Authors: Jinnan Chen, Chen Li, Gim Hee Lee
Abstract: We introduce DiHuR, a novel Diffusion-guided model for generalizable Human 3D Reconstruction and view synthesis from sparse, minimally overlapping images. While existing generalizable human radiance fields excel at novel view synthesis, they often struggle with comprehensive 3D reconstruction. Similarly, directly optimizing implicit Signed Distance Function (SDF) fields from sparse-view images typically yields poor results due to limited overlap. To enhance 3D reconstruction quality, we propose using learnable tokens associated with SMPL vertices to aggregate sparse view features and then to guide SDF prediction. These tokens learn a generalizable prior across different identities in training datasets, leveraging the consistent projection of SMPL vertices onto similar semantic areas across various human identities. This consistency enables effective knowledge transfer to unseen identities during inference. Recognizing SMPL's limitations in capturing clothing details, we incorporate a diffusion model as an additional prior to fill in missing information, particularly for complex clothing geometries. Our method integrates two key priors in a coherent manner: the prior from generalizable feed-forward models and the 2D diffusion prior, and it requires only multi-view image training, without 3D supervision. DiHuR demonstrates superior performance in both within-dataset and cross-dataset generalization settings, as validated on THuman, ZJU-MoCap, and HuMMan datasets compared to existing methods.
Authors: Yue Zhou, Mengcheng Lan, Xiang Li, Yiping Ke, Xue Jiang, Litong Feng, Wayne Zhang
Abstract: Remote sensing (RS) visual grounding aims to use natural language expression to locate specific objects (in the form of the bounding box or segmentation mask) in RS images, enhancing human interaction with intelligent RS interpretation systems. Early research in this area was primarily based on horizontal bounding boxes (HBBs), but as more diverse RS datasets have become available, tasks involving oriented bounding boxes (OBBs) and segmentation masks have emerged. In practical applications, different targets require different grounding types: HBB can localize an object's position, OBB provides its orientation, and mask depicts its shape. However, existing specialized methods are typically tailored to a single type of RS visual grounding task and are hard to generalize across tasks. In contrast, large vision-language models (VLMs) exhibit powerful multi-task learning capabilities but struggle to handle dense prediction tasks like segmentation. This paper proposes GeoGround, a novel framework that unifies support for HBB, OBB, and mask RS visual grounding tasks, allowing flexible output selection. Rather than customizing the architecture of VLM, our work aims to elegantly support pixel-level visual grounding output through the Text-Mask technique. We define prompt-assisted and geometry-guided learning to enhance consistency across different signals. To support model training, we present refGeo, a large-scale RS visual instruction-following dataset containing 161k image-text pairs. Experimental results show that GeoGround demonstrates strong performance across four RS visual grounding tasks, matching or surpassing the performance of specialized methods on multiple benchmarks. Code available at https://github.com/zytx121/GeoGround
Authors: Peizhe Xia, Long Peng, Xin Di, Renjing Pei, Yang Wang, Yang Cao, Zheng-Jun Zha
Abstract: Arbitrary scale super-resolution (ASSR) aims to super-resolve low-resolution images to high-resolution images at any scale using a single model, addressing the limitations of traditional super-resolution methods that are restricted to fixed-scale factors (e.g., $\times2$, $\times4$). The advent of Implicit Neural Representations (INR) has brought forth a plethora of novel methodologies for ASSR, which facilitate the reconstruction of original continuous signals by modeling a continuous representation space for coordinates and pixel values, thereby enabling arbitrary-scale super-resolution. Consequently, the primary objective of ASSR is to construct a continuous representation space derived from low-resolution inputs. However, existing methods, primarily based on CNNs and Transformers, face significant challenges such as high computational complexity and inadequate modeling of long-range dependencies, which hinder their effectiveness in real-world applications. To overcome these limitations, we propose a novel arbitrary-scale super-resolution method, called $\text{S}^{3}$Mamba, to construct a scalable continuous representation space. Specifically, we propose a Scalable State Space Model (SSSM) to modulate the state transition matrix and the sampling matrix of step size during the discretization process, achieving scalable and continuous representation modeling with linear computational complexity. Additionally, we propose a novel scale-aware self-attention mechanism to further enhance the network's ability to perceive global important features at different scales, thereby building the $\text{S}^{3}$Mamba to achieve superior arbitrary-scale super-resolution. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our method achieves state-of-the-art performance and superior generalization capabilities at arbitrary super-resolution scales.
Authors: Hongrui Jia, Chaoya Jiang, Haiyang Xu, Wei Ye, Mengfan Dong, Ming Yan, Ji Zhang, Fei Huang, Shikun Zhang
Abstract: As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these techniques to develop Large Multimodal Models (LMMs) with ICL capabilities. However, existing LMMs face a critical issue: they often fail to effectively leverage the visual context in multimodal demonstrations and instead simply follow textual patterns. This indicates that LMMs do not achieve effective alignment between multimodal demonstrations and model outputs. To address this problem, we propose Symbol Demonstration Direct Preference Optimization (SymDPO). Specifically, SymDPO aims to break the traditional paradigm of constructing multimodal demonstrations by using random symbols to replace text answers within instances. This forces the model to carefully understand the demonstration images and establish a relationship between the images and the symbols to answer questions correctly. We validate the effectiveness of this method on multiple benchmarks, demonstrating that with SymDPO, LMMs can more effectively understand the multimodal context within examples and utilize this knowledge to answer questions better.
Authors: Pramit Saha, Felix Wagner, Divyanshu Mishra, Can Peng, Anshul Thakur, David Clifton, Konstantinos Kamnitsas, J. Alison Noble
Abstract: Effective training of large Vision-Language Models (VLMs) on resource-constrained client devices in Federated Learning (FL) requires the usage of parameter-efficient fine-tuning (PEFT) strategies. To this end, we demonstrate the impact of two factors \textit{viz.}, client-specific layer importance score that selects the most important VLM layers for fine-tuning and inter-client layer diversity score that encourages diverse layer selection across clients for optimal VLM layer selection. We first theoretically motivate and leverage the principal eigenvalue magnitude of layerwise Neural Tangent Kernels and show its effectiveness as client-specific layer importance score. Next, we propose a novel layer updating strategy dubbed F$^3$OCUS that jointly optimizes the layer importance and diversity factors by employing a data-free, multi-objective, meta-heuristic optimization on the server. We explore 5 different meta-heuristic algorithms and compare their effectiveness for selecting model layers and adapter layers towards PEFT-FL. Furthermore, we release a new MedVQA-FL dataset involving overall 707,962 VQA triplets and 9 modality-specific clients and utilize it to train and evaluate our method. Overall, we conduct more than 10,000 client-level experiments on 6 Vision-Language FL task settings involving 58 medical image datasets and 4 different VLM architectures of varying sizes to demonstrate the effectiveness of the proposed method.
Authors: Seonghyeon Moon, Haein Kong, Muhammad Haris Khan, Yuewei Lin
Abstract: Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for guiding the initial training of FSS, which leads to the success of few-shot segmentation in challenging cases, such as when the target object shows considerable variation in appearance, texture, or scale across the support and query images. Previous methods have tried to obtain prior information by creating correlation maps from pixel-level correlation on final-layer or same-layer features. However, we found these approaches can offer limited and partial information when advanced models like Vision Transformers are used as the backbone. Vision Transformer encoders have a multi-layer structure with identical shapes in their intermediate layers. Leveraging the feature comparison from all layers in the encoder can enhance the performance of few-shot segmentation. We introduce FCC (Fully Connected Correlation) to integrate pixel-level correlations between support and query features, capturing associations that reveal target-specific patterns and correspondences in both same-layers and cross-layers. FCC captures previously inaccessible target information, effectively addressing the limitations of support mask. Our approach consistently demonstrates state-of-the-art performance on PASCAL, COCO, and domain shift tests. We conducted an ablation study and cross-layer correlation analysis to validate FCC's core methodology. These findings reveal the effectiveness of FCC in enhancing prior information and overall model performance.
Authors: Ruiyang Zhang, Hu Zhang, Zhedong Zheng
Abstract: Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we introduce VL-Uncertainty, the first uncertainty-based framework for detecting hallucinations in LVLMs. Different from most existing methods that require ground-truth or pseudo annotations, VL-Uncertainty utilizes uncertainty as an intrinsic metric. We measure uncertainty by analyzing the prediction variance across semantically equivalent but perturbed prompts, including visual and textual data. When LVLMs are highly confident, they provide consistent responses to semantically equivalent queries. However, when uncertain, the responses of the target LVLM become more random. Considering semantically similar answers with different wordings, we cluster LVLM responses based on their semantic content and then calculate the cluster distribution entropy as the uncertainty measure to detect hallucination. Our extensive experiments on 10 LVLMs across four benchmarks, covering both free-form and multi-choice tasks, show that VL-Uncertainty significantly outperforms strong baseline methods in hallucination detection.
