D grounding, there has been limited exploration of 3D-ERU, which also incorporates human pointing gestures. To address this gap, we introduce a data augmentation framework-Imputer, and use it to curate a new benchmark dataset-ImputeRefer for 3D-ERU, by incorporating human pointing gestures into existing 3D scene datasets that only contain language instructions. We also propose Ges3ViG, a novel model for 3D-ERU that achieves ~30% improvement in accuracy as compared to other 3D-ERU models and ~9% compared to other purely language-based 3D grounding models. Our code and dataset are available at https://github.com/AtharvMane/Ges3ViG.
Authors: Xingjian Zhang, Siwei Wen, Wenjun Wu, Lei Huang
Abstract: Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as mathematics and code, and researchers generally choose large-scale models as the foundation. We argue that exploring small-scale models' reasoning capabilities remains valuable for researchers with limited computational resources. Moreover, enabling models to explain their reasoning processes on general question-answering datasets is equally meaningful. Therefore, we present the small-scale video reasoning model TinyLLaVA-Video-R1. Based on TinyLLaVA-Video, a traceably trained video understanding model with no more than 4B parameters, it not only demonstrates significantly improved reasoning and thinking capabilities after using reinforcement learning on general Video-QA datasets, but also exhibits the emergent characteristic of "aha moments". Furthermore, we share a series of experimental findings, aiming to provide practical insights for future exploration of video reasoning (thinking) abilities in small-scale models. It is available at https://github.com/ZhangXJ199/TinyLLaVA-Video-R1.
Authors: Kaiyu Li, Zepeng Xin, Li Pang, Chao Pang, Yupeng Deng, Jing Yao, Guisong Xia, Deyu Meng, Zhi Wang, Xiangyong Cao
Abstract: Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to handle complex, implicit queries that require reasoning over spatial context, domain knowledge, and implicit user intent. Motivated by this, we introduce a new task, \ie, geospatial pixel reasoning, which allows implicit querying and reasoning and generates the mask of the target region. To advance this task, we construct and release the first large-scale benchmark dataset called EarthReason, which comprises 5,434 manually annotated image masks with over 30,000 implicit question-answer pairs. Moreover, we propose SegEarth-R1, a simple yet effective language-guided segmentation baseline that integrates a hierarchical visual encoder, a large language model (LLM) for instruction parsing, and a tailored mask generator for spatial correlation. The design of SegEarth-R1 incorporates domain-specific adaptations, including aggressive visual token compression to handle ultra-high-resolution remote sensing images, a description projection module to fuse language and multi-scale features, and a streamlined mask prediction pipeline that directly queries description embeddings. Extensive experiments demonstrate that SegEarth-R1 achieves state-of-the-art performance on both reasoning and referring segmentation tasks, significantly outperforming traditional and LLM-based segmentation methods. Our data and code will be released at https://github.com/earth-insights/SegEarth-R1.
Authors: Xingrui Wang, Jiang Liu, Ze Wang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Yusheng Su, Alan Yuille, Zicheng Liu, Emad Barsoum
Abstract: Generating video from various conditions, such as text, image, and audio, enables both spatial and temporal control, leading to high-quality generation results. Videos with dramatic motions often require a higher frame rate to ensure smooth motion. Currently, most audio-to-visual animation models use uniformly sampled frames from video clips. However, these uniformly sampled frames fail to capture significant key moments in dramatic motions at low frame rates and require significantly more memory when increasing the number of frames directly. In this paper, we propose KeyVID, a keyframe-aware audio-to-visual animation framework that significantly improves the generation quality for key moments in audio signals while maintaining computation efficiency. Given an image and an audio input, we first localize keyframe time steps from the audio. Then, we use a keyframe generator to generate the corresponding visual keyframes. Finally, we generate all intermediate frames using the motion interpolator. Through extensive experiments, we demonstrate that KeyVID significantly improves audio-video synchronization and video quality across multiple datasets, particularly for highly dynamic motions. The code is released in https://github.com/XingruiWang/KeyVID.
Authors: Yao Yuan, Pan Gao, Qun Dai, Jie Qin, Wei Xiang
Abstract: Recently, salient object detection (SOD) methods have achieved impressive performance. However, salient regions predicted by existing methods usually contain unsaturated regions and shadows, which limits the model for reliable fine-grained predictions. To address this, we introduce the uncertainty guidance learning approach to SOD, intended to enhance the model's perception of uncertain regions. Specifically, we design a novel Uncertainty Guided Refinement Attention Network (UGRAN), which incorporates three important components, i.e., the Multilevel Interaction Attention (MIA) module, the Scale Spatial-Consistent Attention (SSCA) module, and the Uncertainty Refinement Attention (URA) module. Unlike conventional methods dedicated to enhancing features, the proposed MIA facilitates the interaction and perception of multilevel features, leveraging the complementary characteristics among multilevel features. Then, through the proposed SSCA, the salient information across diverse scales within the aggregated features can be integrated more comprehensively and integrally. In the subsequent steps, we utilize the uncertainty map generated from the saliency prediction map to enhance the model's perception capability of uncertain regions, generating a highly-saturated fine-grained saliency prediction map. Additionally, we devise an adaptive dynamic partition (ADP) mechanism to minimize the computational overhead of the URA module and improve the utilization of uncertainty guidance. Experiments on seven benchmark datasets demonstrate the superiority of the proposed UGRAN over the state-of-the-art methodologies. Codes will be released at https://github.com/I2-Multimedia-Lab/UGRAN.
Authors: Pranav Manu, Astitva Srivastava, Amit Raj, Varun Jampani, Avinash Sharma, P. J. Narayanan
Abstract: Creating photorealistic, animatable, and relightable 3D head avatars traditionally requires expensive Lightstage with multiple calibrated cameras, making it inaccessible for widespread adoption. To bridge this gap, we present a novel, cost-effective approach for creating high-quality relightable head avatars using only a smartphone equipped with polaroid filters. Our approach involves simultaneously capturing cross-polarized and parallel-polarized video streams in a dark room with a single point-light source, separating the skin's diffuse and specular components during dynamic facial performances. We introduce a hybrid representation that embeds 2D Gaussians in the UV space of a parametric head model, facilitating efficient real-time rendering while preserving high-fidelity geometric details. Our learning-based neural analysis-by-synthesis pipeline decouples pose and expression-dependent geometrical offsets from appearance, decomposing the surface into albedo, normal, and specular UV texture maps, along with the environment maps. We collect a unique dataset of various subjects performing diverse facial expressions and head movements.
Authors: Jiachen Liu, Yuan Xue, Haomiao Ni, Rui Yu, Zihan Zhou, Sharon X. Huang
Abstract: Generating realistic building layouts for automatic building design has been studied in both the computer vision and architecture domains. Traditional approaches from the architecture domain, which are based on optimization techniques or heuristic design guidelines, can synthesize desirable layouts, but usually require post-processing and involve human interaction in the design pipeline, making them costly and timeconsuming. The advent of deep generative models has significantly improved the fidelity and diversity of the generated architecture layouts, reducing the workload by designers and making the process much more efficient. In this paper, we conduct a comprehensive review of three major research topics of architecture layout design and generation: floorplan layout generation, scene layout synthesis, and generation of some other formats of building layouts. For each topic, we present an overview of the leading paradigms, categorized either by research domains (architecture or machine learning) or by user input conditions or constraints. We then introduce the commonly-adopted benchmark datasets that are used to verify the effectiveness of the methods, as well as the corresponding evaluation metrics. Finally, we identify the well-solved problems and limitations of existing approaches, then propose new perspectives as promising directions for future research in this important research area. A project associated with this survey to maintain the resources is available at awesome-building-layout-generation.
Authors: Zijian Wu, Shuojue Yang, Yueming Jin, Septimiu E Salcudean
Abstract: In robot-assisted laparoscopic radical prostatectomy (RALP), the location of the instrument tip is important to register the ultrasound frame with the laparoscopic camera frame. A long-standing limitation is that the instrument tip position obtained from the da Vinci API is inaccurate and requires hand-eye calibration. Thus, directly computing the position of the tool tip in the camera frame using the vision-based method becomes an attractive solution. Besides, surgical instrument tip detection is the key component of other tasks, like surgical skill assessment and surgery automation. However, this task is challenging due to the small size of the tool tip and the articulation of the surgical instrument. Surgical instrument segmentation becomes relatively easy due to the emergence of the Segmentation Foundation Model, i.e., Segment Anything. Based on this advancement, we explore the deep learning-based surgical instrument tip detection approach that takes the part-level instrument segmentation mask as input. Comparison experiments with a hand-crafted image-processing approach demonstrate the superiority of the proposed method on simulated and real datasets.
Authors: Gaurav Shinde, Anuradha Ravi, Emon Dey, Shadman Sakib, Milind Rampure, Nirmalya Roy
Abstract: Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs of efficient VLMs. Furthermore, we establish a GitHub repository at https://github.com/MPSCUMBC/Efficient-Vision-Language-Models-A-Survey to compile all surveyed papers, which we will actively update. Our objective is to foster deeper research in this area.
URLs: https://github.com/MPSCUMBC/Efficient-Vision-Language-Models-A-Survey
Authors: Vasilii Korolkov, Andrey Yanchenko
Abstract: Detecting transitions between intro/credits and main content in videos is a crucial task for content segmentation, indexing, and recommendation systems. Manual annotation of such transitions is labor-intensive and error-prone, while heuristic-based methods often fail to generalize across diverse video styles. In this work, we introduce a deep learning-based approach that formulates the problem as a sequence-to-sequence classification task, where each second of a video is labeled as either "intro" or "film." Our method extracts frames at a fixed rate of 1 FPS, encodes them using CLIP (Contrastive Language-Image Pretraining), and processes the resulting feature representations with a multihead attention model incorporating learned positional encoding. The system achieves an F1-score of 91.0%, Precision of 89.0%, and Recall of 97.0% on the test set, and is optimized for real-time inference, achieving 11.5 FPS on CPU and 107 FPS on high-end GPUs. This approach has practical applications in automated content indexing, highlight detection, and video summarization. Future work will explore multimodal learning, incorporating audio features and subtitles to further enhance detection accuracy.
Authors: Yuyang Ji, Haohan Wang
Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable versatility but face challenges in demonstrating true visual understanding, particularly in chart reasoning tasks. Existing benchmarks like ChartQA reveal significant reliance on text-based shortcuts and probabilistic pattern-matching rather than genuine visual reasoning. To rigorously evaluate visual reasoning, we introduce a more challenging test scenario by removing textual labels and introducing chart perturbations in the ChartQA dataset. Under these conditions, models like GPT-4o and Gemini-2.0 Pro experience up to a 30% performance drop, underscoring their limitations. To address these challenges, we propose Socratic Chart, a new framework that transforms chart images into Scalable Vector Graphics (SVG) representations, enabling MLLMs to integrate textual and visual modalities for enhanced chart understanding. Socratic Chart employs a multi-agent pipeline with specialized agent-generators to extract primitive chart attributes (e.g., bar heights, line coordinates) and an agent-critic to validate results, ensuring high-fidelity symbolic representations. Our framework surpasses state-of-the-art models in accurately capturing chart primitives and improving reasoning performance, establishing a robust pathway for advancing MLLM visual understanding.
Authors: Diego Marcondes
Abstract: This paper introduces the class of grey-scale image stack operators as those that (a) map binary-images into binary-images and (b) commute in average with cross-sectioning. We show that stack operators are 1-Lipchitz extensions of set operators which can be represented by applying a characteristic set operator to the cross-sections of the image and summing. In particular, they are a generalisation of stack filters, for which the characteristic set operators are increasing. Our main result is that stack operators inherit lattice properties of the characteristic set operators. We focus on the case of translation-invariant and locally defined stack operators and show the main result by deducing the characteristic function, kernel, and basis representation of stack operators. The results of this paper have implications on the design of image operators, since imply that to solve some grey-scale image processing problems it is enough to design an operator for performing the desired transformation on binary images, and then considering its extension given by a stack operator. We leave many topics for future research regarding the machine learning of stack operators and the characterisation of the image processing problems that can be solved by them.
Authors: Chao Liu, Arash Vahdat
Abstract: Temporally consistent video-to-video generation is essential for applications of video diffusion models in areas such as sim-to-real, style-transfer, video upsampling, etc. In this paper, we propose a video diffusion framework that leverages temporally consistent noise to generate coherent video frames without specialized modules or additional constraints. We show that the standard training objective of diffusion models, when applied with temporally consistent noise, encourages the model to be equivariant to spatial transformations in input video and noise. This enables our model to better follow motion patterns from the input video, producing aligned motion and high-fidelity frames. Furthermore, we extend our approach to 3D-consistent video generation by attaching noise as textures on 3D meshes, ensuring 3D consistency in sim-to-real applications. Experimental results demonstrate that our method surpasses state-of-the-art baselines in motion alignment, 3D consistency, and video quality while requiring only a few sampling steps in practice.
Authors: Dinh Dai Quan Tran, Hoang-Thien Nguyen. Thanh-Huy Nguyen, Gia-Van To, Tien-Huy Nguyen, Quan Nguyen
Abstract: Semi-Supervised Semantic Segmentation (SSSS) aims to improve segmentation accuracy by leveraging a small set of labeled images alongside a larger pool of unlabeled data. Recent advances primarily focus on pseudo-labeling, consistency regularization, and co-training strategies. However, existing methods struggle to balance global semantic representation with fine-grained local feature extraction. To address this challenge, we propose a novel tri-branch semi-supervised segmentation framework incorporating a dual-teacher strategy, named IGL-DT. Our approach employs SwinUnet for high-level semantic guidance through Global Context Learning and ResUnet for detailed feature refinement via Local Regional Learning. Additionally, a Discrepancy Learning mechanism mitigates over-reliance on a single teacher, promoting adaptive feature learning. Extensive experiments on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches, achieving superior segmentation performance across various data regimes.
Authors: Beomseok Kang, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi, Han-Pang Chiu, Supun Samarasekera
Abstract: Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally identical teacher and student networks, relying on Exponential Moving Average (EMA) updates. However, these approaches face substantial performance degradation with lightweight models due to inherent architectural inflexibility leading to low-quality pseudo-labels. To address this, we propose Distilled Unsupervised Domain Adaptation (DUDA), a novel framework that combines EMA-based self-training with knowledge distillation (KD). Our method employs an auxiliary student network to bridge the architectural gap between heavyweight and lightweight models for EMA-based updates, resulting in improved pseudo-label quality. DUDA employs a strategic fusion of UDA and KD, incorporating innovative elements such as gradual distillation from large to small networks, inconsistency loss prioritizing poorly adapted classes, and learning with multiple teachers. Extensive experiments across four UDA benchmarks demonstrate DUDA's superiority in achieving SOTA performance with lightweight models, often surpassing the performance of heavyweight models from other approaches.
Authors: Chenyang Zhao, Jia Wan, Antoni B. Chan
Abstract: Compared with the generic scenes, crowded scenes contain highly-overlapped instances, which result in: 1) more ambiguous anchors during training of object detectors, and 2) more predictions are likely to be mistakenly suppressed in post-processing during inference. To address these problems, we propose two new strategies, density-guided anchors (DGA) and density-guided NMS (DG-NMS), which uses object density maps to jointly compute optimal anchor assignments and reweighing, as well as an adaptive NMS. Concretely, based on an unbalanced optimal transport (UOT) problem, the density owned by each ground-truth object is transported to each anchor position at a minimal transport cost. And density on anchors comprises an instance-specific density distribution, from which DGA decodes the optimal anchor assignment and re-weighting strategy. Meanwhile, DG-NMS utilizes the predicted density map to adaptively adjust the NMS threshold to reduce mistaken suppressions. In the UOT, a novel overlap-aware transport cost is specifically designed for ambiguous anchors caused by overlapped neighboring objects. Extensive experiments on the challenging CrowdHuman dataset with Citypersons dataset demonstrate that our proposed density-guided detector is effective and robust to crowdedness. The code and pre-trained models will be made available later.
Authors: Hezhao Liu, Yang Lu, Mengke Li, Yiqun Zhang, Shreyank N Gowda, Chen Gong, Hanzi Wang
Abstract: Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as a single labeled sample in the dataset. General SSL approaches struggle to train effectively from scratch under such constraints, while methods utilizing pre-trained models often fail to find an optimal balance between leveraging limited labeled data and abundant unlabeled data. To address this challenge, we propose Firstly Adapt, Then catEgorize (FATE), a novel SSL framework tailored for scenarios with extremely limited labeled data. At its core, the two-stage prompt tuning paradigm FATE exploits unlabeled data to compensate for scarce supervision signals, then transfers to downstream tasks. Concretely, FATE first adapts a pre-trained model to the feature distribution of downstream data using volumes of unlabeled samples in an unsupervised manner. It then applies an SSL method specifically designed for pre-trained models to complete the final classification task. FATE is designed to be compatible with both vision and vision-language pre-trained models. Extensive experiments demonstrate that FATE effectively mitigates challenges arising from the scarcity of labeled samples in SSL, achieving an average performance improvement of 33.74% across seven benchmarks compared to state-of-the-art SSL methods. Code is available at https://anonymous.4open.science/r/Semi-supervised-learning-BA72.
URLs: https://anonymous.4open.science/r/Semi-supervised-learning-BA72.
Authors: Lu Yue, Dongliang Zhou, Liang Xie, Erwei Yin, Feitian Zhang
Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to navigate unknown, continuous spaces based on natural language instructions. Compared to discrete settings, VLN-CE poses two core perception challenges. First, the absence of predefined observation points leads to heterogeneous visual memories and weakened global spatial correlations. Second, cumulative reconstruction errors in three-dimensional scenes introduce structural noise, impairing local feature perception. To address these challenges, this paper proposes ST-Booster, an iterative spatiotemporal booster that enhances navigation performance through multi-granularity perception and instruction-aware reasoning. ST-Booster consists of three key modules -- Hierarchical SpatioTemporal Encoding (HSTE), Multi-Granularity Aligned Fusion (MGAF), and ValueGuided Waypoint Generation (VGWG). HSTE encodes long-term global memory using topological graphs and captures shortterm local details via grid maps. MGAF aligns these dualmap representations with instructions through geometry-aware knowledge fusion. The resulting representations are iteratively refined through pretraining tasks. During reasoning, VGWG generates Guided Attention Heatmaps (GAHs) to explicitly model environment-instruction relevance and optimize waypoint selection. Extensive comparative experiments and performance analyses are conducted, demonstrating that ST-Booster outperforms existing state-of-the-art methods, particularly in complex, disturbance-prone environments.
Authors: Boris Kriuk, Simranjit Kaur Gill, Shoaib Aslam, Amir Fakhrutdinov
Abstract: Fine-Grained Image Classification (FGIC) remains a complex task in computer vision, as it requires models to distinguish between categories with subtle localized visual differences. Well-studied CNN-based models, while strong in local feature extraction, often fail to capture the global context required for fine-grained recognition, while more recent ViT-backboned models address FGIC with attention-driven mechanisms but lack the ability to adaptively focus on truly discriminative regions. TransFG and other ViT-based extensions introduced part-aware token selection to enhance attention localization, yet they still struggle with computational efficiency, attention region selection flexibility, and detail-focus narrative in complex environments. This paper introduces GFT (Gradient Focal Transformer), a new ViT-derived framework created for FGIC tasks. GFT integrates the Gradient Attention Learning Alignment (GALA) mechanism to dynamically prioritize class-discriminative features by analyzing attention gradient flow. Coupled with a Progressive Patch Selection (PPS) strategy, the model progressively filters out less informative regions, reducing computational overhead while enhancing sensitivity to fine details. GFT achieves SOTA accuracy on FGVC Aircraft, Food-101, and COCO datasets with 93M parameters, outperforming ViT-based advanced FGIC models in efficiency. By bridging global context and localized detail extraction, GFT sets a new benchmark in fine-grained recognition, offering interpretable solutions for real-world deployment scenarios.
Authors: Tran Quoc Khanh Le, Nguyen Lan Vi Vu, Ha-Hieu Pham, Xuan-Loc Huynh, Tien-Huy Nguyen, Minh Huu Nhat Le, Quan Nguyen, Hien D. Nguyen
Abstract: Transvaginal ultrasound is a critical imaging modality for evaluating cervical anatomy and detecting physiological changes. However, accurate segmentation of cervical structures remains challenging due to low contrast, shadow artifacts, and fuzzy boundaries. While convolutional neural networks (CNNs) have shown promising results in medical image segmentation, their performance is often limited by the need for large-scale annotated datasets - an impractical requirement in clinical ultrasound imaging. Semi-supervised learning (SSL) offers a compelling solution by leveraging unlabeled data, but existing teacher-student frameworks often suffer from confirmation bias and high computational costs. We propose HDC, a novel semi-supervised segmentation framework that integrates Hierarchical Distillation and Consistency learning within a multi-level noise mean-teacher framework. Unlike conventional approaches that rely solely on pseudo-labeling, we introduce a hierarchical distillation mechanism that guides feature-level learning via two novel objectives: (1) Correlation Guidance Loss to align feature representations between the teacher and main student branch, and (2) Mutual Information Loss to stabilize representations between the main and noisy student branches. Our framework reduces model complexity while improving generalization. Extensive experiments on two fetal ultrasound datasets, FUGC and PSFH, demonstrate that our method achieves competitive performance with significantly lower computational overhead than existing multi-teacher models.
Authors: Yunpeng Tan, Junlin Hao, Jiangkai Wu, Liming Liu, Qingyang Li, Xinggong Zhang
Abstract: Neural Radiance Field (NeRF) is widely known for high-fidelity novel view synthesis. However, even the state-of-the-art NeRF model, Gaussian Splatting, requires minutes for training, far from the real-time performance required by multimedia scenarios like telemedicine. One of the obstacles is its inefficient sampling, which is only partially addressed by existing works. Existing point-sampling algorithms uniformly sample simple-texture regions (easy to fit) and complex-texture regions (hard to fit), while existing ray-sampling algorithms sample these regions all in the finest granularity (i.e. the pixel level), both wasting GPU training resources. Actually, regions with different texture intensities require different sampling granularities. To this end, we propose a novel dynamic-resolution ray-sampling algorithm, MCBlock, which employs Monte Carlo Tree Search (MCTS) to partition each training image into pixel blocks with different sizes for active block-wise training. Specifically, the trees are initialized according to the texture of training images to boost the initialization speed, and an expansion/pruning module dynamically optimizes the block partition. MCBlock is implemented in Nerfstudio, an open-source toolset, and achieves a training acceleration of up to 2.33x, surpassing other ray-sampling algorithms. We believe MCBlock can apply to any cone-tracing NeRF model and contribute to the multimedia community.
Authors: Changwei Wang, Shunpeng Chen, Yukun Song, Rongtao Xu, Zherui Zhang, Jiguang Zhang, Haoran Yang, Yu Zhang, Kexue Fu, Shide Du, Zhiwei Xu, Longxiang Gao, Li Guo, Shibiao Xu
Abstract: Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. Code and models are available at https://github.com/chenshunpeng/FoL
Authors: Yiwen Wang, Ying Liang, Yuxuan Zhang, Xinning Chai, Zhengxue Cheng, Yingsheng Qin, Yucai Yang, Rong Xie, Li Song
Abstract: Due to the disparity between real-world degradations in user-generated content(UGC) images and synthetic degradations, traditional super-resolution methods struggle to generalize effectively, necessitating a more robust approach to model real-world distortions. In this paper, we propose a novel approach to UGC image super-resolution by integrating semantic guidance into a diffusion framework. Our method addresses the inconsistency between degradations in wild and synthetic datasets by separately simulating the degradation processes on the LSDIR dataset and combining them with the official paired training set. Furthermore, we enhance degradation removal and detail generation by incorporating a pretrained semantic extraction model (SAM2) and fine-tuning key hyperparameters for improved perceptual fidelity. Extensive experiments demonstrate the superiority of our approach against state-of-the-art methods. Additionally, the proposed model won second place in the CVPR NTIRE 2025 Short-form UGC Image Super-Resolution Challenge, further validating its effectiveness. The code is available at https://github.c10pom/Moonsofang/NTIRE-2025-SRlab.
Authors: Jaewoo Lee (May), Keyang Xuan (May), Chanakya Ekbote (May), Sandeep Polisetty (May), Yi R. (May), Fung, Paul Pu Liang
Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in unimodal models, its application to MLLMs often yields limited success. Our analysis discovers that conventional methods fail to account for the unique token attributes across layers and modalities inherent to MLLMs. Inspired by this observation, we propose TAMP, a simple yet effective pruning framework tailored for MLLMs, featuring two key components: (1) Diversity-Aware Sparsity, which adjusts sparsity ratio per layer based on diversities among multimodal output tokens, preserving more parameters in high-diversity layers; and (2) Adaptive Multimodal Input Activation, which identifies representative multimodal input tokens using attention scores to guide unstructured weight pruning. We validate our method on two state-of-the-art MLLMs: LLaVA-NeXT, designed for vision-language tasks, and VideoLLaMA2, capable of processing audio, visual, and language modalities. Empirical experiments across various multimodal evaluation benchmarks demonstrate that each component of our approach substantially outperforms existing pruning techniques.
Authors: Ziwang Xu, Lanqing Guo, Satoshi Tsutsui, Shuyan Zhang, Alex C. Kot, Bihan Wen
Abstract: Staining is essential in cell imaging and medical diagnostics but poses significant challenges, including high cost, time consumption, labor intensity, and irreversible tissue alterations. Recent advances in deep learning have enabled digital staining through supervised model training. However, collecting large-scale, perfectly aligned pairs of stained and unstained images remains difficult. In this work, we propose a novel unsupervised deep learning framework for digital cell staining that reduces the need for extensive paired data using knowledge distillation. We explore two training schemes: (1) unpaired and (2) paired-but-misaligned settings. For the unpaired case, we introduce a two-stage pipeline, comprising light enhancement followed by colorization, as a teacher model. Subsequently, we obtain a student staining generator through knowledge distillation with hybrid non-reference losses. To leverage the pixel-wise information between adjacent sections, we further extend to the paired-but-misaligned setting, adding the Learning to Align module to utilize pixel-level information. Experiment results on our dataset demonstrate that our proposed unsupervised deep staining method can generate stained images with more accurate positions and shapes of the cell targets in both settings. Compared with competing methods, our method achieves improved results both qualitatively and quantitatively (e.g., NIQE and PSNR).We applied our digital staining method to the White Blood Cell (WBC) dataset, investigating its potential for medical applications.
Authors: Muhammad Fasih Tariq, Muhammad Azeem Javed
Abstract: This paper provides an extensive evaluation of YOLO object detection models (v5, v8, v9, v10, v11) by com- paring their performance across various hardware platforms and optimization libraries. Our study investigates inference speed and detection accuracy on Intel and AMD CPUs using popular libraries such as ONNX and OpenVINO, as well as on GPUs through TensorRT and other GPU-optimized frameworks. Furthermore, we analyze the sensitivity of these YOLO models to object size within the image, examining performance when detecting objects that occupy 1%, 2.5%, and 5% of the total area of the image. By identifying the trade-offs in efficiency, accuracy, and object size adaptability, this paper offers insights for optimal model selection based on specific hardware constraints and detection requirements, aiding practitioners in deploying YOLO models effectively for real-world applications.
Authors: Mert Asim Karaoglu, Wenbo Ji, Ahmed Abbas, Nassir Navab, Benjamin Busam, Alexander Ladikos
Abstract: Tissue tracking plays a critical role in various surgical navigation and extended reality (XR) applications. While current methods trained on large synthetic datasets achieve high tracking accuracy and generalize well to endoscopic scenes, their runtime performances fail to meet the low-latency requirements necessary for real-time surgical applications. To address this limitation, we propose LiteTracker, a low-latency method for tissue tracking in endoscopic video streams. LiteTracker builds on a state-of-the-art long-term point tracking method, and introduces a set of training-free runtime optimizations. These optimizations enable online, frame-by-frame tracking by leveraging a temporal memory buffer for efficient feature reuse and utilizing prior motion for accurate track initialization. LiteTracker demonstrates significant runtime improvements being around 7x faster than its predecessor and 2x than the state-of-the-art. Beyond its primary focus on efficiency, LiteTracker delivers high-accuracy tracking and occlusion prediction, performing competitively on both the STIR and SuPer datasets. We believe LiteTracker is an important step toward low-latency tissue tracking for real-time surgical applications in the operating room.
Authors: Maria Tzelepi, Vasileios Mezaris
Abstract: Memes have become a dominant form of communication in social media in recent years. Memes are typically humorous and harmless, however there are also memes that promote hate speech, being in this way harmful to individuals and groups based on their identity. Therefore, detecting hateful content in memes has emerged as a task of critical importance. The need for understanding the complex interactions of images and their embedded text renders the hateful meme detection a challenging multimodal task. In this paper we propose to address the aforementioned task leveraging knowledge encoded in powerful Large Multimodal Models (LMM). Specifically, we propose to exploit LMMs in a two-fold manner. First, by extracting knowledge oriented to the hateful meme detection task in order to build strong meme representations. Specifically, generic semantic descriptions and emotions that the images along with their embedded texts elicit are extracted, which are then used to train a simple classification head for hateful meme detection. Second, by developing a novel hard mining approach introducing directly LMM-encoded knowledge to the training process, providing further improvements. We perform extensive experiments on two datasets that validate the effectiveness of the proposed method, achieving state-of-the-art performance. Our code and trained models are publicly available at: https://github.com/IDT-ITI/LMM-CLIP-meme.
Authors: Zheng Liu, Mengjie Liu, Jingzhou Chen, Jingwei Xu, Bin Cui, Conghui He, Wentao Zhang
Abstract: We introduce FUSION, a family of multimodal large language models (MLLMs) with a fully vision-language alignment and integration paradigm. Unlike existing methods that primarily rely on late-stage modality interaction during LLM decoding, our approach achieves deep, dynamic integration throughout the entire processing pipeline. To this end, we propose Text-Guided Unified Vision Encoding, incorporating textual information in vision encoding to achieve pixel-level integration. We further design Context-Aware Recursive Alignment Decoding that recursively aggregates visual features conditioned on textual context during decoding, enabling fine-grained, question-level semantic integration. To guide feature mapping and mitigate modality discrepancies, we develop Dual-Supervised Semantic Mapping Loss. Additionally, we construct a Synthesized Language-Driven Question-Answer (QA) dataset through a new data synthesis method, prioritizing high-quality QA pairs to optimize text-guided feature integration. Building on these foundations, we train FUSION at two scales-3B, 8B-and demonstrate that our full-modality integration approach significantly outperforms existing methods with only 630 vision tokens. Notably, FUSION 3B surpasses Cambrian-1 8B and Florence-VL 8B on most benchmarks. FUSION 3B continues to outperform Cambrian-1 8B even when limited to 300 vision tokens. Our ablation studies show that FUSION outperforms LLaVA-NeXT on over half of the benchmarks under same configuration without dynamic resolution, highlighting the effectiveness of our approach. We release our code, model weights, and dataset. https://github.com/starriver030515/FUSION
Authors: Huijie Liu, Bingcan Wang, Jie Hu, Xiaoming Wei, Guoliang Kang
Abstract: Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and e-commerce. In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes. To address this limitation, we propose Omni-Dish, the first text-to-image generation model specifically tailored for Chinese dishes. We develop a comprehensive dish curation pipeline, building the largest dish dataset to date. Additionally, we introduce a recaption strategy and employ a coarse-to-fine training scheme to help the model better learn fine-grained culinary nuances. During inference, we enhance the user's textual input using a pre-constructed high-quality caption library and a large language model, enabling more photorealistic and faithful image generation. Furthermore, to extend our model's capability for dish editing tasks, we propose Concept-Enhanced P2P. Based on this approach, we build a dish editing dataset and train a specialized editing model. Extensive experiments demonstrate the superiority of our methods.
Authors: Katja Ludwig, Yuliia Oksymets, Robin Sch\"on, Daniel Kienzle, Rainer Lienhart
Abstract: In sports analytics, accurately capturing both the 3D locations and rotations of body joints is essential for understanding an athlete's biomechanics. While Human Mesh Recovery (HMR) models can estimate joint rotations, they often exhibit lower accuracy in joint localization compared to 3D Human Pose Estimation (HPE) models. Recent work addressed this limitation by combining a 3D HPE model with inverse kinematics (IK) to estimate both joint locations and rotations. However, IK is computationally expensive. To overcome this, we propose a novel 2D-to-3D uplifting model that directly estimates 3D human poses, including joint rotations, in a single forward pass. We investigate multiple rotation representations, loss functions, and training strategies - both with and without access to ground truth rotations. Our models achieve state-of-the-art accuracy in rotation estimation, are 150 times faster than the IK-based approach, and surpass HMR models in joint localization precision.
Authors: Katarzyna Filus, Micha{\l} Romaszewski, Mateusz \.Zarski
Abstract: Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current evaluation methodologies lack transparency, particularly in explaining the underlying causes of network misclassifications. To address this, we introduce a novel framework that investigates the relationship between the semantic hierarchy depth perceived by a network and its real-data misclassification patterns. Central to our framework is the Similarity Depth (SD) metric, which quantifies the semantic hierarchy depth perceived by a network along with a method of evaluation of how closely the network's errors align with its internally perceived similarity structure. We also propose a graph-based visualization of model semantic relationships and misperceptions. A key advantage of our approach is that leveraging class templates -- representations derived from classifier layer weights -- is applicable to already trained networks without requiring additional data or experiments. Our approach reveals that deep vision networks encode specific semantic hierarchies and that high semantic depth improves the compliance between perceived class similarities and actual errors.
Authors: Hoang M. Truong, Vinh-Thuan Ly, Huy G. Tran, Thuan-Phat Nguyen, Tram T. Doan
Abstract: Event-based eye tracking has become a pivotal technology for augmented reality and human-computer interaction. Yet, existing methods struggle with real-world challenges such as abrupt eye movements and environmental noise. Building on the efficiency of the Lightweight Spatiotemporal Network-a causal architecture optimized for edge devices-we introduce two key advancements. First, a robust data augmentation pipeline incorporating temporal shift, spatial flip, and event deletion improves model resilience, reducing Euclidean distance error by 12% (1.61 vs. 1.70 baseline) on challenging samples. Second, we propose KnightPupil, a hybrid architecture combining an EfficientNet-B3 backbone for spatial feature extraction, a bidirectional GRU for contextual temporal modeling, and a Linear Time-Varying State-Space Module to adapt to sparse inputs and noise dynamically. Evaluated on the 3ET+ benchmark, our framework achieved 1.61 Euclidean distance on the private test set of the Event-based Eye Tracking Challenge at CVPR 2025, demonstrating its effectiveness for practical deployment in AR/VR systems while providing a foundation for future innovations in neuromorphic vision.
Authors: Dongliang Luo, Hanshen Zhu, Ziyang Zhang, Dingkang Liang, Xudong Xie, Yuliang Liu, Xiang Bai
Abstract: Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled images. However, directly applying existing semi-supervised methods of general scenes to SSTS will face new challenges: 1) inconsistent pseudo labels between detection and recognition tasks, and 2) sub-optimal supervisions caused by inconsistency between teacher/student. Thus, we propose a new Semi-supervised framework for End-to-end Text Spotting, namely SemiETS that leverages the complementarity of text detection and recognition. Specifically, it gradually generates reliable hierarchical pseudo labels for each task, thereby reducing noisy labels. Meanwhile, it extracts important information in locations and transcriptions from bidirectional flows to improve consistency. Extensive experiments on three datasets under various settings demonstrate the effectiveness of SemiETS on arbitrary-shaped text. For example, it outperforms previous state-of-the-art SSL methods by a large margin on end-to-end spotting (+8.7%, +5.6%, and +2.6% H-mean under 0.5%, 1%, and 2% labeled data settings on Total-Text, respectively). More importantly, it still improves upon a strongly supervised text spotter trained with plenty of labeled data by 2.0%. Compelling domain adaptation ability shows practical potential. Moreover, our method demonstrates consistent improvement on different text spotters.
Authors: Xun Zhu, Fanbin Mo, Zheng Zhang, Jiaxi Wang, Yiming Shi, Ming Wu, Chuang Zhang, Miao Li, Ji Wu
Abstract: The emergence of medical generalist foundation models has revolutionized conventional task-specific model development paradigms, aiming to better handle multiple tasks through joint training on large-scale medical datasets. However, recent advances prioritize simple data scaling or architectural component enhancement, while neglecting to re-examine multi-task learning from a data-centric perspective. Critically, simply aggregating existing data resources leads to decentralized image-task alignment, which fails to cultivate comprehensive image understanding or align with clinical needs for multi-dimensional image interpretation. In this paper, we introduce the image-centric multi-annotation X-ray dataset (IMAX), the first attempt to enhance the multi-task learning capabilities of medical multi-modal large language models (MLLMs) from the data construction level. To be specific, IMAX is featured from the following attributes: 1) High-quality data curation. A comprehensive collection of more than 354K entries applicable to seven different medical tasks. 2) Image-centric dense annotation. Each X-ray image is associated with an average of 4.10 tasks and 7.46 training entries, ensuring multi-task representation richness per image. Compared to the general decentralized multi-annotation X-ray dataset (DMAX), IMAX consistently demonstrates significant multi-task average performance gains ranging from 3.20% to 21.05% across seven open-source state-of-the-art medical MLLMs. Moreover, we investigate differences in statistical patterns exhibited by IMAX and DMAX training processes, exploring potential correlations between optimization dynamics and multi-task performance. Finally, leveraging the core concept of IMAX data construction, we propose an optimized DMAX-based training strategy to alleviate the dilemma of obtaining high-quality IMAX data in practical scenarios.
Authors: Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie
Abstract: All-in-one image restoration, addressing diverse degradation types with a unified model, presents significant challenges in designing task-specific prompts that effectively guide restoration across multiple degradation scenarios. While adaptive prompt learning enables end-to-end optimization, it often yields overlapping or redundant task representations. Conversely, explicit prompts derived from pretrained classifiers enhance discriminability but may discard critical visual information for reconstruction. To address these limitations, we introduce Contrastive Prompt Learning (CPL), a novel framework that fundamentally enhances prompt-task alignment through two complementary innovations: a \emph{Sparse Prompt Module (SPM)} that efficiently captures degradation-specific features while minimizing redundancy, and a \emph{Contrastive Prompt Regularization (CPR)} that explicitly strengthens task boundaries by incorporating negative prompt samples across different degradation types. Unlike previous approaches that focus primarily on degradation classification, CPL optimizes the critical interaction between prompts and the restoration model itself. Extensive experiments across five comprehensive benchmarks demonstrate that CPL consistently enhances state-of-the-art all-in-one restoration models, achieving significant improvements in both standard multi-task scenarios and challenging composite degradation settings. Our framework establishes new state-of-the-art performance while maintaining parameter efficiency, offering a principled solution for unified image restoration.
Authors: Teppei Suzuki, Keisuke Ozawa
Abstract: We propose an efficient evaluation protocol for large vision-language models (VLMs). Given their broad knowledge and reasoning capabilities, multiple benchmarks are needed for comprehensive assessment, making evaluation computationally expensive. To improve efficiency, we construct a subset that yields results comparable to full benchmark evaluations. Our benchmark classification experiments reveal that no single benchmark fully covers all challenges. We then introduce a subset construction method using farthest point sampling (FPS). Our experiments show that FPS-based benchmarks maintain a strong correlation (> 0.96) with full evaluations while using only ~1\% of the data. Additionally, applying FPS to an existing benchmark improves correlation with overall evaluation results, suggesting its potential to reduce unintended dataset biases.
Authors: LeiLei Ma, Shuo Xu, MingKun Xie, Lei Wang, Dengdi Sun, Haifeng Zhao
Abstract: Modeling label correlations has always played a pivotal role in multi-label image classification (MLC), attracting significant attention from researchers. However, recent studies have overemphasized co-occurrence relationships among labels, which can lead to overfitting risk on this overemphasis, resulting in suboptimal models. To tackle this problem, we advocate for balancing correlative and discriminative relationships among labels to mitigate the risk of overfitting and enhance model performance. To this end, we propose the Multi-Label Visual Prompt Tuning framework, a novel and parameter-efficient method that groups classes into multiple class subsets according to label co-occurrence and mutual exclusivity relationships, and then models them respectively to balance the two relationships. In this work, since each group contains multiple classes, multiple prompt tokens are adopted within Vision Transformer (ViT) to capture the correlation or discriminative label relationship within each group, and effectively learn correlation or discriminative representations for class subsets. On the other hand, each group contains multiple group-aware visual representations that may correspond to multiple classes, and the mixture of experts (MoE) model can cleverly assign them from the group-aware to the label-aware, adaptively obtaining label-aware representation, which is more conducive to classification. Experiments on multiple benchmark datasets show that our proposed approach achieves competitive results and outperforms SOTA methods on multiple pre-trained models.
Authors: Alejandro Luque-Cerpa, Elizabeth Polgreen, Ajitha Rajan, Hazem Torfah
Abstract: Class activation mapping (CAM) is a widely adopted class of saliency methods used to explain the behavior of convolutional neural networks (CNNs). These methods generate heatmaps that highlight the parts of the input most relevant to the CNN output. Various CAM methods have been proposed, each distinguished by the expressions used to derive heatmaps. In general, users look for heatmaps with specific properties that reflect different aspects of CNN functionality. These may include similarity to ground truth, robustness, equivariance, and more. Although existing CAM methods implicitly encode some of these properties in their expressions, they do not allow for variability in heatmap generation following the user's intent or domain knowledge. In this paper, we address this limitation by introducing SyCAM, a metric-based approach for synthesizing CAM expressions. Given a predefined evaluation metric for saliency maps, SyCAM automatically generates CAM expressions optimized for that metric. We specifically explore a syntax-guided synthesis instantiation of SyCAM, where CAM expressions are derived based on predefined syntactic constraints and the given metric. Using several established evaluation metrics, we demonstrate the efficacy and flexibility of our approach in generating targeted heatmaps. We compare SyCAM with other well-known CAM methods on three prominent models: ResNet50, VGG16, and VGG19.
Authors: Junlin Hao, Peiheng Wang, Haoyang Wang, Xinggong Zhang, Zongming Guo
Abstract: Single-image 3D scene reconstruction presents significant challenges due to its inherently ill-posed nature and limited input constraints. Recent advances have explored two promising directions: multiview generative models that train on 3D consistent datasets but struggle with out-of-distribution generalization, and 3D scene inpainting and completion frameworks that suffer from cross-view inconsistency and suboptimal error handling, as they depend exclusively on depth data or 3D smoothness, which ultimately degrades output quality and computational performance. Building upon these approaches, we present GaussVideoDreamer, which advances generative multimedia approaches by bridging the gap between image, video, and 3D generation, integrating their strengths through two key innovations: (1) A progressive video inpainting strategy that harnesses temporal coherence for improved multiview consistency and faster convergence. (2) A 3D Gaussian Splatting consistency mask to guide the video diffusion with 3D consistent multiview evidence. Our pipeline combines three core components: a geometry-aware initialization protocol, Inconsistency-Aware Gaussian Splatting, and a progressive video inpainting strategy. Experimental results demonstrate that our approach achieves 32% higher LLaVA-IQA scores and at least 2x speedup compared to existing methods while maintaining robust performance across diverse scenes.
Authors: Mat\'ias Piqueras, Alexandra Segerberg, Matteo Magnani, M{\aa}ns Magnusson, Nata\v{s}a Sladoje
Abstract: Political scientists are increasingly interested in analyzing visual content at scale. However, the existing computational toolbox is still in need of methods and models attuned to the specific challenges and goals of social and political inquiry. In this article, we introduce a visual Structural Topic Model (vSTM) that combines pretrained image embeddings with a structural topic model. This has important advantages compared to existing approaches. First, pretrained embeddings allow the model to capture the semantic complexity of images relevant to political contexts. Second, the structural topic model provides the ability to analyze how topics and covariates are related, while maintaining a nuanced representation of images as a mixture of multiple topics. In our empirical application, we show that the vSTM is able to identify topics that are interpretable, coherent, and substantively relevant to the study of online political communication.
Authors: Yufei Deng, Yuanjian Wang, Rong Xiao, Chenwei Tang, Jizhe Zhou, Jiahao Fan, Deng Xiong, Jiancheng Lv, Huajin Tang
Abstract: While 3D Gaussian Splatting (3D-GS) achieves photorealistic novel view synthesis, its performance degrades with motion blur. In scenarios with rapid motion or low-light conditions, existing RGB-based deblurring methods struggle to model camera pose and radiance changes during exposure, reducing reconstruction accuracy. Event cameras, capturing continuous brightness changes during exposure, can effectively assist in modeling motion blur and improving reconstruction quality. Therefore, we propose Event-driven Bundle Adjusted Deblur Gaussian Splatting (EBAD-Gaussian), which reconstructs sharp 3D Gaussians from event streams and severely blurred images. This method jointly learns the parameters of these Gaussians while recovering camera motion trajectories during exposure time. Specifically, we first construct a blur loss function by synthesizing multiple latent sharp images during the exposure time, minimizing the difference between real and synthesized blurred images. Then we use event stream to supervise the light intensity changes between latent sharp images at any time within the exposure period, supplementing the light intensity dynamic changes lost in RGB images. Furthermore, we optimize the latent sharp images at intermediate exposure times based on the event-based double integral (EDI) prior, applying consistency constraints to enhance the details and texture information of the reconstructed images. Extensive experiments on synthetic and real-world datasets show that EBAD-Gaussian can achieve high-quality 3D scene reconstruction under the condition of blurred images and event stream inputs.
Authors: Xiao Wang, Haiyang Wang, Shiao Wang, Qiang Chen, Jiandong Jin, Haoyu Song, Bo Jiang, Chenglong Li
Abstract: Existing pedestrian attribute recognition methods are generally developed based on RGB frame cameras. However, these approaches are constrained by the limitations of RGB cameras, such as sensitivity to lighting conditions and motion blur, which hinder their performance. Furthermore, current attribute recognition primarily focuses on analyzing pedestrians' external appearance and clothing, lacking an exploration of emotional dimensions. In this paper, we revisit these issues and propose a novel multi-modal RGB-Event attribute recognition task by drawing inspiration from the advantages of event cameras in low-light, high-speed, and low-power consumption. Specifically, we introduce the first large-scale multi-modal pedestrian attribute recognition dataset, termed EventPAR, comprising 100K paired RGB-Event samples that cover 50 attributes related to both appearance and six human emotions, diverse scenes, and various seasons. By retraining and evaluating mainstream PAR models on this dataset, we establish a comprehensive benchmark and provide a solid foundation for future research in terms of data and algorithmic baselines. In addition, we propose a novel RWKV-based multi-modal pedestrian attribute recognition framework, featuring an RWKV visual encoder and an asymmetric RWKV fusion module. Extensive experiments are conducted on our proposed dataset as well as two simulated datasets (MARS-Attribute and DukeMTMC-VID-Attribute), achieving state-of-the-art results. The source code and dataset will be released on https://github.com/Event-AHU/OpenPAR
Authors: Nikolai R\"ohrich (XITASO GmbH,LMU Munich), Alwin Hoffmann (XITASO GmbH), Richard Nordsieck (XITASO GmbH), Emilio Zarbali (XITASO GmbH), Alireza Javanmardi (LMU Munich,Munich Center for Machine Learning)
Abstract: Whereas in general computer vision, transformer-based architectures have quickly become the gold standard, microelectronics defect detection still heavily relies on convolutional neural networks (CNNs). We hypothesize that this is due to the fact that a) transformers have an increased need for data and b) labelled image generation procedures for microelectronics are costly, and labelled data is therefore sparse. Whereas in other domains, pre-training on large natural image datasets can mitigate this problem, in microelectronics transfer learning is hindered due to the dissimilarity of domain data and natural images. Therefore, we evaluate self pre-training, where models are pre-trained on the target dataset, rather than another dataset. We propose a vision transformer (ViT) pre-training framework for defect detection in microelectronics based on masked autoencoders (MAE). In MAE, a large share of image patches is masked and reconstructed by the model during pre-training. We perform pre-training and defect detection using a dataset of less than 10.000 scanning acoustic microscopy (SAM) images labelled using transient thermal analysis (TTA). Our experimental results show that our approach leads to substantial performance gains compared to a) supervised ViT, b) ViT pre-trained on natural image datasets, and c) state-of-the-art CNN-based defect detection models used in the literature. Additionally, interpretability analysis reveals that our self pre-trained models, in comparison to ViT baselines, correctly focus on defect-relevant features such as cracks in the solder material. This demonstrates that our approach yields fault-specific feature representations, making our self pre-trained models viable for real-world defect detection in microelectronics.
Authors: Mengkun She, Felix Seegr\"aber, David Nakath, Patricia Sch\"ontag, Kevin K\"oser
Abstract: We address the challenge of constructing a consistent and photorealistic Neural Radiance Field in inhomogeneously illuminated, scattering environments with unknown, co-moving light sources. While most existing works on underwater scene representation focus on a static homogeneous illumination, limited attention has been paid to scenarios such as when a robot explores water deeper than a few tens of meters, where sunlight becomes insufficient. To address this, we propose a novel illumination field locally attached to the camera, enabling the capture of uneven lighting effects within the viewing frustum. We combine this with a volumetric medium representation to an overall method that effectively handles interaction between dynamic illumination field and static scattering medium. Evaluation results demonstrate the effectiveness and flexibility of our approach.
Authors: Thomas Gossard, Andreas Ziegler, Andreas Zell
Abstract: Sports analysis requires processing large amounts of data, which is time-consuming and costly. Advancements in neural networks have significantly alleviated this burden, enabling highly accurate ball tracking in sports broadcasts. However, relying solely on 2D ball tracking is limiting, as it depends on the camera's viewpoint and falls short of supporting comprehensive game analysis. To address this limitation, we propose a novel approach for reconstructing precise 3D ball trajectories from online table tennis match recordings. Our method leverages the underlying physics of the ball's motion to identify the bounce state that minimizes the reprojection error of the ball's flying trajectory, hence ensuring an accurate and reliable 3D reconstruction. A key advantage of our approach is its ability to infer ball spin without relying on human pose estimation or racket tracking, which are often unreliable or unavailable in broadcast footage. We developed an automated camera calibration method capable of reliably tracking camera movements. Additionally, we adapted an existing 3D pose estimation model, which lacks depth motion capture, to accurately track player movements. Together, these contributions enable the full 3D reconstruction of a table tennis rally.
Authors: Sergey Kuznetsov, Sanduni Pinnawala, Peter A. Wijeratne, Ivor J. A. Simpson
Abstract: Inpainting has recently emerged as a valuable and interesting technology to employ in the analysis of medical imaging data, in particular brain MRI. A wide variety of methodologies for inpainting MRI have been proposed and demonstrated on tasks including anomaly detection. In this work we investigate the statistical relationship between inpainted brain structures and the amount of subject-specific conditioning information, i.e. the other areas of the image that are masked. In particular, we analyse the distribution of inpainting results when masking additional regions of the image, specifically the contra-lateral structure. This allows us to elucidate where in the brain the model is drawing information from, and in particular, what is the importance of hemispherical symmetry? Our experiments interrogate a diffusion inpainting model through analysing the inpainting of subcortical brain structures based on intensity and estimated area change. We demonstrate that some structures show a strong influence of symmetry in the conditioning of the inpainting process.
Authors: Bingwen Zhu, Yudong Jiang, Baohan Xu, Siqian Yang, Mingyu Yin, Yidi Wu, Huyang Sun, Zuxuan Wu
Abstract: Anime video generation faces significant challenges due to the scarcity of anime data and unusual motion patterns, leading to issues such as motion distortion and flickering artifacts, which result in misalignment with human preferences. Existing reward models, designed primarily for real-world videos, fail to capture the unique appearance and consistency requirements of anime. In this work, we propose a pipeline to enhance anime video generation by leveraging human feedback for better alignment. Specifically, we construct the first multi-dimensional reward dataset for anime videos, comprising 30k human-annotated samples that incorporating human preferences for both visual appearance and visual consistency. Based on this, we develop AnimeReward, a powerful reward model that employs specialized vision-language models for different evaluation dimensions to guide preference alignment. Furthermore, we introduce Gap-Aware Preference Optimization (GAPO), a novel training method that explicitly incorporates preference gaps into the optimization process, enhancing alignment performance and efficiency. Extensive experiment results show that AnimeReward outperforms existing reward models, and the inclusion of GAPO leads to superior alignment in both quantitative benchmarks and human evaluations, demonstrating the effectiveness of our pipeline in enhancing anime video quality. Our dataset and code will be publicly available.
Authors: Chengyi Du, Keyan Jin
Abstract: Multi-object grounding in 3D scenes involves localizing multiple objects based on natural language input. While previous work has primarily focused on single-object grounding, real-world scenarios often demand the localization of several objects. To tackle this challenge, we propose Hierarchical Contrastive Siamese Transformers (H-COST), which employs a Hierarchical Processing strategy to progressively refine object localization, enhancing the understanding of complex language instructions. Additionally, we introduce a Contrastive Siamese Transformer framework, where two networks with the identical structure are used: one auxiliary network processes robust object relations from ground-truth labels to guide and enhance the second network, the reference network, which operates on segmented point-cloud data. This contrastive mechanism strengthens the model' s semantic understanding and significantly enhances its ability to process complex point-cloud data. Our approach outperforms previous state-of-the-art methods by 9.5% on challenging multi-object grounding benchmarks.
Authors: Th\'eo Gigant, Camille Guinaudeau, Fr\'ed\'eric Dufaux
Abstract: Vision-Language Models (VLMs) can process visual and textual information in multiple formats: texts, images, interleaved texts and images, or even hour-long videos. In this work, we conduct fine-grained quantitative and qualitative analyses of automatic summarization of multimodal presentations using VLMs with various representations as input. From these experiments, we suggest cost-effective strategies for generating summaries from text-heavy multimodal documents under different input-length budgets using VLMs. We show that slides extracted from the video stream can be beneficially used as input against the raw video, and that a structured representation from interleaved slides and transcript provides the best performance. Finally, we reflect and comment on the nature of cross-modal interactions in multimodal presentations and share suggestions to improve the capabilities of VLMs to understand documents of this nature.
Authors: Yang Shi, Jiaheng Liu, Yushuo Guan, Zhenhua Wu, Yuanxing Zhang, Zihao Wang, Weihong Lin, Jingyun Hua, Zekun Wang, Xinlong Chen, Bohan Zeng, Wentao Zhang, Fuzheng Zhang, Wenjing Yang, Di Zhang
Abstract: Long-context video understanding in multimodal large language models (MLLMs) faces a critical challenge: balancing computational efficiency with the retention of fine-grained spatio-temporal patterns. Existing approaches (e.g., sparse sampling, dense sampling with low resolution, and token compression) suffer from significant information loss in temporal dynamics, spatial details, or subtle interactions, particularly in videos with complex motion or varying resolutions. To address this, we propose $\mathbf{Mavors}$, a novel framework that introduces $\mathbf{M}$ulti-gr$\mathbf{a}$nularity $\mathbf{v}$ide$\mathbf{o}$ $\mathbf{r}$epre$\mathbf{s}$entation for holistic long-video modeling. Specifically, Mavors directly encodes raw video content into latent representations through two core components: 1) an Intra-chunk Vision Encoder (IVE) that preserves high-resolution spatial features via 3D convolutions and Vision Transformers, and 2) an Inter-chunk Feature Aggregator (IFA) that establishes temporal coherence across chunks using transformer-based dependency modeling with chunk-level rotary position encodings. Moreover, the framework unifies image and video understanding by treating images as single-frame videos via sub-image decomposition. Experiments across diverse benchmarks demonstrate Mavors' superiority in maintaining both spatial fidelity and temporal continuity, significantly outperforming existing methods in tasks requiring fine-grained spatio-temporal reasoning.
Authors: Kiana Hoshanfar, Alireza Hosseini, Ahmad Kalhor, Babak Nadjar Araabi
Abstract: Audio-visual saliency prediction aims to mimic human visual attention by identifying salient regions in videos through the integration of both visual and auditory information. Although visual-only approaches have significantly advanced, effectively incorporating auditory cues remains challenging due to complex spatio-temporal interactions and high computational demands. To address these challenges, we propose Dynamic Token Fusion Saliency (DFTSal), a novel audio-visual saliency prediction framework designed to balance accuracy with computational efficiency. Our approach features a multi-scale visual encoder equipped with two novel modules: the Learnable Token Enhancement Block (LTEB), which adaptively weights tokens to emphasize crucial saliency cues, and the Dynamic Learnable Token Fusion Block (DLTFB), which employs a shifting operation to reorganize and merge features, effectively capturing long-range dependencies and detailed spatial information. In parallel, an audio branch processes raw audio signals to extract meaningful auditory features. Both visual and audio features are integrated using our Adaptive Multimodal Fusion Block (AMFB), which employs local, global, and adaptive fusion streams for precise cross-modal fusion. The resulting fused features are processed by a hierarchical multi-decoder structure, producing accurate saliency maps. Extensive evaluations on six audio-visual benchmarks demonstrate that DFTSal achieves SOTA performance while maintaining computational efficiency.
Authors: Hongyu Qu, Ling Xing, Rui Yan, Yazhou Yao, Guo-Sen Xie, Xiangbo Shu
Abstract: Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level representations independently for each video by designing various inter-frame temporal modeling strategies. However, they neglect explicit relation modeling between videos and tasks, thus failing to capture shared temporal patterns across videos and reuse temporal knowledge from historical tasks. In light of this, we propose HR2G-shot, a Hierarchical Relation-augmented Representation Generalization framework for FSAR, which unifies three types of relation modeling (inter-frame, inter-video, and inter-task) to learn task-specific temporal patterns from a holistic view. In addition to conducting inter-frame temporal interactions, we further devise two components to respectively explore inter-video and inter-task relationships: i) Inter-video Semantic Correlation (ISC) performs cross-video frame-level interactions in a fine-grained manner, thereby capturing task-specific query features and learning intra- and inter-class temporal correlations among support features; ii) Inter-task Knowledge Transfer (IKT) retrieves and aggregates relevant temporal knowledge from the bank, which stores diverse temporal patterns from historical tasks. Extensive experiments on five benchmarks show that HR2G-shot outperforms current top-leading FSAR methods.
Authors: Yucheng Lu, Shunxin Wang, Dovile Juodelyte, Veronika Cheplygina
Abstract: In this paper, we explore how conventional image enhancement can improve model robustness in medical image analysis. By applying commonly used normalization methods to images from various vendors and studying their influence on model generalization in transfer learning, we show that the nonlinear characteristics of domain-specific image dynamics cannot be addressed by simple linear transforms. To tackle this issue, we reformulate the image harmonization task as an exposure correction problem and propose a method termed Global Deep Curve Estimation (GDCE) to reduce domain-specific exposure mismatch. GDCE performs enhancement via a pre-defined polynomial function and is trained with the help of a ``domain discriminator'', aiming to improve model transparency in downstream tasks compared to existing black-box methods.
Authors: Yating Liu, Yaowei Li, Xiangyuan Lan, Wenming Yang, Zimo Liu, Qingmin Liao
Abstract: Text-based Person Retrieval (TPR) as a multi-modal task, which aims to retrieve the target person from a pool of candidate images given a text description, has recently garnered considerable attention due to the progress of contrastive visual-language pre-trained model. Prior works leverage pre-trained CLIP to extract person visual and textual features and fully fine-tune the entire network, which have shown notable performance improvements compared to uni-modal pre-training models. However, full-tuning a large model is prone to overfitting and hinders the generalization ability. In this paper, we propose a novel Unified Parameter-Efficient Transfer Learning (PETL) method for Text-based Person Retrieval (UP-Person) to thoroughly transfer the multi-modal knowledge from CLIP. Specifically, UP-Person simultaneously integrates three lightweight PETL components including Prefix, LoRA and Adapter, where Prefix and LoRA are devised together to mine local information with task-specific information prompts, and Adapter is designed to adjust global feature representations. Additionally, two vanilla submodules are optimized to adapt to the unified architecture of TPR. For one thing, S-Prefix is proposed to boost attention of prefix and enhance the gradient propagation of prefix tokens, which improves the flexibility and performance of the vanilla prefix. For another thing, L-Adapter is designed in parallel with layer normalization to adjust the overall distribution, which can resolve conflicts caused by overlap and interaction among multiple submodules. Extensive experimental results demonstrate that our UP-Person achieves state-of-the-art results across various person retrieval datasets, including CUHK-PEDES, ICFG-PEDES and RSTPReid while merely fine-tuning 4.7\% parameters. Code is available at https://github.com/Liu-Yating/UP-Person.
Authors: I-Sheng Fang, Jun-Cheng Chen
Abstract: Large language models (LLMs) and multimodal large language models (MLLMs) have significantly advanced artificial intelligence. However, visual reasoning, reasoning involving both visual and textual inputs, remains underexplored. Recent advancements, including the reasoning models like OpenAI o1 and Gemini 2.0 Flash Thinking, which incorporate image inputs, have opened this capability. In this ongoing work, we focus specifically on photography-related tasks because a photo is a visual snapshot of the physical world where the underlying physics (i.e., illumination, blur extent, etc.) interplay with the camera parameters. Successfully reasoning from the visual information of a photo to identify these numerical camera settings requires the MLLMs to have a deeper understanding of the underlying physics for precise visual comprehension, representing a challenging and intelligent capability essential for practical applications like photography assistant agents. We aim to evaluate MLLMs on their ability to distinguish visual differences related to numerical camera settings, extending a methodology previously proposed for vision-language models (VLMs). Our preliminary results demonstrate the importance of visual reasoning in photography-related tasks. Moreover, these results show that no single MLLM consistently dominates across all evaluation tasks, demonstrating ongoing challenges and opportunities in developing MLLMs with better visual reasoning.
Authors: Zexin Ji, Beiji Zou, Xiaoyan Kui, Sebastien Thureau, Su Ruan
Abstract: Convolutional neural networks and Transformer have made significant progresses in multi-modality medical image super-resolution. However, these methods either have a fixed receptive field for local learning or significant computational burdens for global learning, limiting the super-resolution performance. To solve this problem, State Space Models, notably Mamba, is introduced to efficiently model long-range dependencies in images with linear computational complexity. Relying on the Mamba and the fact that low-resolution images rely on global information to compensate for missing details, while high-resolution reference images need to provide more local details for accurate super-resolution, we propose a global and local Mamba network (GLMamba) for multi-modality medical image super-resolution. To be specific, our GLMamba is a two-branch network equipped with a global Mamba branch and a local Mamba branch. The global Mamba branch captures long-range relationships in low-resolution inputs, and the local Mamba branch focuses more on short-range details in high-resolution reference images. We also use the deform block to adaptively extract features of both branches to enhance the representation ability. A modulator is designed to further enhance deformable features in both global and local Mamba blocks. To fully integrate the reference image for low-resolution image super-resolution, we further develop a multi-modality feature fusion block to adaptively fuse features by considering similarities, differences, and complementary aspects between modalities. In addition, a contrastive edge loss (CELoss) is developed for sufficient enhancement of edge textures and contrast in medical images.
Authors: Marc Guti\'errez-P\'erez, Antonio Agudo
Abstract: Sports video analysis is a key domain in computer vision, enabling detailed spatial understanding through multi-view correspondences. In this work, we introduce SoccerNet-v3D and ISSIA-3D, two enhanced and scalable datasets designed for 3D scene understanding in soccer broadcast analysis. These datasets extend SoccerNet-v3 and ISSIA by incorporating field-line-based camera calibration and multi-view synchronization, enabling 3D object localization through triangulation. We propose a monocular 3D ball localization task built upon the triangulation of ground-truth 2D ball annotations, along with several calibration and reprojection metrics to assess annotation quality on demand. Additionally, we present a single-image 3D ball localization method as a baseline, leveraging camera calibration and ball size priors to estimate the ball's position from a monocular viewpoint. To further refine 2D annotations, we introduce a bounding box optimization technique that ensures alignment with the 3D scene representation. Our proposed datasets establish new benchmarks for 3D soccer scene understanding, enhancing both spatial and temporal analysis in sports analytics. Finally, we provide code to facilitate access to our annotations and the generation pipelines for the datasets.
Authors: Peizheng Li, Shuxiao Ding, You Zhou, Qingwen Zhang, Onat Inak, Larissa Triess, Niklas Hanselmann, Marius Cordts, Andreas Zell
Abstract: Open-world 3D semantic occupancy prediction aims to generate a voxelized 3D representation from sensor inputs while recognizing both known and unknown objects. Transferring open-vocabulary knowledge from vision-language models (VLMs) offers a promising direction but remains challenging. However, methods based on VLM-derived 2D pseudo-labels with traditional supervision are limited by a predefined label space and lack general prediction capabilities. Direct alignment with pretrained image embeddings, on the other hand, fails to achieve reliable performance due to often inconsistent image and text representations in VLMs. To address these challenges, we propose AGO, a novel 3D occupancy prediction framework with adaptive grounding to handle diverse open-world scenarios. AGO first encodes surrounding images and class prompts into 3D and text embeddings, respectively, leveraging similarity-based grounding training with 3D pseudo-labels. Additionally, a modality adapter maps 3D embeddings into a space aligned with VLM-derived image embeddings, reducing modality gaps. Experiments on Occ3D-nuScenes show that AGO improves unknown object prediction in zero-shot and few-shot transfer while achieving state-of-the-art closed-world self-supervised performance, surpassing prior methods by 4.09 mIoU.
Authors: Tzu-Yun Tseng, Hongyu Lyu, Josephine Li, Julie Stephany Berrio, Mao Shan, Stewart Worrall
Abstract: Road damage can create safety and comfort challenges for both human drivers and autonomous vehicles (AVs). This damage is particularly prevalent in rural areas due to less frequent surveying and maintenance of roads. Automated detection of pavement deterioration can be used as an input to AVs and driver assistance systems to improve road safety. Current research in this field has predominantly focused on urban environments driven largely by public datasets, while rural areas have received significantly less attention. This paper introduces M2S-RoAD, a dataset for the semantic segmentation of different classes of road damage. M2S-RoAD was collected in various towns across New South Wales, Australia, and labelled for semantic segmentation to identify nine distinct types of road damage. This dataset will be released upon the acceptance of the paper.
Authors: Chunyang Zhang, Zhenhong Sun, Zhicheng Zhang, Junyan Wang, Yu Zhang, Dong Gong, Huadong Mo, Daoyi Dong
Abstract: Text-to-image (T2I) generation models often struggle with multi-instance synthesis (MIS), where they must accurately depict multiple distinct instances in a single image based on complex prompts detailing individual features. Traditional MIS control methods for UNet architectures like SD v1.5/SDXL fail to adapt to DiT-based models like FLUX and SD v3.5, which rely on integrated attention between image and text tokens rather than text-image cross-attention. To enhance MIS in DiT, we first analyze the mixed attention mechanism in DiT. Our token-wise and layer-wise analysis of attention maps reveals a hierarchical response structure: instance tokens dominate early layers, background tokens in middle layers, and attribute tokens in later layers. Building on this observation, we propose a training-free approach for enhancing MIS in DiT-based models with hierarchical and step-layer-wise attention specialty tuning (AST). AST amplifies key regions while suppressing irrelevant areas in distinct attention maps across layers and steps, guided by the hierarchical structure. This optimizes multimodal interactions by hierarchically decoupling the complex prompts with instance-based sketches. We evaluate our approach using upgraded sketch-based layouts for the T2I-CompBench and customized complex scenes. Both quantitative and qualitative results confirm our method enhances complex layout generation, ensuring precise instance placement and attribute representation in MIS.
Authors: Jiansheng Li, Xingxuan Zhang, Hao Zou, Yige Guo, Renzhe Xu, Yilong Liu, Chuzhao Zhu, Yue He, Peng Cui
Abstract: Current object detectors often suffer significant perfor-mance degradation in real-world applications when encountering distributional shifts. Consequently, the out-of-distribution (OOD) generalization capability of object detectors has garnered increasing attention from researchers. Despite this growing interest, there remains a lack of a large-scale, comprehensive dataset and evaluation benchmark with fine-grained annotations tailored to assess the OOD generalization on more intricate tasks like object detection and grounding. To address this gap, we introduce COUNTS, a large-scale OOD dataset with object-level annotations. COUNTS encompasses 14 natural distributional shifts, over 222K samples, and more than 1,196K labeled bounding boxes. Leveraging COUNTS, we introduce two novel benchmarks: O(OD)2 and OODG. O(OD)2 is designed to comprehensively evaluate the OOD generalization capabilities of object detectors by utilizing controlled distribution shifts between training and testing data. OODG, on the other hand, aims to assess the OOD generalization of grounding abilities in multimodal large language models (MLLMs). Our findings reveal that, while large models and extensive pre-training data substantially en hance performance in in-distribution (IID) scenarios, significant limitations and opportunities for improvement persist in OOD contexts for both object detectors and MLLMs. In visual grounding tasks, even the advanced GPT-4o and Gemini-1.5 only achieve 56.7% and 28.0% accuracy, respectively. We hope COUNTS facilitates advancements in the development and assessment of robust object detectors and MLLMs capable of maintaining high performance under distributional shifts.
Authors: Nguyen Ngoc Dat, Tom Richardson, Matthew Watson, Kilian Meier, Jenna Kline, Sid Reid, Guy Maalouf, Duncan Hine, Majid Mirmehdi, Tilo Burghardt
Abstract: Live tracking of wildlife via high-resolution video processing directly onboard drones is widely unexplored and most existing solutions rely on streaming video to ground stations to support navigation. Yet, both autonomous animal-reactive flight control beyond visual line of sight and/or mission-specific individual and behaviour recognition tasks rely to some degree on this capability. In response, we introduce WildLive -- a near real-time animal detection and tracking framework for high-resolution imagery running directly onboard uncrewed aerial vehicles (UAVs). The system performs multi-animal detection and tracking at 17fps+ for HD and 7fps+ on 4K video streams suitable for operation during higher altitude flights to minimise animal disturbance. Our system is optimised for Jetson Orin AGX onboard hardware. It integrates the efficiency of sparse optical flow tracking and mission-specific sampling with device-optimised and proven YOLO-driven object detection and segmentation techniques. Essentially, computational resource is focused onto spatio-temporal regions of high uncertainty to significantly improve UAV processing speeds without domain-specific loss of accuracy. Alongside, we introduce our WildLive dataset, which comprises 200k+ annotated animal instances across 19k+ frames from 4K UAV videos collected at the Ol Pejeta Conservancy in Kenya. All frames contain ground truth bounding boxes, segmentation masks, as well as individual tracklets and tracking point trajectories. We compare our system against current object tracking approaches including OC-SORT, ByteTrack, and SORT. Our multi-animal tracking experiments with onboard hardware confirm that near real-time high-resolution wildlife tracking is possible on UAVs whilst maintaining high accuracy levels as needed for future navigational and mission-specific animal-centric operational autonomy.
Authors: Yiding Lu, Mouxing Yang, Dezhong Peng, Peng Hu, Yijie Lin, Xi Peng
Abstract: Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often partial or vague. To address this limitation, we introduce a new task called interactive person re-identification (Inter-ReID). Inter-ReID is a dialogue-based retrieval task that iteratively refines initial descriptions through ongoing interactions with the witnesses. To facilitate the study of this new task, we construct a dialogue dataset that incorporates multiple types of questions by decomposing fine-grained attributes of individuals. We further propose LLaVA-ReID, a question model that generates targeted questions based on visual and textual contexts to elicit additional details about the target person. Leveraging a looking-forward strategy, we prioritize the most informative questions as supervision during training. Experimental results on both Inter-ReID and text-based ReID benchmarks demonstrate that LLaVA-ReID significantly outperforms baselines.
Authors: Kaushik Bhargav Sivangi, Idris Zakariyya, Paul Henderson, Fani Deligianni
Abstract: Human pose estimation (HPE) has become essential in numerous applications including healthcare, activity recognition, and human-computer interaction. However, the privacy implications of processing sensitive visual data present significant deployment barriers in critical domains. While traditional anonymization techniques offer limited protection and often compromise data utility for broader motion analysis, Differential Privacy (DP) provides formal privacy guarantees but typically degrades model performance when applied naively. In this work, we present the first differentially private 2D human pose estimation (2D-HPE) by applying Differentially Private Stochastic Gradient Descent (DP-SGD) to this task. To effectively balance privacy with performance, we adopt Projected DP-SGD (PDP-SGD), which projects the noisy gradients to a low-dimensional subspace. Additionally, we adapt TinyViT, a compact and efficient vision transformer for coordinate classification in HPE, providing a lightweight yet powerful backbone that enhances privacy-preserving deployment feasibility on resource-limited devices. Our approach is particularly valuable for multimedia interpretation tasks, enabling privacy-safe analysis and understanding of human motion across diverse visual media while preserving the semantic meaning required for downstream applications. Comprehensive experiments on the MPII Human Pose Dataset demonstrate significant performance enhancement with PDP-SGD achieving 78.48% PCKh@0.5 at a strict privacy budget ($\epsilon=0.2$), compared to 63.85% for standard DP-SGD. This work lays foundation for privacy-preserving human pose estimation in real-world, sensitive applications.
Authors: Raphael Achddou, Yann Gousseau, Sa\"id Ladjal, Sabine S\"usstrunk
Abstract: Even though Deep Neural Networks are extremely powerful for image restoration tasks, they have several limitations. They are poorly understood and suffer from strong biases inherited from the training sets. One way to address these shortcomings is to have a better control over the training sets, in particular by using synthetic sets. In this paper, we propose a synthetic image generator relying on a few simple principles. In particular, we focus on geometric modeling, textures, and a simple modeling of image acquisition. These properties, integrated in a classical Dead Leaves model, enable the creation of efficient training sets. Standard image denoising and super-resolution networks can be trained on such datasets, reaching performance almost on par with training on natural image datasets. As a first step towards explainability, we provide a careful analysis of the considered principles, identifying which image properties are necessary to obtain good performances. Besides, such training also yields better robustness to various geometric and radiometric perturbations of the test sets.
Authors: Songze Li, Qixing Xu, Tonghua Su, Xu-Yao Zhang, Zhongjie Wang
Abstract: The balance between stability and plasticity remains a fundamental challenge in pretrained model-based incremental object detection (PTMIOD). While existing PTMIOD methods demonstrate strong performance on in-domain tasks aligned with pretraining data, their plasticity to cross-domain scenarios remains underexplored. Through systematic component-wise analysis of pretrained detectors, we reveal a fundamental discrepancy: the localization modules demonstrate inherent cross-domain stability-preserving precise bounding box estimation across distribution shifts-while the classification components require enhanced plasticity to mitigate discriminability degradation in cross-domain scenarios. Motivated by these findings, we propose a dual-path framework built upon pretrained DETR-based detectors which decouples localization stability and classification plasticity: the localization path maintains stability to preserve pretrained localization knowledge, while the classification path facilitates plasticity via parameter-efficient fine-tuning and resists forgetting with pseudo-feature replay. Extensive evaluations on both in-domain (MS COCO and PASCAL VOC) and cross-domain (TT100K) benchmarks show state-of-the-art performance, demonstrating our method's ability to effectively balance stability and plasticity in PTMIOD, achieving robust cross-domain adaptation and strong retention of anti-forgetting capabilities.
Authors: Tianyu Xin, Jin-Liang Xiao, Zeyu Xia, Shan Yin, Liang-Jian Deng
Abstract: Pansharpening is a crucial remote sensing technique that fuses low-resolution multispectral (LRMS) images with high-resolution panchromatic (PAN) images to generate high-resolution multispectral (HRMS) imagery. Although deep learning techniques have significantly advanced pansharpening, many existing methods suffer from limited cross-sensor generalization and high computational overhead, restricting their real-time applications. To address these challenges, we propose an efficient framework that quickly adapts to a specific input instance, completing both training and inference in a short time. Our framework splits the input image into multiple patches, selects a subset for unsupervised CAT training, and then performs inference on all patches, stitching them into the final output. The CAT module, integrated between the feature extraction and channel transformation stages of a pre-trained network, tailors the fused features and fixes the parameters for efficient inference, generating improved results. Our approach offers two key advantages: (1) $\textit{Improved Generalization Ability}$: by mitigating cross-sensor degradation, our model--although pre-trained on a specific dataset--achieves superior performance on datasets captured by other sensors; (2) $\textit{Enhanced Computational Efficiency}$: the CAT-enhanced network can swiftly adapt to the test sample using the single LRMS-PAN pair input, without requiring extensive large-scale data retraining. Experiments on the real-world data from WorldView-3 and WorldView-2 datasets demonstrate that our method achieves state-of-the-art performance on cross-sensor real-world data, while achieving both training and inference of $512\times512$ image within $\textit{0.4 seconds}$ and $4000\times4000$ image within $\textit{3 seconds}$ at the fastest setting on a commonly used RTX 3090 GPU.
Authors: Xuqiang Cao, Linnan Zhao, Jiaxuan Zhao, Fang Liu, Puhua Chen, Wenping Ma
Abstract: Complex video object segmentation continues to face significant challenges in small object recognition, occlusion handling, and dynamic scene modeling. This report presents our solution, which ranked second in the MOSE track of CVPR 2025 PVUW Challenge. Based on an existing segmentation framework, we propose an improved model named MASSeg for complex video object segmentation, and construct an enhanced dataset, MOSE+, which includes typical scenarios with occlusions, cluttered backgrounds, and small target instances. During training, we incorporate a combination of inter-frame consistent and inconsistent data augmentation strategies to improve robustness and generalization. During inference, we design a mask output scaling strategy to better adapt to varying object sizes and occlusion levels. As a result, MASSeg achieves a J score of 0.8250, F score of 0.9007, and a J&F score of 0.8628 on the MOSE test set.