Authors: Chensheng Peng, Chengwei Zhang, Yixiao Wang, Chenfeng Xu, Yichen Xie, Wenzhao Zheng, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan
Abstract: We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios. Our approach employs a two-stage optimization pipeline of dynamic street Gaussians. In the first stage, we extract 2D motion masks based on the observation that 3D Gaussian Splatting inherently can reconstruct only the static regions in dynamic environments. These extracted 2D motion priors are then mapped into the Gaussian space in a differentiable manner, leveraging an efficient formulation of dynamic Gaussians in the second stage. Combined with the introduced geometric regularizations, our method are able to address the over-fitting issues caused by data sparsity in autonomous driving, reconstructing physically plausible Gaussians that align with object surfaces rather than floating in air. Furthermore, we introduce temporal cross-view consistency to ensure coherence across time and viewpoints, resulting in high-quality surface reconstruction. Comprehensive experiments demonstrate the efficiency and effectiveness of DeSiRe-GS, surpassing prior self-supervised arts and achieving accuracy comparable to methods relying on external 3D bounding box annotations. Code is available at \url{https://github.com/chengweialan/DeSiRe-GS}
Authors: Cheng-Yen Yang, Hsiang-Wei Huang, Wenhao Chai, Zhongyu Jiang, Jenq-Neng Hwang
Abstract: The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next frame, leading to error propagation in videos. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. By incorporating temporal motion cues with the proposed motion-aware memory selection mechanism, SAMURAI effectively predicts object motion and refines mask selection, achieving robust, accurate tracking without the need for retraining or fine-tuning. SAMURAI operates in real-time and demonstrates strong zero-shot performance across diverse benchmark datasets, showcasing its ability to generalize without fine-tuning. In evaluations, SAMURAI achieves significant improvements in success rate and precision over existing trackers, with a 7.1% AUC gain on LaSOT$_{\text{ext}}$ and a 3.5% AO gain on GOT-10k. Moreover, it achieves competitive results compared to fully supervised methods on LaSOT, underscoring its robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments. Code and results are available at https://github.com/yangchris11/samurai.
Authors: Zili Wang, Robert Zhang, Kun Ding, Qi Yang, Fei Li, Shiming Xiang
Abstract: Continuous-valued Autoregressive (AR) image generation models have demonstrated notable superiority over their discrete-token counterparts, showcasing considerable reconstruction quality and higher generation fidelity. However, the computational demands of the autoregressive framework result in significant inference overhead. While speculative decoding has proven effective in accelerating Large Language Models (LLMs), their adaptation to continuous-valued visual autoregressive models remains unexplored. This work generalizes the speculative decoding algorithm from discrete tokens to continuous space. By analyzing the intrinsic properties of output distribution, we establish a tailored acceptance criterion for the diffusion distributions prevalent in such models. To overcome the inconsistency that occurred in speculative decoding output distributions, we introduce denoising trajectory alignment and token pre-filling methods. Additionally, we identify the hard-to-sample distribution in the rejection phase. To mitigate this issue, we propose a meticulous acceptance-rejection sampling method with a proper upper bound, thereby circumventing complex integration. Experimental results show that our continuous speculative decoding achieves a remarkable $2.33\times$ speed-up on off-the-shelf models while maintaining the output distribution. Codes will be available at https://github.com/MarkXCloud/CSpD
Authors: Akansh Agrawal, Akshan Agrawal, Shashwat Gupta, Priyanka Bagade
Abstract: Medical image segmentation is crucial in robotic surgeries, disease diagnosis, and treatment plans. This research presents an innovative methodology that combines Kolmogorov-Arnold Networks (KAN) with an adapted Mamba layer for medical image segmentation. The proposed KAN-Mamba FusionNet framework improves image segmentation by integrating attention-driven mechanisms with convolutional parallel training and autoregressive deployment, while preserving interpretability, in contrast to the state-of-the-art techniques that depend exclusively on Mamba for ailment localization and accurate diagnosis. We evaluated our proposed KAN-Mamba FusionNet model on three distinct medical image segmentation datasets, BUSI, Kvasir-Seg and GlaS. The results indicated that the KAN-Mamba FusionNet consistently yields better IoU and F1 scores in comparison to the state-of-the-art methods. Further, we offer insights into the model's behavior via ablation studies, examining the effects of various components and assessing their contributions to the overall performance of the proposed model. The findings illustrate the strength and effectiveness of this methodology for dependable medical image segmentation, providing a unique approach to address intricate visual data issues in healthcare.
Authors: Anjia Cao, Xing Wei, Zhiheng Ma
Abstract: Language-image pre-training faces significant challenges due to limited data in specific formats and the constrained capacities of text encoders. While prevailing methods attempt to address these issues through data augmentation and architecture modifications, they continue to struggle with processing long-form text inputs, and the inherent limitations of traditional CLIP text encoders lead to suboptimal downstream generalization. In this paper, we propose FLAME (Frozen Large lAnguage Models Enable data-efficient language-image pre-training) that leverages frozen large language models as text encoders, naturally processing long text inputs and demonstrating impressive multilingual generalization. FLAME comprises two key components: 1) a multifaceted prompt distillation technique for extracting diverse semantic representations from long captions, which better aligns with the multifaceted nature of images, and 2) a facet-decoupled attention mechanism, complemented by an offline embedding strategy, to ensure efficient computation. Extensive empirical evaluations demonstrate FLAME's superior performance. When trained on CC3M, FLAME surpasses the previous state-of-the-art by 4.9\% in ImageNet top-1 accuracy. On YFCC15M, FLAME surpasses the WIT-400M-trained CLIP by 44.4\% in average image-to-text recall@1 across 36 languages, and by 34.6\% in text-to-image recall@1 for long-context retrieval on Urban-1k. Code is available at \url{https://github.com/MIV-XJTU/FLAME}.
Authors: Kun Xiang, Zhili Liu, Zihao Jiang, Yunshuang Nie, Runhui Huang, Haoxiang Fan, Hanhui Li, Weiran Huang, Yihan Zeng, Jianhua Han, Lanqing Hong, Hang Xu, Xiaodan Liang
Abstract: In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of ``slow thinking" into multimodal large language models (MLLMs). Contrary to existing methods that rely on direct or fast thinking, our key idea is to construct long chains of thought (CoT) consisting of atomic actions in a step-by-step manner, guiding MLLMs to perform complex reasoning. To this end, we design a novel AtomThink framework composed of three key modules: (i) a CoT annotation engine that automatically generates high-quality CoT annotations to address the lack of high-quality visual mathematical data; (ii) an atomic step fine-tuning strategy that jointly optimizes an MLLM and a policy reward model (PRM) for step-wise reasoning; and (iii) four different search strategies that can be applied with the PRM to complete reasoning. Additionally, we propose AtomMATH, a large-scale multimodal dataset of long CoTs, and an atomic capability evaluation metric for mathematical tasks. Extensive experimental results show that the proposed AtomThink significantly improves the performance of baseline MLLMs, achieving approximately 50\% relative accuracy gains on MathVista and 120\% on MathVerse. To support the advancement of multimodal slow-thinking models, we will make our code and dataset publicly available on https://github.com/Quinn777/AtomThink.
Authors: Zhen Lv, Yangqi Long, Congzhentao Huang, Cao Li, Chengfei Lv, Hao Ren, Dian Zheng
Abstract: Stereo video synthesis from a monocular input is a demanding task in the fields of spatial computing and virtual reality. The main challenges of this task lie on the insufficiency of high-quality paired stereo videos for training and the difficulty of maintaining the spatio-temporal consistency between frames. Existing methods primarily address these issues by directly applying novel view synthesis (NVS) techniques to video, while facing limitations such as the inability to effectively represent dynamic scenes and the requirement for large amounts of training data. In this paper, we introduce a novel self-supervised stereo video synthesis paradigm via a video diffusion model, termed SpatialDreamer, which meets the challenges head-on. Firstly, to address the stereo video data insufficiency, we propose a Depth based Video Generation module DVG, which employs a forward-backward rendering mechanism to generate paired videos with geometric and temporal priors. Leveraging data generated by DVG, we propose RefinerNet along with a self-supervised synthetic framework designed to facilitate efficient and dedicated training. More importantly, we devise a consistency control module, which consists of a metric of stereo deviation strength and a Temporal Interaction Learning module TIL for geometric and temporal consistency ensurance respectively. We evaluated the proposed method against various benchmark methods, with the results showcasing its superior performance.
Authors: Hanieh Shojaei Miandashti, Qianqian Zou, Claus Brenner
Abstract: Reliable deep learning models require not only accurate predictions but also well-calibrated confidence estimates to ensure dependable uncertainty estimation. This is crucial in safety-critical applications like autonomous driving, which depend on rapid and precise semantic segmentation of LiDAR point clouds for real-time 3D scene understanding. In this work, we introduce a sampling-free approach for estimating well-calibrated confidence values for classification tasks, achieving alignment with true classification accuracy and significantly reducing inference time compared to sampling-based methods. Our evaluation using the Adaptive Calibration Error (ACE) metric for LiDAR semantic segmentation shows that our approach maintains well-calibrated confidence values while achieving increased processing speed compared to a sampling baseline. Additionally, reliability diagrams reveal that our method produces underconfidence rather than overconfident predictions, an advantage for safety-critical applications. Our sampling-free approach offers well-calibrated and time-efficient predictions for LiDAR scene semantic segmentation.
Authors: Milad Masroor, Tahir Hassan, Yu Tian, Kevin Wells, David Rosewarne, Thanh-Toan Do, Gustavo Carneiro
Abstract: Deep learning has achieved remarkable success in image classification and segmentation tasks. However, fairness concerns persist, as models often exhibit biases that disproportionately affect demographic groups defined by sensitive attributes such as race, gender, or age. Existing bias-mitigation techniques, including Subgroup Re-balancing, Adversarial Training, and Domain Generalization, aim to balance accuracy across demographic groups, but often fail to simultaneously improve overall accuracy, group-specific accuracy, and fairness due to conflicts among these interdependent objectives. We propose the Fair Distillation (FairDi) method, a novel fairness approach that decomposes these objectives by leveraging biased ``teacher'' models, each optimized for a specific demographic group. These teacher models then guide the training of a unified ``student'' model, which distills their knowledge to maximize overall and group-specific accuracies, while minimizing inter-group disparities. Experiments on medical imaging datasets show that FairDi achieves significant gains in both overall and group-specific accuracy, along with improved fairness, compared to existing methods. FairDi is adaptable to various medical tasks, such as classification and segmentation, and provides an effective solution for equitable model performance.