Authors: Shuai Liu, Youmeng Li, Jizeng Wei
Abstract: Document Reading Order Recovery is a fundamental task in document image understanding, playing a pivotal role in enhancing Retrieval-Augmented Generation (RAG) and serving as a critical preprocessing step for large language models (LLMs). Existing methods often struggle with complex layouts(e.g., multi-column newspapers), high-overhead interactions between cross-modal elements (visual regions and textual semantics), and a lack of robust evaluation benchmarks. We introduce XY-Cut++, an advanced layout ordering method that integrates pre-mask processing, multi-granularity segmentation, and cross-modal matching to address these challenges. Our method significantly enhances layout ordering accuracy compared to traditional XY-Cut techniques. Specifically, XY-Cut++ achieves state-of-the-art performance (98.8 BLEU overall) while maintaining simplicity and efficiency. It outperforms existing baselines by up to 24\% and demonstrates consistent accuracy across simple and complex layouts on the newly introduced DocBench-100 dataset. This advancement establishes a reliable foundation for document structure recovery, setting a new standard for layout ordering tasks and facilitating more effective RAG and LLM preprocessing.
Authors: Mengdi Wang, Efe Bozkir, Enkelejda Kasneci
Abstract: Recent developments in hardware, computer graphics, and AI may soon enable AR/VR head-mounted displays (HMDs) to become everyday devices like smartphones and tablets. Eye trackers within HMDs provide a special opportunity for such setups as it is possible to facilitate gaze-based research and interaction. However, estimating users' gaze information often requires raw eye images and videos that contain iris textures, which are considered a gold standard biometric for user authentication, and this raises privacy concerns. Previous research in the eye-tracking community focused on obfuscating iris textures while keeping utility tasks such as gaze estimation accurate. Despite these attempts, there is no comprehensive benchmark that evaluates state-of-the-art approaches. Considering all, in this paper, we benchmark blurring, noising, downsampling, rubber sheet model, and iris style transfer to obfuscate user identity, and compare their impact on image quality, privacy, utility, and risk of imposter attack on two datasets. We use eye segmentation and gaze estimation as utility tasks, and reduction in iris recognition accuracy as a measure of privacy protection, and false acceptance rate to estimate risk of attack. Our experiments show that canonical image processing methods like blurring and noising cause a marginal impact on deep learning-based tasks. While downsampling, rubber sheet model, and iris style transfer are effective in hiding user identifiers, iris style transfer, with higher computation cost, outperforms others in both utility tasks, and is more resilient against spoof attacks. Our analyses indicate that there is no universal optimal approach to balance privacy, utility, and computation burden. Therefore, we recommend practitioners consider the strengths and weaknesses of each approach, and possible combinations of those to reach an optimal privacy-utility trade-off.
Authors: Harsh Yadav, Maximilian Schaefer, Kun Zhao, Tobias Meisen
Abstract: Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMFormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMFormer to train on multiple datasets and achieve better performance.
Authors: Jinyue Zhang, Xiangrong Zhang, Zhongjian Huang, Tianyang Zhang, Yifei Jiang, Licheng Jiao
Abstract: Moving object detection (MOD) in remote sensing is significantly challenged by low resolution, extremely small object sizes, and complex noise interference. Current deep learning-based MOD methods rely on probability density estimation, which restricts flexible information interaction between objects and across temporal frames. To flexibly capture high-order inter-object and temporal relationships, we propose a point-based MOD in remote sensing. Inspired by diffusion models, the network optimization is formulated as a progressive denoising process that iteratively recovers moving object centers from sparse noisy points. Specifically, we sample scattered features from the backbone outputs as atomic units for subsequent processing, while global feature embeddings are aggregated to compensate for the limited coverage of sparse point features. By modeling spatial relative positions and semantic affinities, Spatial Relation Aggregation Attention is designed to enable high-order interactions among point-level features for enhanced object representation. To enhance temporal consistency, the Temporal Propagation and Global Fusion module is designed, which leverages an implicit memory reasoning mechanism for robust cross-frame feature integration. To align with the progressive denoising process, we propose a progressive MinK optimal transport assignment strategy that establishes specialized learning objectives at each denoising level. Additionally, we introduce a missing loss function to counteract the clustering tendency of denoised points around salient objects. Experiments on the RsData remote sensing MOD dataset show that our MOD method based on scattered point denoising can more effectively explore potential relationships between sparse moving objects and improve the detection capability and temporal consistency.
Authors: Mathieu Manni, Dmitry Karpov, K. Joost Batenburg, Sharon Shwartz, Nicola Vigan\`o
Abstract: We present a new self-supervised deep-learning-based Ghost Imaging (GI) reconstruction method, which provides unparalleled reconstruction performance for noisy acquisitions among unsupervised methods. We present the supporting mathematical framework and results from theoretical and real data use cases. Self-supervision removes the need for clean reference data while offering strong noise reduction. This provides the necessary tools for addressing signal-to-noise ratio concerns for GI acquisitions in emerging and cutting-edge low-light GI scenarios. Notable examples include micro- and nano-scale x-ray emission imaging, e.g., x-ray fluorescence imaging of dose-sensitive samples. Their applications include in-vivo and in-operando case studies for biological samples and batteries.
Authors: Huiqi Wu, Jianbo Mei, Yingjie Huang, Yining Xu, Jingjiao You, Yilong Liu, Li Yao
Abstract: In recent years, significant advancements have been made in text-driven 3D content generation. However, several challenges remain. In practical applications, users often provide extremely simple text inputs while expecting high-quality 3D content. Generating optimal results from such minimal text is a difficult task due to the strong dependency of text-to-3D models on the quality of input prompts. Moreover, the generation process exhibits high variability, making it difficult to control. Consequently, multiple iterations are typically required to produce content that meets user expectations, reducing generation efficiency. To address this issue, we propose GPT-4V for self-optimization, which significantly enhances the efficiency of generating satisfactory content in a single attempt. Furthermore, the controllability of text-to-3D generation methods has not been fully explored. Our approach enables users to not only provide textual descriptions but also specify additional conditions, such as style, edges, scribbles, poses, or combinations of multiple conditions, allowing for more precise control over the generated 3D content. Additionally, during training, we effectively integrate multi-view information, including multi-view depth, masks, features, and images, to address the common Janus problem in 3D content generation. Extensive experiments demonstrate that our method achieves robust generalization, facilitating the efficient and controllable generation of high-quality 3D content.
Authors: Yuxin Wen, Jim Wu, Ajay Jain, Tom Goldstein, Ashwinee Panda
Abstract: We conduct an in-depth analysis of attention in video diffusion transformers (VDiTs) and report a number of novel findings. We identify three key properties of attention in VDiTs: Structure, Sparsity, and Sinks. Structure: We observe that attention patterns across different VDiTs exhibit similar structure across different prompts, and that we can make use of the similarity of attention patterns to unlock video editing via self-attention map transfer. Sparse: We study attention sparsity in VDiTs, finding that proposed sparsity methods do not work for all VDiTs, because some layers that are seemingly sparse cannot be sparsified. Sinks: We make the first study of attention sinks in VDiTs, comparing and contrasting them to attention sinks in language models. We propose a number of future directions that can make use of our insights to improve the efficiency-quality Pareto frontier for VDiTs.
Authors: Zongcan Ding, Haodong Zhang, Peng Wu, Guansong Pang, Zhiwei Yang, Peng Wang, Yanning Zhang
Abstract: Video anomaly detection (VAD) aims to identify unexpected events in videos and has wide applications in safety-critical domains. While semi-supervised methods trained on only normal samples have gained traction, they often suffer from high false alarm rates and poor interpretability. Recently, vision-language models (VLMs) have demonstrated strong multimodal reasoning capabilities, offering new opportunities for explainable anomaly detection. However, their high computational cost and lack of domain adaptation hinder real-time deployment and reliability. Inspired by dual complementary pathways in human visual perception, we propose SlowFastVAD, a hybrid framework that integrates a fast anomaly detector with a slow anomaly detector (namely a retrieval augmented generation (RAG) enhanced VLM), to address these limitations. Specifically, the fast detector first provides coarse anomaly confidence scores, and only a small subset of ambiguous segments, rather than the entire video, is further analyzed by the slower yet more interpretable VLM for elaborate detection and reasoning. Furthermore, to adapt VLMs to domain-specific VAD scenarios, we construct a knowledge base including normal patterns based on few normal samples and abnormal patterns inferred by VLMs. During inference, relevant patterns are retrieved and used to augment prompts for anomaly reasoning. Finally, we smoothly fuse the anomaly confidence of fast and slow detectors to enhance robustness of anomaly detection. Extensive experiments on four benchmarks demonstrate that SlowFastVAD effectively combines the strengths of both fast and slow detectors, and achieves remarkable detection accuracy and interpretability with significantly reduced computational overhead, making it well-suited for real-world VAD applications with high reliability requirements.
Authors: Xingyu Lu, Yuhang Hu, YiFan Zhang, Kaiyu Jiang, Changyi Liu, Tianke Zhang, Jinpeng Wang, Bin Wen, Chun Yuan, Fan Yang, Tingting Gao, Di Zhang
Abstract: Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models. Existing methods face certain limitations in terms of both data and algorithm. For training data, most approaches rely on manual annotated preference data, either by directly fine-tuning the generators or by training reward models to provide training signals. However, the high annotation cost makes them difficult to scale up, the reward model consumes extra computation and cannot guarantee accuracy. From an algorithmic perspective, most methods neglect the value of text and only take the image feedback as a comparative signal, which is inefficient and sparse. To alleviate these drawbacks, we propose the InstructEngine framework. Regarding annotation cost, we first construct a taxonomy for text-to-image generation, then develop an automated data construction pipeline based on it. Leveraging advanced large multimodal models and human-defined rules, we generate 25K text-image preference pairs. Finally, we introduce cross-validation alignment method, which refines data efficiency by organizing semantically analogous samples into mutually comparable pairs. Evaluations on DrawBench demonstrate that InstructEngine improves SD v1.5 and SDXL's performance by 10.53% and 5.30%, outperforming state-of-the-art baselines, with ablation study confirming the benefits of InstructEngine's all components. A win rate of over 50% in human reviews also proves that InstructEngine better aligns with human preferences.
Authors: Hao Sun, Fenggen Yu, Huiyao Xu, Tao Zhang, Changqing Zou
Abstract: Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs characterized by severe noise, low dynamic range (LDR) and unreliable initialization. While recent NeRF-based approaches have shown promising results, most suffer from high computational costs, and some rely on carefully captured or pre-processed data--such as RAW sensor inputs or multi-exposure sequences--which severely limits their practicality. In contrast, 3D Gaussian Splatting (3DGS) enables real-time rendering with competitive visual fidelity; however, existing 3DGS-based methods struggle with low-light sRGB inputs, resulting in unstable Gaussian initialization and ineffective noise suppression. To address these challenges, we propose LL-Gaussian, a novel framework for 3D reconstruction and enhancement from low-light sRGB images, enabling pseudo normal-light novel view synthesis. Our method introduces three key innovations: 1) an end-to-end Low-Light Gaussian Initialization Module (LLGIM) that leverages dense priors from learning-based MVS approach to generate high-quality initial point clouds; 2) a dual-branch Gaussian decomposition model that disentangles intrinsic scene properties (reflectance and illumination) from transient interference, enabling stable and interpretable optimization; 3) an unsupervised optimization strategy guided by both physical constrains and diffusion prior to jointly steer decomposition and enhancement. Additionally, we contribute a challenging dataset collected in extreme low-light environments and demonstrate the effectiveness of LL-Gaussian. Compared to state-of-the-art NeRF-based methods, LL-Gaussian achieves up to 2,000 times faster inference and reduces training time to just 2%, while delivering superior reconstruction and rendering quality.
Authors: Filipa Lino, Carlos Santiago, Manuel Marques
Abstract: This paper addresses critical challenges in 3D Human Pose Estimation (HPE) by analyzing the robustness and sensitivity of existing models to occlusions, camera position, and action variability. Using a novel synthetic dataset, BlendMimic3D, which includes diverse scenarios with multi-camera setups and several occlusion types, we conduct specific tests on several state-of-the-art models. Our study focuses on the discrepancy in keypoint formats between common datasets such as Human3.6M, and 2D datasets such as COCO, commonly used for 2D detection models and frequently input of 3D HPE models. Our work explores the impact of occlusions on model performance and the generality of models trained exclusively under standard conditions. The findings suggest significant sensitivity to occlusions and camera settings, revealing a need for models that better adapt to real-world variability and occlusion scenarios. This research contributed to ongoing efforts to improve the fidelity and applicability of 3D HPE systems in complex environments.
Authors: Kaiwen Zheng, Xuri Ge, Junchen Fu, Jun Peng, Joemon M. Jose
Abstract: Multimodal foundation models have significantly improved feature representation by integrating information from multiple modalities, making them highly suitable for a broader set of applications. However, the exploration of multimodal facial representation for understanding perception has been limited. Understanding and analyzing facial states, such as Action Units (AUs) and emotions, require a comprehensive and robust framework that bridges visual and linguistic modalities. In this paper, we present a comprehensive pipeline for multimodal facial state analysis. First, we compile a new Multimodal Face Dataset (MFA) by generating detailed multilevel language descriptions of face, incorporating Action Unit (AU) and emotion descriptions, by leveraging GPT-4o. Second, we introduce a novel Multilevel Multimodal Face Foundation model (MF^2) tailored for Action Unit (AU) and emotion recognition. Our model incorporates comprehensive visual feature modeling at both local and global levels of face image, enhancing its ability to represent detailed facial appearances. This design aligns visual representations with structured AU and emotion descriptions, ensuring effective cross-modal integration. Third, we develop a Decoupled Fine-Tuning Network (DFN) that efficiently adapts MF^2 across various tasks and datasets. This approach not only reduces computational overhead but also broadens the applicability of the foundation model to diverse scenarios. Experimentation show superior performance for AU and emotion detection tasks.
Authors: Jeremiah Giordani
Abstract: Autonomous fabrication systems are transforming construction and manufacturing, yet they remain vulnerable to print errors. Texture classification is a key component of computer vision systems that enable real-time monitoring and adjustment during cementitious fabrication. Traditional classification methods often rely on global image features, which can bias the model toward semantic content rather than low-level textures. In this paper, we introduce a novel preprocessing technique called "patch and shuffle," which segments input images into smaller patches, shuffles them, and reconstructs a jumbled image before classification. This transformation removes semantic context, forcing the classifier to rely on local texture features. We evaluate this approach on a dataset of extruded cement images, using a ResNet-18-based architecture. Our experiments compare the patch and shuffle method to a standard pipeline, holding all other factors constant. Results show a significant improvement in accuracy: the patch and shuffle model achieved 90.64% test accuracy versus 72.46% for the baseline. These findings suggest that disrupting global structure enhances performance in texture-based classification tasks. This method has implications for broader vision tasks where low-level features matter more than high-level semantics. The technique may improve classification in applications ranging from fabrication monitoring to medical imaging.
Authors: Rui Chen, Lei Sun, Jing Tang, Geng Li, Xiangxiang Chu
Abstract: Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The various inconsistencies and defects observed in such videos are inherently complex, making overall scoring notoriously difficult. In this paper, we emphasize the critical importance of integrating fine-grained reasoning into video evaluation, and we propose $\textbf{F}$ing$\textbf{ER}$, a novel entity-level reasoning evaluation framework that first automatically generates $\textbf{F}$ine-grained $\textbf{E}$ntity-level questions, and then answers those questions by a $\textbf{R}$easoning model with scores, which can be subsequently weighted summed to an overall score for different applications. Specifically, we leverage LLMs to derive entity-level questions across five distinct perspectives, which (i) often focus on some specific entities of the content, thereby making answering or scoring much easier by MLLMs, and (ii) are more interpretable. Then we construct a FingER dataset, consisting of approximately 3.3k videos and corresponding 60k fine-grained QA annotations, each with detailed reasons. Based on that, we further investigate various training protocols to best incentivize the reasoning capability of MLLMs for correct answer prediction. Extensive experiments demonstrate that a reasoning model trained using Group Relative Policy Optimization (GRPO) with a cold-start strategy achieves the best performance. Notably, our model surpasses existing methods by a relative margin of $11.8\%$ on GenAI-Bench and $5.5\%$ on MonetBench with only 3.3k training videos, which is at most one-tenth of the training samples utilized by other methods. Our code and dataset will be released soon.
Authors: Maud Biquard, Marie Chabert, Florence Genin, Christophe Latry, Thomas Oberlin
Abstract: Poisson-Gaussian noise describes the noise of various imaging systems thus the need of efficient algorithms for Poisson-Gaussian image restoration. Deep learning methods offer state-of-the-art performance but often require sensor-specific training when used in a supervised setting. A promising alternative is given by plug-and-play (PnP) methods, which consist in learning only a regularization through a denoiser, allowing to restore images from several sources with the same network. This paper introduces PG-DPIR, an efficient PnP method for high-count Poisson-Gaussian inverse problems, adapted from DPIR. While DPIR is designed for white Gaussian noise, a naive adaptation to Poisson-Gaussian noise leads to prohibitively slow algorithms due to the absence of a closed-form proximal operator. To address this, we adapt DPIR for the specificities of Poisson-Gaussian noise and propose in particular an efficient initialization of the gradient descent required for the proximal step that accelerates convergence by several orders of magnitude. Experiments are conducted on satellite image restoration and super-resolution problems. High-resolution realistic Pleiades images are simulated for the experiments, which demonstrate that PG-DPIR achieves state-of-the-art performance with improved efficiency, which seems promising for on-ground satellite processing chains.
Authors: Ragini Bal Mahesh, Ronny H\"ansch
Abstract: Estimating forest height from Synthetic Aperture Radar (SAR) images often relies on traditional physical models, which, while interpretable and data-efficient, can struggle with generalization. In contrast, Deep Learning (DL) approaches lack physical insight. To address this, we propose CoHNet - an end-to-end framework that combines the best of both worlds: DL optimized with physics-informed constraints. We leverage a pre-trained neural surrogate model to enforce physical plausibility through a unique training loss. Our experiments show that this approach not only improves forest height estimation accuracy but also produces meaningful features that enhance the reliability of predictions.
Authors: Pietro Bonazzi, Christian Vogt, Michael Jost, Lyes Khacef, Federico Paredes-Vall\'es, Michele Magno
Abstract: This work quantitatively evaluates the performance of event-based vision systems (EVS) against conventional RGB-based models for action prediction in collision avoidance on an FPGA accelerator. Our experiments demonstrate that the EVS model achieves a significantly higher effective frame rate (1 kHz) and lower temporal (-20 ms) and spatial prediction errors (-20 mm) compared to the RGB-based model, particularly when tested on out-of-distribution data. The EVS model also exhibits superior robustness in selecting optimal evasion maneuvers. In particular, in distinguishing between movement and stationary states, it achieves a 59 percentage point advantage in precision (78% vs. 19%) and a substantially higher F1 score (0.73 vs. 0.06), highlighting the susceptibility of the RGB model to overfitting. Further analysis in different combinations of spatial classes confirms the consistent performance of the EVS model in both test data sets. Finally, we evaluated the system end-to-end and achieved a latency of approximately 2.14 ms, with event aggregation (1 ms) and inference on the processing unit (0.94 ms) accounting for the largest components. These results underscore the advantages of event-based vision for real-time collision avoidance and demonstrate its potential for deployment in resource-constrained environments.
Authors: Mingchuan Ma, Yuhao Zhou, Jindi Lv, Yuxin Tian, Dan Si, Shujian Li, Qing Ye, Jiancheng Lv
Abstract: Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-based methods address this by maintaining a small memory buffer of previous samples, achieving competitive performance. For effective replay under constrained storage, recent approaches leverage distilled data to enhance the informativeness of memory. However, such approaches often involve significant computational overhead due to the use of bi-level optimization. Motivated by these limitations, we introduce Grid-based Patch Sampling (GPS), a lightweight and effective strategy for distilling informative memory samples without relying on a trainable model. GPS generates informative samples by sampling a subset of pixels from the original image, yielding compact low-resolution representations that preserve both semantic content and structural information. During replay, these representations are reassembled to support training and evaluation. Experiments on extensive benchmarks demonstrate that GRS can be seamlessly integrated into existing replay frameworks, leading to 3%-4% improvements in average end accuracy under memory-constrained settings, with limited computational overhead.
Authors: Jiaxin Lu, Chun-Hao Paul Huang, Uttaran Bhattacharya, Qixing Huang, Yi Zhou
Abstract: We present Human Motions with Objects (HUMOTO), a high-fidelity dataset of human-object interactions for motion generation, computer vision, and robotics applications. Featuring 736 sequences (7,875 seconds at 30 fps), HUMOTO captures interactions with 63 precisely modeled objects and 72 articulated parts. Our innovations include a scene-driven LLM scripting pipeline creating complete, purposeful tasks with natural progression, and a mocap-and-camera recording setup to effectively handle occlusions. Spanning diverse activities from cooking to outdoor picnics, HUMOTO preserves both physical accuracy and logical task flow. Professional artists rigorously clean and verify each sequence, minimizing foot sliding and object penetrations. We also provide benchmarks compared to other datasets. HUMOTO's comprehensive full-body motion and simultaneous multi-object interactions address key data-capturing challenges and provide opportunities to advance realistic human-object interaction modeling across research domains with practical applications in animation, robotics, and embodied AI systems. Project: https://jiaxin-lu.github.io/humoto/ .
Authors: Jian Liu, Wei Sun, Hui Yang, Jin Zheng, Zichen Geng, Hossein Rahmani, Ajmal Mian
Abstract: Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on shape priors or CAD models of the intra-class known objects. We propose a diffusion-based monocular category-level 9D object pose generation method, MonoDiff9D. Our motivation is to leverage the probabilistic nature of diffusion models to alleviate the need for shape priors, CAD models, or depth sensors for intra-class unknown object pose estimation. We first estimate coarse depth via DINOv2 from the monocular image in a zero-shot manner and convert it into a point cloud. We then fuse the global features of the point cloud with the input image and use the fused features along with the encoded time step to condition MonoDiff9D. Finally, we design a transformer-based denoiser to recover the object pose from Gaussian noise. Extensive experiments on two popular benchmark datasets show that MonoDiff9D achieves state-of-the-art monocular category-level 9D object pose estimation accuracy without the need for shape priors or CAD models at any stage. Our code will be made public at https://github.com/CNJianLiu/MonoDiff9D.
Authors: Taihang Hu, Linxuan Li, Kai Wang, Yaxing Wang, Jian Yang, Ming-Ming Cheng
Abstract: Text-to-image generation has seen groundbreaking advancements with diffusion models, enabling high-fidelity synthesis and precise image editing through cross-attention manipulation. Recently, autoregressive (AR) models have re-emerged as powerful alternatives, leveraging next-token generation to match diffusion models. However, existing editing techniques designed for diffusion models fail to translate directly to AR models due to fundamental differences in structural control. Specifically, AR models suffer from spatial poverty of attention maps and sequential accumulation of structural errors during image editing, which disrupt object layouts and global consistency. In this work, we introduce Implicit Structure Locking (ISLock), the first training-free editing strategy for AR visual models. Rather than relying on explicit attention manipulation or fine-tuning, ISLock preserves structural blueprints by dynamically aligning self-attention patterns with reference images through the Anchor Token Matching (ATM) protocol. By implicitly enforcing structural consistency in latent space, our method ISLock enables structure-aware editing while maintaining generative autonomy. Extensive experiments demonstrate that ISLock achieves high-quality, structure-consistent edits without additional training and is superior or comparable to conventional editing techniques. Our findings pioneer the way for efficient and flexible AR-based image editing, further bridging the performance gap between diffusion and autoregressive generative models. The code will be publicly available at https://github.com/hutaiHang/ATM
Authors: Haoran Hao, Jiaming Han, Yiyuan Zhang, Xiangyu Yue
Abstract: Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast amount of information within the video. Although some recent methods are designed for long video understanding, they often lose crucial information during token compression and struggle with additional modality like audio. In this work, we propose a dynamic long video encoding method utilizing the temporal relationship between frames, named Temporal Dynamic Context (TDC). Firstly, we segment the video into semantically consistent scenes based on inter-frame similarities, then encode each frame into tokens using visual-audio encoders. Secondly, we propose a novel temporal context compressor to reduce the number of tokens within each segment. Specifically, we employ a query-based Transformer to aggregate video, audio, and instruction text tokens into a limited set of temporal context tokens. Finally, we feed the static frame tokens and the temporal context tokens into the LLM for video understanding. Furthermore, to handle extremely long videos, we propose a training-free chain-of-thought strategy that progressively extracts answers from multiple video segments. These intermediate answers serve as part of the reasoning process and contribute to the final answer. We conduct extensive experiments on general video understanding and audio-video understanding benchmarks, where our method demonstrates strong performance. The code and models are available at https://github.com/Hoar012/TDC-Video.
Authors: Ramin Mousa, Hadis Taherinia, Khabiba Abdiyeva, Amir Ali Bengari, Mohammadmahdi Vahediahmar
Abstract: Effective recognition of acute and difficult-to-heal wounds is a necessary step in wound diagnosis. An efficient classification model can help wound specialists classify wound types with less financial and time costs and also help in deciding on the optimal treatment method. Traditional machine learning models suffer from feature selection and are usually cumbersome models for accurate recognition. Recently, deep learning (DL) has emerged as a powerful tool in wound diagnosis. Although DL seems promising for wound type recognition, there is still a large scope for improving the efficiency and accuracy of the model. In this study, a DL-based multimodal classifier was developed using wound images and their corresponding locations to classify them into multiple classes, including diabetic, pressure, surgical, and venous ulcers. A body map was also created to provide location data, which can help wound specialists label wound locations more effectively. The model uses a Vision Transformer to extract hierarchical features from input images, a Discrete Wavelet Transform (DWT) layer to capture low and high frequency components, and a Transformer to extract spatial features. The number of neurons and weight vector optimization were performed using three swarm-based optimization techniques (Monster Gorilla Toner (MGTO), Improved Gray Wolf Optimization (IGWO), and Fox Optimization Algorithm). The evaluation results show that weight vector optimization using optimization algorithms can increase diagnostic accuracy and make it a very effective approach for wound detection. In the classification using the original body map, the proposed model was able to achieve an accuracy of 0.8123 using image data and an accuracy of 0.8007 using a combination of image data and wound location. Also, the accuracy of the model in combination with the optimization models varied from 0.7801 to 0.8342.
Authors: Xiaobo Xia, Run Luo
Abstract: Existing efforts in building Graphical User Interface (GUI) agents largely rely on the training paradigm of supervised fine-tuning on Large Vision-Language Models (LVLMs). However, this approach not only demands extensive amounts of training data but also struggles to effectively understand GUI screenshots and generalize to unseen interfaces. The issue significantly limits its application in real-world scenarios, especially for high-level tasks. Inspired by Reinforcement Fine-Tuning (RFT) in large reasoning models (e.g., DeepSeek-R1), which efficiently enhances the problem-solving capabilities of large language models in real-world settings, we propose \name, the first reinforcement learning framework designed to enhance the GUI capabilities of LVLMs in high-level real-world task scenarios, through unified action space rule modeling. By leveraging a small amount of carefully curated high-quality data across multiple platforms (including Windows, Linux, MacOS, Android, and Web) and employing policy optimization algorithms such as Group Relative Policy Optimization (GRPO) to update the model, \name achieves superior performance using only 0.02\% of the data (3K vs. 13M) compared to previous state-of-the-art methods like OS-Atlas across eight benchmarks spanning three different platforms (mobile, desktop, and web). These results demonstrate the immense potential of reinforcement learning based on unified action space rule modeling in improving the execution capabilities of LVLMs for real-world GUI agent tasks.
Authors: Weixian Lei, Jiacong Wang, Haochen Wang, Xiangtai Li, Jun Hao Liew, Jiashi Feng, Zilong Huang
Abstract: This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture. Unlike existing modular MLLMs, which rely on a pre-trained vision transformer (ViT), SAIL eliminates the need for a separate vision encoder, presenting a more minimalist architecture design. Instead of introducing novel architectural components, SAIL adapts mix-attention mechanisms and multimodal positional encodings to better align with the distinct characteristics of visual and textual modalities. We systematically compare SAIL's properties-including scalability, cross-modal information flow patterns, and visual representation capabilities-with those of modular MLLMs. By scaling both training data and model size, SAIL achieves performance comparable to modular MLLMs. Notably, the removal of pretrained ViT components enhances SAIL's scalability and results in significantly different cross-modal information flow patterns. Moreover, SAIL demonstrates strong visual representation capabilities, achieving results on par with ViT-22B in vision tasks such as semantic segmentation. Code and models are available at https://github.com/bytedance/SAIL.
Authors: Tao Zhang, Xiangtai Li, Zilong Huang, Yanwei Li, Weixian Lei, Xueqing Deng, Shihao Chen, Shunping Ji, Jiashi Feng
Abstract: Multimodal Large Language Models (MLLMs) achieve remarkable performance for fine-grained pixel-level understanding tasks. However, all the works rely heavily on extra components, such as vision encoder (CLIP), segmentation experts, leading to high system complexity and limiting model scaling. In this work, our goal is to explore a highly simplified MLLM without introducing extra components. Our work is motivated by the recent works on Single trAnsformer as a unified vIsion-Language Model (SAIL) design, where these works jointly learn vision tokens and text tokens in transformers. We present Pixel-SAIL, a single transformer for pixel-wise MLLM tasks. In particular, we present three technical improvements on the plain baseline. First, we design a learnable upsampling module to refine visual token features. Secondly, we propose a novel visual prompt injection strategy to enable the single transformer to understand visual prompt inputs and benefit from the early fusion of visual prompt embeddings and vision tokens. Thirdly, we introduce a vision expert distillation strategy to efficiently enhance the single transformer's fine-grained feature extraction capability. In addition, we have collected a comprehensive pixel understanding benchmark (PerBench), using a manual check. It includes three tasks: detailed object description, visual prompt-based question answering, and visual-text referring segmentation. Extensive experiments on four referring segmentation benchmarks, one visual prompt benchmark, and our PerBench show that our Pixel-SAIL achieves comparable or even better results with a much simpler pipeline. Code and model will be released at https://github.com/magic-research/Sa2VA.
Authors: Xiaoyan Cong, Jiayi Shen, Zekun Li, Rao Fu, Tao Lu, Srinath Sridhar
Abstract: Large-scale pre-trained image-to-3D generative models have exhibited remarkable capabilities in diverse shape generations. However, most of them struggle to synthesize plausible 3D assets when the reference image is flat-colored like hand drawings due to the lack of 3D illusion, which are often the most user-friendly input modalities in art content creation. To this end, we propose Art3D, a training-free method that can lift flat-colored 2D designs into 3D. By leveraging structural and semantic features with pre- trained 2D image generation models and a VLM-based realism evaluation, Art3D successfully enhances the three-dimensional illusion in reference images, thus simplifying the process of generating 3D from 2D, and proves adaptable to a wide range of painting styles. To benchmark the generalization performance of existing image-to-3D models on flat-colored images without 3D feeling, we collect a new dataset, Flat-2D, with over 100 samples. Experimental results demonstrate the performance and robustness of Art3D, exhibiting superior generalizable capacity and promising practical applicability. Our source code and dataset will be publicly available on our project page: https://joy-jy11.github.io/ .
Authors: Chenghao Xiao, Isaac Chung, Imene Kerboua, Jamie Stirling, Xin Zhang, M\'arton Kardos, Roman Solomatin, Noura Al Moubayed, Kenneth Enevoldsen, Niklas Muennighoff
Abstract: Image representations are often evaluated through disjointed, task-specific protocols, leading to a fragmented understanding of model capabilities. For instance, it is unclear whether an image embedding model adept at clustering images is equally good at retrieving relevant images given a piece of text. We introduce the Massive Image Embedding Benchmark (MIEB) to evaluate the performance of image and image-text embedding models across the broadest spectrum to date. MIEB spans 38 languages across 130 individual tasks, which we group into 8 high-level categories. We benchmark 50 models across our benchmark, finding that no single method dominates across all task categories. We reveal hidden capabilities in advanced vision models such as their accurate visual representation of texts, and their yet limited capabilities in interleaved encodings and matching images and texts in the presence of confounders. We also show that the performance of vision encoders on MIEB correlates highly with their performance when used in multimodal large language models. Our code, dataset, and leaderboard are publicly available at https://github.com/embeddings-benchmark/mteb.
Authors: Jinguo Zhu, Weiyun Wang, Zhe Chen, Zhaoyang Liu, Shenglong Ye, Lixin Gu, Yuchen Duan, Hao Tian, Weijie Su, Jie Shao, Zhangwei Gao, Erfei Cui, Yue Cao, Yangzhou Liu, Weiye Xu, Hao Li, Jiahao Wang, Han Lv, Dengnian Chen, Songze Li, Yinan He, Tan Jiang, Jiapeng Luo, Yi Wang, Conghui He, Botian Shi, Xingcheng Zhang, Wenqi Shao, Junjun He, Yingtong Xiong, Wenwen Qu, Peng Sun, Penglong Jiao, Lijun Wu, Kaipeng Zhang, Huipeng Deng, Jiaye Ge, Kai Chen, Limin Wang, Min Dou, Lewei Lu, Xizhou Zhu, Tong Lu, Dahua Lin, Yu Qiao, Jifeng Dai, Wenhai Wang
Abstract: We introduce InternVL3, a significant advancement in the InternVL series featuring a native multimodal pre-training paradigm. Rather than adapting a text-only large language model (LLM) into a multimodal large language model (MLLM) that supports visual inputs, InternVL3 jointly acquires multimodal and linguistic capabilities from both diverse multimodal data and pure-text corpora during a single pre-training stage. This unified training paradigm effectively addresses the complexities and alignment challenges commonly encountered in conventional post-hoc training pipelines for MLLMs. To further improve performance and scalability, InternVL3 incorporates variable visual position encoding (V2PE) to support extended multimodal contexts, employs advanced post-training techniques such as supervised fine-tuning (SFT) and mixed preference optimization (MPO), and adopts test-time scaling strategies alongside an optimized training infrastructure. Extensive empirical evaluations demonstrate that InternVL3 delivers superior performance across a wide range of multi-modal tasks. In particular, InternVL3-78B achieves a score of 72.2 on the MMMU benchmark, setting a new state-of-the-art among open-source MLLMs. Its capabilities remain highly competitive with leading proprietary models, including ChatGPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro, while also maintaining strong pure-language proficiency. In pursuit of open-science principles, we will publicly release both the training data and model weights to foster further research and development in next-generation MLLMs.
Authors: Xingjian Leng, Jaskirat Singh, Yunzhong Hou, Zhenchang Xing, Saining Xie, Liang Zheng
Abstract: In this paper we tackle a fundamental question: "Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?" Traditional deep-learning wisdom dictates that end-to-end training is often preferable when possible. However, for latent diffusion transformers, it is observed that end-to-end training both VAE and diffusion-model using standard diffusion-loss is ineffective, even causing a degradation in final performance. We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss -- allowing both VAE and diffusion model to be jointly tuned during the training process. Despite its simplicity, the proposed training recipe (REPA-E) shows remarkable performance; speeding up diffusion model training by over 17x and 45x over REPA and vanilla training recipes, respectively. Interestingly, we observe that end-to-end tuning with REPA-E also improves the VAE itself; leading to improved latent space structure and downstream generation performance. In terms of final performance, our approach sets a new state-of-the-art; achieving FID of 1.26 and 1.83 with and without classifier-free guidance on ImageNet 256 x 256. Code is available at https://end2end-diffusion.github.io.
Authors: Yunsong Zhou, Naisheng Ye, William Ljungbergh, Tianyu Li, Jiazhi Yang, Zetong Yang, Hongzi Zhu, Christoffer Petersson, Hongyang Li
Abstract: Controllable scene generation could reduce the cost of diverse data collection substantially for autonomous driving. Prior works formulate the traffic layout generation as predictive progress, either by denoising entire sequences at once or by iteratively predicting the next frame. However, full sequence denoising hinders online reaction, while the latter's short-sighted next-frame prediction lacks precise goal-state guidance. Further, the learned model struggles to generate complex or challenging scenarios due to a large number of safe and ordinal driving behaviors from open datasets. To overcome these, we introduce Nexus, a decoupled scene generation framework that improves reactivity and goal conditioning by simulating both ordinal and challenging scenarios from fine-grained tokens with independent noise states. At the core of the decoupled pipeline is the integration of a partial noise-masking training strategy and a noise-aware schedule that ensures timely environmental updates throughout the denoising process. To complement challenging scenario generation, we collect a dataset consisting of complex corner cases. It covers 540 hours of simulated data, including high-risk interactions such as cut-in, sudden braking, and collision. Nexus achieves superior generation realism while preserving reactivity and goal orientation, with a 40% reduction in displacement error. We further demonstrate that Nexus improves closed-loop planning by 20% through data augmentation and showcase its capability in safety-critical data generation.
Authors: Zeren Jiang, Shaofei Wang, Siyu Tang
Abstract: Creating relightable and animatable human avatars from monocular videos is a rising research topic with a range of applications, e.g. virtual reality, sports, and video games. Previous works utilize neural fields together with physically based rendering (PBR), to estimate geometry and disentangle appearance properties of human avatars. However, one drawback of these methods is the slow rendering speed due to the expensive Monte Carlo ray tracing. To tackle this problem, we proposed to distill the knowledge from implicit neural fields (teacher) to explicit 2D Gaussian splatting (student) representation to take advantage of the fast rasterization property of Gaussian splatting. To avoid ray-tracing, we employ the split-sum approximation for PBR appearance. We also propose novel part-wise ambient occlusion probes for shadow computation. Shadow prediction is achieved by querying these probes only once per pixel, which paves the way for real-time relighting of avatars. These techniques combined give high-quality relighting results with realistic shadow effects. Our experiments demonstrate that the proposed student model achieves comparable or even better relighting results with our teacher model while being 370 times faster at inference time, achieving a 67 FPS rendering speed.
Authors: Yasser Benigmim, Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Raoul de Charette
Abstract: Recent Open-Vocabulary Semantic Segmentation (OVSS) models extend the CLIP model to segmentation while maintaining the use of multiple templates (e.g., a photo of
Authors: Xiaobing Yu, Jin Yang, Xiao Wu, Peijie Qiu, Xiaofeng Liu
Abstract: How to adapt a pre-trained model continuously for sequential tasks with different prediction class labels and domains and finally learn a generalizable model across diverse tasks is a long-lasting challenge. Continual learning (CL) has emerged as a promising approach to leverage pre-trained models (e.g., Transformers) for sequential tasks. While many existing CL methods incrementally store additional learned structures, such as Low-Rank Adaptation (LoRA) adapters or prompts and sometimes even preserve features from previous samples to maintain performance. This leads to unsustainable parameter growth and escalating storage costs as the number of tasks increases. Moreover, current approaches often lack task similarity awareness, which further hinders the models ability to effectively adapt to new tasks without interfering with previously acquired knowledge. To address these challenges, we propose FM-LoRA, a novel and efficient low-rank adaptation method that integrates both a dynamic rank selector (DRS) and dynamic meta-prompting (DMP). This framework allocates model capacity more effectively across tasks by leveraging a shared low-rank subspace critical for preserving knowledge, thereby avoiding continual parameter expansion. Extensive experiments on various CL benchmarks, including ImageNet-R, CIFAR100, and CUB200 for class-incremental learning (CIL), and DomainNet for domain-incremental learning (DIL), with Transformers backbone demonstrate that FM-LoRA effectively mitigates catastrophic forgetting while delivering robust performance across a diverse range of tasks and domains.