Authors: DaDong Jiang, Zhihui Ke, Xiaobo Zhou, Zhi Hou, Xianghui Yang, Wenbo Hu, Tie Qiu, Chunchao Guo
Abstract: Dynamic scene reconstruction is a long-term challenge in 3D vision. Recent methods extend 3D Gaussian Splatting to dynamic scenes via additional deformation fields and apply explicit constraints like motion flow to guide the deformation. However, they learn motion changes from individual timestamps independently, making it challenging to reconstruct complex scenes, particularly when dealing with violent movement, extreme-shaped geometries, or reflective surfaces. To address the above issue, we design a plug-and-play module called TimeFormer to enable existing deformable 3D Gaussians reconstruction methods with the ability to implicitly model motion patterns from a learning perspective. Specifically, TimeFormer includes a Cross-Temporal Transformer Encoder, which adaptively learns the temporal relationships of deformable 3D Gaussians. Furthermore, we propose a two-stream optimization strategy that transfers the motion knowledge learned from TimeFormer to the base stream during the training phase. This allows us to remove TimeFormer during inference, thereby preserving the original rendering speed. Extensive experiments in the multi-view and monocular dynamic scenes validate qualitative and quantitative improvement brought by TimeFormer. Project Page: https://patrickddj.github.io/TimeFormer/
Authors: Xu Cao, Kaizhao Liang, Kuei-Da Liao, Tianren Gao, Wenqian Ye, Jintai Chen, Zhiguang Ding, Jianguo Cao, James M. Rehg, Jimeng Sun
Abstract: Modeling disease progression is crucial for improving the quality and efficacy of clinical diagnosis and prognosis, but it is often hindered by a lack of longitudinal medical image monitoring for individual patients. To address this challenge, we propose the first Medical Video Generation (MVG) framework that enables controlled manipulation of disease-related image and video features, allowing precise, realistic, and personalized simulations of disease progression. Our approach begins by leveraging large language models (LLMs) to recaption prompt for disease trajectory. Next, a controllable multi-round diffusion model simulates the disease progression state for each patient, creating realistic intermediate disease state sequence. Finally, a diffusion-based video transition generation model interpolates disease progression between these states. We validate our framework across three medical imaging domains: chest X-ray, fundus photography, and skin image. Our results demonstrate that MVG significantly outperforms baseline models in generating coherent and clinically plausible disease trajectories. Two user studies by veteran physicians, provide further validation and insights into the clinical utility of the generated sequences. MVG has the potential to assist healthcare providers in modeling disease trajectories, interpolating missing medical image data, and enhancing medical education through realistic, dynamic visualizations of disease progression.
Authors: Libing Zeng, Nima Khademi Kalantari
Abstract: With the advances in generative adversarial networks (GANs) and neural rendering, 3D relightable face generation has received significant attention. Among the existing methods, a particularly successful technique uses an implicit lighting representation and generates relit images through the product of synthesized albedo and light-dependent shading images. While this approach produces high-quality results with intricate shading details, it often has difficulty producing relit images with consistent skin tones, particularly when the lighting condition is extracted from images of individuals with dark skin. Additionally, this technique is biased towards producing albedo images with lighter skin tones. Our main observation is that this problem is rooted in the biased spherical harmonics (SH) coefficients, used during training. Following this observation, we conduct an analysis and demonstrate that the bias appears not only in band 0 (DC term), but also in the other bands of the estimated SH coefficients. We then propose a simple, but effective, strategy to mitigate the problem. Specifically, we normalize the SH coefficients by their DC term to eliminate the inherent magnitude bias, while statistically align the coefficients in the other bands to alleviate the directional bias. We also propose a scaling strategy to match the distribution of illumination magnitude in the generated images with the training data. Through extensive experiments, we demonstrate the effectiveness of our solution in increasing the skin tone consistency and mitigating bias.
Authors: Israt Zarin Era, Fan Zhou, Ahmed Shoyeb Raihan, Imtiaz Ahmed, Alan Abul-Haj, James Craig, Srinjoy Das, Zhichao Liu
Abstract: Directed Energy Deposition (DED) offers significant potential for manufacturing complex and multi-material parts. However, internal defects such as porosity and cracks can compromise mechanical properties and overall performance. This study focuses on in-situ monitoring and characterization of melt pools associated with porosity, aiming to improve defect detection and quality control in DED-printed parts. Traditional machine learning approaches for defect identification rely on extensive labeled datasets, often scarce and expensive to generate in real-world manufacturing. To address this, our framework employs self-supervised learning on unlabeled melt pool data using a Vision Transformer-based Masked Autoencoder (MAE) to produce highly representative embeddings. These fine-tuned embeddings are leveraged via transfer learning to train classifiers on a limited labeled dataset, enabling the effective identification of melt pool anomalies. We evaluate two classifiers: (1) a Vision Transformer (ViT) classifier utilizing the fine-tuned MAE Encoder's parameters and (2) the fine-tuned MAE Encoder combined with an MLP classifier head. Our framework achieves overall accuracy ranging from 95.44% to 99.17% and an average F1 score exceeding 80%, with the ViT Classifier slightly outperforming the MAE Encoder Classifier. This demonstrates the scalability and cost-effectiveness of our approach for automated quality control in DED, effectively detecting defects with minimal labeled data.
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: Zuzanna Buchnajzer, Kacper Dobek, Stanis{\l}aw Hapke, Daniel Jankowski, Krzysztof Krawiec
Abstract: Deep learning architectures based on convolutional neural networks tend to rely on continuous, smooth features. While this characteristics provides significant robustness and proves useful in many real-world tasks, it is strikingly incompatible with the physical characteristic of the world, which, at the scale in which humans operate, comprises crisp objects, typically representing well-defined categories. This study proposes a class of neurosymbolic systems that learn by reconstructing the observed images in terms of visual primitives and are thus forced to form high-level, structural explanations of them. When applied to the task of diagnosing abnormalities in histological imaging, the method proved superior to a conventional deep learning architecture in terms of classification accuracy, while being more transparent.
Authors: Brian B. Moser, Stanislav Frolov, Tobias C. Nauen, Federico Raue, Andreas Dengel
Abstract: Large-scale, pre-trained Text-to-Image (T2I) diffusion models have gained significant popularity in image generation tasks and have shown unexpected potential in image Super-Resolution (SR). However, most existing T2I diffusion models are trained with a resolution limit of 512x512, making scaling beyond this resolution an unresolved but necessary challenge for image SR. In this work, we introduce a novel approach that, for the first time, enables these models to generate 2K, 4K, and even 8K images without any additional training. Our method leverages MultiDiffusion, which distributes the generation across multiple diffusion paths to ensure global coherence at larger scales, and local degradation-aware prompt extraction, which guides the T2I model to reconstruct fine local structures according to its low-resolution input. These innovations unlock higher resolutions, allowing T2I diffusion models to be applied to image SR tasks without limitation on resolution.
Authors: Arundhati S. Shanbhag, Brian B. Moser, Tobias C. Nauen, Stanislav Frolov, Federico Raue, Andreas Dengel
Abstract: Diffusion models, known for their generative capabilities, have recently shown unexpected potential in image classification tasks by using Bayes' theorem. However, most diffusion classifiers require evaluating all class labels for a single classification, leading to significant computational costs that can hinder their application in large-scale scenarios. To address this, we present a Hierarchical Diffusion Classifier (HDC) that exploits the inherent hierarchical label structure of a dataset. By progressively pruning irrelevant high-level categories and refining predictions only within relevant subcategories, i.e., leaf nodes, HDC reduces the total number of class evaluations. As a result, HDC can accelerate inference by up to 60% while maintaining and, in some cases, improving classification accuracy. Our work enables a new control mechanism of the trade-off between speed and precision, making diffusion-based classification more viable for real-world applications, particularly in large-scale image classification tasks.
Authors: Fangyu Wu, Yuhao Chen
Abstract: In the real world, objects reveal internal textures when sliced or cut, yet this behavior is not well-studied in 3D generation tasks today. For example, slicing a virtual 3D watermelon should reveal flesh and seeds. Given that no available dataset captures an object's full internal structure and collecting data from all slices is impractical, generative methods become the obvious approach. However, current 3D generation and inpainting methods often focus on visible appearance and overlook internal textures. To bridge this gap, we introduce FruitNinja, the first method to generate internal textures for 3D objects undergoing geometric and topological changes. Our approach produces objects via 3D Gaussian Splatting (3DGS) with both surface and interior textures synthesized, enabling real-time slicing and rendering without additional optimization. FruitNinja leverages a pre-trained diffusion model to progressively inpaint cross-sectional views and applies voxel-grid-based smoothing to achieve cohesive textures throughout the object. Our OpaqueAtom GS strategy overcomes 3DGS limitations by employing densely distributed opaque Gaussians, avoiding biases toward larger particles that destabilize training and sharp color transitions for fine-grained textures. Experimental results show that FruitNinja substantially outperforms existing approaches, showcasing unmatched visual quality in real-time rendered internal views across arbitrary geometry manipulations.
Authors: Brian B. Moser, Federico Raue, Tobias C. Nauen, Stanislav Frolov, Andreas Dengel
Abstract: Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel "Prune First, Distill After" framework that systematically prunes datasets via loss-based sampling prior to distillation. By leveraging pruning before classical distillation techniques and generative priors, we create a representative core-set that leads to enhanced generalization for unseen architectures - a significant challenge of current distillation methods. More specifically, our proposed framework significantly boosts distilled quality, achieving up to a 5.2 percentage points accuracy increase even with substantial dataset pruning, i.e., removing 80% of the original dataset prior to distillation. Overall, our experimental results highlight the advantages of our easy-sample prioritization and cross-architecture robustness, paving the way for more effective and high-quality dataset distillation.