Authors: Natalia Sikora, Robert L. Manschke, Alethea M. Tang, Peter Dunstan, Dean A. Harris, Su Yang
Abstract: Colorectal cancer (CRC) ranks as the second leading cause of cancer-related deaths and the third most prevalent malignant tumour worldwide. Early detection of CRC remains problematic due to its non-specific and often embarrassing symptoms, which patients frequently overlook or hesitate to report to clinicians. Crucially, the stage at which CRC is diagnosed significantly impacts survivability, with a survival rate of 80-95\% for Stage I and a stark decline to 10\% for Stage IV. Unfortunately, in the UK, only 14.4\% of cases are diagnosed at the earliest stage (Stage I). In this study, we propose ColonScopeX, a machine learning framework utilizing explainable AI (XAI) methodologies to enhance the early detection of CRC and pre-cancerous lesions. Our approach employs a multimodal model that integrates signals from blood sample measurements, processed using the Savitzky-Golay algorithm for fingerprint smoothing, alongside comprehensive patient metadata, including medication history, comorbidities, age, weight, and BMI. By leveraging XAI techniques, we aim to render the model's decision-making process transparent and interpretable, thereby fostering greater trust and understanding in its predictions. The proposed framework could be utilised as a triage tool or a screening tool of the general population. This research highlights the potential of combining diverse patient data sources and explainable machine learning to tackle critical challenges in medical diagnostics.
Authors: Islam Mansour, Georg Fischer, Ronny Haensch, Irena Hajnsek
Abstract: Digital elevation models derived from Interferometric Synthetic Aperture Radar (InSAR) data over glacial and snow-covered regions often exhibit systematic elevation errors, commonly termed "penetration bias." We leverage existing physics-based models and propose an integrated correction framework that combines parametric physical modeling with machine learning. We evaluate the approach across three distinct training scenarios - each defined by a different set of acquisition parameters - to assess overall performance and the model's ability to generalize. Our experiments on Greenland's ice sheet using TanDEM-X data show that the proposed hybrid model corrections significantly reduce the mean and standard deviation of DEM errors compared to a purely physical modeling baseline. The hybrid framework also achieves significantly improved generalization than a pure ML approach when trained on data with limited diversity in acquisition parameters.
Authors: Minjie Deng, Yan Wei, Hao Zhai, An Wu, Yuncan Ouyang, Qianyao Peng
Abstract: In image fusion tasks, due to the lack of real fused images as priors, most deep learning-based fusion methods obtain global weight features from original images in large-scale data pairs to generate images that approximate real fused images. However, unlike previous studies, this paper utilizes Granular Ball adaptation to extract features in the brightness space as priors for deep networks, enabling the fusion network to converge quickly and complete the fusion task. This leads to few-shot training for a general image fusion network, and based on this, we propose the GBFF fusion method. According to the information expression division of pixel pairs in the original fused image, we classify pixel pairs with significant performance as the positive domain and non-significant pixel pairs as the boundary domain. We perform split inference in the brightness space using Granular Ball adaptation to compute weights for pixels that express information to varying degrees, generating approximate supervision images that provide priors for the neural network in the structural brightness space. Additionally, the extracted global saliency features also adaptively provide priors for setting the loss function weights of each image in the network, guiding the network to converge quickly at both global and pixel levels alongside the supervised images, thereby enhancing the expressiveness of the fused images. Each modality only used 10 pairs of images as the training set, completing the fusion task with a limited number of iterations. Experiments validate the effectiveness of the algorithm and theory, and qualitative and quantitative comparisons with SOTA methods show that this approach is highly competitive in terms of fusion time and image expressiveness.
Authors: Pouya Pezeshkpour, Moin Aminnaseri, Estevam Hruschka
Abstract: Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data together, nor how the flow of information between modalities is structured. In this paper, we examine how VLMs reason by analyzing their biases when confronted with scenarios that present conflicting image and text cues, a common occurrence in real-world applications. To uncover the extent and nature of these biases, we build upon existing benchmarks to create five datasets containing mismatched image-text pairs, covering topics in mathematics, science, and visual descriptions. Our analysis shows that VLMs favor text in simpler queries but shift toward images as query complexity increases. This bias correlates with model scale, with the difference between the percentage of image- and text-preferred responses ranging from +56.8% (image favored) to -74.4% (text favored), depending on the task and model. In addition, we explore three mitigation strategies: simple prompt modifications, modifications that explicitly instruct models on how to handle conflicting information (akin to chain-of-thought prompting), and a task decomposition strategy that analyzes each modality separately before combining their results. Our findings indicate that the effectiveness of these strategies in identifying and mitigating bias varies significantly and is closely linked to the model's overall performance on the task and the specific modality in question.
Authors: Yonghao Huang, Leiting Chen, Chuan Zhou
Abstract: Due to the success of CNN-based and Transformer-based models in various computer vision tasks, recent works study the applicability of CNN-Transformer hybrid architecture models in 3D multi-modality medical segmentation tasks. Introducing Transformer brings long-range dependent information modeling ability in 3D medical images to hybrid models via the self-attention mechanism. However, these models usually employ fixed receptive fields of 3D volumetric features within each self-attention layer, ignoring the multi-scale volumetric lesion features. To address this issue, we propose a CNN-Transformer hybrid 3D medical image segmentation model, named TMA-TransBTS, based on an encoder-decoder structure. TMA-TransBTS realizes simultaneous extraction of multi-scale 3D features and modeling of long-distance dependencies by multi-scale division and aggregation of 3D tokens in a self-attention layer. Furthermore, TMA-TransBTS proposes a 3D multi-scale cross-attention module to establish a link between the encoder and the decoder for extracting rich volume representations by exploiting the mutual attention mechanism of cross-attention and multi-scale aggregation of 3D tokens. Extensive experimental results on three public 3D medical segmentation datasets show that TMA-TransBTS achieves higher averaged segmentation results than previous state-of-the-art CNN-based 3D methods and CNN-Transform hybrid 3D methods for the segmentation of 3D multi-modality brain tumors.
Authors: Zeyu Yang, Zhilin Chen, Yipeng Sun, Anika Strittmatter, Anish Raj, Ahmad Allababidi, Johann S. Rink, Frank G. Z\"ollner
Abstract: In this study, we present seg2med, an advanced medical image synthesis framework that uses Denoising Diffusion Probabilistic Models (DDPM) to generate high-quality synthetic medical images conditioned on anatomical masks from TotalSegmentator. The framework synthesizes CT and MR images from segmentation masks derived from real patient data and XCAT digital phantoms, achieving a Structural Similarity Index Measure (SSIM) of 0.94 +/- 0.02 for CT and 0.89 +/- 0.04 for MR images compared to ground-truth images of real patients. It also achieves a Feature Similarity Index Measure (FSIM) of 0.78 +/- 0.04 for CT images from XCAT. The generative quality is further supported by a Fr\'echet Inception Distance (FID) of 3.62 for CT image generation. Additionally, seg2med can generate paired CT and MR images with consistent anatomical structures and convert images between CT and MR modalities, achieving SSIM values of 0.91 +/- 0.03 for MR-to-CT and 0.77 +/- 0.04 for CT-to-MR conversion. Despite the limitations of incomplete anatomical details in segmentation masks, the framework shows strong performance in cross-modality synthesis and multimodal imaging. seg2med also demonstrates high anatomical fidelity in CT synthesis, achieving a mean Dice coefficient greater than 0.90 for 11 abdominal organs and greater than 0.80 for 34 organs out of 59 in 58 test cases. The highest Dice of 0.96 +/- 0.01 was recorded for the right scapula. Leveraging the TotalSegmentator toolkit, seg2med enables segmentation mask generation across diverse datasets, supporting applications in clinical imaging, data augmentation, multimodal synthesis, and diagnostic algorithm development.
Authors: Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Jianqiang Ren, Liefeng Bo, Zhigang Tu
Abstract: Masked modeling framework has shown promise in co-speech motion generation. However, it struggles to identify semantically significant frames for effective motion masking. In this work, we propose a speech-queried attention-based mask modeling framework for co-speech motion generation. Our key insight is to leverage motion-aligned speech features to guide the masked motion modeling process, selectively masking rhythm-related and semantically expressive motion frames. Specifically, we first propose a motion-audio alignment module (MAM) to construct a latent motion-audio joint space. In this space, both low-level and high-level speech features are projected, enabling motion-aligned speech representation using learnable speech queries. Then, a speech-queried attention mechanism (SQA) is introduced to compute frame-level attention scores through interactions between motion keys and speech queries, guiding selective masking toward motion frames with high attention scores. Finally, the motion-aligned speech features are also injected into the generation network to facilitate co-speech motion generation. Qualitative and quantitative evaluations confirm that our method outperforms existing state-of-the-art approaches, successfully producing high-quality co-speech motion.
Authors: Lei Kang, Jia Li, Mi Tian, Hua Huang
Abstract: Sparsely activated Mixture-of-Experts (MoE) models effectively increase the number of parameters while maintaining consistent computational costs per token. However, vanilla MoE models often suffer from limited diversity and specialization among experts, constraining their performance and scalability, especially as the number of experts increases. In this paper, we present a novel perspective on vanilla MoE with top-$k$ routing inspired by sparse representation. This allows us to bridge established theoretical insights from sparse representation into MoE models. Building on this foundation, we propose a group sparse regularization approach for the input of top-$k$ routing, termed Mixture of Group Experts (MoGE). MoGE indirectly regularizes experts by imposing structural constraints on the routing inputs, while preserving the original MoE architecture. Furthermore, we organize the routing input into a 2D topographic map, spatially grouping neighboring elements. This structure enables MoGE to capture representations invariant to minor transformations, thereby significantly enhancing expert diversity and specialization. Comprehensive evaluations across various Transformer models for image classification and language modeling tasks demonstrate that MoGE substantially outperforms its MoE counterpart, with minimal additional memory and computation overhead. Our approach provides a simple yet effective solution to scale the number of experts and reduce redundancy among them. The source code is included in the supplementary material and will be publicly released.
Authors: Hsuan Wei Liao, Christopher Klugmann, Daniel Kondermann, Rafid Mahmood
Abstract: High-quality data annotation is an essential but laborious and costly aspect of developing machine learning-based software. We explore the inherent tradeoff between annotation accuracy and cost by detecting and removing minority reports -- instances where annotators provide incorrect responses -- that indicate unnecessary redundancy in task assignments. We propose an approach to prune potentially redundant annotation task assignments before they are executed by estimating the likelihood of an annotator disagreeing with the majority vote for a given task. Our approach is informed by an empirical analysis over computer vision datasets annotated by a professional data annotation platform, which reveals that the likelihood of a minority report event is dependent primarily on image ambiguity, worker variability, and worker fatigue. Simulations over these datasets show that we can reduce the number of annotations required by over 60% with a small compromise in label quality, saving approximately 6.6 days-equivalent of labor. Our approach provides annotation service platforms with a method to balance cost and dataset quality. Machine learning practitioners can tailor annotation accuracy levels according to specific application needs, thereby optimizing budget allocation while maintaining the data quality necessary for critical settings like autonomous driving technology.
Authors: Iason Chaimalas, Arnas Vy\v{s}niauskas, Gabriel Brostow
Abstract: Automation of existing Graphical User Interfaces (GUIs) is important but hard to achieve. Upstream of making the GUI user-accessible or somehow scriptable, even the data-collection to understand the original interface poses significant challenges. For example, large quantities of general UI data seem helpful for training general machine learning (ML) models, but accessibility for each person can hinge on the ML's precision on a specific app. We therefore take the perspective that a given user needs confidence, that the relevant UI elements are being detected correctly throughout one app or digital environment. We mostly assume that the target application is known in advance, so that data collection and ML-training can be personalized for the test-time target domain. The proposed Explorer system focuses on detecting on-screen buttons and text-entry fields, i.e. interactables, where the training process has access to a live version of the application. The live application can run on almost any popular platform except iOS phones, and the collection is especially streamlined for Android phones or for desktop Chrome browsers. Explorer also enables the recording of interactive user sessions, and subsequent mapping of how such sessions overlap and sometimes loop back to similar states. We show how having such a map enables a kind of path planning through the GUI, letting a user issue audio commands to get to their destination. Critically, we are releasing our code for Explorer openly at https://github.com/varnelis/Explorer.
Authors: Ruiwen Ding, Lin Li, Rajath Soans, Tosha Shah, Radha Krishnan, Marc Alexander Sze, Sasha Lukyanov, Yash Deshpande, Antong Chen
Abstract: Inflammatory bowel disease (IBD) involves chronic inflammation of the digestive tract, with treatment options often burdened by adverse effects. Identifying biomarkers for personalized treatment is crucial. While immune cells play a key role in IBD, accurately identifying ulcer regions in whole slide images (WSIs) is essential for characterizing these cells and exploring potential therapeutics. Multiple instance learning (MIL) approaches have advanced WSI analysis but they lack spatial context awareness. In this work, we propose a weakly-supervised model called DomainGCN that employs a graph convolution neural network (GCN) and incorporates domain-specific knowledge of ulcer features, specifically, the presence of epithelium, lymphocytes, and debris for WSI-level ulcer prediction in IBD. We demonstrate that DomainGCN outperforms various state-of-the-art (SOTA) MIL methods and show the added value of domain knowledge.
Authors: Pengkun Jiao, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang
Abstract: Large Multimodal Models (LMMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their vulnerability to user gaslighting-the deliberate use of misleading or contradictory inputs-raises critical concerns about their reliability in real-world applications. In this paper, we address the novel and challenging issue of mitigating the negative impact of negation-based gaslighting on LMMs, where deceptive user statements lead to significant drops in model accuracy. Specifically, we introduce GasEraser, a training-free approach that reallocates attention weights from misleading textual tokens to semantically salient visual regions. By suppressing the influence of "attention sink" tokens and enhancing focus on visually grounded cues, GasEraser significantly improves LMM robustness without requiring retraining or additional supervision. Extensive experimental results demonstrate that GasEraser is effective across several leading open-source LMMs on the GaslightingBench. Notably, for LLaVA-v1.5-7B, GasEraser reduces the misguidance rate by 48.2%, demonstrating its potential for more trustworthy LMMs.
Authors: Yasar Abbas Ur Rehman, Kin Wai Lau, Yuyang Xie, Ma Lan, JiaJun Shen
Abstract: Recent studies have demonstrated that vision models can effectively learn multimodal audio-image representations when paired. However, the challenge of enabling deep models to learn representations from unpaired modalities remains unresolved. This issue is especially pertinent in scenarios like Federated Learning (FL), where data is often decentralized, heterogeneous, and lacks a reliable guarantee of paired data. Previous attempts tackled this issue through the use of auxiliary pretrained encoders or generative models on local clients, which invariably raise computational cost with increasing number modalities. Unlike these approaches, in this paper, we aim to address the task of unpaired audio and image recognition using \texttt{FSSUAVL}, a single deep model pretrained in FL with self-supervised contrastive learning (SSL). Instead of aligning the audio and image modalities, \texttt{FSSUAVL} jointly discriminates them by projecting them into a common embedding space using contrastive SSL. This extends the utility of \texttt{FSSUAVL} to paired and unpaired audio and image recognition tasks. Our experiments with CNN and ViT demonstrate that \texttt{FSSUAVL} significantly improves performance across various image- and audio-based downstream tasks compared to using separate deep models for each modality. Additionally, \texttt{FSSUAVL}'s capacity to learn multimodal feature representations allows for integrating auxiliary information, if available, to enhance recognition accuracy.
Authors: Yemin Yu, Neil Tenenholtz, Lester Mackey, Ying Wei, David Alvarez-Melis, Ava P. Amini, Alex X. Lu
Abstract: Recent advances in self-supervised deep learning have improved our ability to quantify cellular morphological changes in high-throughput microscopy screens, a process known as morphological profiling. However, most current methods only learn from images, despite many screens being inherently multimodal, as they involve both a chemical or genetic perturbation as well as an image-based readout. We hypothesized that incorporating chemical compound structure during self-supervised pre-training could improve learned representations of images in high-throughput microscopy screens. We introduce a representation learning framework, MICON (Molecular-Image Contrastive Learning), that models chemical compounds as treatments that induce counterfactual transformations of cell phenotypes. MICON significantly outperforms classical hand-crafted features such as CellProfiler and existing deep-learning-based representation learning methods in challenging evaluation settings where models must identify reproducible effects of drugs across independent replicates and data-generating centers. We demonstrate that incorporating chemical compound information into the learning process provides consistent improvements in our evaluation setting and that modeling compounds specifically as treatments in a causal framework outperforms approaches that directly align images and compounds in a single representation space. Our findings point to a new direction for representation learning in morphological profiling, suggesting that methods should explicitly account for the multimodal nature of microscopy screening data.
Authors: Yuta Matsui, Ryosuke Yamaki, Ryo Ueda, Seitaro Shinagawa, Tadahiro Taniguchi
Abstract: We propose the Metropolis-Hastings Captioning Game (MHCG), a method to fuse knowledge of multiple vision-language models (VLMs) by learning from each other. Although existing methods that combine multiple models suffer from inference costs and architectural constraints, MHCG avoids these problems by performing decentralized Bayesian inference through a process resembling a language game. The knowledge fusion process establishes communication between two VLM agents alternately captioning images and learning from each other. We conduct two image-captioning experiments with two VLMs, each pre-trained on a different dataset. The first experiment demonstrates that MHCG achieves consistent improvement in reference-free evaluation metrics. The second experiment investigates how MHCG contributes to sharing VLMs' category-level vocabulary by observing the occurrence of the vocabulary in the generated captions.
Authors: Guixian Chen, Jianhao Ma, Salar Fattahi
Abstract: In this paper, we study the problem of robust subspace recovery (RSR) in the presence of both strong adversarial corruptions and Gaussian noise. Specifically, given a limited number of noisy samples -- some of which are tampered by an adaptive and strong adversary -- we aim to recover a low-dimensional subspace that approximately contains a significant fraction of the uncorrupted samples, up to an error that scales with the Gaussian noise. Existing approaches to this problem often suffer from high computational costs or rely on restrictive distributional assumptions, limiting their applicability in truly adversarial settings. To address these challenges, we revisit the classical random sample consensus (RANSAC) algorithm, which offers strong robustness to adversarial outliers, but sacrifices efficiency and robustness against Gaussian noise and model misspecification in the process. We propose a two-stage algorithm, RANSAC+, that precisely pinpoints and remedies the failure modes of standard RANSAC. Our method is provably robust to both Gaussian and adversarial corruptions, achieves near-optimal sample complexity without requiring prior knowledge of the subspace dimension, and is more efficient than existing RANSAC-type methods.
Authors: Justin Namuk Kim, Yiqiao Liu, Rajath Soans, Keith Persson, Sarah Halek, Michal Tomaszewski, Jianda Yuan, Gregory Goldmacher, Antong Chen
Abstract: Accurate segmentation of longitudinal CT scans is important for monitoring tumor progression and evaluating treatment responses. However, existing 3D segmentation models solely focus on spatial information. To address this gap, we propose OmniMamba4D, a novel segmentation model designed for 4D medical images (3D images over time). OmniMamba4D utilizes a spatio-temporal tetra-orientated Mamba block to effectively capture both spatial and temporal features. Unlike traditional 3D models, which analyze single-time points, OmniMamba4D processes 4D CT data, providing comprehensive spatio-temporal information on lesion progression. Evaluated on an internal dataset comprising of 3,252 CT scans, OmniMamba4D achieves a competitive Dice score of 0.682, comparable to state-of-the-arts (SOTA) models, while maintaining computational efficiency and better detecting disappeared lesions. This work demonstrates a new framework to leverage spatio-temporal information for longitudinal CT lesion segmentation.
Authors: Julius Broomfield, Tom Gibbs, Ethan Kosak-Hine, George Ingebretsen, Tia Nasir, Jason Zhang, Reihaneh Iranmanesh, Sara Pieri, Reihaneh Rabbany, Kellin Pelrine
Abstract: LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the target by requiring desirable tractability properties of attacks to study: explainability, transferability between models, and transferability between goals. We perform red-teaming within this framework by uncovering new vulnerabilities to multi-turn, multi-image, and translation-based attacks. These attacks are semantically equivalent by our design to their single-turn, single-image, or untranslated counterparts, enabling systematic comparisons; we show that the different structures yield different safety outcomes. We then demonstrate the potential for this framework to enable new defenses by proposing a Structure Rewriting Guardrail, which converts an input to a structure more conducive to safety assessment. This guardrail significantly improves refusal of harmful inputs, without over-refusing benign ones. Thus, by framing this intermediate challenge - more tractable than universal defenses but essential for long-term safety - we highlight a critical milestone for AI safety research.
Authors: Ryota Tanaka, Taichi Iki, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, Jun Suzuki
Abstract: We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we introduce a new RAG framework, VDocRAG, which can directly understand varied documents and modalities in a unified image format to prevent missing information that occurs by parsing documents to obtain text. To improve the performance, we propose novel self-supervised pre-training tasks that adapt large vision-language models for retrieval by compressing visual information into dense token representations while aligning them with textual content in documents. Furthermore, we introduce OpenDocVQA, the first unified collection of open-domain document visual question answering datasets, encompassing diverse document types and formats. OpenDocVQA provides a comprehensive resource for training and evaluating retrieval and question answering models on visually-rich documents in an open-domain setting. Experiments show that VDocRAG substantially outperforms conventional text-based RAG and has strong generalization capability, highlighting the potential of an effective RAG paradigm for real-world documents.
Authors: Zihao Liu, Mingwen Ou, Zunnan Xu, Jiaqi Huang, Haonan Han, Ronghui Li, Xiu Li
Abstract: Automating the synthesis of coordinated bimanual piano performances poses significant challenges, particularly in capturing the intricate choreography between the hands while preserving their distinct kinematic signatures. In this paper, we propose a dual-stream neural framework designed to generate synchronized hand gestures for piano playing from audio input, addressing the critical challenge of modeling both hand independence and coordination. Our framework introduces two key innovations: (i) a decoupled diffusion-based generation framework that independently models each hand's motion via dual-noise initialization, sampling distinct latent noise for each while leveraging a shared positional condition, and (ii) a Hand-Coordinated Asymmetric Attention (HCAA) mechanism suppresses symmetric (common-mode) noise to highlight asymmetric hand-specific features, while adaptively enhancing inter-hand coordination during denoising. The system operates hierarchically: it first predicts 3D hand positions from audio features and then generates joint angles through position-aware diffusion models, where parallel denoising streams interact via HCAA. Comprehensive evaluations demonstrate that our framework outperforms existing state-of-the-art methods across multiple metrics.
Authors: Heming Xu, Xiaohui Liu, Zhilu Zhang, Hongzhi Zhang, Xiaohe Wu, Wangmeng Zuo
Abstract: Real-world image de-weathering aims at removingvarious undesirable weather-related artifacts, e.g., rain, snow,and fog. To this end, acquiring ideal training pairs is crucial.Existing real-world datasets are typically constructed paired databy extracting clean and degraded images from live streamsof landscape scene on the Internet. Despite the use of strictfiltering mechanisms during collection, training pairs inevitablyencounter inconsistency in terms of lighting, object position, scenedetails, etc, making de-weathering models possibly suffer fromdeformation artifacts under non-ideal supervision. In this work,we propose a unified solution for real-world image de-weatheringwith non-ideal supervision, i.e., a pseudo-label guided learningframework, to address various inconsistencies within the realworld paired dataset. Generally, it consists of a de-weatheringmodel (De-W) and a Consistent Label Constructor (CLC), bywhich restoration result can be adaptively supervised by originalground-truth image to recover sharp textures while maintainingconsistency with the degraded inputs in non-weather contentthrough the supervision of pseudo-labels. Particularly, a Crossframe Similarity Aggregation (CSA) module is deployed withinCLC to enhance the quality of pseudo-labels by exploring thepotential complementary information of multi-frames throughgraph model. Moreover, we introduce an Information AllocationStrategy (IAS) to integrate the original ground-truth imagesand pseudo-labels, thereby facilitating the joint supervision forthe training of de-weathering model. Extensive experimentsdemonstrate that our method exhibits significant advantageswhen trained on imperfectly aligned de-weathering datasets incomparison with other approaches.
Authors: Si-Tong Wei, Rui-Huan Wang, Chuan-Zhi Zhou, Baoquan Chen, Peng-Shuai Wang
Abstract: Autoregressive models have achieved remarkable success across various domains, yet their performance in 3D shape generation lags significantly behind that of diffusion models. In this paper, we introduce OctGPT, a novel multiscale autoregressive model for 3D shape generation that dramatically improves the efficiency and performance of prior 3D autoregressive approaches, while rivaling or surpassing state-of-the-art diffusion models. Our method employs a serialized octree representation to efficiently capture the hierarchical and spatial structures of 3D shapes. Coarse geometry is encoded via octree structures, while fine-grained details are represented by binary tokens generated using a vector quantized variational autoencoder (VQVAE), transforming 3D shapes into compact \emph{multiscale binary sequences} suitable for autoregressive prediction. To address the computational challenges of handling long sequences, we incorporate octree-based transformers enhanced with 3D rotary positional encodings, scale-specific embeddings, and token-parallel generation schemes. These innovations reduce training time by 13 folds and generation time by 69 folds, enabling the efficient training of high-resolution 3D shapes, e.g.,$1024^3$, on just four NVIDIA 4090 GPUs only within days. OctGPT showcases exceptional versatility across various tasks, including text-, sketch-, and image-conditioned generation, as well as scene-level synthesis involving multiple objects. Extensive experiments demonstrate that OctGPT accelerates convergence and improves generation quality over prior autoregressive methods, offering a new paradigm for high-quality, scalable 3D content creation.
Authors: Yanbo Wang, Jiyang Guan, Jian Liang, Ran He
Abstract: Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful generations. However, the lack of safety measures specifically designed for multi-modal inputs creates an alignment gap, leaving MLLMs vulnerable to vision-domain attacks such as typographic manipulation. Current methods utilize a carefully designed safety dataset to enhance model defense capability, while the specific knowledge or patterns acquired from the high-quality dataset remain unclear. Through comparison experiments, we find that the alignment gap primarily arises from data distribution biases, while image content, response quality, or the contrastive behavior of the dataset makes little contribution to boosting multi-modal safety. To further investigate this and identify the key factors in improving MLLM safety, we propose finetuning MLLMs on a small set of benign instruct-following data with responses replaced by simple, clear rejection sentences. Experiments show that, without the need for labor-intensive collection of high-quality malicious data, model safety can still be significantly improved, as long as a specific fraction of rejection data exists in the finetuning set, indicating the security alignment is not lost but rather obscured during multi-modal pretraining or instruction finetuning. Simply correcting the underlying data bias could narrow the safety gap in the vision domain.
Authors: Yiming Zeng, Hao Ren, Shuhang Wang, Junlong Huang, Hui Cheng
Abstract: Visual navigation, a fundamental challenge in mobile robotics, demands versatile policies to handle diverse environments. Classical methods leverage geometric solutions to minimize specific costs, offering adaptability to new scenarios but are prone to system errors due to their multi-modular design and reliance on hand-crafted rules. Learning-based methods, while achieving high planning success rates, face difficulties in generalizing to unseen environments beyond the training data and often require extensive training. To address these limitations, we propose a hybrid approach that combines the strengths of learning-based methods and classical approaches for RGB-only visual navigation. Our method first trains a conditional diffusion model on diverse path-RGB observation pairs. During inference, it integrates the gradients of differentiable scene-specific and task-level costs, guiding the diffusion model to generate valid paths that meet the constraints. This approach alleviates the need for retraining, offering a plug-and-play solution. Extensive experiments in both indoor and outdoor settings, across simulated and real-world scenarios, demonstrate zero-shot transfer capability of our approach, achieving higher success rates and fewer collisions compared to baseline methods. Code will be released at https://github.com/SYSU-RoboticsLab/NaviD.
Authors: Jiani Ni, He Zhao, Jintong Gao, Dandan Guo, Hongyuan Zha
Abstract: In recent years, deep neural networks (DNNs) have demonstrated state-of-the-art performance across various domains. However, despite their success, they often face calibration issues, particularly in safety-critical applications such as autonomous driving and healthcare, where unreliable predictions can have serious consequences. Recent research has started to improve model calibration from the view of the classifier. However, the exploration of designing the classifier to solve the model calibration problem is insufficient. Let alone most of the existing methods ignore the calibration errors arising from underconfidence. In this work, we propose a novel method by balancing learnable and ETF classifiers to solve the overconfidence or underconfidence problem for model Calibration named BalCAL. By introducing a confidence-tunable module and a dynamic adjustment method, we ensure better alignment between model confidence and its true accuracy. Extensive experimental validation shows that ours significantly improves model calibration performance while maintaining high predictive accuracy, outperforming existing techniques. This provides a novel solution to the calibration challenges commonly encountered in deep learning.
Authors: Hang Yin, Yan-Ming Zhang, Jian Xu, Jian-Long Chang, Yin Li, Cheng-Lin Liu
Abstract: Air quality prediction plays a crucial role in public health and environmental protection. Accurate air quality prediction is a complex multivariate spatiotemporal problem, that involves interactions across temporal patterns, pollutant correlations, spatial station dependencies, and particularly meteorological influences that govern pollutant dispersion and chemical transformations. Existing works underestimate the critical role of atmospheric conditions in air quality prediction and neglect comprehensive meteorological data utilization, thereby impairing the modeling of dynamic interdependencies between air quality and meteorological data. To overcome this, we propose MDSTNet, an encoder-decoder framework that explicitly models air quality observations and atmospheric conditions as distinct modalities, integrating multi-pressure-level meteorological data and weather forecasts to capture atmosphere-pollution dependencies for prediction. Meantime, we construct ChinaAirNet, the first nationwide dataset combining air quality records with multi-pressure-level meteorological observations. Experimental results on ChinaAirNet demonstrate MDSTNet's superiority, substantially reducing 48-hour prediction errors by 17.54\% compared to the state-of-the-art model. The source code and dataset will be available on github.
Authors: Hao Yin, Gunagzong Si, Zilei Wang
Abstract: Contrastive decoding strategies are widely used to reduce hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples to induce hallucinations and then suppressing them in the output distribution. However, this paper demonstrates that such approaches fail to effectively mitigate the hallucination problem. The performance improvements observed on POPE Benchmark are largely driven by two misleading factors: (1) crude, unidirectional adjustments to the model's output distribution and (2) the adaptive plausibility constraint, which reduces the sampling strategy to greedy search. To further illustrate these issues, we introduce a series of spurious improvement methods and evaluate their performance against contrastive decoding techniques. Experimental results reveal that the observed performance gains in contrastive decoding are entirely unrelated to its intended goal of mitigating hallucinations. Our findings challenge common assumptions about the effectiveness of contrastive decoding strategies and pave the way for developing genuinely effective solutions to hallucinations in MLLMs.
Authors: Uyen Phan, Ozer Can Devecioglu, Serkan Kiranyaz, Moncef Gabbouj
Abstract: Diabetic retinopathy is a leading cause of vision impairment, making its early diagnosis through fundus imaging critical for effective treatment planning. However, the presence of poor quality fundus images caused by factors such as inadequate illumination, noise, blurring and other motion artifacts yields a significant challenge for accurate DR screening. In this study, we propose progressive transfer learning for multi pass restoration to iteratively enhance the quality of degraded fundus images, ensuring more reliable DR screening. Unlike previous methods that often focus on a single pass restoration, multi pass restoration via PTL can achieve a superior blind restoration performance that can even improve most of the good quality fundus images in the dataset. Initially, a Cycle GAN model is trained to restore low quality images, followed by PTL induced restoration passes over the latest restored outputs to improve overall quality in each pass. The proposed method can learn blind restoration without requiring any paired data while surpassing its limitations by leveraging progressive learning and fine tuning strategies to minimize distortions and preserve critical retinal features. To evaluate PTL's effectiveness on multi pass restoration, we conducted experiments on DeepDRiD, a large scale fundus imaging dataset specifically curated for diabetic retinopathy detection. Our result demonstrates state of the art performance, showcasing PTL's potential as a superior approach to iterative image quality restoration.
Authors: Hao Ren, Yiming Zeng, Zetong Bi, Zhaoliang Wan, Junlong Huang, Hui Cheng
Abstract: Recent advancements in diffusion-based imitation learning, which show impressive performance in modeling multimodal distributions and training stability, have led to substantial progress in various robot learning tasks. In visual navigation, previous diffusion-based policies typically generate action sequences by initiating from denoising Gaussian noise. However, the target action distribution often diverges significantly from Gaussian noise, leading to redundant denoising steps and increased learning complexity. Additionally, the sparsity of effective action distributions makes it challenging for the policy to generate accurate actions without guidance. To address these issues, we propose a novel, unified visual navigation framework leveraging the denoising diffusion bridge models named NaviBridger. This approach enables action generation by initiating from any informative prior actions, enhancing guidance and efficiency in the denoising process. We explore how diffusion bridges can enhance imitation learning in visual navigation tasks and further examine three source policies for generating prior actions. Extensive experiments in both simulated and real-world indoor and outdoor scenarios demonstrate that NaviBridger accelerates policy inference and outperforms the baselines in generating target action sequences. Code is available at https://github.com/hren20/NaiviBridger.
Authors: Junlei Zhang, Zichen Ding, Chang Ma, Zijie Chen, Qiushi Sun, Zhenzhong Lan, Junxian He
Abstract: Graphical User Interface (GUI) agents offer cross-platform solutions for automating complex digital tasks, with significant potential to transform productivity workflows. However, their performance is often constrained by the scarcity of high-quality trajectory data. To address this limitation, we propose training Vision Language Models (VLMs) on data-rich, reasoning-intensive tasks during a dedicated mid-training stage, and then examine how incorporating these tasks facilitates generalization to GUI planning scenarios. Specifically, we explore a range of tasks with readily available instruction-tuning data, including GUI perception, multimodal reasoning, and textual reasoning. Through extensive experiments across 11 mid-training tasks, we demonstrate that: (1) Task generalization proves highly effective, yielding substantial improvements across most settings. For instance, multimodal mathematical reasoning enhances performance on AndroidWorld by an absolute 6.3%. Remarkably, text-only mathematical data significantly boosts GUI web agent performance, achieving a 5.6% improvement on WebArena and 5.4% improvement on AndroidWorld, underscoring notable cross-modal generalization from text-based to visual domains; (2) Contrary to prior assumptions, GUI perception data - previously considered closely aligned with GUI agent tasks and widely utilized for training - has a comparatively limited impact on final performance; (3) Building on these insights, we identify the most effective mid-training tasks and curate optimized mixture datasets, resulting in absolute performance gains of 8.0% on WebArena and 12.2% on AndroidWorld. Our work provides valuable insights into cross-domain knowledge transfer for GUI agents and offers a practical approach to addressing data scarcity challenges in this emerging field. The code, data and models will be available at https://github.com/hkust-nlp/GUIMid.
Authors: Yichao Cai, Yuhang Liu, Erdun Gao, Tianjiao Jiang, Zhen Zhang, Anton van den Hengel, Javen Qinfeng Shi
Abstract: Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that the exemplar image-text pairs constitute two representations of an identical concept. However, recent research has revealed that real-world datasets often exhibit misalignment. There are two distinct viewpoints on how to address this issue: one suggests mitigating the misalignment, and the other leveraging it. We seek here to reconcile these seemingly opposing perspectives, and to provide a practical guide for practitioners. Using latent variable models we thus formalize misalignment by introducing two specific mechanisms: selection bias, where some semantic variables are missing, and perturbation bias, where semantic variables are distorted -- both affecting latent variables shared across modalities. Our theoretical analysis demonstrates that, under mild assumptions, the representations learned by MMCL capture exactly the information related to the subset of the semantic variables invariant to selection and perturbation biases. This provides a unified perspective for understanding misalignment. Based on this, we further offer actionable insights into how misalignment should inform the design of real-world ML systems. We validate our theoretical findings through extensive empirical studies on both synthetic data and real image-text datasets, shedding light on the nuanced impact of misalignment on multimodal representation learning.
Authors: Ziyao Shang, Misha Kaandorp, Kelly Payette, Marina Fernandez Garcia, Roxane Licandro, Georg Langs, Jordina Aviles Verdera, Jana Hutter, Bjoern Menze, Gregor Kasprian, Meritxell Bach Cuadra, Andras Jakab
Abstract: Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data, and ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines.
Authors: Jingyun Yang, Ruoyan Avery Yin, Chi Jiang, Yuepeng Hu, Xiaokai Zhu, Xingjian Hu, Sutharsika Kumar, Xiao Wang, Xiaohua Zhai, Keran Rong, Yunyue Zhu, Tianyi Zhang, Zongyou Yin, Jing Kong, Neil Zhenqiang Gong, Zhichu Ren, Haozhe Wang
Abstract: Characterization of atomic-scale materials traditionally requires human experts with months to years of specialized training. Even for trained human operators, accurate and reliable characterization remains challenging when examining newly discovered materials such as two-dimensional (2D) structures. This bottleneck drives demand for fully autonomous experimentation systems capable of comprehending research objectives without requiring large training datasets. In this work, we present ATOMIC (Autonomous Technology for Optical Microscopy & Intelligent Characterization), an end-to-end framework that integrates foundation models to enable fully autonomous, zero-shot characterization of 2D materials. Our system integrates the vision foundation model (i.e., Segment Anything Model), large language models (i.e., ChatGPT), unsupervised clustering, and topological analysis to automate microscope control, sample scanning, image segmentation, and intelligent analysis through prompt engineering, eliminating the need for additional training. When analyzing typical MoS2 samples, our approach achieves 99.7% segmentation accuracy for single layer identification, which is equivalent to that of human experts. In addition, the integrated model is able to detect grain boundary slits that are challenging to identify with human eyes. Furthermore, the system retains robust accuracy despite variable conditions including defocus, color temperature fluctuations, and exposure variations. It is applicable to a broad spectrum of common 2D materials-including graphene, MoS2, WSe2, SnSe-regardless of whether they were fabricated via chemical vapor deposition or mechanical exfoliation. This work represents the implementation of foundation models to achieve autonomous analysis, establishing a scalable and data-efficient characterization paradigm that fundamentally transforms the approach to nanoscale materials research.
Authors: Suyu Ye, Haojun Shi, Darren Shih, Hyokun Yun, Tanya Roosta, Tianmin Shu
Abstract: To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing web-based agent benchmarks, sequential instruction following in the real world poses significant challenges beyond performing a single, clearly defined task. For instance, real-world human instructions can be ambiguous, require different levels of AI assistance, and may evolve over time, reflecting changes in the user's mental state. To address this gap, we introduce RealWebAssist, a novel benchmark designed to evaluate sequential instruction-following in realistic scenarios involving long-horizon interactions with the web, visual GUI grounding, and understanding ambiguous real-world user instructions. RealWebAssist includes a dataset of sequential instructions collected from real-world human users. Each user instructs a web-based assistant to perform a series of tasks on multiple websites. A successful agent must reason about the true intent behind each instruction, keep track of the mental state of the user, understand user-specific routines, and ground the intended tasks to actions on the correct GUI elements. Our experimental results show that state-of-the-art models struggle to understand and ground user instructions, posing critical challenges in following real-world user instructions for long-horizon web assistance.
Authors: Yassir Zardoua, Boulaala Mohammed, Mhamed El Mrabet, Astito Abdelali
Abstract: Accurate and fast sea horizon detection is vital for tasks in autonomous navigation and maritime security, such as video stabilization, target region reduction, precise tracking, and obstacle avoidance. This paper introduces a novel sea horizon detector from RGB videos, focusing on rapid and effective sea noise suppression while preserving weak horizon edges. Line fitting methods are subsequently employed on filtered edges for horizon detection. We address the filtering problem by extracting line segments with a very low edge threshold, ensuring the detection of line segments even in low-contrast horizon conditions. We show that horizon line segments have simple and relevant properties in RGB images, which we exploit to suppress noisy segments. Then we use the surviving segments to construct a filtered edge map and infer the horizon from the filtered edges. We propose a careful incorporation of temporal information for horizon inference and experimentally show its effectiveness. We address the computational constraint by providing a vectorized implementation for efficient CPU execution, and leveraging image downsizing with minimal loss of accuracy on the original size. Moreover, we contribute a public horizon line dataset to enrich existing data resources. Our algorithm's performance is rigorously evaluated against state-of-the-art methods, and its components are validated through ablation experiments. Source code and dataset files are available at: https://github.com/Zardoua-Yassir/A_fast_horizon_detector_and_a_new_annotated_dataset_for_maritime_video_processing
Authors: Siladittya Manna, Umapada Pal, Saumik Bhattacharya
Abstract: Self-supervised contrastive learning frameworks have progressed rapidly over the last few years. In this paper, we propose a novel loss function for contrastive learning. We model our pre-training task as a binary classification problem to induce an implicit contrastive effect. We further improve the n\"aive loss function after removing the effect of the positive-positive repulsion and incorporating the upper bound of the negative pair repulsion. Unlike existing methods, the proposed loss function optimizes the mutual information in positive and negative pairs. We also present a closed-form expression for the parameter gradient flow and compare the behaviour of self-supervised contrastive frameworks using Hessian eigenspectrum to analytically study their convergence. The proposed method outperforms SOTA self-supervised contrastive frameworks on benchmark datasets such as CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet. After 200 pretraining epochs with ResNet-18 as the backbone, the proposed model achieves an accuracy of 86.36%, 58.18%, 80.50%, and 30.87% on the CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet datasets, respectively, and surpasses the SOTA contrastive baseline by 1.93%, 3.57%, 4.85%, and 0.33%, respectively. The proposed framework also achieves a state-of-the-art accuracy of 78.4% (200 epochs) and 65.22% (100 epochs) Top-1 Linear Evaluation accuracy on ImageNet100 and ImageNet1K datasets, respectively.
Authors: Chengpeng Dai, Fuhai Chen, Xiaoshuai Sun, Rongrong Ji, Qixiang Ye, Yongjian Wu
Abstract: Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as their spatial-temporal correlations from the redundant frames and semantic content. To this end, existing works select either the key video clips in a global level~(across multi frames), or key regions within each frame, which, however, neglect the hierarchical order, i.e., key frames first and key regions latter. In this paper, we propose a novel joint-hierarchical attention model for video captioning, which embeds the key clips, the key frames and the key regions jointly into the captioning model in a hierarchical manner. Such a joint-hierarchical attention model first conducts a global selection to identify key frames, followed by a Gumbel sampling operation to identify further key regions based on the key frames, achieving an accurate global-to-local feature representation to guide the captioning. Extensive quantitative evaluations on two public benchmark datasets MSVD and MSR-VTT demonstrates the superiority of the proposed method over the state-of-the-art methods.
Authors: Boyang Deng, Meiyan Lin, Shoulun Long
Abstract: Developing data-efficient instance detection models that can handle rare object categories remains a key challenge in computer vision. However, existing research often overlooks data collection strategies and evaluation metrics tailored to real-world scenarios involving neural networks. In this study, we systematically investigate data collection and augmentation techniques focused on object occlusion, aiming to mimic occlusion relationships observed in practical applications. Surprisingly, we find that even a simple occlusion mechanism is sufficient to achieve strong performance when introducing new object categories. Notably, by adding just 15 images of a new category to a large-scale training dataset containing over half a million images across hundreds of categories, the model achieves 95\% accuracy on an unseen test set with thousands of instances of the new category.
Authors: Sunjae Yoon, Ji Woo Hong, Eunseop Yoon, Dahyun Kim, Junyeong Kim, Hee Suk Yoon, Chang D. Yoo
Abstract: Video moment retrieval (VMR) aims to localize target moments in untrimmed videos pertinent to a given textual query. Existing retrieval systems tend to rely on retrieval bias as a shortcut and thus, fail to sufficiently learn multi-modal interactions between query and video. This retrieval bias stems from learning frequent co-occurrence patterns between query and moments, which spuriously correlate objects (e.g., a pencil) referred in the query with moments (e.g., scene of writing with a pencil) where the objects frequently appear in the video, such that they converge into biased moment predictions. Although recent debiasing methods have focused on removing this retrieval bias, we argue that these biased predictions sometimes should be preserved because there are many queries where biased predictions are rather helpful. To conjugate this retrieval bias, we propose a Selective Query-guided Debiasing network (SQuiDNet), which incorporates the following two main properties: (1) Biased Moment Retrieval that intentionally uncovers the biased moments inherent in objects of the query and (2) Selective Query-guided Debiasing that performs selective debiasing guided by the meaning of the query. Our experimental results on three moment retrieval benchmarks (i.e., TVR, ActivityNet, DiDeMo) show the effectiveness of SQuiDNet and qualitative analysis shows improved interpretability.
Authors: Rotem Shalev-Arkushin, Amit Moryossef, Ohad Fried
Abstract: Translating spoken languages into Sign languages is necessary for open communication between the hearing and hearing-impaired communities. To achieve this goal, we propose the first method for animating a text written in HamNoSys, a lexical Sign language notation, into signed pose sequences. As HamNoSys is universal, our proposed method offers a generic solution invariant to the target Sign language. Our method gradually generates pose predictions using transformer encoders that create meaningful representations of the text and poses while considering their spatial and temporal information. We use weak supervision for the training process and show that our method succeeds in learning from partial and inaccurate data. Additionally, we offer a new distance measurement for pose sequences, normalized Dynamic Time Warping (nDTW), based on DTW over normalized keypoints trajectories, and validate its correctness using AUTSL, a large-scale Sign language dataset. We show that it measures the distance between pose sequences more accurately than existing measurements and use it to assess the quality of our generated pose sequences. Code for the data pre-processing, the model, and the distance measurement is publicly released for future research.
Authors: Shangzan Zhang, Sida Peng, Tianrun Chen, Linzhan Mou, Haotong Lin, Kaicheng Yu, Yiyi Liao, Xiaowei Zhou
Abstract: We introduce a novel approach that takes a single semantic mask as input to synthesize multi-view consistent color images of natural scenes, trained with a collection of single images from the Internet. Prior works on 3D-aware image synthesis either require multi-view supervision or learning category-level prior for specific classes of objects, which can hardly work for natural scenes. Our key idea to solve this challenging problem is to use a semantic field as the intermediate representation, which is easier to reconstruct from an input semantic mask and then translate to a radiance field with the assistance of off-the-shelf semantic image synthesis models. Experiments show that our method outperforms baseline methods and produces photorealistic, multi-view consistent videos of a variety of natural scenes.
Authors: Pucheng Dang, Xing Hu, Kaidi Xu, Jinhao Duan, Di Huang, Husheng Han, Rui Zhang, Zidong Du
Abstract: Unlearnable examples are proposed to prevent third parties from exploiting unauthorized data, which generates unlearnable examples by adding imperceptible perturbations to public publishing data. These unlearnable examples proficiently misdirect the model training process, leading it to focus on learning perturbation features while neglecting the semantic features of the image. In this paper, we make an in-depth analysis and observe that models can learn both image features and perturbation features of unlearnable examples at an early training stage, but are rapidly trapped in perturbation features learning since the shallow layers tend to learn on perturbation features and propagate harmful activations to deeper layers. Based on the observations, we propose Progressive Staged Training, a self-adaptive training framework specially designed to break unlearnable examples. The proposed framework effectively prevents models from becoming trapped in learning perturbation features. We evaluated our method on multiple model architectures over diverse datasets, e.g., CIFAR-10, CIFAR-100, and ImageNet-mini. Our method circumvents the unlearnability of all state-of-the-art methods in the literature, revealing that existing unlearnable examples give a false sense of privacy protection and provide a reliable baseline for further evaluation of unlearnable techniques.
Authors: Shangzan Zhang, Sida Peng, Yinji ShenTu, Qing Shuai, Tianrun Chen, Kaicheng Yu, Hujun Bao, Xiaowei Zhou
Abstract: Recently, the editing of neural radiance fields (NeRFs) has gained considerable attention, but most prior works focus on static scenes while research on the appearance editing of dynamic scenes is relatively lacking. In this paper, we propose a novel framework to edit the local appearance of dynamic NeRFs by manipulating pixels in a single frame of training video. Specifically, to locally edit the appearance of dynamic NeRFs while preserving unedited regions, we introduce a local surface representation of the edited region, which can be inserted into and rendered along with the original NeRF and warped to arbitrary other frames through a learned invertible motion representation network. By employing our method, users without professional expertise can easily add desired content to the appearance of a dynamic scene. We extensively evaluate our approach on various scenes and show that our approach achieves spatially and temporally consistent editing results. Notably, our approach is versatile and applicable to different variants of dynamic NeRF representations.
Authors: Oren Shrout, Ori Nizan, Yizhak Ben-Shabat, Ayellet Tal
Abstract: Accurately detecting objects in the environment is a key challenge for autonomous vehicles. However, obtaining annotated data for detection is expensive and time-consuming. We introduce PatchContrast, a novel self-supervised point cloud pre-training framework for 3D object detection. We propose to utilize two levels of abstraction to learn discriminative representation from unlabeled data: proposal-level and patch-level. The proposal-level aims at localizing objects in relation to their surroundings, whereas the patch-level adds information about the internal connections between the object's components, hence distinguishing between different objects based on their individual components. We demonstrate how these levels can be integrated into self-supervised pre-training for various backbones to enhance the downstream 3D detection task. We show that our method outperforms existing state-of-the-art models on three commonly-used 3D detection datasets.
Authors: Sunjae Yoon, Gwanhyeong Koo, Dahyun Kim, Chang D. Yoo
Abstract: Video moment retrieval aims to localize moments in video corresponding to a given language query. To avoid the expensive cost of annotating the temporal moments, weakly-supervised VMR (wsVMR) systems have been studied. For such systems, generating a number of proposals as moment candidates and then selecting the most appropriate proposal has been a popular approach. These proposals are assumed to contain many distinguishable scenes in a video as candidates. However, existing proposals of wsVMR systems do not respect the varying numbers of scenes in each video, where the proposals are heuristically determined irrespective of the video. We argue that the retrieval system should be able to counter the complexities caused by varying numbers of scenes in each video. To this end, we present a novel concept of a retrieval system referred to as Scene Complexity Aware Network (SCANet), which measures the `scene complexity' of multiple scenes in each video and generates adaptive proposals responding to variable complexities of scenes in each video. Experimental results on three retrieval benchmarks (i.e., Charades-STA, ActivityNet, TVR) achieve state-of-the-art performances and demonstrate the effectiveness of incorporating the scene complexity.
Authors: S. M. Fazle Rabby Labib, Joyanta Jyoti Mondal, Meem Arafat Manab, Xi Xiao, Sarfaraz Newaz
Abstract: The susceptibility of deep neural networks (DNNs) to adversarial attacks undermines their reliability across numerous applications, underscoring the necessity for an in-depth exploration of these vulnerabilities and the formulation of robust defense strategies. The DeepFool algorithm by Moosavi-Dezfooli et al. (2016) represents a pivotal step in identifying minimal perturbations required to induce misclassification of input images. Nonetheless, its generic methodology falls short in scenarios necessitating targeted interventions. Additionally, previous research studies have predominantly concentrated on the success rate of attacks without adequately addressing the consequential distortion of images, the maintenance of image quality, or the confidence threshold required for misclassification. To bridge these gaps, we introduce the Enhanced Targeted DeepFool (ET DeepFool) algorithm, an evolution of DeepFool that not only facilitates the specification of desired misclassification targets but also incorporates a configurable minimum confidence score. Our empirical investigations demonstrate the superiority of this refined approach in maintaining the integrity of images and minimizing perturbations across a variety of DNN architectures. Unlike previous iterations, such as the Targeted DeepFool by Gajjar et al. (2022), our method grants unparalleled control over the perturbation process, enabling precise manipulation of model responses. Preliminary outcomes reveal that certain models, including AlexNet and the advanced Vision Transformer, display commendable robustness to such manipulations. This discovery of varying levels of model robustness, as unveiled through our confidence level adjustments, could have far-reaching implications for the field of image recognition. Our code is available at https://github.com/FazleLabib/et_deepfool.
Authors: Hong Chen, Xin Wang, Guanning Zeng, Yipeng Zhang, Yuwei Zhou, Feilin Han, Yaofei Wu, Wenwu Zhu
Abstract: Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation, leaving the more challenging problem of customized multi-subject generation unexplored. In this paper, we fill this gap and propose a novel VideoDreamer framework, which can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects. Specifically, VideoDreamer adopts the pretrained Stable Diffusion with temporal modules as its base video generator, taking the power of the text-to-image model to generate diversified content. The video generator is further customized for multi-subjects, which leverages the proposed Disen-Mix Finetuning and Human-in-the-Loop Re-finetuning strategy, to tackle the attribute binding problem of multi-subject generation. Additionally, we present a disentangled motion customization strategy to finetune the temporal modules so that we can generate videos with both customized subjects and motions. To evaluate the performance of customized multi-subject text-to-video generation, we introduce the MultiStudioBench benchmark. Extensive experiments demonstrate the remarkable ability of VideoDreamer to generate videos with new content such as new events and backgrounds, tailored to the customized multiple subjects.
Authors: Jiazhen Liu, Yuhan Fu, Ruobing Xie, Runquan Xie, Xingwu Sun, Fengzong Lian, Zhanhui Kang, Xirong Li
Abstract: Multimodal Large Language Models (MLLMs) hallucinate, resulting in an emerging topic of visual hallucination evaluation (VHE). This paper contributes a ChatGPT-Prompted visual hallucination evaluation Dataset (PhD) for objective VHE at a large scale. The essence of VHE is to ask an MLLM questions about specific images to assess its susceptibility to hallucination. Depending on what to ask (objects, attributes, sentiment, etc.) and how the questions are asked, we structure PhD along two dimensions, i.e. task and mode. Five visual recognition tasks, ranging from low-level (object / attribute recognition) to middle-level (sentiment / position recognition and counting), are considered. Besides a normal visual QA mode, which we term PhD-base, PhD also asks questions with specious context (PhD-sec) or with incorrect context ({PhD-icc), or with AI-generated counter common sense images (PhD-ccs). We construct PhD by a ChatGPT-assisted semi-automated pipeline, encompassing four pivotal modules: task-specific hallucinatory item (hitem) selection, hitem-embedded question generation, specious / incorrect context generation, and counter-common-sense (CCS) image generation. With over 14k daily images, 750 CCS images and 102k VQA triplets in total, PhD reveals considerable variability in MLLMs' performance across various modes and tasks, offering valuable insights into the nature of hallucination. As such, PhD stands as a potent tool not only for VHE but may also play a significant role in the refinement of MLLMs.
Authors: Pengna Li, Kangyi Wu, Wenli Huang, Sanping Zhou, Jinjun Wang
Abstract: Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Many recent unsupervised Re-ID approaches adopt clustering-based methods to measure cross-camera feature similarity to roughly divide images into clusters. They ignore the feature distribution discrepancy induced by camera domain gap, resulting in the unavoidable performance degradation. Camera information is usually available, and the feature distribution in the single camera usually focuses more on the appearance of the individual and has less intra-identity variance. Inspired by the observation, we introduce a \textbf{C}amera-\textbf{A}ware \textbf{L}abel \textbf{R}efinement~(CALR) framework that reduces camera discrepancy by clustering intra-camera similarity. Specifically, we employ intra-camera training to obtain reliable local pseudo labels within each camera, and then refine global labels generated by inter-camera clustering and train the discriminative model using more reliable global pseudo labels in a self-paced manner. Meanwhile, we develop a camera-alignment module to align feature distributions under different cameras, which could help deal with the camera variance further. Extensive experiments validate the superiority of our proposed method over state-of-the-art approaches. The code is accessible at https://github.com/leeBooMla/CALR.
Authors: Olatunji Mumini Omisore, Toluwanimi Akinyemi, Anh Nguyen, Lei Wang
Abstract: Robot-assisted catheterization has garnered a good attention for its potentials in treating cardiovascular diseases. However, advancing surgeon-robot collaboration still requires further research, particularly on task-specific automation. For instance, automated tool segmentation can assist surgeons in visualizing and tracking of endovascular tools during cardiac procedures. While learning-based models have demonstrated state-of-the-art segmentation performances, generating ground-truth labels for fully-supervised methods is both labor-intensive time consuming, and costly. In this study, we propose a weakly-supervised learning method with multi-lateral pseudo labeling for tool segmentation in cardiovascular angiogram datasets. The method utilizes a modified U-Net architecture featuring one encoder and multiple laterally branched decoders. The decoders generate diverse pseudo labels under different perturbations, augmenting available partial labels. The pseudo labels are self-generated using a mixed loss function with shared consistency across the decoders. The weakly-supervised model was trained end-to-end and validated using partially annotated angiogram data from three cardiovascular catheterization procedures. Validation results show that the model could perform closer to fully-supervised models. Also, the proposed weakly-supervised multi-lateral method outperforms three well known methods used for weakly-supervised learning, offering the highest segmentation performance across the three angiogram datasets. Furthermore, numerous ablation studies confirmed the model's consistent performance under different parameters. Finally, the model was applied for tool segmentation in a robot-assisted catheterization experiments. The model enhanced visualization with high connectivity indices for guidewire and catheter, and a mean processing time of 35 ms per frame.
Authors: Chengrui Wang, Pengfei Liu, Min Zhou, Ming Zeng, Xubin Li, Tiezheng Ge, Bo zheng
Abstract: Although diffusion models can generate high-quality human images, their applications are limited by the instability in generating hands with correct structures. In this paper, we introduce RHanDS, a conditional diffusion-based framework designed to refine malformed hands by utilizing decoupled structure and style guidance. The hand mesh reconstructed from the malformed hand offers structure guidance for correcting the structure of the hand, while the malformed hand itself provides style guidance for preserving the style of the hand. To alleviate the mutual interference between style and structure guidance, we introduce a two-stage training strategy and build a series of multi-style hand datasets. In the first stage, we use paired hand images for training to ensure stylistic consistency in hand refining. In the second stage, various hand images generated based on human meshes are used for training, enabling the model to gain control over the hand structure. Experimental results demonstrate that RHanDS can effectively refine hand structure while preserving consistency in hand style.
Authors: Shangzan Zhang, Sida Peng, Tao Xu, Yuanbo Yang, Tianrun Chen, Nan Xue, Yujun Shen, Hujun Bao, Ruizhen Hu, Xiaowei Zhou
Abstract: This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to generate segment-wise procedural material graphs as the appearance representation, which supports high-quality rendering and provides substantial flexibility in editing. Instead of relying on extensive paired data, i.e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs. Specifically, our approach decomposes a shape into a set of segments and designs a segment-controlled diffusion model to synthesize 2D images that are aligned with mesh parts. Based on generated images, we initialize parameters of material graphs and fine-tune them through the differentiable rendering module to produce materials in accordance with the textual description. Extensive experiments demonstrate the superior performance of our framework in photorealism, resolution, and editability over existing methods. Project page: https://zju3dv.github.io/MaPa
Authors: Zhiming Chang, Boyang Liu, Yifei Xia, Youming Guo, Boxin Shi, He Sun
Abstract: Monitoring space objects is crucial for space situational awareness, yet reconstructing 3D satellite models from ground-based telescope images is challenging due to atmospheric turbulence, long observation distances, limited viewpoints, and low signal-to-noise ratios. In this paper, we propose a novel computational imaging framework that overcomes these obstacles by integrating a hybrid image pre-processing pipeline with a joint pose estimation and 3D reconstruction module based on controlled Gaussian Splatting (GS) and Branch-and-Bound (BnB) search. We validate our approach on both synthetic satellite datasets and on-sky observations of China's Tiangong Space Station and the International Space Station, achieving robust 3D reconstructions of low-Earth orbit satellites from ground-based data. Quantitative evaluations using SSIM, PSNR, LPIPS, and Chamfer Distance demonstrate that our method outperforms state-of-the-art NeRF-based approaches, and ablation studies confirm the critical role of each component. Our framework enables high-fidelity 3D satellite monitoring from Earth, offering a cost-effective alternative for space situational awareness. Project page: https://ai4scientificimaging.org/ReconstructingSatellites
URLs: https://ai4scientificimaging.org/ReconstructingSatellites
Authors: Felix Gr\"un, Marcus Nolte, Markus Maurer
Abstract: The foundational role of datasets in defining the capabilities of deep learning models has led to their rapid proliferation. At the same time, published research focusing on the process of dataset development for environment perception in automated driving has been scarce, thereby reducing the applicability of openly available datasets and impeding the development of effective environment perception systems. Sensor-based, mapless automated driving is one of the contexts where this limitation is evident. While leveraging real-time sensor data, instead of pre-defined HD maps promises enhanced adaptability and safety by effectively navigating unexpected environmental changes, it also increases the demands on the scope and complexity of the information provided by the perception system. To address these challenges, we propose a scenario- and capability-based approach to dataset development. Grounded in the principles of ISO 21448 (safety of the intended functionality, SOTIF), extended by ISO/TR 4804, our approach facilitates the structured derivation of dataset requirements. This not only aids in the development of meaningful new datasets but also enables the effective comparison of existing ones. Applying this methodology to a broad range of existing lane detection datasets, we identify significant limitations in current datasets, particularly in terms of real-world applicability, a lack of labeling of critical features, and an absence of comprehensive information for complex driving maneuvers.
Authors: Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe, Mubarak Shah
Abstract: Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum learning for text-to-image generation. Our method is divided into two training stages. First, a ranking of the examples generated for each prompt is obtained by employing a reward model. Then, increasingly difficult pairs of examples are sampled and provided to a text-to-image generative (diffusion or consistency) model. Generated samples that are far apart in the ranking are considered to form easy pairs, while those that are close in the ranking form hard pairs. In other words, we use the rank difference between samples as a measure of difficulty. The sampled pairs are split into batches according to their difficulty levels, which are gradually used to train the generative model. Our approach, Curriculum DPO, is compared against state-of-the-art fine-tuning approaches on nine benchmarks, outperforming the competing methods in terms of text alignment, aesthetics and human preference. Our code is available at https://github.com/CroitoruAlin/Curriculum-DPO.
Authors: Divya Kothandaraman, Ming Lin, Dinesh Manocha
Abstract: We introduce a novel approach for concept blending in pretrained text-to-image diffusion models, aiming to generate images at the intersection of multiple text prompts. At each time step during diffusion denoising, our algorithm forecasts predictions w.r.t. the generated image and makes informed text conditioning decisions. Central to our method is the unique analogy between diffusion models, which are rooted in non-equilibrium thermodynamics, and the Black-Scholes model for financial option pricing. By drawing parallels between key variables in both domains, we derive a robust algorithm for concept blending that capitalizes on the Markovian dynamics of the Black-Scholes framework. Our text-based concept blending algorithm is data-efficient, meaning it does not need additional training. Furthermore, it operates without human intervention or hyperparameter tuning. We highlight the benefits of our approach by comparing it qualitatively and quantitatively to other text based concept blending techniques, including linear interpolation, alternating prompts, step-wise prompt switching, and CLIP-guided prompt selection across various scenarios such as single object per text prompt, multiple objects per text prompt and objects against backgrounds. Our work shows that financially inspired techniques can enhance text-to-image concept blending in generative AI, paving the way for broader innovation. Code is available at https://github.com/divyakraman/BlackScholesDiffusion2024.
URLs: https://github.com/divyakraman/BlackScholesDiffusion2024.
Authors: Gabriel Moreira, Manuel Marques, Jo\~ao Paulo Costeira, Alexander Hauptmann
Abstract: Learning image representations that capture rich semantic relationships remains a significant challenge. Existing approaches are either contrastive, lacking robust theoretical guarantees, or struggle to effectively represent the partial orders inherent to structured visual-semantic data. In this paper, we introduce a nuclear norm-based loss function, grounded in the same information theoretic principles that have proved effective in self-supervised learning. We present a theoretical characterization of this loss, demonstrating that, in addition to promoting class orthogonality, it encodes the spectral geometry of the data within a subspace lattice. This geometric representation allows us to associate logical propositions with subspaces, ensuring that our learned representations adhere to a predefined symbolic structure.
Authors: Zhaozhi Wang, Yue Liu, Yunjie Tian, Yunfan Liu, Yaowei Wang, Qixiang Ye
Abstract: Visual representation models leveraging attention mechanisms are challenged by significant computational overhead, particularly when pursuing large receptive fields. In this study, we aim to mitigate this challenge by introducing the Heat Conduction Operator (HCO) built upon the physical heat conduction principle. HCO conceptualizes image patches as heat sources and models their correlations through adaptive thermal energy diffusion, enabling robust visual representations. HCO enjoys a computational complexity of O(N^1.5), as it can be implemented using discrete cosine transformation (DCT) operations. HCO is plug-and-play, combining with deep learning backbones produces visual representation models (termed vHeat) with global receptive fields. Experiments across vision tasks demonstrate that, beyond the stronger performance, vHeat achieves up to a 3x throughput, 80% less GPU memory allocation, and 35% fewer computational FLOPs compared to the Swin-Transformer. Code is available at https://github.com/MzeroMiko/vHeat.
Authors: Kengo Uchida, Takashi Shibuya, Yuhta Takida, Naoki Murata, Julian Tanke, Shusuke Takahashi, Yuki Mitsufuji
Abstract: In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and editing the generated motions according to control signals, such as the start-end positions and the pelvis trajectory. In this paper, we propose MoLA, which provides fast, high-quality, variable-length motion generation and can also deal with multiple editing tasks in a single framework. Our approach revisits the motion representation used as inputs and outputs in the model, incorporating an activation variable to enable variable-length motion generation. Additionally, we integrate a variational autoencoder and a latent diffusion model, further enhanced through adversarial training, to achieve high-quality and fast generation. Moreover, we apply a training-free guided generation framework to achieve various editing tasks with motion control inputs. We quantitatively show the effectiveness of adversarial learning in text-to-motion generation, and demonstrate the applicability of our editing framework to multiple editing tasks in the motion domain.
Authors: Yuhao Li, Jiale Cao, Muzammal Naseer, Yu Zhu, Jinqiu Sun, Yanning Zhang, Fahad Shahbaz Khan
Abstract: Most existing multi-object tracking methods typically learn visual tracking features via maximizing dis-similarities of different instances and minimizing similarities of the same instance. While such a feature learning scheme achieves promising performance, learning discriminative features solely based on visual information is challenging especially in case of environmental interference such as occlusion, blur and domain variance. In this work, we argue that multi-modal language-driven features provide complementary information to classical visual features, thereby aiding in improving the robustness to such environmental interference. To this end, we propose a new multi-object tracking framework, named LG-MOT, that explicitly leverages language information at different levels of granularity (scene-and instance-level) and combines it with standard visual features to obtain discriminative representations. To develop LG-MOT, we annotate existing MOT datasets with scene-and instance-level language descriptions. We then encode both instance-and scene-level language information into high-dimensional embeddings, which are utilized to guide the visual features during training. At inference, our LG-MOT uses the standard visual features without relying on annotated language descriptions. Extensive experiments on three benchmarks, MOT17, DanceTrack and SportsMOT, reveal the merits of the proposed contributions leading to state-of-the-art performance. On the DanceTrack test set, our LG-MOT achieves an absolute gain of 2.2\% in terms of target object association (IDF1 score), compared to the baseline using only visual features. Further, our LG-MOT exhibits strong cross-domain generalizability. The dataset and code will be available at https://github.com/WesLee88524/LG-MOT.
Authors: Sunjae Yoon, Gwanhyeong Koo, Geonwoo Kim, Chang D. Yoo
Abstract: In video editing, the hallmark of a quality edit lies in its consistent and unobtrusive adjustment. Modification, when integrated, must be smooth and subtle, preserving the natural flow and aligning seamlessly with the original vision. Therefore, our primary focus is on overcoming the current challenges in high quality edit to ensure that each edit enhances the final product without disrupting its intended essence. However, quality deterioration such as blurring and flickering is routinely observed in recent diffusion video editing systems. We confirm that this deterioration often stems from high-frequency leak: the diffusion model fails to accurately synthesize high-frequency components during denoising process. To this end, we devise Frequency Adapting Group (FRAG) which enhances the video quality in terms of consistency and fidelity by introducing a novel receptive field branch to preserve high-frequency components during the denoising process. FRAG is performed in a model-agnostic manner without additional training and validates the effectiveness on video editing benchmarks (i.e., TGVE, DAVIS).
Authors: Rotem Shalev-Arkushin, Aharon Azulay, Tavi Halperin, Eitan Richardson, Amit H. Bermano, Ohad Fried
Abstract: Diffusion-based generative models have recently shown remarkable image and video editing capabilities. However, local video editing, particularly removal of small attributes like glasses, remains a challenge. Existing methods either alter the videos excessively, generate unrealistic artifacts, or fail to perform the requested edit consistently throughout the video. In this work, we focus on consistent and identity-preserving removal of glasses in videos, using it as a case study for consistent local attribute removal in videos. Due to the lack of paired data, we adopt a weakly supervised approach and generate synthetic imperfect data, using an adjusted pretrained diffusion model. We show that despite data imperfection, by learning from our generated data and leveraging the prior of pretrained diffusion models, our model is able to perform the desired edit consistently while preserving the original video content. Furthermore, we exemplify the generalization ability of our method to other local video editing tasks by applying it successfully to facial sticker-removal. Our approach demonstrates significant improvement over existing methods, showcasing the potential of leveraging synthetic data and strong video priors for local video editing tasks.
Authors: M. Rempe, F. H\"orst, C. Seibold, B. Hadaschik, M. Schlimbach, J. Egger, K. Kr\"oninger, F. Breuer, M. Blaimer, J. Kleesiek
Abstract: We present a novel preprocessing and prediction pipeline for the classification of magnetic resonance imaging (MRI) that takes advantage of the information rich complex valued k-Space. Using a publicly available MRI raw dataset with 312 subject and a total of 9508 slices, we show the advantage of utilizing the k-Space for better prostate cancer likelihood estimation in comparison to just using the magnitudinal information in the image domain, with an AUROC of $86.1\%\pm1.8\%$. Additionally, by using high undersampling rates and a simple principal component analysis (PCA) for coil compression, we reduce the time needed for reconstruction by avoiding the time intensive GRAPPA reconstruction algorithm. By using digital undersampling for our experiments, we show that scanning and reconstruction time could be reduced. Even with an undersampling factor of 16, our approach achieves meaningful results, with an AUROC of $71.4\%\pm2.9\%$, using the PCA coil combination and taking into account the k-Space information. With this study, we were able to show the feasibility of preserving phase and k-Space information, with consistent results. Besides preserving valuable information for further diagnostics, this approach can work without the time intensive ADC and reconstruction calculations, greatly reducing the post processing, as well as potential scanning time, increasing patient comfort and allowing a close to real-time prediction.
Authors: Haruna Yunusa, Qin Shiyin, Abdulrahman Hamman Adama Chukkol, Adamu Lawan, Abdulganiyu Abdu Yusuf, Isah Bello
Abstract: The recent emergence of hybrid models has introduced a transformative approach to computer vision, gradually moving beyond conventional convolutional neural net-works and vision transformers. However, efficiently combining these two paradigms to better capture long-range dependencies in complex images remains a challenge. In this paper, we present iiANET (Inception Inspired Attention Network), an efficient hybrid visual backbone designed to improve the modeling of long-range dependen-cies. The core innovation of iiANET is the iiABlock, a unified building block that in-tegrates global r-MHSA (Multi-Head Self-Attention) and convolutional layers in paral-lel. This design enables iiABlock to simultaneously capture global context and local details, making it highly effective for extracting rich and diverse features. By effi-ciently fusing these complementary representations, iiABlock allows iiANET to achieve strong feature interaction while maintaining computational efficiency. Exten-sive qualitative and quantitative evaluations across various benchmarks show im-proved performance over several state-of-the-art models.
Authors: Pengfei Chen, Lingxi Xie, Xinyue Huo, Xuehui Yu, Xiaopeng Zhang, Yingfei Sun, Zhenjun Han, Qi Tian
Abstract: The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. This paper presents SAM-CP, a simple approach that establishes two types of composable prompts beyond SAM and composes them for versatile segmentation. Specifically, given a set of classes (in texts) and a set of SAM patches, the Type-I prompt judges whether a SAM patch aligns with a text label, and the Type-II prompt judges whether two SAM patches with the same text label also belong to the same instance. To decrease the complexity in dealing with a large number of semantic classes and patches, we establish a unified framework that calculates the affinity between (semantic and instance) queries and SAM patches and merges patches with high affinity to the query. Experiments show that SAM-CP achieves semantic, instance, and panoptic segmentation in both open and closed domains. In particular, it achieves state-of-the-art performance in open-vocabulary segmentation. Our research offers a novel and generalized methodology for equipping vision foundation models like SAM with multi-grained semantic perception abilities.
Authors: Biao Wu, Yutong Xie, Zeyu Zhang, Minh Hieu Phan, Qi Chen, Ling Chen, Qi Wu
Abstract: Vision-and-language pretraining (VLP) in the medical field utilizes contrastive learning on image-text pairs to achieve effective transfer across tasks. Yet, current VLP approaches with the masked modeling strategy face two challenges when applied to the medical domain. First, current models struggle to accurately reconstruct key pathological features due to the scarcity of medical data. Second, most methods only adopt either paired image-text or image-only data, failing to exploit the combination of both paired and unpaired data. To this end, this paper proposes the MMCLIP (Masked Medical Contrastive Language-Image Pre-Training) framework to enhance pathological learning and feature learning via unpaired data. First, we introduce the attention-masked image modeling (AttMIM) and entity-driven masked language modeling module (EntMLM), which learns to reconstruct pathological visual and textual tokens via multi-modal feature interaction, thus improving medical-enhanced features. The AttMIM module masks a portion of the image features that are highly responsive to textual features. This allows MMCLIP to improve the reconstruction of highly similar image data in medicine efficiency. Second, our MMCLIP capitalizes unpaired data to enhance multimodal learning by introducing disease-kind prompts. The experimental results show that MMCLIP achieves SOTA for zero-shot and fine-tuning classification performance on five datasets. Our code will be available at https://github.com/White65534/MMCLIP.
Authors: Kumar Ashutosh, Tushar Nagarajan, Georgios Pavlakos, Kris Kitani, Kristen Grauman
Abstract: Feedback is essential for learning a new skill or improving one's current skill-level. However, current methods for skill-assessment from video only provide scores or compare demonstrations, leaving the burden of knowing what to do differently on the user. We introduce a novel method to generate actionable feedback (AF) from video of a person doing a physical activity, such as basketball or soccer. Our method takes a video demonstration and its accompanying 3D body pose and generates (1) free-form expert commentary describing what the person is doing well and what they could improve, and (2) a visual expert demonstration that incorporates the required corrections. We show how to leverage Ego-Exo4D's [29] videos of skilled activity and expert commentary together with a strong language model to create a weakly-supervised training dataset for this task, and we devise a multimodal video-language model to infer coaching feedback. Our method is able to reason across multi-modal input combinations to output full spectrum, actionable coaching-expert commentary, expert video retrieval, and expert pose generation-outperforming strong vision-language models on both established metrics and human preference studies.
Authors: Jaehyuk Heo, Pilsung Kang
Abstract: Active learning (AL) aims to enhance model performance by selectively collecting highly informative data, thereby minimizing annotation costs. However, in practical scenarios, unlabeled data may contain out-of-distribution (OOD) samples, which are not used for training, leading to wasted annotation costs if data is incorrectly selected. Therefore, to make active learning feasible in real-world applications, it is crucial to consider not only the informativeness of unlabeled samples but also their purity to determine whether they belong to the in-distribution (ID). Recent studies have applied AL under these assumptions, but challenges remain due to the trade-off between informativeness and purity, as well as the heavy dependence on OOD samples. These issues lead to the collection of OOD samples, resulting in a significant waste of annotation costs. To address these challenges, we propose a novel query strategy, VLPure-AL, which minimizes cost losses while reducing dependence on OOD samples. VLPure-AL sequentially evaluates the purity and informativeness of data. First, it utilizes a pre-trained vision-language model to detect and exclude OOD data with high accuracy by leveraging linguistic and visual information of ID data. Second, it selects highly informative data from the remaining ID data, and then the selected samples are annotated by human experts. Experimental results on datasets with various open-set conditions demonstrate that VLPure-AL achieves the lowest cost loss and highest performance across all scenarios. Code is available at https://github.com/DSBA-Lab/OpenAL.
Authors: Francesco Di Salvo, Sebastian Doerrich, Ines Rieger, Christian Ledig
Abstract: The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address label noise exhibit severe limitations due to computational complexity and application dependency. In this work, we propose WANN, a Weighted Adaptive Nearest Neighbor approach that builds on self-supervised feature representations obtained from foundation models. To guide the weighted voting scheme, we introduce a reliability score $\eta$, which measures the likelihood of a data label being correct. WANN outperforms reference methods, including a linear layer trained with robust loss functions, on diverse datasets of varying size and under various noise types and severities. WANN also exhibits superior generalization on imbalanced data compared to both Adaptive-NNs (ANN) and fixed k-NNs. Furthermore, the proposed weighting scheme enhances supervised dimensionality reduction under noisy labels. This yields a significant boost in classification performance with 10x and 100x smaller image embeddings, minimizing latency and storage requirements. Our approach, emphasizing efficiency and explainability, emerges as a simple, robust solution to overcome inherent limitations of deep neural network training. The code is available at https://github.com/francescodisalvo05/wann-noisy-labels .