Authors: Yuyang Xiao
Abstract: This study aims to optimize the few-shot image classification task and improve the model's feature extraction and classification performance by combining self-supervised learning with the deep network model ResNet-101. During the training process, we first pre-train the model with self-supervision to enable it to learn common feature expressions on a large amount of unlabeled data; then fine-tune it on the few-shot dataset Mini-ImageNet to improve the model's accuracy and generalization ability under limited data. The experimental results show that compared with traditional convolutional neural networks, ResNet-50, DenseNet, and other models, our method has achieved excellent performance of about 95.12% in classification accuracy (ACC) and F1 score, verifying the effectiveness of self-supervised learning in few-shot classification. This method provides an efficient and reliable solution for the field of few-shot image classification.
Authors: Tianhao Xie, Noam Aigerman, Eugene Belilovsky, Tiberiu Popa
Abstract: 3D Gaussian Splatting (GS) is one of the most promising novel 3D representations that has received great interest in computer graphics and computer vision. While various systems have introduced editing capabilities for 3D GS, such as those guided by text prompts, fine-grained control over deformation remains an open challenge. In this work, we present a novel sketch-guided 3D GS deformation system that allows users to intuitively modify the geometry of a 3D GS model by drawing a silhouette sketch from a single viewpoint. Our approach introduces a new deformation method that combines cage-based deformations with a variant of Neural Jacobian Fields, enabling precise, fine-grained control. Additionally, it leverages large-scale 2D diffusion priors and ControlNet to ensure the generated deformations are semantically plausible. Through a series of experiments, we demonstrate the effectiveness of our method and showcase its ability to animate static 3D GS models as one of its key applications.
Authors: Zhuangwei Zhuang, Ziyin Wang, Sitao Chen, Lizhao Liu, Hui Luo, Mingkui Tan
Abstract: 3D semantic occupancy prediction, which seeks to provide accurate and comprehensive representations of environment scenes, is important to autonomous driving systems. For autonomous cars equipped with multi-camera and LiDAR, it is critical to aggregate multi-sensor information into a unified 3D space for accurate and robust predictions. Recent methods are mainly built on the 2D-to-3D transformation that relies on sensor calibration to project the 2D image information into the 3D space. These methods, however, suffer from two major limitations: First, they rely on accurate sensor calibration and are sensitive to the calibration noise, which limits their application in real complex environments. Second, the spatial transformation layers are computationally expensive and limit their running on an autonomous vehicle. In this work, we attempt to exploit a Robust and Efficient 3D semantic Occupancy (REO) prediction scheme. To this end, we propose a calibration-free spatial transformation based on vanilla attention to implicitly model the spatial correspondence. In this way, we robustly project the 2D features to a predefined BEV plane without using sensor calibration as input. Then, we introduce 2D and 3D auxiliary training tasks to enhance the discrimination power of 2D backbones on spatial, semantic, and texture features. Last, we propose a query-based prediction scheme to efficiently generate large-scale fine-grained occupancy predictions. By fusing point clouds that provide complementary spatial information, our REO surpasses the existing methods by a large margin on three benchmarks, including OpenOccupancy, Occ3D-nuScenes, and SemanticKITTI Scene Completion. For instance, our REO achieves 19.8$\times$ speedup compared to Co-Occ, with 1.1 improvements in geometry IoU on OpenOccupancy. Our code will be available at https://github.com/ICEORY/REO.
Authors: Shuntaro Okada, Kenji Doi, Ryota Yoshihashi, Hirokatsu Kataoka, Tomohiro Tanaka
Abstract: We propose a noise schedule that ensures a constant rate of change in the probability distribution of diffused data throughout the diffusion process. To obtain this noise schedule, we measure the rate of change in the probability distribution of the forward process and use it to determine the noise schedule before training diffusion models. The functional form of the noise schedule is automatically determined and tailored to each dataset and type of diffusion model. We evaluate the effectiveness of our noise schedule on unconditional and class-conditional image generation tasks using the LSUN (bedroom/church/cat/horse), ImageNet, and FFHQ datasets. Through extensive experiments, we confirmed that our noise schedule broadly improves the performance of the diffusion models regardless of the dataset, sampler, number of function evaluations, or type of diffusion model.
Authors: Qi Chen, Ruoshan Zhao, Sinuo Wang, Vu Minh Hieu Phan, Anton van den Hengel, Johan Verjans, Zhibin Liao, Minh-Son To, Yong Xia, Jian Chen, Yutong Xie, Qi Wu
Abstract: Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced public health monitoring, disease surveillance, and policy-making through more efficient analysis of large data sets. MVLMS integrate natural language processing with medical images to enable a more comprehensive and contextual understanding of medical images alongside their corresponding textual information. Unlike general vision-and-language models trained on diverse, non-specialized datasets, MVLMs are purpose-built for the medical domain, automatically extracting and interpreting critical information from medical images and textual reports to support clinical decision-making. Popular clinical applications of MVLMs include automated medical report generation, medical visual question answering, medical multimodal segmentation, diagnosis and prognosis and medical image-text retrieval. Here, we provide a comprehensive overview of MVLMs and the various medical tasks to which they have been applied. We conduct a detailed analysis of various vision-and-language model architectures, focusing on their distinct strategies for cross-modal integration/exploitation of medical visual and textual features. We also examine the datasets used for these tasks and compare the performance of different models based on standardized evaluation metrics. Furthermore, we highlight potential challenges and summarize future research trends and directions. The full collection of papers and codes is available at: https://github.com/YtongXie/Medical-Vision-and-Language-Tasks-and-Methodologies-A-Survey.
URLs: https://github.com/YtongXie/Medical-Vision-and-Language-Tasks-and-Methodologies-A-Survey.
Authors: Yu Liu, Ruowei Wang, Jiaqi Li, Zixiang Xu, Qijun Zhao
Abstract: Reconstructing 3D models from single-view images is a long-standing problem in computer vision. The latest advances for single-image 3D reconstruction extract a textual description from the input image and further utilize it to synthesize 3D models. However, existing methods focus on capturing a single key attribute of the image (e.g., object type, artistic style) and fail to consider the multi-perspective information required for accurate 3D reconstruction, such as object shape and material properties. Besides, the reliance on Neural Radiance Fields hinders their ability to reconstruct intricate surfaces and texture details. In this work, we propose MTFusion, which leverages both image data and textual descriptions for high-fidelity 3D reconstruction. Our approach consists of two stages. First, we adopt a novel multi-word textual inversion technique to extract a detailed text description capturing the image's characteristics. Then, we use this description and the image to generate a 3D model with FlexiCubes. Additionally, MTFusion enhances FlexiCubes by employing a special decoder network for Signed Distance Functions, leading to faster training and finer surface representation. Extensive evaluations demonstrate that our MTFusion surpasses existing image-to-3D methods on a wide range of synthetic and real-world images. Furthermore, the ablation study proves the effectiveness of our network designs.
Authors: Yifan Xie, Jingge Wang, Tao Feng, Fei Ma, Yang Li
Abstract: Colonoscopy is crucial for identifying adenomatous polyps and preventing colorectal cancer. However, developing robust models for polyp detection is challenging by the limited size and accessibility of existing colonoscopy datasets. While previous efforts have attempted to synthesize colonoscopy images, current methods suffer from instability and insufficient data diversity. Moreover, these approaches lack precise control over the generation process, resulting in images that fail to meet clinical quality standards. To address these challenges, we propose CCIS-DIFF, a Controlled generative model for high-quality Colonoscopy Image Synthesis based on a Diffusion architecture. Our method offers precise control over both the spatial attributes (polyp location and shape) and clinical characteristics of polyps that align with clinical descriptions. Specifically, we introduce a blur mask weighting strategy to seamlessly blend synthesized polyps with the colonic mucosa, and a text-aware attention mechanism to guide the generated images to reflect clinical characteristics. Notably, to achieve this, we construct a new multi-modal colonoscopy dataset that integrates images, mask annotations, and corresponding clinical text descriptions. Experimental results demonstrate that our method generates high-quality, diverse colonoscopy images with fine control over both spatial constraints and clinical consistency, offering valuable support for downstream segmentation and diagnostic tasks.
Authors: Tae-Min Choi, Juyoun Park
Abstract: Surgical instrument segmentation (SIS) is an essential task in computer-assisted surgeries, with deep learning-based research improving accuracy in complex environments. Recently, text-promptable segmentation methods have been introduced to generate masks based on text prompts describing target objects. However, these methods assume that the object described by a given text prompt exists in the scene. This results in mask generation whenever a related text prompt is provided, even if the object is absent from the image. Existing methods handle this by using prompts only for objects known to be present in the image, which introduces inaccessible information in a vision-based method setting and results in unfair comparisons. For fair comparison, we redefine existing text-promptable SIS settings to robust conditions, called Robust text-promptable SIS (R-SIS), designed to forward prompts of all classes and determine the existence of an object from a given text prompt for the fair comparison. Furthermore, we propose a novel framework, Robust Surgical Instrument Segmentation (RoSIS), which combines visual and language features for promptable segmentation in the R-SIS setting. RoSIS employs an encoder-decoder architecture with a Multi-Modal Fusion Block (MMFB) and a Selective Gate Block (SGB) to achieve balanced integration of vision and language features. Additionally, we introduce an iterative inference strategy that refines segmentation masks in two steps: an initial pass using name-based prompts, followed by a refinement step using location prompts. Experiments on various datasets and settings demonstrate that RoSIS outperforms existing vision-based and promptable methods under robust conditions.