URLs: https://github.com/francescodisalvo05/wann-noisy-labels
Authors: Andrea Dosi, Massimo Brescia, Stefano Cavuoti, Mariarca D'Aniello, Michele Delli Veneri, Carlo Donadio, Adriano Ettari, Giuseppe Longo, Alvi Rownok, Luca Sannino, Maria Zampella
Abstract: Deep learning has revolutionized the field of hyperspectral image (HSI) analysis, enabling the extraction of complex spectral and spatial features. While convolutional neural networks (CNNs) have been the backbone of HSI classification, their limitations in capturing global contextual features have led to the exploration of Vision Transformers (ViTs). This paper introduces AMBER, an advanced SegFormer specifically designed for multi-band image segmentation. AMBER enhances the original SegFormer by incorporating three-dimensional convolutions, custom kernel sizes, and a Funnelizer layer. This architecture enables processing hyperspectral data directly, without requiring spectral dimensionality reduction during preprocessing. Our experiments, conducted on three benchmark datasets (Salinas, Indian Pines, and Pavia University) and on a dataset from the PRISMA satellite, show that AMBER outperforms traditional CNN-based methods in terms of Overall Accuracy, Kappa coefficient, and Average Accuracy on the first three datasets, and achieves state-of-the-art performance on the PRISMA dataset. These findings highlight AMBER's robustness, adaptability to both airborne and spaceborne data, and its potential as a powerful solution for remote sensing and other domains requiring advanced analysis of high-dimensional data.
Authors: Jinchang Zhang, Ningning Xu, Hao Zhang, Guoyu Lu
Abstract: Depth estimation is a fundamental task in 3D geometry. While stereo depth estimation can be achieved through triangulation methods, it is not as straightforward for monocular methods, which require the integration of global and local information. The Depth from Defocus (DFD) method utilizes camera lens models and parameters to recover depth information from blurred images and has been proven to perform well. However, these methods rely on All-In-Focus (AIF) images for depth estimation, which is nearly impossible to obtain in real-world applications. To address this issue, we propose a self-supervised framework based on 3D Gaussian splatting and Siamese networks. By learning the blur levels at different focal distances of the same scene in the focal stack, the framework predicts the defocus map and Circle of Confusion (CoC) from a single defocused image, using the defocus map as input to DepthNet for monocular depth estimation. The 3D Gaussian splatting model renders defocused images using the predicted CoC, and the differences between these and the real defocused images provide additional supervision signals for the Siamese Defocus self-supervised network. This framework has been validated on both artificially synthesized and real blurred datasets. Subsequent quantitative and visualization experiments demonstrate that our proposed framework is highly effective as a DFD method.
Authors: Yongqi Wang, Xinxiao Wu, Shuo Yang, Jiebo Luo
Abstract: Open-vocabulary video visual relationship detection aims to expand video visual relationship detection beyond annotated categories by detecting unseen relationships between both seen and unseen objects in videos. Existing methods usually use trajectory detectors trained on closed datasets to detect object trajectories, and then feed these trajectories into large-scale pre-trained vision-language models to achieve open-vocabulary classification. Such heavy dependence on the pre-trained trajectory detectors limits their ability to generalize to novel object categories, leading to performance degradation. To address this challenge, we propose to unify object trajectory detection and relationship classification into an end-to-end open-vocabulary framework. Under this framework, we propose a relationship-aware open-vocabulary trajectory detector. It primarily consists of a query-based Transformer decoder, where the visual encoder of CLIP is distilled for frame-wise open-vocabulary object detection, and a trajectory associator. To exploit relationship context during trajectory detection, a relationship query is embedded into the Transformer decoder, and accordingly, an auxiliary relationship loss is designed to enable the decoder to perceive the relationships between objects explicitly. Moreover, we propose an open-vocabulary relationship classifier that leverages the rich semantic knowledge of CLIP to discover novel relationships. To adapt CLIP well to relationship classification, we design a multi-modal prompting method that employs spatio-temporal visual prompting for visual representation and vision-guided language prompting for language input. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate the effectiveness of our framework. Our framework is also applied to a more difficult cross-dataset scenario to further demonstrate its generalization ability.
Authors: Xinrui Zhou, Yuhao Huang, Haoran Dou, Shijing Chen, Ao Chang, Jia Liu, Weiran Long, Jian Zheng, Erjiao Xu, Jie Ren, Ruobing Huang, Jun Cheng, Wufeng Xue, Dong Ni
Abstract: In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this issue, having been proven effective in advancing downstream medical recognition tasks. Nevertheless, existing works lack sufficient semantic and sequential steerability for challenging video/3D sequence generation, and neglect quality control of noisy synthesized samples, resulting in unreliable synthetic databases and severely limiting the performance of downstream tasks. In this work, we present Ctrl-GenAug, a novel and general generative augmentation framework that enables highly semantic- and sequential-customized sequence synthesis and suppresses incorrectly synthesized samples, to aid medical sequence classification. Specifically, we first design a multimodal conditions-guided sequence generator for controllably synthesizing diagnosis-promotive samples. A sequential augmentation module is integrated to enhance the temporal/stereoscopic coherence of generated samples. Then, we propose a noisy synthetic data filter to suppress unreliable cases at semantic and sequential levels. Extensive experiments on 3 medical datasets, using 11 networks trained on 3 paradigms, comprehensively analyze the effectiveness and generality of Ctrl-GenAug, particularly in underrepresented high-risk populations and out-domain conditions.
Authors: Katja Ludwig, Julian Lorenz, Daniel Kienzle, Tuan Bui, Rainer Lienhart
Abstract: The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes.
Authors: Zhipei Xu, Xuanyu Zhang, Runyi Li, Zecheng Tang, Qing Huang, Jian Zhang
Abstract: The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect. Although current image forgery detection and localization (IFDL) methods are generally effective, they tend to face two challenges: \textbf{1)} black-box nature with unknown detection principle, \textbf{2)} limited generalization across diverse tampering methods (e.g., Photoshop, DeepFake, AIGC-Editing). To address these issues, we propose the explainable IFDL task and design FakeShield, a multi-modal framework capable of evaluating image authenticity, generating tampered region masks, and providing a judgment basis based on pixel-level and image-level tampering clues. Additionally, we leverage GPT-4o to enhance existing IFDL datasets, creating the Multi-Modal Tamper Description dataSet (MMTD-Set) for training FakeShield's tampering analysis capabilities. Meanwhile, we incorporate a Domain Tag-guided Explainable Forgery Detection Module (DTE-FDM) and a Multi-modal Forgery Localization Module (MFLM) to address various types of tamper detection interpretation and achieve forgery localization guided by detailed textual descriptions. Extensive experiments demonstrate that FakeShield effectively detects and localizes various tampering techniques, offering an explainable and superior solution compared to previous IFDL methods. The code is available at https://github.com/zhipeixu/FakeShield.
Authors: Kaifeng Zhao, Gen Li, Siyu Tang
Abstract: Text-conditioned human motion generation, which allows for user interaction through natural language, has become increasingly popular. Existing methods typically generate short, isolated motions based on a single input sentence. However, human motions are continuous and can extend over long periods, carrying rich semantics. Creating long, complex motions that precisely respond to streams of text descriptions, particularly in an online and real-time setting, remains a significant challenge. Furthermore, incorporating spatial constraints into text-conditioned motion generation presents additional challenges, as it requires aligning the motion semantics specified by text descriptions with geometric information, such as goal locations and 3D scene geometry. To address these limitations, we propose DartControl, in short DART, a Diffusion-based Autoregressive motion primitive model for Real-time Text-driven motion control. Our model effectively learns a compact motion primitive space jointly conditioned on motion history and text inputs using latent diffusion models. By autoregressively generating motion primitives based on the preceding history and current text input, DART enables real-time, sequential motion generation driven by natural language descriptions. Additionally, the learned motion primitive space allows for precise spatial motion control, which we formulate either as a latent noise optimization problem or as a Markov decision process addressed through reinforcement learning. We present effective algorithms for both approaches, demonstrating our model's versatility and superior performance in various motion synthesis tasks. Experiments show our method outperforms existing baselines in motion realism, efficiency, and controllability. Video results are available on the project page: https://zkf1997.github.io/DART/.
Authors: Hanrong Ye, Haotian Zhang, Erik Daxberger, Lin Chen, Zongyu Lin, Yanghao Li, Bowen Zhang, Haoxuan You, Dan Xu, Zhe Gan, Jiasen Lu, Yinfei Yang
Abstract: This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a \textit{global glimpse} step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding.
Authors: Shuai Jiang, Christina Robinson, Joseph Anderson, William Hisey, Lynn Butterly, Arief Suriawinata, Saeed Hassanpour
Abstract: Colonoscopy screening effectively identifies and removes polyps before they progress to colorectal cancer (CRC), but current follow-up guidelines rely primarily on histopathological features, overlooking other important CRC risk factors. Variability in polyp characterization among pathologists also hinders consistent surveillance decisions. Advances in digital pathology and deep learning enable the integration of pathology slides and medical records for more accurate CRC risk prediction. Using data from the New Hampshire Colonoscopy Registry, including longitudinal follow-up, we adapted a transformer-based model for histopathology image analysis to predict 5-year CRC risk. We further explored multi-modal fusion strategies to combine clinical records with deep learning-derived image features. Training the model to predict intermediate clinical variables improved 5-year CRC risk prediction (AUC = 0.630) compared to direct prediction (AUC = 0.615, p = 0.013). Incorporating both imaging and non-imaging data, without requiring manual slide review, further improved performance (AUC = 0.674) compared to traditional features from colonoscopy and microscopy reports (AUC = 0.655, p = 0.001). These results highlight the value of integrating diverse data modalities with computational methods to enhance CRC risk stratification.
Authors: Siyuan Yan, Zhen Yu, Clare Primiero, Cristina Vico-Alonso, Zhonghua Wang, Litao Yang, Philipp Tschandl, Ming Hu, Lie Ju, Gin Tan, Vincent Tang, Aik Beng Ng, David Powell, Paul Bonnington, Simon See, Elisabetta Magnaterra, Peter Ferguson, Jennifer Nguyen, Pascale Guitera, Jose Banuls, Monika Janda, Victoria Mar, Harald Kittler, H. Peter Soyer, Zongyuan Ge
Abstract: Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks like skin cancer diagnosis from dermoscopic images, they struggle to meet the complex, multimodal requirements of clinical practice. Here, we introduce PanDerm, a multimodal dermatology foundation model pretrained through self-supervised learning on over 2 million real-world skin disease images from 11 clinical institutions across 4 imaging modalities. We evaluated PanDerm on 28 diverse benchmarks, including skin cancer screening, risk stratification, differential diagnosis of common and rare skin conditions, lesion segmentation, longitudinal monitoring, and metastasis prediction and prognosis. PanDerm achieved state-of-the-art performance across all evaluated tasks, often outperforming existing models when using only 10% of labeled data. We conducted three reader studies to assess PanDerm's potential clinical utility. PanDerm outperformed clinicians by 10.2% in early-stage melanoma detection through longitudinal analysis, improved clinicians' skin cancer diagnostic accuracy by 11% on dermoscopy images, and enhanced non-dermatologist healthcare providers' differential diagnosis by 16.5% across 128 skin conditions on clinical photographs. These results demonstrate PanDerm's potential to improve patient care across diverse clinical scenarios and serve as a model for developing multimodal foundation models in other medical specialties, potentially accelerating the integration of AI support in healthcare. The code can be found at https://github.com/SiyuanYan1/PanDerm.
Authors: Sunjae Yoon, Gwanhyeong Koo, Younghwan Lee, Chang D. Yoo
Abstract: Human image animation aims to generate a human motion video from the inputs of a reference human image and a target motion video. Current diffusion-based image animation systems exhibit high precision in transferring human identity into targeted motion, yet they still exhibit irregular quality in their outputs. Their optimal precision is achieved only when the physical compositions (i.e., scale and rotation) of the human shapes in the reference image and target pose frame are aligned. In the absence of such alignment, there is a noticeable decline in fidelity and consistency. Especially, in real-world environments, this compositional misalignment commonly occurs, posing significant challenges to the practical usage of current systems. To this end, we propose Test-time Procrustes Calibration (TPC), which enhances the robustness of diffusion-based image animation systems by maintaining optimal performance even when faced with compositional misalignment, effectively addressing real-world scenarios. The TPC provides a calibrated reference image for the diffusion model, enhancing its capability to understand the correspondence between human shapes in the reference and target images. Our method is simple and can be applied to any diffusion-based image animation system in a model-agnostic manner, improving the effectiveness at test time without additional training.
Authors: Lorenzo Basile, Valentino Maiorca, Luca Bortolussi, Emanuele Rodol\`a, Francesco Locatello
Abstract: When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions (e.g., attention heads) sometimes specialize in specific tasks or input attributes. In this paper, we analyze this phenomenon in vision transformers, focusing on the spectral geometry of residuals, and explore its implications for modality alignment in vision-language models. First, we link it to the intrinsically low-dimensional structure of visual head representations, zooming into their principal components and showing that they encode specialized roles across a wide variety of input data distributions. Then, we analyze the effect of head specialization in multimodal models, focusing on how improved alignment between text and specialized heads impacts zero-shot classification performance. This specialization-performance link consistently holds across diverse pre-training data, network sizes, and objectives, demonstrating a powerful new mechanism for boosting zero-shot classification through targeted alignment. Ultimately, we translate these insights into actionable terms by introducing ResiDual, a technique for spectral alignment of the residual stream. Much like panning for gold, it lets the noise from irrelevant unit principal components (i.e., attributes) wash away to amplify task-relevant ones. Remarkably, this dual perspective on modality alignment yields fine-tuning level performance on different data distributions while modelling an extremely interpretable and parameter-efficient transformation, as we extensively show on 70 pre-trained network-dataset combinations (7 models, 10 datasets).
Authors: Yuelin Zhang, Long Lei, Wanquan Yan, Tianyi Zhang, Raymond Shing-Yan Tang, Shing Shin Cheng
Abstract: Ultrasound (US)-guided needle insertion is widely employed in percutaneous interventions. However, providing feedback on the needle tip position via US imaging presents challenges due to noise, artifacts, and the thin imaging plane of US, which degrades needle features and leads to intermittent tip visibility. In this paper, a Mamba-based US needle tracker MambaXCTrack utilizing structured state space models cross-correlation (SSMX-Corr) and implicit motion prompt is proposed, which is the first application of Mamba in US needle tracking. The SSMX-Corr enhances cross-correlation by long-range modeling and global searching of distant semantic features between template and search maps, benefiting the tracking under noise and artifacts by implicitly learning potential distant semantic cues. By combining with cross-map interleaved scan (CIS), local pixel-wise interaction with positional inductive bias can also be introduced to SSMX-Corr. The implicit low-level motion descriptor is proposed as a non-visual prompt to enhance tracking robustness, addressing the intermittent tip visibility problem. Extensive experiments on a dataset with motorized needle insertion in both phantom and tissue samples demonstrate that the proposed tracker outperforms other state-of-the-art trackers while ablation studies further highlight the effectiveness of each proposed tracking module.
Authors: M. Arda Ayd{\i}n, Efe Mert \c{C}{\i}rpar, Elvin Abdinli, Gozde Unal, Yusuf H. Sahin
Abstract: Recent advances in foundational Vision Language Models (VLMs) have reshaped the evaluation paradigm in computer vision tasks. These foundational models, especially CLIP, have accelerated research in open-vocabulary computer vision tasks, including Open-Vocabulary Semantic Segmentation (OVSS). Although the initial results are promising, the dense prediction capabilities of VLMs still require further improvement. In this study, we enhance the semantic segmentation performance of CLIP by introducing new modules and modifications: 1) architectural changes in the last layer of ViT and the incorporation of attention maps from the middle layers with the last layer, 2) Image Engineering: applying data augmentations to enrich input image representations, and 3) using Large Language Models (LLMs) to generate definitions and synonyms for each class name to leverage CLIP's open-vocabulary capabilities. Our training-free method, ITACLIP, outperforms current state-of-the-art approaches on segmentation benchmarks such as COCO-Stuff, COCO-Object, Pascal Context, and Pascal VOC. Our code is available at https://github.com/m-arda-aydn/ITACLIP.
Authors: Manuel Knott, Divinefavour Odion, Sameer Sontakke, Anup Karwa, Thijs Defraeye
Abstract: Visual inspection for defect grading in agricultural supply chains is crucial but traditionally labor-intensive and error-prone. Automated computer vision methods typically require extensively annotated datasets, which are often unavailable in decentralized supply chains. We address this challenge by evaluating the Segment Anything Model (SAM) to generate dense panoptic segmentation masks from sparse annotations. These dense predictions are then used to train a supervised panoptic segmentation model. Focusing on banana surface defects (bruises and scars), we validate our approach using 476 field images annotated with 1440 defects. While SAM-generated masks generally align with human annotations, substantially reducing annotation effort, we explicitly identify failure cases associated with specific defect sizes and shapes. Despite these limitations, our approach offers practical estimates of defect number and relative size from panoptic masks, underscoring the potential and current boundaries of foundation models for defect quantification in low-data agricultural scenarios. GitHub: https://github.com/manuelknott/banana-defect-segmentation
URLs: https://github.com/manuelknott/banana-defect-segmentation
Authors: Jiajing Lin, Zhenzhong Wang, Dejun Xu, Shu Jiang, YunPeng Gong, Min Jiang
Abstract: 4D content generation aims to create dynamically evolving 3D content that responds to specific input objects such as images or 3D representations. Current approaches typically incorporate physical priors to animate 3D representations, but these methods suffer from significant limitations: they not only require users lacking physics expertise to manually specify material properties but also struggle to effectively handle the generation of multi-material composite objects. To address these challenges, we propose Phys4DGen, a novel 4D generation framework that integrates multi-material composition perception with physical simulation. The framework achieves automated, physically plausible 4D generation through three innovative modules: first, the 3D Material Grouping module partitions heterogeneous material regions on 3D representation surfaces via semantic segmentation; second, the Internal Physical Structure Discovery module constructs the mechanical structure of object interiors; finally, we distill physical prior knowledge from multimodal large language models to enable rapid and automatic material properties identification for both objects' surfaces and interiors. Experiments on both synthetic and real-world datasets demonstrate that Phys4DGen can generate high-fidelity 4D content with physical realism in open-world scenarios, significantly outperforming state-of-the-art methods.
Authors: Youjia Zhang, Anpei Chen, Yumin Wan, Zikai Song, Junqing Yu, Yawei Luo, Wei Yang
Abstract: In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the deferred rendering of Gaussian splatting and applies directional encoding to the deferred-rendered surface, effectively reducing the ambiguity between orientation and viewing angle. Next, we introduce a spherical Mip-grid to capture varying levels of surface roughness, enabling roughness-aware Gaussian shading. Additionally, we propose a simple yet efficient geometry-lighting factorization that connects geometry and lighting via the vector outer product, significantly reducing renderer overhead when integrating volumetric attributes. Our method achieves superior photorealistic rendering for a range of open-world scenes while also accurately recovering geometry.
Authors: Kumar Ashutosh, Georgios Pavlakos, Kristen Grauman
Abstract: Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-capturing physically ungrounded predictions of "what" and ignoring the "where" and "how". We introduce FIction for 4D future interaction prediction from videos. Given an input video of a human activity, the goal is to predict which objects at what 3D locations the person will interact with in the next time period (e.g., cabinet, fridge), and how they will execute that interaction (e.g., poses for bending, reaching, pulling). Our novel model FIction fuses the past video observation of the person's actions and their environment to predict both the "where" and "how" of future interactions. Through comprehensive experiments on a variety of activities and real-world environments in EgoExo4D, we show that our proposed approach outperforms prior autoregressive and (lifted) 2D video models substantially, with more than 30% relative gains.
Authors: Amir Bar, Gaoyue Zhou, Danny Tran, Trevor Darrell, Yann LeCun
Abstract: Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and navigation actions. To capture complex environment dynamics, NWM employs a Conditional Diffusion Transformer (CDiT), trained on a diverse collection of egocentric videos of both human and robotic agents, and scaled up to 1 billion parameters. In familiar environments, NWM can plan navigation trajectories by simulating them and evaluating whether they achieve the desired goal. Unlike supervised navigation policies with fixed behavior, NWM can dynamically incorporate constraints during planning. Experiments demonstrate its effectiveness in planning trajectories from scratch or by ranking trajectories sampled from an external policy. Furthermore, NWM leverages its learned visual priors to imagine trajectories in unfamiliar environments from a single input image, making it a flexible and powerful tool for next-generation navigation systems.
Authors: Zijian Zhao, Tingwei Chen, Fanyi Meng, Zhijie Cai, Hang Li, Xiaoyang Li, Guangxu Zhu
Abstract: Data-driven Wi-Fi localization and tracking have shown great promise due to their lower reliance on specialized hardware compared to model-based methods. However, most existing data collection techniques provide only coarse-grained ground truth or a limited number of labeled points, significantly hindering the advancement of data-driven approaches. While systems like lidar can deliver precise ground truth, their high costs make them inaccessible to many users. To address these challenges, we propose LoFi, a vision-aided label generator for Wi-Fi localization and tracking. LoFi can generate ground truth position coordinates solely from 2D images, offering high precision, low cost, and ease of use. Utilizing our method, we have compiled a Wi-Fi tracking and localization dataset using the ESP32-S3 and a webcam, which will be open-sourced along with the code upon publication.
Authors: Tuur Stuyck, Gene Wei-Chin Lin, Egor Larionov, Hsiao-yu Chen, Aljaz Bozic, Nikolaos Sarafianos, Doug Roble
Abstract: Realistic hair motion is crucial for high-quality avatars, but it is often limited by the computational resources available for real-time applications. To address this challenge, we propose a novel neural approach to predict physically plausible hair deformations that generalizes to various body poses, shapes, and hairstyles. Our model is trained using a self-supervised loss, eliminating the need for expensive data generation and storage. We demonstrate our method's effectiveness through numerous results across a wide range of pose and shape variations, showcasing its robust generalization capabilities and temporally smooth results. Our approach is highly suitable for real-time applications with an inference time of only a few milliseconds on consumer hardware and its ability to scale to predicting the drape of 1000 grooms in 0.3 seconds. Please see our project page here following https://tuurstuyck.github.io/quaffure/quaffure.html
Authors: Jiapeng Tang, Davide Davoli, Tobias Kirschstein, Liam Schoneveld, Matthias Niessner
Abstract: We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to limited observations, which leaves unobserved regions under-constrained and can lead to artifacts in novel views. To address this problem, we introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency in Gaussian splatting renderings. To enable precise viewpoint control, we use normal maps rendered from FLAME-based head reconstruction, which provides pixel-aligned inductive biases. We also condition the diffusion model on VAE features extracted from the input image to preserve facial identity and appearance details. For Gaussian avatar reconstruction, we distill multi-view diffusion priors by using iteratively denoised images as pseudo-ground truths, effectively mitigating over-saturation issues. To further improve photorealism, we apply latent upsampling priors to refine the denoised latent before decoding it into an image. We evaluate our method on the NeRSemble dataset, showing that GAF outperforms previous state-of-the-art methods in novel view synthesis. Furthermore, we demonstrate higher-fidelity avatar reconstructions from monocular videos captured on commodity devices.
Authors: Jiaxu Li, Rui Li, Jianyu Qi, Songning Lai, Linpu Lv, Kejia Fan, Jianheng Tang, Yutao Yue, Dongzhan Zhou, Yuanhuai Liu, Huiping Zhuang
Abstract: 2D images and 3D point clouds are foundational data types for multimedia applications, including real-time video analysis, augmented reality (AR), and 3D scene understanding. Class-incremental semantic segmentation (CSS) requires incrementally learning new semantic categories while retaining prior knowledge. Existing methods typically rely on computationally expensive training based on stochastic gradient descent, employing complex regularization or exemplar replay. However, stochastic gradient descent-based approaches inevitably update the model's weights for past knowledge, leading to catastrophic forgetting, a problem exacerbated by pixel/point-level granularity. To address these challenges, we propose CFSSeg, a novel exemplar-free approach that leverages a closed-form solution, offering a practical and theoretically grounded solution for continual semantic segmentation tasks. This eliminates the need for iterative gradient-based optimization and storage of past data, requiring only a single pass through new samples per step. It not only enhances computational efficiency but also provides a practical solution for dynamic, privacy-sensitive multimedia environments. Extensive experiments on 2D and 3D benchmark datasets such as Pascal VOC2012, S3DIS, and ScanNet demonstrate CFSSeg's superior performance.
Authors: Yujin Wang, Quanfeng Liu, Jiaqi Fan, Jinlong Hong, Hongqing Chu, Mengjian Tian, Bingzhao Gao, Hong Chen
Abstract: Understanding and addressing corner cases is essential for ensuring the safety and reliability of autonomous driving systems. Vision-language models (VLMs) play a crucial role in enhancing scenario comprehension, yet they face significant challenges, such as hallucination and insufficient real-world grounding, which compromise their performance in critical driving scenarios. In this work, RAC3, a novel framework designed to enhance the performance of VLMs in corner case comprehension, is proposed. RAC3 integrates a frequency-spatial fusion (FSF) image encoder, cross-modal alignment fine-tuning with hard and semi-hard negative mining, and a fast querying pipeline based on KMeans clustering and hierarchical navigable small world (HNSW) indexing. A multimodal chain-of-thought (CoT) prompting strategy to guide analogical reasoning and reduce hallucinations during inference is introduced. Moreover, an update mechanism is integrated into RAC3 to ensure continual learning within the framework. Extensive experiments on the CODA and NuScenes datasets demonstrate that RAC3 significantly improves corner case comprehension across multiple downstream tasks. Compared to prior state-of-the-art methods, RAC3 achieves the highest final score of 74.46 on the CODA-LM benchmark and shows consistent performance gains when integrated with end-to-end frameworks like DriveLM. These results demonstrate the effectiveness of retrieval-augmented strategies and cross-modal alignment for safer and more interpretable autonomous driving.
Authors: Namhyuk Ahn, KiYoon Yoo, Wonhyuk Ahn, Daesik Kim, Seung-Hun Nam
Abstract: Recent advancements in diffusion models revolutionize image generation but pose risks of misuse, such as replicating artworks or generating deepfakes. Existing image protection methods, though effective, struggle to balance protection efficacy, invisibility, and latency, thus limiting practical use. We introduce perturbation pre-training to reduce latency and propose a mixture-of-perturbations approach that dynamically adapts to input images to minimize performance degradation. Our novel training strategy computes protection loss across multiple VAE feature spaces, while adaptive targeted protection at inference enhances robustness and invisibility. Experiments show comparable protection performance with improved invisibility and drastically reduced inference time. The code and demo are available at https://webtoon.github.io/impasto
Authors: Bingwen Hu, Heng Liu, Zhedong Zheng, Ping Liu
Abstract: Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe downsampling rates (\eg, 8$\times$ or 16$\times$). The recently developed text-guided SR approaches leverage textual descriptions to enhance their detail restoration capabilities but frequently struggle with effectively performing alignment, resulting in semantic inconsistencies. To address these challenges, we propose a multi-modal semantic enhancement framework that integrates textual semantics with visual features, effectively mitigating semantic mismatches and detail losses in highly degraded low-resolution (LR) images. Our method enables realistic, high-quality SR to be performed at large upscaling factors, with a maximum scaling ratio of 16$\times$. The framework integrates both text and image inputs using the prompt predictor, the Text-Image Fusion Block (TIFBlock), and the Iterative Refinement Module, leveraging Contrastive Language-Image Pretraining (CLIP) features to guide a progressive enhancement process with fine-grained alignment. This synergy produces high-resolution outputs with sharp textures and strong semantic coherence, even at substantial scaling factors. Extensive comparative experiments and ablation studies validate the effectiveness of our approach. Furthermore, by leveraging textual semantics, our method offers a degree of super-resolution editability, allowing for controlled enhancements while preserving semantic consistency. The code is available at https://github.com/hengliusky/CLIP-SR.
Authors: Mingjia Shi, Yuhao Zhou, Ruiji Yu, Zekai Li, Zhiyuan Liang, Xuanlei Zhao, Xiaojiang Peng, Shanmukha Ramakrishna Vedantam, Wangbo Zhao, Kai Wang, Yang You
Abstract: Vision Mamba has shown close to state of the art performance on computer vision tasks, drawing much interest in increasing it's efficiency. A promising approach is token reduction (that has been successfully implemented in ViTs). Pruning informative tokens in Mamba leads to a high loss of key knowledge and degraded performance. An alternative, of merging tokens preserves more information than pruning, also suffers for large compression ratios. Our key insight is that a quick round of retraining after token merging yeilds robust results across various compression ratios. Empirically, pruned Vims only drop up to 0.9% accuracy on ImageNet-1K, recovered by our proposed framework R-MeeTo in our main evaluation. We show how simple and effective the fast recovery can be achieved at minute-level, in particular, a 35.9% accuracy spike over 3 epochs of training on Vim-Ti. Moreover, Vim-Ti/S/B are re-trained within 5/7/17 minutes, and Vim-S only drops 1.3% with 1.2x (up to 1.5x) speed up in inference.
Authors: Guoxing Sun, Rishabh Dabral, Heming Zhu, Pascal Fua, Christian Theobalt, Marc Habermann
Abstract: Real-time free-view human rendering from sparse-view RGB inputs is a challenging task due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods leverage 2D CNNs operating in texture space to learn rendering primitives. However, they either jointly learn geometry and appearance, or completely ignore sparse image information for geometry estimation, significantly harming visual quality and robustness to unseen body poses. To address these issues, we present Double Unprojected Textures, which at the core disentangles coarse geometric deformation estimation from appearance synthesis, enabling robust and photorealistic 4K rendering in real-time. Specifically, we first introduce a novel image-conditioned template deformation network, which estimates the coarse deformation of the human template from a first unprojected texture. This updated geometry is then used to apply a second and more accurate texture unprojection. The resulting texture map has fewer artifacts and better alignment with input views, which benefits our learning of finer-level geometry and appearance represented by Gaussian splats. We validate the effectiveness and efficiency of the proposed method in quantitative and qualitative experiments, which significantly surpasses other state-of-the-art methods. Project page: https://vcai.mpi-inf.mpg.de/projects/DUT/
Authors: Aodi Li, Liansheng Zhuang, Xiao Long, Minghong Yao, Shafei Wang
Abstract: Domain generalization aims to learn a model from multiple training domains and generalize it to unseen test domains. Recent theory has shown that seeking the deep models, whose parameters lie in the flat minima of the loss landscape, can significantly reduce the out-of-domain generalization error. However, existing methods often neglect the consistency of loss landscapes in different domains, resulting in models that are not simultaneously in the optimal flat minima in all domains, which limits their generalization ability. To address this issue, this paper proposes an iterative Self-Feedback Training (SFT) framework to seek consistent flat minima that are shared across different domains by progressively refining loss landscapes during training. It alternatively generates a feedback signal by measuring the inconsistency of loss landscapes in different domains and refines these loss landscapes for greater consistency using this feedback signal. Benefiting from the consistency of the flat minima within these refined loss landscapes, our SFT helps achieve better out-of-domain generalization. Extensive experiments on DomainBed demonstrate superior performances of SFT when compared to state-of-the-art sharpness-aware methods and other prevalent DG baselines. On average across five DG benchmarks, SFT surpasses the sharpness-aware minimization by 2.6% with ResNet-50 and 1.5% with ViT-B/16, respectively. The code will be available soon.
Authors: Ma Zhuoqi, Zhang Yixuan, You Zejun, Tian Long, Liu Xiyang
Abstract: Artistic image stylization aims to render the content provided by text or image with the target style, where content and style decoupling is the key to achieve satisfactory results. However, current methods for content and style disentanglement primarily rely on image supervision, which leads to two problems: 1) models can only support one modality for style or content input;2) incomplete disentanglement resulting in content leakage from the reference image. To address the above issues, this paper proposes a multimodal approach to content-style disentanglement for artistic image stylization. We construct a \textit{WikiStyle+} dataset consists of artworks with corresponding textual descriptions for style and content. Based on the multimodal dataset, we propose a disentangled representations-guided diffusion model. The disentangled representations are first learned by Q-Formers and then injected into a pre-trained diffusion model using learnable multi-step cross-attention layers. Experimental results show that our method achieves a thorough disentanglement of content and style in reference images under multimodal supervision, thereby enabling more refined stylization that aligns with the artistic characteristics of the reference style. The code of our method will be available upon acceptance.
Authors: Zhongwei Chen, Zhao-Xu Yang, Hai-Jun Rong
Abstract: Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images. However, the imaging gaps between platforms are often significant and the variations in viewpoints are substantial, which limits the ability of existing methods to effectively associate cross-view features and extract consistent and invariant characteristics. Moreover, existing methods often overlook the problem of increased computational and storage requirements when improving model performance. To handle these limitations, we propose a lightweight enhanced alignment network, called the Multi-Level Embedding and Alignment Network (MEAN). The MEAN network uses a progressive multi-level enhancement strategy, global-to-local associations, and cross-domain alignment, enabling feature communication across levels. This allows MEAN to effectively connect features at different levels and learn robust cross-view consistent mappings and modality-invariant features. Moreover, MEAN adopts a shallow backbone network combined with a lightweight branch design, effectively reducing parameter count and computational complexity. Experimental results on the University-1652 and SUES-200 datasets demonstrate that MEAN reduces parameter count by 62.17% and computational complexity by 70.99% compared to state-of-the-art models, while maintaining competitive or even superior performance. Our code and models will be released on https://github.com/ISChenawei/MEAN.
Authors: Mingliang Liang, Martha Larson
Abstract: Vision Language Models (VLMs) can be trained more efficiently if training sets can be reduced in size. Recent work has shown the benefits of masking text during VLM training using a variety of approaches: truncation, random masking, block masking and syntax masking. In this paper, we show that the best masking strategy changes over training epochs and that, given sufficient training epochs. We analyze existing text masking approaches including syntax masking, which is currently the state of the art, and identify the word frequency distribution as important in determining their success. Experiments on a large range of data sets demonstrate that syntax masking is outperformed by other approaches, given sufficient epochs, and that our proposed frequency-based approach, called Contrastive Language-Image Pre-training with Word Frequency Masking (CLIPF) has numerous advantages. The benefits are particularly evident as the number of input tokens decreases.
Authors: Siyang Wang, Feng Zhao
Abstract: Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for transforming degraded features into clean ones in image restoration. VAR, a novel image generative paradigm, surpasses diffusion models in generation quality by applying a next-scale prediction approach. It progressively captures both global structures and fine-grained details through the autoregressive process, consistent with the multi-scale restoration principle widely acknowledged in the restoration community. Furthermore, we observe that during the image reconstruction process utilizing VAR, scale predictions automatically modulate the input, facilitating the alignment of representations at subsequent scales with the distribution of clean images. To harness VAR's adaptive distribution alignment capability in image restoration tasks, we formulate the multi-scale latent representations within VAR as the restoration prior, thus advancing our delicately designed VarFormer framework. The strategic application of these priors enables our VarFormer to achieve remarkable generalization on unseen tasks while also reducing training computational costs. Extensive experiments underscores that our VarFormer outperforms existing multi-task image restoration methods across various restoration tasks.
Authors: Tiange Luo, Ang Cao, Gunhee Lee, Justin Johnson, Honglak Lee
Abstract: Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring deliberately out-of-distribution images synthesized via image generation models and out-of-distribution Q&A pairs. Each question in ViLP is coupled with three potential answers and three corresponding images: one that can be resolved by text priors alone and two that demand visual reasoning. Although, humans achieve near-perfect accuracy, modern VLMs falter; for instance, GPT-4 achieves only 66.17% on ViLP. To alleviate this, we propose a self-improving framework in which models generate new VQA data, then apply pixel-level and semantic corruptions to form "good-bad" image pairs for self-training. Our training objectives compel VLMs to focus more on the actual visual inputs, and we demonstrate their effectiveness in boosting the performance of open-source VLMs, including LLaVA-v1.5 and Cambrian.
Authors: Yulong Li, Yuxuan Zhang, Feilong Tang, Ming Hu, Zhixiang Lu, Haochen Xue, Jianghao Wu, Mian Zhou, Kang Dang, Chong Li, Yifang Wang, Imran Razzak, Jionglong Su
Abstract: Sign language is the primary communication mode for 72 million hearing-impaired individuals worldwide, necessitating effective bidirectional Sign Language Production and Sign Language Translation systems. However, functional bidirectional systems require a unified linguistic environment, hindered by the lack of suitable unified datasets, particularly those providing the necessary pose information for accurate Sign Language Production (SLP) evaluation. Concurrently, current SLP evaluation methods like back-translation ignore pose accuracy, and high-quality coordinated generation remains challenging. To create this crucial environment and overcome these challenges, we introduce CNText2Sign and CNSign, which together constitute the first unified dataset aimed at supporting bidirectional accessibility systems for Chinese sign language; CNText2Sign provides 15,000 natural language-to-sign mappings and standardized skeletal keypoints for 8,643 vocabulary items supporting pose assessment. Building upon this foundation, we propose the AuraLLM model, which leverages a decoupled architecture with CNText2Sign's pose data for novel direct gesture accuracy assessment. The model employs retrieval augmentation and Cascading Vocabulary Resolution to handle semantic mapping and out-of-vocabulary words and achieves all-scenario production with controllable coordination of gestures and facial expressions via pose-conditioned video synthesis. Concurrently, our Sign Language Translation model SignMST-C employs targeted self-supervised pretraining for dynamic feature capture, achieving new SOTA results on PHOENIX2014-T with BLEU-4 scores up to 32.08. AuraLLM establishes a strong performance baseline on CNText2Sign with a BLEU-4 score of 50.41 under direct evaluation.
Authors: Zhi Jin, Yuwei Qiu, Kaihao Zhang, Hongdong Li, Wenhan Luo
Abstract: Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention poses a significant limitation on its extensive application in image restoration tasks, particularly for high-resolution images. To tackle this challenge, we propose a novel variant of the Transformer. This variant leverages the Taylor expansion to approximate the Softmax-attention and utilizes the concept of norm-preserving mapping to approximate the remainder of the first-order Taylor expansion, resulting in a linear computational complexity. Moreover, we introduce a multi-branch architecture featuring multi-scale patch embedding into the proposed Transformer, which has four distinct advantages: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field; 4) accelerated training and inference speed. Hence, the proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder. Experimental results across diverse image restoration benchmarks demonstrate that MB-TaylorFormer V2 achieves state-of-the-art performance in multiple image restoration tasks, such as image dehazing, deraining, desnowing, motion deblurring, and denoising, with very little computational overhead. The source code is available at https://github.com/FVL2020/MB-TaylorFormerV2.
Authors: Shangjin Zhai, Zhichao Ye, Jialin Liu, Weijian Xie, Jiaqi Hu, Zhen Peng, Hua Xue, Danpeng Chen, Xiaomeng Wang, Lei Yang, Nan Wang, Haomin Liu, Guofeng Zhang
Abstract: Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small area, making long-range consistent scene generation challenging. To address this, we propose StarGen, a novel framework that employs a pre-trained video diffusion model in an autoregressive manner for long-range scene generation. The generation of each video clip is conditioned on the 3D warping of spatially adjacent images and the temporally overlapping image from previously generated clips, improving spatiotemporal consistency in long-range scene generation with precise pose control. The spatiotemporal condition is compatible with various input conditions, facilitating diverse tasks, including sparse view interpolation, perpetual view generation, and layout-conditioned city generation. Quantitative and qualitative evaluations demonstrate StarGen's superior scalability, fidelity, and pose accuracy compared to state-of-the-art methods. Project page: https://zju3dv.github.io/StarGen.
Authors: Hongruixuan Chen, Jian Song, Olivier Dietrich, Clifford Broni-Bediako, Weihao Xuan, Junjue Wang, Xinlei Shao, Yimin Wei, Junshi Xia, Cuiling Lan, Konrad Schindler, Naoto Yokoya
Abstract: Disaster events occur around the world and cause significant damage to human life and property. Earth observation (EO) data enables rapid and comprehensive building damage assessment (BDA), an essential capability in the aftermath of a disaster to reduce human casualties and to inform disaster relief efforts. Recent research focuses on the development of AI models to achieve accurate mapping of unseen disaster events, mostly using optical EO data. However, solutions based on optical data are limited to clear skies and daylight hours, preventing a prompt response to disasters. Integrating multimodal (MM) EO data, particularly the combination of optical and SAR imagery, makes it possible to provide all-weather, day-and-night disaster responses. Despite this potential, the development of robust multimodal AI models has been constrained by the lack of suitable benchmark datasets. In this paper, we present a BDA dataset using veRy-hIGH-resoluTion optical and SAR imagery (BRIGHT) to support AI-based all-weather disaster response. To the best of our knowledge, BRIGHT is the first open-access, globally distributed, event-diverse MM dataset specifically curated to support AI-based disaster response. It covers five types of natural disasters and two types of man-made disasters across 14 regions worldwide, with a particular focus on developing countries where external assistance is most needed. The optical and SAR imagery in BRIGHT, with a spatial resolution between 0.3-1 meters, provides detailed representations of individual buildings, making it ideal for precise BDA. In our experiments, we have tested seven advanced AI models trained with our BRIGHT to validate the transferability and robustness. The dataset and code are available at https://github.com/ChenHongruixuan/BRIGHT. BRIGHT also serves as the official dataset for the 2025 IEEE GRSS Data Fusion Contest.
Authors: Yue Hu, Rong Liu, Meida Chen, Peter Beerel, Andrew Feng
Abstract: Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details. While differentiable rendering techniques such as Neural Radiance Fields (NeRF) address some of these challenges, their high computational costs make them unsuitable for real-time applications. Additionally, existing 3D Gaussian Splatting (3DGS) methods often focus on photometric consistency, neglecting geometric accuracy and failing to exploit SLAM's dynamic depth and pose updates for scene refinement. We propose a framework integrating dense SLAM with 3DGS for real-time, high-fidelity dense reconstruction. Our approach introduces SLAM-Informed Adaptive Densification, which dynamically updates and densifies the Gaussian model by leveraging dense point clouds from SLAM. Additionally, we incorporate Geometry-Guided Optimization, which combines edge-aware geometric constraints and photometric consistency to jointly optimize the appearance and geometry of the 3DGS scene representation, enabling detailed and accurate SLAM mapping reconstruction. Experiments on the Replica and TUM-RGBD datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results among monocular systems. Specifically, our method achieves a PSNR of 36.864, SSIM of 0.985, and LPIPS of 0.040 on Replica, representing improvements of 10.7%, 6.4%, and 49.4%, respectively, over the previous SOTA. On TUM-RGBD, our method outperforms the closest baseline by 10.2%, 6.6%, and 34.7% in the same metrics. These results highlight the potential of our framework in bridging the gap between photometric and geometric dense 3D scene representations, paving the way for practical and efficient monocular dense reconstruction.
Authors: Abdalwhab Abdalwhab, Ali Imran, Sina Heydarian, Ivanka Iordanova, David St-Onge
Abstract: The construction industry has long explored robotics and computer vision, yet their deployment on construction sites remains very limited. These technologies have the potential to revolutionize traditional workflows by enhancing accuracy, efficiency, and safety in construction management. Ground robots equipped with advanced vision systems could automate tasks such as monitoring mechanical, electrical, and plumbing (MEP) systems. The present research evaluates the applicability of open-vocabulary vision-language models compared to fine-tuned, lightweight, closed-set object detectors for detecting MEP components using a mobile ground robotic platform. A dataset collected with cameras mounted on a ground robot was manually annotated and analyzed to compare model performance. The results demonstrate that, despite the versatility of vision-language models, fine-tuned lightweight models still largely outperform them in specialized environments and for domain-specific tasks.
Authors: Zixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You, Zheming Lu, Fan Zhang, Shi Guo, Tianfan Xue
Abstract: Capturing high dynamic range (HDR) scenes is one of the most important issues in camera design. Majority of cameras use exposure fusion, which fuses images captured by different exposure levels, to increase dynamic range. However, this approach can only handle images with limited exposure difference, normally 3-4 stops. When applying to very high dynamic range scenes where a large exposure difference is required, this approach often fails due to incorrect alignment or inconsistent lighting between inputs, or tone mapping artifacts. In this work, we propose \model, the first exposure fusion technique that can merge inputs with 9 stops differences. The key idea is that we model exposure fusion as a guided inpainting problem, where the under-exposed image is used as a guidance to fill the missing information of over-exposed highlights in the over-exposed region. Using an under-exposed image as a soft guidance, instead of a hard constraint, our model is robust to potential alignment issue or lighting variations. Moreover, by utilizing the image prior of the generative model, our model also generates natural tone mapping, even for very high-dynamic range scenes. Our approach outperforms HDR-Transformer on latest HDR benchmarks. Moreover, to test its performance in ultra high dynamic range scenes, we capture a new real-world exposure fusion benchmark, UltraFusion dataset, with exposure differences up to 9 stops, and experiments show that UltraFusion can generate beautiful and high-quality fusion results under various scenarios. Code and data will be available at https://openimaginglab.github.io/UltraFusion.
Authors: Taegyeong Lee, Jinsik Bang, Soyeong Kwon, Taehwan Kim
Abstract: Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs). Our approach involves: 1) querying Large Language Model with multi-aspect questions relevant to the knowledge we want to transfer to the model, 2) extracting corresponding logits from MLLM, and 3) expanding the model's output dimensions to distill these multi-aspect logits. We then apply cross-entropy loss to class logits and binary cross-entropy loss to multi-aspect logits. Through our method, the model can learn not only the knowledge about visual aspects but also the abstract and complex aspects that require a deeper understanding. We primarily apply our method to image classification, and to explore the potential for extending our model, such as object detection. In all experimental results, our method improves the performance of the baselines. Additionally, we analyze the effect of multi-aspect knowledge distillation. These results demonstrate that our method can transfer knowledge about various aspects to the model and the aspect knowledge can enhance model performance in computer vision tasks.
Authors: Dan Song, Shumeng Huo, Wenhui Li, Lanjun Wang, Chao Xue, An-An Liu
Abstract: The classification and recognition of maritime objects are crucial for enhancing maritime safety, monitoring, and intelligent sea environment prediction. However, existing unsupervised methods for maritime object classification often struggle with the long-tail data distributions in both object categories and weather conditions. In this paper, we construct a dataset named AIMO produced by large-scale generative models with diverse weather conditions and balanced object categories, and collect a dataset named RMO with real-world images where long-tail issue exists. We propose a novel domain adaptation approach that leverages AIMO (source domain) to address the problem of limited labeled data, unbalanced distribution and domain shift in RMO (target domain), enhance the generalization of source features with the Vision-Language Models such as CLIP, and propose a difficulty score for curriculum learning to optimize training process. Experimental results shows that the proposed method significantly improves the classification accuracy, particularly for samples within rare object categories and weather conditions. Datasets and codes will be publicly available at https://github.com/honoria0204/AIMO.
Authors: Zhibo Ren, Pritthijit Nath, Pancham Shukla
Abstract: Tropical cyclone (TC) forecasting is crucial for disaster preparedness and mitigation. While recent deep learning approaches have shown promise, existing methods often treat TC evolution as a series of independent frame-to-frame predictions, limiting their ability to capture long-term dynamics. We present a novel application of video diffusion models for TC forecasting that explicitly models temporal dependencies through additional temporal layers. Our approach enables the model to generate multiple frames simultaneously, better capturing cyclone evolution patterns. We introduce a two-stage training strategy that significantly improves individual-frame quality and performance in low-data regimes. Experimental results show our method outperforms the previous approach of Nath et al. by 19.3% in MAE, 16.2% in PSNR, and 36.1% in SSIM. Most notably, we extend the reliable forecasting horizon from 36 to 50 hours. Through comprehensive evaluation using both traditional metrics and Fr\'echet Video Distance (FVD), we demonstrate that our approach produces more temporally coherent forecasts while maintaining competitive single-frame quality. Code accessible at https://github.com/Ren-creater/forecast-video-diffmodels.
URLs: https://github.com/Ren-creater/forecast-video-diffmodels.
Authors: Zihui Zhao, Yingxin Li, Yang Li
Abstract: Vision-Language Models (VLMs) have achieved remarkable success across a range of multimodal tasks; however, their practical deployment is often constrained by high computational costs and prolonged inference times. Since the vision modality typically carries more information than the text modality, compressing visual prompts offers a promising solution to alleviate these challenges. Existing approaches predominantly focus on refining model architectures or directly reducing the number of visual tokens. However, these methods often compromise inference performance due to a lack of consideration for the unique spatial and temporal characteristics of visual data. In this work, we propose a token compression paradigm that operates on both spatial and temporal dimensions. Our approach includes a learning-free, plug-and-play compression pipeline that can be seamlessly integrated into most Multimodal Large Language Model (MLLM) frameworks. By leveraging this method, we enhance the model inference capability while simultaneously reducing its computational cost. Experimental results on the Video-QA task demonstrate the effectiveness of the proposed approach, showcasing significant improvements in efficiency without sacrificing performance.
Authors: Matt C. Bendel, Saurav K. Shastri, Rizwan Ahmad, Philip Schniter
Abstract: Imaging inverse problems can be solved in an unsupervised manner using pre-trained diffusion models, but doing so requires approximating the gradient of the measurement-conditional score function in the diffusion reverse process. We show that the approximations produced by existing methods are relatively poor, especially early in the reverse process, and so we propose a new approach that iteratively reestimates and "renoises" the estimate several times per diffusion step. This iterative approach, which we call Fast Iterative REnoising (FIRE), injects colored noise that is shaped to ensure that the pre-trained diffusion model always sees white noise, in accordance with how it was trained. We then embed FIRE into the DDIM reverse process and show that the resulting "DDfire" offers state-of-the-art accuracy and runtime on several linear inverse problems, as well as phase retrieval. Our implementation is at https://github.com/matt-bendel/DDfire
Authors: Jingcheng Ni, Weiguang Zhao, Daniel Wang, Ziyao Zeng, Chenyu You, Alex Wong, Kaizhu Huang
Abstract: 3D object removal is an important sub-task in 3D scene editing, with broad applications in scene understanding, augmented reality, and robotics. However, existing methods struggle to achieve a desirable balance among consistency, usability, and computational efficiency in multi-view settings. These limitations are primarily due to unintuitive user interaction in the source view, inefficient multi-view object mask generation, computationally expensive inpainting procedures, and a lack of applicability across different radiance field representations. To address these challenges, we propose a novel pipeline that improves the quality and efficiency of multi-view object mask generation and inpainting. Our method introduces an intuitive region-based interaction mechanism in the source view and eliminates the need for camera poses or extra model training. Our lightweight HoMM module is employed to achieve high-quality multi-view mask propagation with enhanced efficiency. In the inpainting stage, we further reduce computational costs by performing inpainting only on selected key views and propagating the results to other views via homography-based mapping. Our pipeline is compatible with a variety of radiance field frameworks, including NeRF and 3D Gaussian Splatting, demonstrating improved generalizability and practicality in real-world scenarios. Additionally, we present a new 3D multi-object removal dataset with greater object diversity and viewpoint variation than existing datasets. Experiments on public benchmarks and our proposed dataset show that our method achieves state-of-the-art performance while reducing runtime to one-fifth of that required by leading baselines.
Authors: Can Jin, Ying Li, Mingyu Zhao, Shiyu Zhao, Zhenting Wang, Xiaoxiao He, Ligong Han, Tong Che, Dimitris N. Metaxas
Abstract: Visual prompting has gained popularity as a method for adapting pre-trained models to specific tasks, particularly in the realm of parameter-efficient tuning. However, existing visual prompting techniques often pad the prompt parameters around the image, limiting the interaction between the visual prompts and the original image to a small set of patches while neglecting the inductive bias present in shared information across different patches. In this study, we conduct a thorough preliminary investigation to identify and address these limitations. We propose a novel visual prompt design, introducing Low-Rank matrix multiplication for Visual Prompting (LoR-VP), which enables shared and patch-specific information across rows and columns of image pixels. Extensive experiments across seven network architectures and four datasets demonstrate significant improvements in both performance and efficiency compared to state-of-the-art visual prompting methods, achieving up to 6 times faster training times, utilizing 18 times fewer visual prompt parameters, and delivering a 3.1% improvement in performance. The code is available as https://github.com/jincan333/LoR-VP.
Authors: Runtian Yuan, Mohan Chen, Jilan Xu, Ling Zhou, Qingqiu Li, Yuejie Zhang, Rui Feng, Tao Zhang, Shang Gao
Abstract: Referring Medical Image Sequence Segmentation (Ref-MISS) is a novel and challenging task that aims to segment anatomical structures in medical image sequences (\emph{e.g.} endoscopy, ultrasound, CT, and MRI) based on natural language descriptions. This task holds significant clinical potential and offers a user-friendly advancement in medical imaging interpretation. Existing 2D and 3D segmentation models struggle to explicitly track objects of interest across medical image sequences, and lack support for nteractive, text-driven guidance. To address these limitations, we propose Text-Promptable Propagation (TPP), a model designed for referring medical image sequence segmentation. TPP captures the intrinsic relationships among sequential images along with their associated textual descriptions. Specifically, it enables the recognition of referred objects through cross-modal referring interaction, and maintains continuous tracking across the sequence via Transformer-based triple propagation, using text embeddings as queries. To support this task, we curate a large-scale benchmark, Ref-MISS-Bench, which covers 4 imaging modalities and 20 different organs and lesions. Experimental results on this benchmark demonstrate that TPP consistently outperforms state-of-the-art methods in both medical segmentation and referring video object segmentation.
Authors: Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen
Abstract: Perceiving visual scenes as objects and background -- like humans do -- Object-Centric Learning (OCL) aggregates image or video feature maps into object-level feature vectors, termed \textit{slots}. OCL's self-supervision of reconstructing the input from these aggregated slots struggles with complex object textures, thus Vision Foundation Model (VFM) representations are used as the aggregation input and reconstruction target. However, existing methods leverage VFM representations in diverse ways and often fail to fully exploit their potential. In response, we propose a clean architecture -- Vector-Quantized VFMs for OCL (VQ-VFM-OCL, or VVO) -- that unifies mainstream OCL methods. The key to our unification is simple yet effective, just shared quantizing the same VFM representation as the reconstruction target. Through mathematical modeling and statistical verification, we further analyze why VFM representations facilitate OCL aggregation and how their shared quantization as reconstruction targets strengthens OCL supervision. Experiments show that across different VFMs, aggregators and decoders, our VVO consistently outperforms baselines in object discovery and recognition, as well as downstream visual prediction and reasoning. The source code is available in supplemental files.
Authors: Juan Song, Lijie Yang, Mingtao Feng
Abstract: It remains a significant challenge to compress images at extremely low bitrate while achieving both semantic consistency and high perceptual quality. Inspired by human progressive perception mechanism, we propose a Semantically Disentangled Image Compression framework (SEDIC) in this paper. Initially, an extremely compressed reference image is obtained through a learned image encoder. Then we leverage LMMs to extract essential semantic components, including overall descriptions, object detailed description, and semantic segmentation masks. We propose a training-free Object Restoration model with Attention Guidance (ORAG) built on pre-trained ControlNet to restore object details conditioned by object-level text descriptions and semantic masks. Based on the proposed ORAG, we design a multistage semantic image decoder to progressively restore the details object by object, starting from the extremely compressed reference image, ultimately generating high-quality and high-fidelity reconstructions. Experimental results demonstrate that SEDIC significantly outperforms state-of-the-art approaches, achieving superior perceptual quality and semantic consistency at extremely low-bitrates ($\le$ 0.05 bpp).
Authors: Mengdi Wang, Efe Bozkir, Enkelejda Kasneci
Abstract: Iris texture is widely regarded as a gold standard biometric modality for authentication and identification. The demand for robust iris recognition methods, coupled with growing security and privacy concerns regarding iris attacks, has escalated recently. Inspired by neural style transfer, an advanced technique that leverages neural networks to separate content and style features, we hypothesize that iris texture's style features provide a reliable foundation for recognition and are more resilient to variations like rotation and perspective shifts than traditional approaches. Our experimental results support this hypothesis, showing a significantly higher classification accuracy compared to conventional features. Further, we propose using neural style transfer to obfuscate the identifiable iris style features, ensuring the protection of sensitive biometric information while maintaining the utility of eye images for tasks like eye segmentation and gaze estimation. This work opens new avenues for iris-oriented, secure, and privacy-aware biometric systems.
Authors: Jiakai Lin, Jinchang Zhang, Guoyu Lu
Abstract: Keypoint detection and local feature description are fundamental tasks in robotic perception, critical for applications such as SLAM, robot localization, feature matching, pose estimation, and 3D mapping. While existing methods predominantly operate on RGB images, we propose a novel network that directly processes raw images, bypassing the need for the Image Signal Processor (ISP). This approach significantly reduces hardware requirements and memory consumption, which is crucial for robotic vision systems. Our method introduces two custom-designed convolutional kernels capable of performing convolutions directly on raw images, preserving inter-channel information without converting to RGB. Experimental results show that our network outperforms existing algorithms on raw images, achieving higher accuracy and stability under large rotations and scale variations. This work represents the first attempt to develop a keypoint detection and feature description network specifically for raw images, offering a more efficient solution for resource-constrained environments.
Authors: Jinchang Zhang, Zijun Li, Guoyu Lu
Abstract: Depth-guided multimodal fusion combines depth information from visible and infrared images, significantly enhancing the performance of 3D reconstruction and robotics applications. Existing thermal-visible image fusion mainly focuses on detection tasks, ignoring other critical information such as depth. By addressing the limitations of single modalities in low-light and complex environments, the depth information from fused images not only generates more accurate point cloud data, improving the completeness and precision of 3D reconstruction, but also provides comprehensive scene understanding for robot navigation, localization, and environmental perception. This supports precise recognition and efficient operations in applications such as autonomous driving and rescue missions. We introduce a text-guided and depth-driven infrared and visible image fusion network. The model consists of an image fusion branch for extracting multi-channel complementary information through a diffusion model, equipped with a text-guided module, and two auxiliary depth estimation branches. The fusion branch uses CLIP to extract semantic information and parameters from depth-enriched image descriptions to guide the diffusion model in extracting multi-channel features and generating fused images. These fused images are then input into the depth estimation branches to calculate depth-driven loss, optimizing the image fusion network. This framework aims to integrate vision-language and depth to directly generate color-fused images from multimodal inputs.
Authors: Yuhao Du, Hui Liu, Haoxiang Peng, Xinyuan Cheng, Chenrong Wu, Jiankai Zhang
Abstract: Recent years, weather forecasting has gained significant attention. However, accurately predicting weather remains a challenge due to the rapid variability of meteorological data and potential teleconnections. Current spatiotemporal forecasting models primarily rely on convolution operations or sliding windows for feature extraction. These methods are limited by the size of the convolutional kernel or sliding window, making it difficult to capture and identify potential teleconnection features in meteorological data. Additionally, weather data often involve non-rigid bodies, whose motion processes are accompanied by unpredictable deformations, further complicating the forecasting task. In this paper, we propose the GMG model to address these two core challenges. The Global Focus Module, a key component of our model, enhances the global receptive field, while the Motion Guided Module adapts to the growth or dissipation processes of non-rigid bodies. Through extensive evaluations, our method demonstrates competitive performance across various complex tasks, providing a novel approach to improving the predictive accuracy of complex spatiotemporal data.
Authors: Hangrui Xu, Chuanrui Zhang, Zhengxian Wu, Peng Jiao, Haoqian Wang
Abstract: Gait recognition has emerged as a robust biometric modality due to its non-intrusive nature and resilience to occlusion. Conventional gait recognition methods typically rely on silhouettes or skeletons. Despite their success in gait recognition for controlled laboratory environments, they usually fail in real-world scenarios due to their limited information entropy for gait representations. To achieve accurate gait recognition in the wild, we propose a novel gait representation, named Parsing Skeleton. This representation innovatively introduces the skeleton-guided human parsing method to capture fine-grained body dynamics, so they have much higher information entropy to encode the shapes and dynamics of fine-grained human parts during walking. Moreover, to effectively explore the capability of the Parsing Skeleton representation, we propose a novel Parsing Skeleton-based gait recognition framework, named PSGait, which takes Parsing Skeletons and silhouettes as input. By fusing these two modalities, the resulting image sequences are fed into gait recognition models for enhanced individual differentiation. We conduct comprehensive benchmarks on various datasets to evaluate our model. PSGait outperforms existing state-of-the-art multimodal methods that utilize both skeleton and silhouette inputs while significantly reducing computational resources. Furthermore, as a plug-and-play method, PSGait leads to a maximum improvement of 10.9% in Rank-1 accuracy across various gait recognition models. These results demonstrate that Parsing Skeleton offers a lightweight, effective, and highly generalizable representation for gait recognition in the wild.
Authors: Luming Wang, Hao Shi, Xiaoting Yin, Kailun Yang, Kaiwei Wang, Jian Bai
Abstract: Egocentric gesture recognition is a pivotal technology for enhancing natural human-computer interaction, yet traditional RGB-based solutions suffer from motion blur and illumination variations in dynamic scenarios. While event cameras show distinct advantages in handling high dynamic range with ultra-low power consumption, existing RGB-based architectures face inherent limitations in processing asynchronous event streams due to their synchronous frame-based nature. Moreover, from an egocentric perspective, event cameras record data that includes events generated by both head movements and hand gestures, thereby increasing the complexity of gesture recognition. To address this, we propose a novel network architecture specifically designed for event data processing, incorporating (1) a lightweight CNN with asymmetric depthwise convolutions to reduce parameters while preserving spatiotemporal features, (2) a plug-and-play state-space model as context block that decouples head movement noise from gesture dynamics, and (3) a parameter-free Bins-Temporal Shift Module (BSTM) that shifts features along bins and temporal dimensions to fuse sparse events efficiently. We further establish the EgoEvGesture dataset, the first large-scale dataset for egocentric gesture recognition using event cameras. Experimental results demonstrate that our method achieves 62.7% accuracy tested on unseen subjects with only 7M parameters, 3.1% higher than state-of-the-art approaches. Notable misclassifications in freestyle motions stem from high inter-personal variability and unseen test patterns differing from training data. Moreover, our approach achieved a remarkable accuracy of 97.0% on the DVS128 Gesture, demonstrating the effectiveness and generalization capability of our method on public datasets. The dataset and models are made available at https://github.com/3190105222/EgoEv_Gesture.
Authors: Dewei Zhou, Mingwei Li, Zongxin Yang, Yi Yang
Abstract: Image-conditioned generation methods, such as depth- and canny-conditioned approaches, have demonstrated remarkable abilities for precise image synthesis. However, existing models still struggle to accurately control the content of multiple instances (or regions). Even state-of-the-art models like FLUX and 3DIS face challenges, such as attribute leakage between instances, which limits user control. To address these issues, we introduce DreamRenderer, a training-free approach built upon the FLUX model. DreamRenderer enables users to control the content of each instance via bounding boxes or masks, while ensuring overall visual harmony. We propose two key innovations: 1) Bridge Image Tokens for Hard Text Attribute Binding, which uses replicated image tokens as bridge tokens to ensure that T5 text embeddings, pre-trained solely on text data, bind the correct visual attributes for each instance during Joint Attention; 2) Hard Image Attribute Binding applied only to vital layers. Through our analysis of FLUX, we identify the critical layers responsible for instance attribute rendering and apply Hard Image Attribute Binding only in these layers, using soft binding in the others. This approach ensures precise control while preserving image quality. Evaluations on the COCO-POS and COCO-MIG benchmarks demonstrate that DreamRenderer improves the Image Success Ratio by 17.7% over FLUX and enhances the performance of layout-to-image models like GLIGEN and 3DIS by up to 26.8%. Project Page: https://limuloo.github.io/DreamRenderer/.
Authors: Siyuan Yan, Ming Hu, Yiwen Jiang, Xieji Li, Hao Fei, Philipp Tschandl, Harald Kittler, Zongyuan Ge
Abstract: The emergence of vision-language models has transformed medical AI, enabling unprecedented advances in diagnostic capability and clinical applications. However, progress in dermatology has lagged behind other medical domains due to the lack of standard image-text pairs. Existing dermatological datasets are limited in both scale and depth, offering only single-label annotations across a narrow range of diseases instead of rich textual descriptions, and lacking the crucial clinical context needed for real-world applications. To address these limitations, we present Derm1M, the first large-scale vision-language dataset for dermatology, comprising 1,029,761 image-text pairs. Built from diverse educational resources and structured around a standard ontology collaboratively developed by experts, Derm1M provides comprehensive coverage for over 390 skin conditions across four hierarchical levels and 130 clinical concepts with rich contextual information such as medical history, symptoms, and skin tone. To demonstrate Derm1M potential in advancing both AI research and clinical application, we pretrained a series of CLIP-like models, collectively called DermLIP, on this dataset. The DermLIP family significantly outperforms state-of-the-art foundation models on eight diverse datasets across multiple tasks, including zero-shot skin disease classification, clinical and artifacts concept identification, few-shot/full-shot learning, and cross-modal retrieval. Our dataset and code will be publicly available at https://github.com/SiyuanYan1/Derm1M upon acceptance.
Authors: \`Alex Pujol Vidal, Sergio Escalera, Kamal Nasrollahi, Thomas B. Moeslund
Abstract: Machine unlearning methods have become increasingly important for selective concept removal in large pre-trained models. While recent work has explored unlearning in Euclidean contrastive vision-language models, the effectiveness of concept removal in hyperbolic spaces remains unexplored. This paper investigates machine unlearning in hyperbolic contrastive learning by adapting Alignment Calibration to MERU, a model that embeds images and text in hyperbolic space to better capture semantic hierarchies. Through systematic experiments and ablation studies, we demonstrate that hyperbolic geometry offers distinct advantages for concept removal, achieving near perfect forgetting with reasonable performance on retained concepts, particularly when scaling to multiple concept removal. Our approach introduces hyperbolic-specific components including entailment calibration and norm regularization that leverage the unique properties of hyperbolic space. Comparative analysis with Euclidean models reveals fundamental differences in unlearning dynamics, with hyperbolic unlearning reorganizing the semantic hierarchy while Euclidean approaches merely disconnect cross-modal associations. These findings not only advance machine unlearning techniques but also provide insights into the geometric properties that influence concept representation and removal in multimodal models. Source code available at https://github.com/alex-pv01/HAC
Authors: Jinchang Zhang, Guoyu Lu
Abstract: Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised training, often overlooking the intrinsic information provided by the camera itself. We propose a method that embodies the camera model and its physical characteristics into a deep learning model, computing embodied scene depth through real-time interactions with road environments. The model can calculate embodied scene depth in real-time based on immediate environmental changes using only the intrinsic properties of the camera, without any additional equipment. By combining embodied scene depth with RGB image features, the model gains a comprehensive perspective on both geometric and visual details. Additionally, we incorporate text descriptions containing environmental content and depth information as priors for scene understanding, enriching the model's perception of objects. This integration of image and language - two inherently ambiguous modalities - leverages their complementary strengths for monocular depth estimation. The real-time nature of the embodied language and depth prior model ensures that the model can continuously adjust its perception and behavior in dynamic environments. Experimental results show that the embodied depth estimation method enhances model performance across different scenes.
Authors: Tharun Anand, Siva Sankar Sajeev, Pravin Nair
Abstract: With rapid advancements in generative modeling, deepfake techniques are increasingly narrowing the gap between real and synthetic videos, raising serious privacy and security concerns. Beyond traditional face swapping and reenactment, an emerging trend in recent state-of-the-art deepfake generation methods involves localized edits such as subtle manipulations of specific facial features like raising eyebrows, altering eye shapes, or modifying mouth expressions. These fine-grained manipulations pose a significant challenge for existing detection models, which struggle to capture such localized variations. To the best of our knowledge, this work presents the first detection approach explicitly designed to generalize to localized edits in deepfake videos by leveraging spatiotemporal representations guided by facial action units. Our method leverages a cross-attention-based fusion of representations learned from pretext tasks like random masking and action unit detection, to create an embedding that effectively encodes subtle, localized changes. Comprehensive evaluations across multiple deepfake generation methods demonstrate that our approach, despite being trained solely on the traditional FF+ dataset, sets a new benchmark in detecting recent deepfake-generated videos with fine-grained local edits, achieving a $20\%$ improvement in accuracy over current state-of-the-art detection methods. Additionally, our method delivers competitive performance on standard datasets, highlighting its robustness and generalization across diverse types of local and global forgeries.
Authors: Nan Huang, Wenzhao Zheng, Chenfeng Xu, Kurt Keutzer, Shanghang Zhang, Angjoo Kanazawa, Qianqian Wang
Abstract: Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on optical flow to provide motion cues; however, this approach often results in imperfect predictions due to challenges such as partial motion, complex deformations, motion blur and background distractions. We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features and leverages SAM2 for pixel-level mask densification through an iterative prompting strategy. Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support. Extensive testing on diverse datasets demonstrates state-of-the-art performance, excelling in challenging scenarios and fine-grained segmentation of multiple objects. Our code is available at https://motion-seg.github.io/.
Authors: Jaskaran Singh Walia, Shravan Venkatraman, Pavithra LK
Abstract: Underwater images suffer from severe degradations, including color distortions, reduced visibility, and loss of structural details due to wavelength-dependent attenuation and scattering. Existing enhancement methods primarily focus on spatial-domain processing, neglecting the frequency domain's potential to capture global color distributions and long-range dependencies. To address these limitations, we propose FUSION, a dual-domain deep learning framework that jointly leverages spatial and frequency domain information. FUSION independently processes each RGB channel through multi-scale convolutional kernels and adaptive attention mechanisms in the spatial domain, while simultaneously extracting global structural information via FFT-based frequency attention. A Frequency Guided Fusion module integrates complementary features from both domains, followed by inter-channel fusion and adaptive channel recalibration to ensure balanced color distributions. Extensive experiments on benchmark datasets (UIEB, EUVP, SUIM-E) demonstrate that FUSION achieves state-of-the-art performance, consistently outperforming existing methods in reconstruction fidelity (highest PSNR of 23.717 dB and SSIM of 0.883 on UIEB), perceptual quality (lowest LPIPS of 0.112 on UIEB), and visual enhancement metrics (best UIQM of 3.414 on UIEB), while requiring significantly fewer parameters (0.28M) and lower computational complexity, demonstrating its suitability for real-time underwater imaging applications.
Authors: Haosheng Li, Yuecong Xu, Junjie Chen, Kemi Ding
Abstract: 3D point cloud semantic segmentation technology has been widely used. However, in real-world scenarios, the environment is evolving. Thus, offline-trained segmentation models may lead to catastrophic forgetting of previously seen classes. Class-incremental learning (CIL) is designed to address the problem of catastrophic forgetting. While point clouds are common, we observe high similarity and unclear boundaries between different classes. Meanwhile, they are known to be imbalanced in class distribution. These lead to issues including misclassification between similar classes and the long-tail problem, which have not been adequately addressed in previous CIL methods. We thus propose ProtoGuard and PROPEL (Progressive Refinement Of PsEudo-Labels). In the base-class training phase, ProtoGuard maintains geometric and semantic prototypes for each class, which are combined into prototype features using an attention mechanism. In the novel-class training phase, PROPEL inherits the base feature extractor and classifier, guiding pseudo-label propagation and updates based on density distribution and semantic similarity. Extensive experiments show that our approach achieves remarkable results on both the S3DIS and ScanNet datasets, improving the mIoU of 3D point cloud segmentation by a maximum of 20.39% under the 5-step CIL scenario on S3DIS.
Authors: Haosheng Li, Junjie Chen, Yuecong Xu, Kemi Ding
Abstract: Unsupervised domain adaptation (UDA) frameworks have shown good generalization capabilities for 3D point cloud semantic segmentation models on clean data. However, existing works overlook adversarial robustness when the source domain itself is compromised. To comprehensively explore the robustness of the UDA frameworks, we first design a stealthy adversarial point cloud generation attack that can significantly contaminate datasets with only minor perturbations to the point cloud surface. Based on that, we propose a novel dataset, AdvSynLiDAR, comprising synthesized contaminated LiDAR point clouds. With the generated corrupted data, we further develop the Adversarial Adaptation Framework (AAF) as the countermeasure. Specifically, by extending the key point sensitive (KPS) loss towards the Robust Long-Tail loss (RLT loss) and utilizing a decoder branch, our approach enables the model to focus on long-tail classes during the pre-training phase and leverages high-confidence decoded point cloud information to restore point cloud structures during the adaptation phase. We evaluated our AAF method on the AdvSynLiDAR dataset, where the results demonstrate that our AAF method can mitigate performance degradation under source adversarial perturbations for UDA in the 3D point cloud segmentation application.
Authors: Junjie Chen, Yuecong Xu, Haosheng Li, Kemi Ding
Abstract: 3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving, enabling precise scene understanding through point-wise classification. While unsupervised domain adaptation (UDA) mitigates label scarcity in PCSS, existing methods critically overlook the inherent vulnerability to real-world perturbations (e.g., snow, fog, rain) and adversarial distortions. This work first identifies two intrinsic limitations that undermine current PCSS-UDA robustness: (a) unsupervised features overlap from unaligned boundaries in shared-class regions and (b) feature structure erosion caused by domain-invariant learning that suppresses target-specific patterns. To address the proposed problems, we propose a tripartite framework consisting of: 1) a robustness evaluation model quantifying resilience against adversarial attack/corruption types through robustness metrics; 2) an invertible attention alignment module (IAAM) enabling bidirectional domain mapping while preserving discriminative structure via attention-guided overlap suppression; and 3) a contrastive memory bank with quality-aware contrastive learning that progressively refines pseudo-labels with feature quality for more discriminative representations. Extensive experiments on SynLiDAR-to-SemanticPOSS adaptation demonstrate a maximum mIoU improvement of 14.3\% under adversarial attack.
Authors: Johannes Dollinger, Damien Robert, Elena Plekhanova, Lukas Drees, Jan Dirk Wegner
Abstract: Deep learning on climatic data holds potential for macroecological applications. However, its adoption remains limited among scientists outside the deep learning community due to storage, compute, and technical expertise barriers. To address this, we introduce Climplicit, a spatio-temporal geolocation encoder pretrained to generate implicit climatic representations anywhere on Earth. By bypassing the need to download raw climatic rasters and train feature extractors, our model uses x3500 less disk space and significantly reduces computational needs for downstream tasks. We evaluate our Climplicit embeddings on biomes classification, species distribution modeling, and plant trait regression. We find that single-layer probing our Climplicit embeddings consistently performs better or on par with training a model from scratch on downstream tasks and overall better than alternative geolocation encoding models.
Authors: Artem Zholus, Carl Doersch, Yi Yang, Skanda Koppula, Viorica Patraucean, Xu Owen He, Ignacio Rocco, Mehdi S. M. Sajjadi, Sarath Chandar, Ross Goroshin
Abstract: Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive biases and heuristics, limiting their generality and potential for scaling. To address these challenges, we present TAPNext, a new approach that casts TAP as sequential masked token decoding. Our model is causal, tracks in a purely online fashion, and removes tracking-specific inductive biases. This enables TAPNext to run with minimal latency, and removes the temporal windowing required by many existing state of art trackers. Despite its simplicity, TAPNext achieves a new state-of-the-art tracking performance among both online and offline trackers. Finally, we present evidence that many widely used tracking heuristics emerge naturally in TAPNext through end-to-end training. The TAPNext model and code can be found at https://tap-next.github.io/.
Authors: Abdulkareem Alsudais
Abstract: The primary objective of this paper is to investigate how a popular Text-to-Image (T2I) model represents people from 208 different nationalities when prompted to generate images of individuals performing typical activities. Two scenarios were developed, and images were generated based on input prompts that specified nationalities. The results show that in one scenario, the majority of images, and in the other, a substantial portion, depict individuals wearing traditional attire. This suggests that the model emphasizes such characteristics even when they are impractical for the given activity. A statistically significant relationship was observed between this representation pattern and the regions associated with the specified countries. This indicates that the issue disproportionately affects certain areas, particularly the Middle East & North Africa and Sub-Saharan Africa. A notable association with income groups was also found. CLIP was used to measure alignment scores between generated images and various prompts and captions. The findings indicate statistically significant higher scores for images featuring individuals in traditional attire in one scenario. The study also examined revised prompts (additional contextual information automatically added to the original input prompts) to assess their potential influence on how individuals are represented in the generated images, finding that the word "traditional" was commonly added to revised prompts. These findings provide valuable insights into how T2I models represent individuals from various countries and highlight potential areas for improvement in future models.
Authors: Songze Li, Tonghua Su, Xu-Yao Zhang, Qixing Xu, Zhongjie Wang
Abstract: Pre-trained model-based continual learning (PTMCL) has garnered growing attention, as it enables more rapid acquisition of new knowledge by leveraging the extensive foundational understanding inherent in pre-trained model (PTM). Most existing PTMCL methods use Parameter-Efficient Fine-Tuning (PEFT) to learn new knowledge while consolidating existing memory. However, they often face some challenges. A major challenge lies in the misalignment of classification heads, as the classification head of each task is trained within a distinct feature space, leading to inconsistent decision boundaries across tasks and, consequently, increased forgetting. Another critical limitation stems from the restricted feature-level knowledge accumulation, with feature learning typically restricted to the initial task only, which constrains the model's representation capabilities. To address these issues, we propose a method named DUal-level Knowledge Accumulation and Ensemble (DUKAE) that leverages both feature-level and decision-level knowledge accumulation by aligning classification heads into a unified feature space through Gaussian distribution sampling and introducing an adaptive expertise ensemble to fuse knowledge across feature subspaces. Extensive experiments on CIFAR-100, ImageNet-R, CUB-200, and Cars-196 datasets demonstrate the superior performance of our approach.