Authors: Tonmoy Hossain, Jing Ma, Jundong Li, Miaomiao Zhang
Abstract: Geometric shape features have been widely used as strong predictors for image classification. Nevertheless, most existing classifiers such as deep neural networks (DNNs) directly leverage the statistical correlations between these shape features and target variables. However, these correlations can often be spurious and unstable across different environments (e.g., in different age groups, certain types of brain changes have unstable relations with neurodegenerative disease); hence leading to biased or inaccurate predictions. In this paper, we introduce a novel framework that for the first time develops invariant shape representation learning (ISRL) to further strengthen the robustness of image classifiers. In contrast to existing approaches that mainly derive features in the image space, our model ISRL is designed to jointly capture invariant features in latent shape spaces parameterized by deformable transformations. To achieve this goal, we develop a new learning paradigm based on invariant risk minimization (IRM) to learn invariant representations of image and shape features across multiple training distributions/environments. By embedding the features that are invariant with regard to target variables in different environments, our model consistently offers more accurate predictions. We validate our method by performing classification tasks on both simulated 2D images, real 3D brain and cine cardiovascular magnetic resonance images (MRIs). Our code is publicly available at https://github.com/tonmoy-hossain/ISRL.
Authors: Zhanqiang Guo, Jiamin Wu, Yonghao Song, Weijian Mai, Qihao Zheng, Wanli Ouyang, Chunfeng Song
Abstract: Human's perception of the visual world is shaped by the stereo processing of 3D information. Understanding how the brain perceives and processes 3D visual stimuli in the real world has been a longstanding endeavor in neuroscience. Towards this goal, we introduce a new neuroscience task: decoding 3D visual perception from EEG signals, a neuroimaging technique that enables real-time monitoring of neural dynamics enriched with complex visual cues. To provide the essential benchmark, we first present EEG-3D, a pioneering dataset featuring multimodal analysis data and extensive EEG recordings from 12 subjects viewing 72 categories of 3D objects rendered in both videos and images. Furthermore, we propose Neuro-3D, a 3D visual decoding framework based on EEG signals. This framework adaptively integrates EEG features derived from static and dynamic stimuli to learn complementary and robust neural representations, which are subsequently utilized to recover both the shape and color of 3D objects through the proposed diffusion-based colored point cloud decoder. To the best of our knowledge, we are the first to explore EEG-based 3D visual decoding. Experiments indicate that Neuro-3D not only reconstructs colored 3D objects with high fidelity, but also learns effective neural representations that enable insightful brain region analysis. The dataset and associated code will be made publicly available.
Authors: Xiao Jiang, Fei Zhou, Jiongzhi Lin
Abstract: Event cameras operate fundamentally differently from traditional Active Pixel Sensor (APS) cameras, offering significant advantages. Recent research has developed simulators to convert video frames into events, addressing the shortage of real event datasets. Current simulators primarily focus on the logical behavior of event cameras. However, the fundamental analogue properties of pixel circuits are seldom considered in simulator design. The gap between analogue pixel circuit and discrete video frames causes the degeneration of synthetic events, particularly in high-contrast scenes. In this paper, we propose a novel method of generating reliable event data based on a detailed analysis of the pixel circuitry in event cameras. We incorporate the analogue properties of event camera pixel circuits into the simulator design: (1) analogue filtering of signals from light intensity to events, and (2) a cutoff frequency that is independent of video frame rate. Experimental results on two relevant tasks, including semantic segmentation and image reconstruction, validate the reliability of simulated event data, even in high-contrast scenes. This demonstrates that deep neural networks exhibit strong generalization from simulated to real event data, confirming that the synthetic events generated by the proposed method are both realistic and well-suited for effective training.
Authors: Baoquan Zhang, Shanshan Feng, Bingqi Shan, Xutao Li, Yunming Ye, Yew-Soon Ong
Abstract: Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then performing class prediction via a cosine classifier with mean-based prototypes. Nevertheless, due to the data scarcity, the mean-based prototypes are usually biased. In this paper, we attempt to diminish the prototype bias by regarding it as a prototype optimization problem. To this end, we propose a novel prototype optimization framework to rectify prototypes, i.e., introducing a meta-optimizer to optimize prototypes. Although the existing meta-optimizers can also be adapted to our framework, they all overlook a crucial gradient bias issue, i.e., the mean-based gradient estimation is also biased on sparse data. To address this issue, in this paper, we regard the gradient and its flow as meta-knowledge and then propose a novel Neural Ordinary Differential Equation (ODE)-based meta-optimizer to optimize prototypes, called MetaNODE. Although MetaNODE has shown superior performance, it suffers from a huge computational burden. To further improve its computation efficiency, we conduct a detailed analysis on MetaNODE and then design an effective and efficient MetaNODE extension version (called E2MetaNODE). It consists of two novel modules: E2GradNet and E2Solver, which aim to estimate accurate gradient flows and solve optimal prototypes in an effective and efficient manner, respectively. Extensive experiments show that 1) our methods achieve superior performance over previous FSL methods and 2) our E2MetaNODE significantly improves computation efficiency meanwhile without performance degradation.
Authors: Maheswar Bora, Saurabh Atreya, Aritra Mukherjee, Abhijit Das
Abstract: In this work, we attempted to extend the thought and showcase a way forward for the Self-supervised Learning (SSL) learning paradigm by combining contrastive learning, self-distillation (knowledge distillation) and masked data modelling, the three major SSL frameworks, to learn a joint and coordinated representation. The proposed technique of SSL learns by the collaborative power of different learning objectives of SSL. Hence to jointly learn the different SSL objectives we proposed a new SSL architecture KDC-MAE, a complementary masking strategy to learn the modular correspondence, and a weighted way to combine them coordinately. Experimental results conclude that the contrastive masking correspondence along with the KD learning objective has lent a hand to performing better learning for multiple modalities over multiple tasks.
Authors: Ziyang Zong, Zhaohuan Zhan, Guang Tan
Abstract: This paper proposes a two-phase text-to-floorplan generation method, which guides a Large Language Model (LLM) to generate an initial layout (Layout-LLM) and refines them into the final floorplans through conditional diffusion model. We incorporate a Chain-of-Thought approach to prompt the LLM based on user text specifications, enabling a more user-friendly and intuitive house layout design. This method allows users to describe their needs in natural language, enhancing accessibility and providing clearer geometric constraints. The final floorplans generated by Layout-LLM through conditional diffusion refinement are more accurate and better meet user requirements. Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, validating its effectiveness in practical home design applications. We plan to release our code for public use.
Authors: Haowen Zheng, Yanyan Liang
Abstract: Recent advancements in 3D diffusion-based semantic scene generation have gained attention. However, existing methods rely on unconditional generation and require multiple resampling steps when editing scenes, which significantly limits their controllability and flexibility. To this end, we propose SSEditor, a controllable Semantic Scene Editor that can generate specified target categories without multiple-step resampling. SSEditor employs a two-stage diffusion-based framework: (1) a 3D scene autoencoder is trained to obtain latent triplane features, and (2) a mask-conditional diffusion model is trained for customizable 3D semantic scene generation. In the second stage, we introduce a geometric-semantic fusion module that enhance the model's ability to learn geometric and semantic information. This ensures that objects are generated with correct positions, sizes, and categories. Extensive experiments on SemanticKITTI and CarlaSC demonstrate that SSEditor outperforms previous approaches in terms of controllability and flexibility in target generation, as well as the quality of semantic scene generation and reconstruction. More importantly, experiments on the unseen Occ-3D Waymo dataset show that SSEditor is capable of generating novel urban scenes, enabling the rapid construction of 3D scenes.
Authors: Alejandro Pardo, Jui-Hsien Wang, Bernard Ghanem, Josef Sivic, Bryan Russell, Fabian Caba Heilbron
Abstract: The objective of this work is to manipulate visual timelines (e.g. a video) through natural language instructions, making complex timeline editing tasks accessible to non-expert or potentially even disabled users. We call this task Instructed visual assembly. This task is challenging as it requires (i) identifying relevant visual content in the input timeline as well as retrieving relevant visual content in a given input (video) collection, (ii) understanding the input natural language instruction, and (iii) performing the desired edits of the input visual timeline to produce an output timeline. To address these challenges, we propose the Timeline Assembler, a generative model trained to perform instructed visual assembly tasks. The contributions of this work are three-fold. First, we develop a large multimodal language model, which is designed to process visual content, compactly represent timelines and accurately interpret timeline editing instructions. Second, we introduce a novel method for automatically generating datasets for visual assembly tasks, enabling efficient training of our model without the need for human-labeled data. Third, we validate our approach by creating two novel datasets for image and video assembly, demonstrating that the Timeline Assembler substantially outperforms established baseline models, including the recent GPT-4o, in accurately executing complex assembly instructions across various real-world inspired scenarios.
Authors: Zhongling Huang, Long Liu, Shuxin Yang, Zhirui Wang, Gong Cheng, Junwei Han
Abstract: The disperse structure distributions (discreteness) and variant scattering characteristics (variability) of SAR airplane targets lead to special challenges of object detection and recognition. The current deep learning-based detectors encounter challenges in distinguishing fine-grained SAR airplanes against complex backgrounds. To address it, we propose a novel physics-guided detector (PGD) learning paradigm for SAR airplanes that comprehensively investigate their discreteness and variability to improve the detection performance. It is a general learning paradigm that can be extended to different existing deep learning-based detectors with "backbone-neck-head" architectures. The main contributions of PGD include the physics-guided self-supervised learning, feature enhancement, and instance perception, denoted as PGSSL, PGFE, and PGIP, respectively. PGSSL aims to construct a self-supervised learning task based on a wide range of SAR airplane targets that encodes the prior knowledge of various discrete structure distributions into the embedded space. Then, PGFE enhances the multi-scale feature representation of a detector, guided by the physics-aware information learned from PGSSL. PGIP is constructed at the detection head to learn the refined and dominant scattering point of each SAR airplane instance, thus alleviating the interference from the complex background. We propose two implementations, denoted as PGD and PGD-Lite, and apply them to various existing detectors with different backbones and detection heads. The experiments demonstrate the flexibility and effectiveness of the proposed PGD, which can improve existing detectors on SAR airplane detection with fine-grained classification task (an improvement of 3.1\% mAP most), and achieve the state-of-the-art performance (90.7\% mAP) on SAR-AIRcraft-1.0 dataset. The project is open-source at \url{https://github.com/XAI4SAR/PGD}.
Authors: Jie Shao, Hanxiao Zhang, Jianxin Wu
Abstract: In this work, we explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We begin by investigating classical vector quantization but find that diffusion models are particularly susceptible to quantization error, with the codebook size limiting generation quality. To address this, we introduce product quantization, which offers improved reconstruction precision and larger capacity -- crucial for preserving the generative capabilities of diffusion models. Furthermore, we propose a method to compress the codebook by evaluating the importance of each vector and removing redundancy, ensuring the model size remaining within the desired range. We also introduce an end-to-end calibration approach that adjusts assignments during the forward pass and optimizes the codebook using the DDPM loss. By compressing the model to as low as 1 bit (resulting in over 24 times reduction in model size), we achieve a balance between compression and quality. We apply our compression method to the DiT model on ImageNet and consistently outperform other quantization approaches, demonstrating competitive generative performance.
Authors: Hao Li, Yuanyuan Gao, Haosong Peng, Chenming Wu, Weicai Ye, Yufeng Zhan, Chen Zhao, Dingwen Zhang, Jingdong Wang, Junwei Han
Abstract: Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. However, these methods rely heavily on dense image inputs and prolonged training times, making them unsuitable where computational resources are limited. Additionally, few-shot methods often struggle with poor reconstruction quality in vast environments. This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes. Our approach divides the scene into regions, processed independently by drones with sparse image inputs. Using a feed-forward Gaussian model, we predict high-quality Gaussian primitives, followed by a global alignment algorithm to ensure geometric consistency. Synthetic views and depth priors are incorporated to further enhance training, while a distillation-based model aggregation mechanism enables efficient reconstruction. Our method achieves high-quality large-scale scene reconstruction and novel-view synthesis in significantly reduced training times, outperforming existing approaches in both speed and scalability. We demonstrate the effectiveness of our framework on vast aerial scenes, achieving high-quality results within minutes. Code will released on our [https://3d-aigc.github.io/DGTR].
Authors: Nhan T. Luu
Abstract: Face recognition is a core task in computer vision designed to identify and authenticate individuals by analyzing facial patterns and features. This field intersects with artificial intelligence image processing and machine learning with applications in security authentication and personalization. Traditional approaches in facial recognition focus on capturing facial features like the eyes, nose and mouth and matching these against a database to verify identities. However challenges such as high false positive rates have persisted often due to the similarity among individuals facial features. Recently Contrastive Language Image Pretraining (CLIP) a model developed by OpenAI has shown promising advancements by linking natural language processing with vision tasks allowing it to generalize across modalities. Using CLIP's vision language correspondence and single-shot finetuning the model can achieve lower false positive rates upon deployment without the need of mass facial features extraction. This integration demonstrating CLIP's potential to address persistent issues in face recognition model performance without complicating our training paradigm.
Authors: Muhammad Usman Khalid
Abstract: Sparse principal component analysis (sPCA) enhances the interpretability of principal components (PCs) by imposing sparsity constraints on loading vectors (LVs). However, when used as a precursor to independent component analysis (ICA) for blind source separation (BSS), sPCA may underperform due to its focus on simplicity, potentially disregarding some statistical information essential for effective ICA. To overcome this limitation, a sophisticated approach is proposed that preserves the interpretability advantages of sPCA while significantly enhancing its source extraction capabilities. This consists of two tailored algorithms, dissociative PCA (DPCA1 and DPCA2), which employ adaptive and firm thresholding alongside gradient and coordinate descent approaches to optimize the proposed model dynamically. These algorithms integrate left and right singular vectors from singular value decomposition (SVD) through dissociation matrices (DMs) that replace traditional singular values, thus capturing latent interdependencies effectively to model complex source relationships. This leads to refined PCs and LVs that more accurately represent the underlying data structure. The proposed approach avoids focusing on individual eigenvectors, instead, it collaboratively combines multiple eigenvectors to disentangle interdependencies within each SVD variate. The superior performance of the proposed DPCA algorithms is demonstrated across four varied imaging applications including functional magnetic resonance imaging (fMRI) source retrieval, foreground-background separation, image reconstruction, and image inpainting. They outperformed traditional methods such as PCA+ICA, PPCA+ICA, SPCA+ICA, PMD, and GPower.
Authors: Yongyu Wang
Abstract: This paper introduces an innovative approach to dramatically accelerate UMAP using spectral data compression.The proposed method significantly reduces the size of the dataset, preserving its essential manifold structure through an advanced spectral compression technique. This allows UMAP to perform much faster while maintaining the quality of its embeddings. Experiments on real-world datasets, such as USPS, demonstrate the method's ability to achieve substantial data reduction without compromising embedding fidelity.
Authors: Bingli Wang, Houcheng Su, Nan Yin, Mengzhu Wang, Li Shen
Abstract: As a technique to alleviate the pressure of data annotation, semi-supervised learning (SSL) has attracted widespread attention. In the specific domain of medical image segmentation, semi-supervised methods (SSMIS) have become a research hotspot due to their ability to reduce the need for large amounts of precisely annotated data. SSMIS focuses on enhancing the model's generalization performance by leveraging a small number of labeled samples and a large number of unlabeled samples. The latest sharpness-aware optimization (SAM) technique, which optimizes the model by reducing the sharpness of the loss function, has shown significant success in SSMIS. However, SAM and its variants may not fully account for the distribution differences between different datasets. To address this issue, we propose a sharpness-aware optimization method based on $f$-divergence minimization (DiM) for semi-supervised medical image segmentation. This method enhances the model's stability by fine-tuning the sensitivity of model parameters and improves the model's adaptability to different datasets through the introduction of $f$-divergence. By reducing $f$-divergence, the DiM method not only improves the performance balance between the source and target datasets but also prevents performance degradation due to overfitting on the source dataset.
Authors: Yudong Han, Qingpei Guo, Liyuan Pan, Liu Liu, Yu Guan, Ming Yang
Abstract: The challenge in LLM-based video understanding lies in preserving visual and semantic information in long videos while maintaining a memory-affordable token count. However, redundancy and correspondence in videos have hindered the performance potential of existing methods. Through statistical learning on current datasets, we observe that redundancy occurs in both repeated and answer-irrelevant frames, and the corresponding frames vary with different questions. This suggests the possibility of adopting dynamic encoding to balance detailed video information preservation with token budget reduction. To this end, we propose a dynamic cooperative network, DynFocus, for memory-efficient video encoding in this paper. Specifically, i) a Dynamic Event Prototype Estimation (DPE) module to dynamically select meaningful frames for question answering; (ii) a Compact Cooperative Encoding (CCE) module that encodes meaningful frames with detailed visual appearance and the remaining frames with sketchy perception separately. We evaluate our method on five publicly available benchmarks, and experimental results consistently demonstrate that our method achieves competitive performance.
Authors: Mustafa M. Abd Zaid, Ahmed Abed Mohammed, Putra Sumari
Abstract: Satellite imagery has dramatically revolutionized the field of geography by giving academics, scientists, and policymakers unprecedented global access to spatial data. Manual methods typically require significant time and effort to detect the generic land structure in satellite images. This study can produce a set of applications such as urban planning and development, environmental monitoring, disaster management, etc. Therefore, the research presents a methodology to minimize human labor, reducing the expenses and duration needed to identify the land structure. This article developed a deep learning-based approach to automate the process of classifying geographical land structures. We used a satellite image dataset acquired from MLRSNet. The study compared the performance of three architectures, namely CNN, ResNet-50, and Inception-v3. We used three optimizers with any model: Adam, SGD, and RMSProp. We conduct the training process for a fixed number of epochs, specifically 100 epochs, with a batch size of 64. The ResNet-50 achieved an accuracy of 76.5% with the ADAM optimizer, the Inception-v3 with RMSProp achieved an accuracy of 93.8%, and the proposed approach, CNN with RMSProp optimizer, achieved the highest level of performance and an accuracy of 94.8%. Moreover, a thorough examination of the CNN model demonstrated its exceptional accuracy, recall, and F1 scores for all categories, confirming its resilience and dependability in precisely detecting various terrain formations. The results highlight the potential of deep learning models in scene understanding, as well as their significance in efficiently identifying and categorizing land structures from satellite imagery.
Authors: Ziyang Chen, Yongjun Zhang, Wenting Li, Bingshu Wang, Yong Zhao, C. L. Philip Chen
Abstract: Real-world applications of stereo matching, such as autonomous driving, place stringent demands on both safety and accuracy. However, learning-based stereo matching methods inherently suffer from the loss of geometric structures in certain feature channels, creating a bottleneck in achieving precise detail matching. Additionally, these methods lack interpretability due to the black-box nature of deep learning. In this paper, we propose MoCha-V2, a novel learning-based paradigm for stereo matching. MoCha-V2 introduces the Motif Correlation Graph (MCG) to capture recurring textures, which are referred to as ``motifs" within feature channels. These motifs reconstruct geometric structures and are learned in a more interpretable way. Subsequently, we integrate features from multiple frequency domains through wavelet inverse transformation. The resulting motif features are utilized to restore geometric structures in the stereo matching process. Experimental results demonstrate the effectiveness of MoCha-V2. MoCha-V2 achieved 1st place on the Middlebury benchmark at the time of its release. Code is available at https://github.com/ZYangChen/MoCha-Stereo.