Authors: Xinhao Li, Ziang Yan, Desen Meng, Lu Dong, Xiangyu Zeng, Yinan He, Yali Wang, Yu Qiao, Yi Wang, Limin Wang
Abstract: Recent advancements in reinforcement learning have significantly advanced the reasoning capabilities of multimodal large language models (MLLMs). While approaches such as Group Relative Policy Optimization (GRPO) and rule-based reward mechanisms demonstrate promise in text and image domains, their application to video understanding remains limited. This paper presents a systematic exploration of Reinforcement Fine-Tuning (RFT) with GRPO for video MLLMs, aiming to enhance spatio-temporal perception while maintaining general capabilities. Our experiments reveal that RFT is highly data-efficient for task-specific improvements. Through multi-task RFT on spatio-temporal perception objectives with limited samples, we develop VideoChat-R1, a powerful video MLLM that achieves state-of-the-art performance on spatio-temporal perception tasks without sacrificing chat ability, while exhibiting emerging spatio-temporal reasoning abilities. Compared to Qwen2.5-VL-7B, VideoChat-R1 boosts performance several-fold in tasks like temporal grounding (+31.8) and object tracking (+31.2). Additionally, it significantly improves on general QA benchmarks such as VideoMME (+0.9), MVBench (+1.0), and Perception Test (+0.9). Our findings underscore the potential of RFT for specialized task enhancement of Video MLLMs. We hope our work offers valuable insights for future RL research in video MLLMs.
Authors: Ran Zhang, Xuanhua He, Ke Cao, Liu Liu, Li Zhang, Man Zhou, Jie Zhang
Abstract: Multi-modality image fusion aims to synthesize a single, comprehensive image from multiple source inputs. Traditional approaches, such as CNNs and GANs, offer efficiency but struggle to handle low-quality or complex inputs. Recent advances in text-guided methods leverage large model priors to overcome these limitations, but at the cost of significant computational overhead, both in memory and inference time. To address this challenge, we propose a novel framework for distilling large model priors, eliminating the need for text guidance during inference while dramatically reducing model size. Our framework utilizes a teacher-student architecture, where the teacher network incorporates large model priors and transfers this knowledge to a smaller student network via a tailored distillation process. Additionally, we introduce spatial-channel cross-fusion module to enhance the model's ability to leverage textual priors across both spatial and channel dimensions. Our method achieves a favorable trade-off between computational efficiency and fusion quality. The distilled network, requiring only 10% of the parameters and inference time of the teacher network, retains 90% of its performance and outperforms existing SOTA methods. Extensive experiments demonstrate the effectiveness of our approach. The implementation will be made publicly available as an open-source resource.
Authors: Chendi Lin, Heshan Liu, Qunshu Lin, Zachary Bright, Shitao Tang, Yihui He, Minghao Liu, Ling Zhu, Cindy Le
Abstract: This paper presents Objaverse++, a curated subset of Objaverse enhanced with detailed attribute annotations by human experts. Recent advances in 3D content generation have been driven by large-scale datasets such as Objaverse, which contains over 800,000 3D objects collected from the Internet. Although Objaverse represents the largest available 3D asset collection, its utility is limited by the predominance of low-quality models. To address this limitation, we manually annotate 10,000 3D objects with detailed attributes, including aesthetic quality scores, texture color classifications, multi-object composition flags, transparency characteristics, etc. Then, we trained a neural network capable of annotating the tags for the rest of the Objaverse dataset. Through experiments and a user study on generation results, we demonstrate that models pre-trained on our quality-focused subset achieve better performance than those trained on the larger dataset of Objaverse in image-to-3D generation tasks. In addition, by comparing multiple subsets of training data filtered by our tags, our results show that the higher the data quality, the faster the training loss converges. These findings suggest that careful curation and rich annotation can compensate for the raw dataset size, potentially offering a more efficient path to develop 3D generative models. We release our enhanced dataset of approximately 500,000 curated 3D models to facilitate further research on various downstream tasks in 3D computer vision. In the near future, we aim to extend our annotations to cover the entire Objaverse dataset.
Authors: Darian Toma\v{s}evi\'c, Fadi Boutros, Chenhao Lin, Naser Damer, Vitomir \v{S}truc, Peter Peer
Abstract: Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, state-of-the-art generative models typically rely on conditioning and fine-tuning of powerful pretrained diffusion models to facilitate the synthesis of realistic images of a desired identity. Yet, these models often do not consider the identity of subjects during training, leading to poor consistency between generated and intended identities. In contrast, methods that employ identity-based training objectives tend to overfit on various aspects of the identity, and in turn, lower the diversity of images that can be generated. To address these issues, we present in this paper a novel generative diffusion-based framework, called ID-Booth. ID-Booth consists of a denoising network responsible for data generation, a variational auto-encoder for mapping images to and from a lower-dimensional latent space and a text encoder that allows for prompt-based control over the generation procedure. The framework utilizes a novel triplet identity training objective and enables identity-consistent image generation while retaining the synthesis capabilities of pretrained diffusion models. Experiments with a state-of-the-art latent diffusion model and diverse prompts reveal that our method facilitates better intra-identity consistency and inter-identity separability than competing methods, while achieving higher image diversity. In turn, the produced data allows for effective augmentation of small-scale datasets and training of better-performing recognition models in a privacy-preserving manner. The source code for the ID-Booth framework is publicly available at https://github.com/dariant/ID-Booth.
Authors: Haozhan Shen, Peng Liu, Jingcheng Li, Chunxin Fang, Yibo Ma, Jiajia Liao, Qiaoli Shen, Zilun Zhang, Kangjia Zhao, Qianqian Zhang, Ruochen Xu, Tiancheng Zhao
Abstract: Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward formulation, which leverages tasks with deterministic ground-truth answers to enable precise and stable reward computation. In the visual domain, we similarly observe that a wide range of visual understanding tasks are inherently equipped with well-defined ground-truth annotations. This property makes them naturally compatible with rule-based reward mechanisms. Motivated by this observation, we investigate the extension of R1-style reinforcement learning to Vision-Language Models (VLMs), aiming to enhance their visual reasoning capabilities. To this end, we develop VLM-R1, a dedicated framework designed to harness RL for improving VLMs' performance on general vision-language tasks. Using this framework, we further explore the feasibility of applying RL to visual domain. Experimental results indicate that the RL-based model not only delivers competitive performance on visual understanding tasks but also surpasses Supervised Fine-Tuning (SFT) in generalization ability. Furthermore, we conduct comprehensive ablation studies that uncover a series of noteworthy insights, including the presence of reward hacking in object detection, the emergence of the "OD aha moment", the impact of training data quality, and the scaling behavior of RL across different model sizes. Through these analyses, we aim to deepen the understanding of how reinforcement learning enhances the capabilities of vision-language models, and we hope our findings and open-source contributions will support continued progress in the vision-language RL community. Our code and model are available at https://github.com/om-ai-lab/VLM-R1
Authors: Mingzhi Pei, Xu Cao, Xiangyi Wang, Heng Guo, Zhanyu Ma
Abstract: Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, PMNI simultaneously recovers accurate camera poses and high-fidelity surface geometry. Experimental results on synthetic and real-world datasets show that our method achieves state-of-the-art performance in the reconstruction of reflective surfaces, even without reliable initial camera poses.
Authors: Low Jian He, Harry Walsh, Ozge Mercanoglu Sincan, Richard Bowden
Abstract: This work tackles the challenge of continuous sign language segmentation, a key task with huge implications for sign language translation and data annotation. We propose a transformer-based architecture that models the temporal dynamics of signing and frames segmentation as a sequence labeling problem using the Begin-In-Out (BIO) tagging scheme. Our method leverages the HaMeR hand features, and is complemented with 3D Angles. Extensive experiments show that our model achieves state-of-the-art results on the DGS Corpus, while our features surpass prior benchmarks on BSLCorpus.
Authors: Boyang Deng, Songyou Peng, Kyle Genova, Gordon Wetzstein, Noah Snavely, Leonidas Guibas, Thomas Funkhouser
Abstract: We present a system using Multimodal LLMs (MLLMs) to analyze a large database with tens of millions of images captured at different times, with the aim of discovering patterns in temporal changes. Specifically, we aim to capture frequent co-occurring changes ("trends") across a city over a certain period. Unlike previous visual analyses, our analysis answers open-ended queries (e.g., "what are the frequent types of changes in the city?") without any predetermined target subjects or training labels. These properties cast prior learning-based or unsupervised visual analysis tools unsuitable. We identify MLLMs as a novel tool for their open-ended semantic understanding capabilities. Yet, our datasets are four orders of magnitude too large for an MLLM to ingest as context. So we introduce a bottom-up procedure that decomposes the massive visual analysis problem into more tractable sub-problems. We carefully design MLLM-based solutions to each sub-problem. During experiments and ablation studies with our system, we find it significantly outperforms baselines and is able to discover interesting trends from images captured in large cities (e.g., "addition of outdoor dining,", "overpass was painted blue," etc.). See more results and interactive demos at https://boyangdeng.com/visual-chronicles.
Authors: M Quamer Nasim, Tannistha Maiti, Ayush Srivastava, Tarry Singh, Jie Mei
Abstract: Deep neural networks (DNNs) can learn accurately from large quantities of labeled input data, but often fail to do so when labelled data are scarce. DNNs sometimes fail to generalize ontest data sampled from different input distributions. Unsupervised Deep Domain Adaptation (DDA)techniques have been proven useful when no labels are available, and when distribution shifts are observed in the target domain (TD). In the present study, experiments are performed on seismic images of the F3 block 3D dataset from offshore Netherlands (source domain; SD) and Penobscot 3D survey data from Canada (target domain; TD). Three geological classes from SD and TD that have similar reflection patterns are considered. A deep neural network architecture named EarthAdaptNet (EAN) is proposed to semantically segment the seismic images when few classes have data scarcity, and we use a transposed residual unit to replace the traditional dilated convolution in the decoder block. The EAN achieved a pixel-level accuracy >84% and an accuracy of ~70% for the minority classes, showing improved performance compared to existing architectures. In addition, we introduce the CORAL (Correlation Alignment) method to the EAN to create an unsupervised deep domain adaptation network (EAN-DDA) for the classification of seismic reflections from F3 and Penobscot, to demonstrate possible approaches when labelled data are unavailable. Maximum class accuracy achieved was ~99% for class 2 of Penobscot, with an overall accuracy>50%. Taken together, the EAN-DDA has the potential to classify target domain seismic facies classes with high accuracy.
Authors: Yang Li, Leo Yan Li-Han, Hua Tian
Abstract: Objective: The clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles -- Center-Edge (CE), Tonnis, and Sharp angles -- from pelvic radiographs, a process that is time-consuming and susceptible to variability. This study aims to develop an automated system that integrates these measurements to enhance the accuracy and consistency of DDH diagnosis. Methods and procedures: We developed an end-to-end deep learning model for keypoint detection that accurately identifies eight anatomical keypoints from pelvic radiographs, enabling the automated calculation of CE, Tonnis, and Sharp angles. To support the diagnostic decision, we introduced a novel data-driven scoring system that combines the information from all three angles into a comprehensive and explainable diagnostic output. Results: The system demonstrated superior consistency in angle measurements compared to a cohort of eight moderately experienced orthopedists. The intraclass correlation coefficients for the CE, Tonnis, and Sharp angles were 0.957 (95% CI: 0.952--0.962), 0.942 (95% CI: 0.937--0.947), and 0.966 (95% CI: 0.964--0.968), respectively. The system achieved a diagnostic F1 score of 0.863 (95% CI: 0.851--0.876), significantly outperforming the orthopedist group (0.777, 95% CI: 0.737--0.817, p = 0.005), as well as using clinical diagnostic criteria for each angle individually (p<0.001). Conclusion: The proposed system provides reliable and consistent automated measurements of radiological angles and an explainable diagnostic output for DDH, outperforming moderately experienced clinicians. Clinical impact: This AI-powered solution reduces the variability and potential errors of manual measurements, offering clinicians a more consistent and interpretable tool for DDH diagnosis.
Authors: Danielle L. Ferreira, Connor Lau, Zaynaf Salaymang, Rima Arnaout
Abstract: Segmentation and measurement of cardiac chambers is critical in cardiac ultrasound but is laborious and poorly reproducible. Neural networks can assist, but supervised approaches require the same laborious manual annotations. We built a pipeline for self-supervised (no manual labels) segmentation combining computer vision, clinical domain knowledge, and deep learning. We trained on 450 echocardiograms (93,000 images) and tested on 8,393 echocardiograms (4,476,266 images; mean 61 years, 51% female), using the resulting segmentations to calculate biometrics. We also tested against external images from an additional 10,030 patients with available manual tracings of the left ventricle. r2 between clinically measured and pipeline-predicted measurements were similar to reported inter-clinician variation and comparable to supervised learning across several different measurements (r2 0.56-0.84). Average accuracy for detecting abnormal chamber size and function was 0.85 (range 0.71-0.97) compared to clinical measurements. A subset of test echocardiograms (n=553) had corresponding cardiac MRIs, where MRI is the gold standard. Correlation between pipeline and MRI measurements was similar to that between clinical echocardiogram and MRI. Finally, the pipeline accurately segments the left ventricle with an average Dice score of 0.89 (95% CI [0.89]) in the external, manually labeled dataset. Our results demonstrate a manual-label free, clinically valid, and highly scalable method for segmentation from ultrasound, a noisy but globally important imaging modality.
Authors: David Stutz, Ali Taylan Cemgil, Abhijit Guha Roy, Tatiana Matejovicova, Melih Barsbey, Patricia Strachan, Mike Schaekermann, Jan Freyberg, Rajeev Rikhye, Beverly Freeman, Javier Perez Matos, Umesh Telang, Dale R. Webster, Yuan Liu, Greg S. Corrado, Yossi Matias, Pushmeet Kohli, Yun Liu, Arnaud Doucet, Alan Karthikesalingam
Abstract: For safety, medical AI systems undergo thorough evaluations before deployment, validating their predictions against a ground truth which is assumed to be fixed and certain. However, this ground truth is often curated in the form of differential diagnoses. While a single differential diagnosis reflects the uncertainty in one expert assessment, multiple experts introduce another layer of uncertainty through disagreement. Both forms of uncertainty are ignored in standard evaluation which aggregates these differential diagnoses to a single label. In this paper, we show that ignoring uncertainty leads to overly optimistic estimates of model performance, therefore underestimating risk associated with particular diagnostic decisions. To this end, we propose a statistical aggregation approach, where we infer a distribution on probabilities of underlying medical condition candidates themselves, based on observed annotations. This formulation naturally accounts for the potential disagreements between different experts, as well as uncertainty stemming from individual differential diagnoses, capturing the entire ground truth uncertainty. Our approach boils down to generating multiple samples of medical condition probabilities, then evaluating and averaging performance metrics based on these sampled probabilities. In skin condition classification, we find that a large portion of the dataset exhibits significant ground truth uncertainty and standard evaluation severely over-estimates performance without providing uncertainty estimates. In contrast, our framework provides uncertainty estimates on common metrics of interest such as top-k accuracy and average overlap, showing that performance can change multiple percentage points. We conclude that, while assuming a crisp ground truth can be acceptable for many AI applications, a more nuanced evaluation protocol should be utilized in medical diagnosis.
Authors: Juan Terven, Diana M. Cordova-Esparza, Alfonso Ramirez-Pedraza, Edgar A. Chavez-Urbiola, Julio A. Romero-Gonzalez
Abstract: This paper presents a comprehensive review of loss functions and performance metrics in deep learning, highlighting key developments and practical insights across diverse application areas. We begin by outlining fundamental considerations in classic tasks such as regression and classification, then extend our analysis to specialized domains like computer vision and natural language processing including retrieval-augmented generation. In each setting, we systematically examine how different loss functions and evaluation metrics can be paired to address task-specific challenges such as class imbalance, outliers, and sequence-level optimization. Key contributions of this work include: (1) a unified framework for understanding how losses and metrics align with different learning objectives, (2) an in-depth discussion of multi-loss setups that balance competing goals, and (3) new insights into specialized metrics used to evaluate modern applications like retrieval-augmented generation, where faithfulness and context relevance are pivotal. Along the way, we highlight best practices for selecting or combining losses and metrics based on empirical behaviors and domain constraints. Finally, we identify open problems and promising directions, including the automation of loss-function search and the development of robust, interpretable evaluation measures for increasingly complex deep learning tasks. Our review aims to equip researchers and practitioners with clearer guidance in designing effective training pipelines and reliable model assessments for a wide spectrum of real-world applications.
Authors: Kaichen Zhou, Lanqing Hong, Xinhai Chang, Yingji Zhong, Enze Xie, Hao Dong, Zhihao Li, Yongxin Yang, Zhenguo Li, Wei Zhang
Abstract: A key challenge in fine-grained 3D-based interactive editing is the absence of an efficient representation that balances diverse modifications with high-quality view synthesis under a given memory constraint. While 3D meshes provide robustness for various modifications, they often yield lower-quality view synthesis compared to 3D Gaussian Splatting, which, in turn, suffers from instability during extensive editing. A straightforward combination of these two representations results in suboptimal performance and fails to meet memory constraints. In this paper, we introduce SplatMesh, a novel fine-grained interactive 3D segmentation and editing algorithm that integrates 3D Gaussian Splat with a precomputed mesh and could adjust the memory request based on the requirement. Specifically, given a mesh, \method simplifies it while considering both color and shape, ensuring it meets memory constraints. Then, SplatMesh aligns Gaussian splats with the simplified mesh by treating each triangle as a new reference point. By segmenting and editing the simplified mesh, we can effectively edit the Gaussian splats as well, which will lead to extensive experiments on real and synthetic datasets, coupled with illustrative visual examples, highlighting the superiority of our approach in terms of representation quality and editing performance. Code of our paper can be found here: https://github.com/kaichen-z/SplatMesh.
Authors: Alvaro Gomariz, Yusuke Kikuchi, Yun Yvonna Li, Thomas Albrecht, Andreas Maunz, Daniela Ferrara, Huanxiang Lu, Orcun Goksel
Abstract: Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a versatile framework designed to segment images across different domains, employing supervised and contrastive learning simultaneously to effectively learn from both labeled and unlabeled data. We demonstrate the superior performance of SegCLR through a comprehensive evaluation involving three diverse clinical datasets of 3D retinal Optical Coherence Tomography (OCT) images, for the slice-wise segmentation of fluids with various network configurations and verification across 10 different network initializations. In an unsupervised domain adaptation context, SegCLR achieves results on par with a supervised upper-bound model trained on the intended target domain. Notably, we discover that the segmentation performance of SegCLR framework is marginally impacted by the abundance of unlabeled data from the target domain, thereby we also propose an effective domain generalization extension of SegCLR, known also as zero-shot domain adaptation, which eliminates the need for any target domain information. This shows that our proposed addition of contrastive loss in standard supervised training for segmentation leads to superior models, inherently more generalizable to both in- and out-of-domain test data. We additionally propose a pragmatic solution for SegCLR deployment in realistic scenarios with multiple domains containing labeled data. Accordingly, our framework pushes the boundaries of deep-learning based segmentation in multi-domain applications, regardless of data availability - labeled, unlabeled, or nonexistent.
Authors: Mahmoud Ghorbel, Halima Bouzidi, Ioan Marius Bilasco, Ihsen Alouani
Abstract: Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services. Prior works consider model hijacking as a training time attack, whereby an adversary requires full access to the ML model training. In this paper, we consider a stronger threat model for an inference-time hijacking attack, where the adversary has no access to the training phase of the victim model. Our intuition is that ML models, which are typically over-parameterized, might have the capacity to (unintentionally) learn more than the intended task they are trained for. We propose SnatchML, a new training-free model hijacking attack, that leverages the extra capacity learnt by the victim model to infer different tasks that can be semantically related or unrelated to the original one. Our results on models deployed on AWS Sagemaker showed that SnatchML can deliver high accuracy on hijacking tasks. Interestingly, while all previous approaches are limited by the number of classes in the benign task, SnatchML can hijack models for tasks that contain more classes than the original. We explore different methods to mitigate this risk; We propose meta-unlearning, which is designed to help the model unlearn a potentially malicious task while training for the original task. We also provide insights on over-parametrization as a possible inherent factor that facilitates model hijacking, and accordingly, we propose a compression-based countermeasure to counteract this attack. We believe this work offers a previously overlooked perspective on model hijacking attacks, presenting a stronger threat model and higher applicability in real-world contexts.
Authors: Md Hasan Shahriar, Ning Wang, Naren Ramakrishnan, Y. Thomas Hou, Wenjing Lou
Abstract: The exponential adoption of machine learning (ML) is propelling the world into a future of distributed and intelligent automation and data-driven solutions. However, the proliferation of malicious data manipulation attacks against ML, namely adversarial and backdoor attacks, jeopardizes its reliability in safety-critical applications. The existing detection methods are attack-specific and built upon some strong assumptions, limiting them in diverse practical scenarios. Thus, motivated by the need for a more robust, unified, and attack-agnostic defense mechanism, we first investigate the shared traits of adversarial and backdoor attacks. Based on our observation, we propose NoiSec, a reconstruction-based intrusion detection system that brings a novel perspective by shifting focus from the reconstructed input to the reconstruction noise itself, which is the foundational root cause of such malicious data alterations. NoiSec disentangles the noise from the test input, extracts the underlying features from the noise, and leverages them to recognize systematic malicious manipulation. Our comprehensive evaluation of NoiSec demonstrates its high effectiveness across various datasets, including basic objects, natural scenes, traffic signs, medical images, spectrogram-based audio data, and wireless sensing against five state-of-the-art adversarial attacks and three backdoor attacks under challenging evaluation conditions. NoiSec demonstrates strong detection performance in both white-box and black-box adversarial attack scenarios, significantly outperforming the closest baseline models, particularly in an adaptive attack setting. We will provide the code for future baseline comparison. Our code and artifacts are publicly available at https://github.com/shahriar0651/NoiSec.
Authors: Jiabo Ma, Zhengrui Guo, Fengtao Zhou, Yihui Wang, Yingxue Xu, Jinbang Li, Fang Yan, Yu Cai, Zhengjie Zhu, Cheng Jin, Yi Lin, Xinrui Jiang, Chenglong Zhao, Danyi Li, Anjia Han, Zhenhui Li, Ronald Cheong Kin Chan, Jiguang Wang, Peng Fei, Kwang-Ting Cheng, Shaoting Zhang, Li Liang, Hao Chen
Abstract: Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath). The generalization ability of foundation models is crucial for the success in various downstream clinical tasks. However, current foundation models have only been evaluated on a limited type and number of tasks, leaving their generalization ability and overall performance unclear. To address this gap, we established a most comprehensive benchmark to evaluate the performance of off-the-shelf foundation models across six distinct clinical task types, encompassing a total of 72 specific tasks, including slide-level classification, survival prediction, ROI-tissue classification, ROI retrieval, visual question answering, and report generation. Our findings reveal that existing foundation models excel at certain task types but struggle to effectively handle the full breadth of clinical tasks. To improve the generalization of pathology foundation models, we propose a unified knowledge distillation framework consisting of both expert and self-knowledge distillation, where the former allows the model to learn from the knowledge of multiple expert models, while the latter leverages self-distillation to enable image representation learning via local-global alignment. Based on this framework, we curated a dataset of 96,000 whole slide images (WSIs) and developed a Generalizable Pathology Foundation Model (GPFM). This advanced model was trained on a substantial dataset comprising 190 million images extracted from approximately 72,000 publicly available slides, encompassing 34 major tissue types. Evaluated on the established benchmark, GPFM achieves an impressive average rank of 1.6, with 42 tasks ranked 1st, while the second-best model, UNI, attains an average rank of 3.7, with only 6 tasks ranked 1st.
Authors: Kanghyun Choi, Hye Yoon Lee, Dain Kwon, SunJong Park, Kyuyeun Kim, Noseong Park, Jonghyun Choi, Jinho Lee
Abstract: Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for vision transformer (ViT) architectures, they fail to achieve efficacy in low-bit settings. Examining the existing methods, we observe that their synthetic data produce misaligned attention maps, while those of the real samples are highly aligned. From this observation, we find that aligning attention maps of synthetic data helps improve the overall performance of quantized ViTs. Motivated by this finding, we devise MimiQ, a novel DFQ method designed for ViTs that enhances inter-head attention similarity. First, we generate synthetic data by aligning head-wise attention outputs from each spatial query patch. Then, we align the attention maps of the quantized network to those of the full-precision teacher by applying head-wise structural attention distillation. The experimental results show that the proposed method significantly outperforms baselines, setting a new state-of-the-art for ViT-DFQ. This paper is an extended version of our work published in the proceedings of AAAI 2025, including additional supplementary material.
Authors: Sina Rismanchian, Yasaman Razeghi, Sameer Singh, Shayan Doroudi
Abstract: Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust evaluation methods to assess these capabilities. We introduce \Turtle, a benchmark designed to evaluate LMMs' capacity to interpret geometric patterns -- given visual examples, textual instructions, or both -- and generate precise code outputs. Inspired by turtle geometry, a notion used to teach children foundational coding and geometric concepts, TurtleBench features tasks with patterned shapes that have underlying algorithmic logic. Our evaluation reveals that leading LMMs struggle significantly with these tasks, with GPT-4o achieving only 19\% accuracy on the simplest tasks and few-shot prompting only marginally improves their performance ($<2\%$). \Turtle highlights the gap between human and AI performance in intuitive and visual geometrical understanding, setting the stage for future research in this area. \Turtle stands as one of the few benchmarks to evaluate the integration of visual understanding and code generation capabilities in LMMs, setting the stage for future research. Code and Dataset for this paper is provided here: \href{https://github.com/sinaris76/TurtleBench}{https://github.com/sinaris76/TurtleBench}
URLs: https://github.com/sinaris76/TurtleBench, https://github.com/sinaris76/TurtleBench
Authors: Zhi Qi, Shihong Yuan, Yulin Yuan, Linling Kuang, Yoshiyuki Kabashima, Xiangming Meng
Abstract: Diffusion models have shown strong performances in solving inverse problems through posterior sampling while they suffer from errors during earlier steps. To mitigate this issue, several Decoupled Posterior Sampling methods have been recently proposed. However, the reverse process in these methods ignores measurement information, leading to errors that impede effective optimization in subsequent steps. To solve this problem, we propose Guided Decoupled Posterior Sampling (GDPS) by integrating a data consistency constraint in the reverse process. The constraint performs a smoother transition within the optimization process, facilitating a more effective convergence toward the target distribution. Furthermore, we extend our method to latent diffusion models and Tweedie's formula, demonstrating its scalability. We evaluate GDPS on the FFHQ and ImageNet datasets across various linear and nonlinear tasks under both standard and challenging conditions. Experimental results demonstrate that GDPS achieves state-of-the-art performance, improving accuracy over existing methods.
Authors: Kehan Chen, Dong An, Yan Huang, Rongtao Xu, Yifei Su, Yonggen Ling, Ian Reid, Liang Wang
Abstract: We address the task of Vision-Language Navigation in Continuous Environments (VLN-CE) under the zero-shot setting. Zero-shot VLN-CE is particularly challenging due to the absence of expert demonstrations for training and minimal environment structural prior to guide navigation. To confront these challenges, we propose a Constraint-Aware Navigator (CA-Nav), which reframes zero-shot VLN-CE as a sequential, constraint-aware sub-instruction completion process. CA-Nav continuously translates sub-instructions into navigation plans using two core modules: the Constraint-Aware Sub-instruction Manager (CSM) and the Constraint-Aware Value Mapper (CVM). CSM defines the completion criteria for decomposed sub-instructions as constraints and tracks navigation progress by switching sub-instructions in a constraint-aware manner. CVM, guided by CSM's constraints, generates a value map on the fly and refines it using superpixel clustering to improve navigation stability. CA-Nav achieves the state-of-the-art performance on two VLN-CE benchmarks, surpassing the previous best method by 12 percent and 13 percent in Success Rate on the validation unseen splits of R2R-CE and RxR-CE, respectively. Moreover, CA-Nav demonstrates its effectiveness in real-world robot deployments across various indoor scenes and instructions.
Authors: Zhibin Wang, Yanxin Cai, Jiayi Zhou, Yangming Zhang, Tianyu Li, Wei Li, Xun Liu, Guoqing Wang, Yang Yang
Abstract: The growing field of remote sensing faces a challenge: the ever-increasing size and volume of imagery data are exceeding the storage and transmission capabilities of satellite platforms. Efficient compression of remote sensing imagery is a critical solution to alleviate these burdens on satellites. However, existing compression methods are often too computationally expensive for satellites. With the continued advancement of compressed sensing theory, single-pixel imaging emerges as a powerful tool that brings new possibilities for on-orbit image compression. However, it still suffers from prolonged imaging times and the inability to perform high-resolution imaging, hindering its practical application. This paper advances the study of compressed sensing in remote sensing image compression, proposing Block Modulated Imaging (BMI). By requiring only a single exposure, BMI significantly enhances imaging acquisition speeds. Additionally, BMI obviates the need for digital micromirror devices and surpasses limitations in image resolution. Furthermore, we propose a novel decoding network specifically designed to reconstruct images compressed under the BMI framework. Leveraging the gated 3D convolutions and promoting efficient information flow across stages through a Two-Way Cross-Attention module, our decoding network exhibits demonstrably superior reconstruction performance. Extensive experiments conducted on multiple renowned remote sensing datasets unequivocally demonstrate the efficacy of our proposed method. To further validate its practical applicability, we developed and tested a prototype of the BMI-based camera, which has shown promising potential for on-orbit image compression. The code is available at https://github.com/Johnathan218/BMNet.
Authors: Ethan Wilson, Naveen Sendhilnathan, Charlie S. Burlingham, Yusuf Mansour, Robert Cavin, Sai Deep Tetali, Ajoy Savio Fernandes, Michael J. Proulx
Abstract: Advanced multimodal AI agents can now collaborate with users to solve challenges in the world. Yet, these emerging contextual AI systems rely on explicit communication channels between the user and system. We hypothesize that implicit communication of the user's interests and intent would reduce friction and improve user experience when collaborating with AI agents. In this work, we explore the potential of wearable eye tracking to convey signals about user attention. We measure the eye tracking signal quality requirements to effectively map gaze traces to physical objects, then conduct experiments that provide visual scanpath history as additional context when querying vision language models. Our results show that eye tracking provides high value as a user attention signal and can convey important context about the user's current task and interests, improving understanding of contextual AI agents.
Authors: Lei Zhao, Linfeng Feng, Dongxu Ge, Rujin Chen, Fangqiu Yi, Chi Zhang, Xiao-Lei Zhang, Xuelong Li
Abstract: With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many are confined to a single task and small-scale datasets. To address these limitations, we first propose UniForm, a unified multi-task diffusion transformer that jointly generates audio and visual modalities in a shared latent space. A single diffusion process models both audio and video, capturing the inherent correlations between sound and vision. Second, we introduce task-specific noise schemes and task tokens, enabling a single model to support multiple tasks, including text-to-audio-video, audio-to-video, and video-to-audio generation. Furthermore, by leveraging large language models and a large-scale text-audio-video combined dataset, UniForm achieves greater generative diversity than prior approaches. Extensive experiments show that UniForm achieves the state-of-the-art performance across audio-video generation tasks, producing content that is both well-aligned and close to real-world data distributions. Our demos are available at https://uniform-t2av.github.io/.
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: Minjoo Lim, Bogyeong Kang, Tae-Eui Kam
Abstract: Multi-modal magnetic resonance imaging (MRI) is essential for providing complementary information about brain anatomy and pathology, leading to more accurate diagnoses. However, obtaining high-quality multi-modal MRI in a clinical setting is difficult due to factors such as time constraints, high costs, and patient movement artifacts. To overcome this difficulty, there is increasing interest in developing generative models that can synthesize missing target modality images from the available source ones. Therefore, our team, PLAVE, design a generative model for missing MRI that integrates multi-modal contrastive learning with a focus on critical tumor regions. Specifically, we integrate multi-modal contrastive learning, tailored for multiple source modalities, and enhance its effectiveness by selecting features based on entropy during the contrastive learning process. Additionally, our network not only generates the missing target modality images but also predicts segmentation outputs, simultaneously. This approach improves the generator's capability to precisely generate tumor regions, ultimately improving performance in downstream segmentation tasks. By leveraging a combination of contrastive, segmentation, and additional self-representation losses, our model effectively reflects target-specific information and generate high-quality target images. Consequently, our results in the Brain MR Image Synthesis challenge demonstrate that the proposed model excelled in generating the missing modality.
Authors: Francesco Iodice, Elena De Momi, Arash Ajoudani
Abstract: The integration of collaborative robots into industrial environments has improved productivity, but has also highlighted significant challenges related to operator safety and ergonomics. This paper proposes an innovative framework that integrates advanced visual perception, continuous ergonomic monitoring, and adaptive Behaviour Tree decision-making to overcome the limitations of traditional methods that typically operate as isolated components. Our approach synthesizes deep learning models, advanced tracking algorithms, and dynamic ergonomic assessments into a modular, scalable, and adaptive system. Experimental validation demonstrates the framework's superiority over existing solutions across multiple dimensions: the visual perception module outperformed previous detection models with 72.4% mAP@50:95; the system achieved high accuracy in recognizing operator intentions (92.5%); it promptly classified ergonomic risks with minimal latency (0.57 seconds); and it dynamically managed robotic interventions with exceptionally responsive decision-making capabilities (0.07 seconds), representing a 56% improvement over benchmark systems. This comprehensive solution provides a robust platform for enhancing human-robot collaboration in industrial environments by prioritizing ergonomic safety, operational efficiency, and real-time adaptability.
Authors: Zhenxin Zheng, Zhenjie Zheng
Abstract: Curse of Dimensionality is an unavoidable challenge in statistical probability models, yet diffusion models seem to overcome this limitation, achieving impressive results in high-dimensional data generation. Diffusion models assume that they can learn the statistical properties of the underlying probability distribution, enabling sampling from this distribution to generate realistic samples. But is this really how they work? To address this question, this paper conducts a detailed analysis of the objective function and inference methods of diffusion models, leading to several important conclusions that help answer the above question: 1) In high-dimensional sparse scenarios, the target of the objective function fitting degrades from a weighted sum of multiple samples to a single sample. 2) The mainstream inference methods can all be represented within a simple unified framework, without requiring statistical concepts such as Markov chains and SDE, while aligning with the degraded objective function. 3) Guided by this simple framework, more efficient inference methods can be discovered.
Authors: Matthieu Terris, Samuel Hurault, Maxime Song, Julian Tachella
Abstract: Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods, that leverage pretrained denoisers, and unrolled architectures that are trained end-to-end for specific imaging problems. Iterative methods in the first class are computationally costly and often provide suboptimal reconstruction performance, whereas unrolled architectures are generally specific to a single inverse problem and require expensive training. In this work, we propose a novel non-iterative, lightweight architecture that incorporates knowledge about the forward operator (acquisition physics and noise parameters) without relying on unrolling. Our model is trained to solve a wide range of inverse problems beyond denoising, including deblurring, magnetic resonance imaging, computed tomography, inpainting, and super-resolution. The proposed model can be easily adapted to unseen inverse problems or datasets with a few fine-tuning steps (up to a few images) in a self-supervised way, without ground-truth references. Throughout a series of experiments, we demonstrate state-of-the-art performance from medical imaging to low-photon imaging and microscopy.
Authors: Tatsuro Sakai, Kanji Tanaka, Jonathan Tay Yu Liang, Muhammad Adil Luqman, Daiki Iwata
Abstract: In robot vision, thermal cameras hold great potential for recognizing humans even in complete darkness. However, their application to multi-person tracking (MPT) has been limited due to data scarcity and the inherent difficulty of distinguishing individuals. In this study, we propose a cooperative MPT system that utilizes co-located RGB and thermal cameras, where pseudo-annotations (bounding boxes and person IDs) are used to train both RGB and thermal trackers. Evaluation experiments demonstrate that the thermal tracker performs robustly in both bright and dark environments. Moreover, the results suggest that a tracker-switching strategy -- guided by a binary brightness classifier -- is more effective for information integration than a tracker-fusion approach. As an application example, we present an image change pattern recognition (ICPR) method, the ``human-as-landmark,'' which combines two key properties: the thermal recognizability of humans in dark environments and the rich landmark characteristics -- appearance, geometry, and semantics -- of static objects (occluders). Whereas conventional SLAM focuses on mapping static landmarks in well-lit environments, the present study takes a first step toward a new Human-Only SLAM paradigm, ``DD-SLAM,'' which aims to map even dynamic landmarks in complete darkness.
Authors: Xuanwen Liang, Jiayu Chen, Eric Wai Ming Lee, Wei Xie
Abstract: Data-driven crowd simulation models offer advantages in enhancing the accuracy and realism of simulations, and improving their generalizability is essential for promoting application. Current data-driven approaches are primarily designed for a single scenario, with very few models validated across more than two scenarios. It is still an open question to develop data-driven crowd simulation models with strong generalizibility. We notice that the key to addressing this challenge lies in effectively and accurately capturing the core common influential features that govern pedestrians' navigation across diverse scenarios. Particularly, we believe that visual information is one of the most dominant influencing features. In light of this, this paper proposes a data-driven model incorporating a refined visual information extraction method and exit cues to enhance generalizability. The proposed model is examined on four common fundamental modules: bottleneck, corridor, corner and T-junction. The evaluation results demonstrate that our model performs excellently across these scenarios, aligning with pedestrian movement in real-world experiments, and significantly outperforms the classical knowledge-driven model. Furthermore, we introduce a modular approach to apply our proposed model in composite scenarios, and the results regarding trajectories and fundamental diagrams indicate that our simulations closely match real-world patterns in the composite scenario. The research outcomes can provide inspiration for the development of data-driven crowd simulation models with high generalizability and advance the application of data-driven approaches.This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.
Authors: Paul Borne--Pons (Adobe Research, ESA), Mikolaj Czerkawski (Asterisk Labs, ESA), Rosalie Martin (Adobe Research), Romain Rouffet (Adobe Research)
Abstract: Terrain modeling has traditionally relied on procedural techniques, which often require extensive domain expertise and handcrafted rules. In this paper, we present MESA - a novel data-centric alternative by training a diffusion model on global remote sensing data. This approach leverages large-scale geospatial information to generate high-quality terrain samples from text descriptions, showcasing a flexible and scalable solution for terrain generation. The model's capabilities are demonstrated through extensive experiments, highlighting its ability to generate realistic and diverse terrain landscapes. The dataset produced to support this work, the Major TOM Core-DEM extension dataset, is released openly as a comprehensive resource for global terrain data. The results suggest that data-driven models, trained on remote sensing data, can provide a powerful tool for realistic terrain modeling and generation.