Authors: Gaoshuang Huang, Yang Zhou, Luying Zhao, Wenjian Gan
Abstract: Cross-view geo-localization (CVGL), which involves matching and retrieving satellite images to determine the geographic location of a ground image, is crucial in GNSS-constrained scenarios. However, this task faces significant challenges due to substantial viewpoint discrepancies, the complexity of localization scenarios, and the need for global localization. To address these issues, we propose a novel CVGL framework that integrates the vision foundational model DINOv2 with an advanced feature mixer. Our framework introduces the symmetric InfoNCE loss and incorporates near-neighbor sampling and dynamic similarity sampling strategies, significantly enhancing localization accuracy. Experimental results show that our framework surpasses existing methods across multiple public and self-built datasets. To further improve globalscale performance, we have developed CV-Cities, a novel dataset for global CVGL. CV-Cities includes 223,736 ground-satellite image pairs with geolocation data, spanning sixteen cities across six continents and covering a wide range of complex scenarios, providing a challenging benchmark for CVGL. The framework trained with CV-Cities demonstrates high localization accuracy in various test cities, highlighting its strong globalization and generalization capabilities. Our datasets and codes are available at https://github.com/GaoShuang98/CVCities.
Authors: Haodong Chen, Runnan Chen, Qiang Qu, Zhaoqing Wang, Tongliang Liu, Xiaoming Chen, Yuk Ying Chung
Abstract: Recent advancements in 3D Gaussian Splatting (3DGS) have substantially improved novel view synthesis, enabling high-quality reconstruction and real-time rendering. However, blurring artifacts, such as floating primitives and over-reconstruction, remain challenging. Current methods address these issues by refining scene structure, enhancing geometric representations, addressing blur in training images, improving rendering consistency, and optimizing density control, yet the role of kernel design remains underexplored. We identify the soft boundaries of Gaussian ellipsoids as one of the causes of these artifacts, limiting detail capture in high-frequency regions. To bridge this gap, we introduce 3D Linear Splatting (3DLS), which replaces Gaussian kernels with linear kernels to achieve sharper and more precise results, particularly in high-frequency regions. Through evaluations on three datasets, 3DLS demonstrates state-of-the-art fidelity and accuracy, along with a 30% FPS improvement over baseline 3DGS. The implementation will be made publicly available upon acceptance.
Authors: Kecheng Chen, Pingping Zhang, Hui Liu, Jie Liu, Yibing Liu, Jixin Huang, Shiqi Wang, Hong Yan, Haoliang Li
Abstract: We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data modalities. This attribute particularly appeals to the lossless image compression community, given the increasing need to compress high-resolution images in the current streaming media era. Consequently, a spontaneous envision emerges: Can the compression performance of the LLM elevate lossless image compression to new heights? However, our findings indicate that the naive application of LLM-based lossless image compressors suffers from a considerable performance gap compared with existing state-of-the-art (SOTA) codecs on common benchmark datasets. In light of this, we are dedicated to fulfilling the unprecedented intelligence (compression) capacity of the LLM for lossless image compression tasks, thereby bridging the gap between theoretical and practical compression performance. Specifically, we propose P$^{2}$-LLM, a next-pixel prediction-based LLM, which integrates various elaborated insights and methodologies, \textit{e.g.,} pixel-level priors, the in-context ability of LLM, and a pixel-level semantic preservation strategy, to enhance the understanding capacity of pixel sequences for better next-pixel predictions. Extensive experiments on benchmark datasets demonstrate that P$^{2}$-LLM can beat SOTA classical and learned codecs.
Authors: Jun Xiao, Zihang Lyu, Hao Xie, Cong Zhang, Yakun Ju, Changjian Shui, Kin-Man Lam
Abstract: Blind image restoration remains a significant challenge in low-level vision tasks. Recently, denoising diffusion models have shown remarkable performance in image synthesis. Guided diffusion models, leveraging the potent generative priors of pre-trained models along with a differential guidance loss, have achieved promising results in blind image restoration. However, these models typically consider data consistency solely in the spatial domain, often resulting in distorted image content. In this paper, we propose a novel frequency-aware guidance loss that can be integrated into various diffusion models in a plug-and-play manner. Our proposed guidance loss, based on 2D discrete wavelet transform, simultaneously enforces content consistency in both the spatial and frequency domains. Experimental results demonstrate the effectiveness of our method in three blind restoration tasks: blind image deblurring, imaging through turbulence, and blind restoration for multiple degradations. Notably, our method achieves a significant improvement in PSNR score, with a remarkable enhancement of 3.72\,dB in image deblurring. Moreover, our method exhibits superior capability in generating images with rich details and reduced distortion, leading to the best visual quality.
Authors: Shaoqing Xu, Fang Li, Shengyin Jiang, Ziying Song, Li Liu, Zhi-xin Yang
Abstract: Self-supervised learning has made substantial strides in image processing, while visual pre-training for autonomous driving is still in its infancy. Existing methods often focus on learning geometric scene information while neglecting texture or treating both aspects separately, hindering comprehensive scene understanding. In this context, we are excited to introduce GaussianPretrain, a novel pre-training paradigm that achieves a holistic understanding of the scene by uniformly integrating geometric and texture representations. Conceptualizing 3D Gaussian anchors as volumetric LiDAR points, our method learns a deepened understanding of scenes to enhance pre-training performance with detailed spatial structure and texture, achieving that 40.6% faster than NeRF-based method UniPAD with 70% GPU memory only. We demonstrate the effectiveness of GaussianPretrain across multiple 3D perception tasks, showing significant performance improvements, such as a 7.05% increase in NDS for 3D object detection, boosts mAP by 1.9% in HD map construction and 0.8% improvement on Occupancy prediction. These significant gains highlight GaussianPretrain's theoretical innovation and strong practical potential, promoting visual pre-training development for autonomous driving. Source code will be available at https://github.com/Public-BOTs/GaussianPretrain
Authors: Zixu Wang, Hao Yang, Yu Guo, Fei Wang
Abstract: Snapshot Compressive Imaging (SCI) offers a possibility for capturing information in high-speed dynamic scenes, requiring efficient reconstruction method to recover scene information. Despite promising results, current deep learning-based and NeRF-based reconstruction methods face challenges: 1) deep learning-based reconstruction methods struggle to maintain 3D structural consistency within scenes, and 2) NeRF-based reconstruction methods still face limitations in handling dynamic scenes. To address these challenges, we propose SCIGS, a variant of 3DGS, and develop a primitive-level transformation network that utilizes camera pose stamps and Gaussian primitive coordinates as embedding vectors. This approach resolves the necessity of camera pose in vanilla 3DGS and enhances multi-view 3D structural consistency in dynamic scenes by utilizing transformed primitives. Additionally, a high-frequency filter is introduced to eliminate the artifacts generated during the transformation. The proposed SCIGS is the first to reconstruct a 3D explicit scene from a single compressed image, extending its application to dynamic 3D scenes. Experiments on both static and dynamic scenes demonstrate that SCIGS not only enhances SCI decoding but also outperforms current state-of-the-art methods in reconstructing dynamic 3D scenes from a single compressed image. The code will be made available upon publication.
Authors: Joanna Kaleta, Weronika Smolak-Dy\.zewska, Dawid Malarz, Diego Dall'Alba, Przemys{\l}aw Korzeniowski, Przemys{\l}aw Spurek
Abstract: Endoscopic procedures are crucial for colorectal cancer diagnosis, and three-dimensional reconstruction of the environment for real-time novel-view synthesis can significantly enhance diagnosis. We present PR-ENDO, a framework that leverages 3D Gaussian Splatting within a physically based, relightable model tailored for the complex acquisition conditions in endoscopy, such as restricted camera rotations and strong view-dependent illumination. By exploiting the connection between the camera and light source, our approach introduces a relighting model to capture the intricate interactions between light and tissue using physically based rendering and MLP. Existing methods often produce artifacts and inconsistencies under these conditions, which PR-ENDO overcomes by incorporating a specialized diffuse MLP that utilizes light angles and normal vectors, achieving stable reconstructions even with limited training camera rotations. We benchmarked our framework using a publicly available dataset and a newly introduced dataset with wider camera rotations. Our methods demonstrated superior image quality compared to baseline approaches.
Authors: Quang Vinh Nguyen, Vo Hoang Thanh Son, Chau Truong Vinh Hoang, Duc Duy Nguyen, Nhat Huy Nguyen Minh, Soo-Hyung Kim
Abstract: Naturalistic driving action localization task aims to recognize and comprehend human behaviors and actions from video data captured during real-world driving scenarios. Previous studies have shown great action localization performance by applying a recognition model followed by probability-based post-processing. Nevertheless, the probabilities provided by the recognition model frequently contain confused information causing challenge for post-processing. In this work, we adopt an action recognition model based on self-supervise learning to detect distracted activities and give potential action probabilities. Subsequently, a constraint ensemble strategy takes advantages of multi-camera views to provide robust predictions. Finally, we introduce a conditional post-processing operation to locate distracted behaviours and action temporal boundaries precisely. Experimenting on test set A2, our method obtains the sixth position on the public leaderboard of track 3 of the 2024 AI City Challenge.
Authors: Yang Zou, Zhixin Chen, Zhipeng Zhang, Xingyuan Li, Long Ma, Jinyuan Liu, Peng Wang, Yanning Zhang
Abstract: Image super-resolution (SR) is a classical yet still active low-level vision problem that aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, serving as a key technique for image enhancement. Current approaches to address SR tasks, such as transformer-based and diffusion-based methods, are either dedicated to extracting RGB image features or assuming similar degradation patterns, neglecting the inherent modal disparities between infrared and visible images. When directly applied to infrared image SR tasks, these methods inevitably distort the infrared spectral distribution, compromising the machine perception in downstream tasks. In this work, we emphasize the infrared spectral distribution fidelity and propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity. Our approach captures high-pass subbands from multi-scale and multi-directional infrared spectral decomposition to recover infrared-degraded information through a gate architecture. The proposed Spectral Fidelity Loss regularizes the spectral frequency distribution during reconstruction, which ensures the preservation of both high- and low-frequency components and maintains the fidelity of infrared-specific features. We propose a two-stage prompt-learning optimization to guide the model in learning infrared HR characteristics from LR degradation. Extensive experiments demonstrate that our approach outperforms existing image SR models in both visual and perceptual tasks while notably enhancing machine perception in downstream tasks. Our code is available at https://github.com/hey-it-s-me/CoRPLE.
Authors: Ismail Nejjar, Hao Dong, Olga Fink
Abstract: Open-set Domain Adaptation (OSDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where novel classes - also referred to as target-private unknown classes - are present. Source-free Open-set Domain Adaptation (SF-OSDA) methods address OSDA without accessing labeled source data, making them particularly relevant under privacy constraints. However, SF-OSDA presents significant challenges due to distribution shifts and the introduction of novel classes. Existing SF-OSDA methods typically rely on thresholding the prediction entropy of a sample to identify it as either a known or unknown class but fail to explicitly learn discriminative features for the target-private unknown classes. We propose Recall and Refine (RRDA), a novel SF-OSDA framework designed to address these limitations by explicitly learning features for target-private unknown classes. RRDA employs a two-step process. First, we enhance the model's capacity to recognize unknown classes by training a target classifier with an additional decision boundary, guided by synthetic samples generated from target domain features. This enables the classifier to effectively separate known and unknown classes. In the second step, we adapt the entire model to the target domain, addressing both domain shifts and improving generalization to unknown classes. Any off-the-shelf source-free domain adaptation method (e.g., SHOT, AaD) can be seamlessly integrated into our framework at this stage. Extensive experiments on three benchmark datasets demonstrate that RRDA significantly outperforms existing SF-OSDA and OSDA methods.
Authors: Zeyu Liang, Hailun Xia, Naichuan Zheng, Huan Xu
Abstract: Skeleton-based action recognition has achieved remarkable performance with the development of graph convolutional networks (GCNs). However, most of these methods tend to construct complex topology learning mechanisms while neglecting the inherent symmetry of the human body. Additionally, the use of temporal convolutions with certain fixed receptive fields limits their capacity to effectively capture dependencies in time sequences. To address the issues, we (1) propose a novel Topological Symmetry Enhanced Graph Convolution (TSE-GC) to enable distinct topology learning across different channel partitions while incorporating topological symmetry awareness and (2) construct a Multi-Branch Deformable Temporal Convolution (MBDTC) for skeleton-based action recognition. The proposed TSE-GC emphasizes the inherent symmetry of the human body while enabling efficient learning of dynamic topologies. Meanwhile, the design of MBDTC introduces the concept of deformable modeling, leading to more flexible receptive fields and stronger modeling capacity of temporal dependencies. Combining TSE-GC with MBDTC, our final model, TSE-GCN, achieves competitive performance with fewer parameters compared with state-of-the-art methods on three large datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA. On the cross-subject and cross-set evaluations of NTU RGB+D 120, the accuracies of our model reach 90.0\% and 91.1\%, with 1.1M parameters and 1.38 GFLOPS for one stream.
Authors: Xudong Yan, Songhe Feng, Yang Zhang, Jian Yang, Yueguan Lin, Haojun Fei
Abstract: Compositional zero-shot learning (CZSL) aims to recognize novel compositions of attributes and objects learned from seen compositions. Previous works disentangle attribute and object by extracting shared and exclusive parts between image pairs sharing the same attribute (object), as well as aligning them with pretrained word embeddings to improve unseen attribute-object recognition. Despite the significant achievements of existing efforts, they are hampered by three limitations: (1) the efficacy of disentanglement is compromised due to the influence of the background and the intricate entanglement of attribute with object in the same parts. (2) existing word embeddings fail to capture complex multimodal semantic information. (3) overconfidence exhibited by existing models in seen compositions hinders their generalization to novel compositions. Being aware of these, we propose a novel framework named Multimodal Large Language Model (MLLM) embeddings and attribute smoothing guided disentanglement (TRIDENT) for CZSL. First, we leverage feature adaptive aggregation modules to mitigate the impact of background, and utilize learnable condition masks to capture multigranularity features for disentanglement. Then, the last hidden states of MLLM are employed as word embeddings for their superior representation capabilities. Moreover, we propose attribute smoothing with auxiliary attributes generated by Large Language Model (LLM) for seen compositions, addressing the issue of overconfidence by encouraging the model to learn more attributes in one given composition. Extensive experiments demonstrate that TRIDENT achieves state-of-the-art performance on three benchmarks.
Authors: Huafeng Li, Jiaqi Fang, Yafei Zhang, Yu Liu
Abstract: Infrared and visible (IR-VIS) image fusion has gained significant attention for its broad application value. However, existing methods often neglect the complementary role of infrared image in restoring visible image features under hazy conditions. To address this, we propose a joint learning framework that utilizes infrared image for the restoration and fusion of hazy IR-VIS images. To mitigate the adverse effects of feature diversity between IR-VIS images, we introduce a prompt generation mechanism that regulates modality-specific feature incompatibility. This creates a prompt selection matrix from non-shared image information, followed by prompt embeddings generated from a prompt pool. These embeddings help generate candidate features for dehazing. We further design an infrared-assisted feature restoration mechanism that selects candidate features based on haze density, enabling simultaneous restoration and fusion within a single-stage framework. To enhance fusion quality, we construct a multi-stage prompt embedding fusion module that leverages feature supplementation from the prompt generation module. Our method effectively fuses IR-VIS images while removing haze, yielding clear, haze-free fusion results. In contrast to two-stage methods that dehaze and then fuse, our approach enables collaborative training in a single-stage framework, making the model relatively lightweight and suitable for practical deployment. Experimental results validate its effectiveness and demonstrate advantages over existing methods.
Authors: Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
Abstract: Transformers have revolutionized Computer Vision (CV) and Natural Language Processing (NLP) through self-attention mechanisms. However, due to their complexity, their latent token representations are often difficult to interpret. We introduce a novel framework that interprets Transformer embeddings, uncovering meaningful semantic patterns within them. Based on this framework, we demonstrate that zero-shot unsupervised semantic segmentation can be performed effectively without any fine-tuning using a model pre-trained for tasks other than segmentation. Our method reveals the inherent capacity of Transformer models for understanding input semantics and achieves state-of-the-art performance in semantic segmentation, outperforming traditional segmentation models. Specifically, our approach achieves an accuracy of 67.2 % and an mIoU of 32.9 % on the COCO-Stuff dataset, as well as an mIoU of 51.9 % on the PASCAL VOC dataset. Additionally, we validate our interpretability framework on LLMs for text summarization, demonstrating its broad applicability and robustness.
Authors: Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Estelle Aflalo, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
Abstract: Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots that can engage in conversations about a provided input, such as an image. However, their responses are influenced by societal biases present in their training datasets, leading to undesirable differences in how the model responds when presented with images depicting people of different demographics. In this work, we propose a novel debiasing framework for LMMs that directly removes biased representations during text generation to decrease outputs related to protected attributes, or even representing them internally. Our proposed method is training-free; given a single image and a list of target attributes, we can ablate the corresponding representations with just one step of gradient descent on the image itself. Our experiments show that not only can we can minimize the propensity of LMMs to generate text related to protected attributes, but we can improve sentiment and even simply use synthetic data to inform the ablation while retaining language modeling capabilities on real data such as COCO or FACET. Furthermore, we find the resulting generations from a debiased LMM exhibit similar accuracy as a baseline biased model, showing that debiasing effects can be achieved without sacrificing model performance.
Authors: Haojie Zheng, Tianyang Xu, Hanchi Sun, Shu Pu, Ruoxi Chen, Lichao Sun
Abstract: Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension. In this paper, we find that the thinking while looking paradigm in current multimodal CoT approaches--where reasoning chains are generated alongside visual input--fails to mitigate hallucinations caused by misleading images. To address these limitations, we propose the Visual Inference Chain (VIC) framework, a novel approach that constructs reasoning chains using textual context alone before introducing visual input, effectively reducing cross-modal biases and enhancing multimodal reasoning accuracy. Comprehensive evaluations demonstrate that VIC significantly improves zero-shot performance across various vision-related tasks, mitigating hallucinations while refining the reasoning capabilities of MLLMs. Our code repository can be found at https://github.com/Terry-Xu-666/visual_inference_chain.
URLs: https://github.com/Terry-Xu-666/visual_inference_chain.
Authors: Yutao Tang, Yuxiang Guo, Deming Li, Cheng Peng
Abstract: Recent efforts in Gaussian-Splat-based Novel View Synthesis can achieve photorealistic rendering; however, such capability is limited in sparse-view scenarios due to sparse initialization and over-fitting floaters. Recent progress in depth estimation and alignment can provide dense point cloud with few views; however, the resulting pose accuracy is suboptimal. In this work, we present SPARS3R, which combines the advantages of accurate pose estimation from Structure-from-Motion and dense point cloud from depth estimation. To this end, SPARS3R first performs a Global Fusion Alignment process that maps a prior dense point cloud to a sparse point cloud from Structure-from-Motion based on triangulated correspondences. RANSAC is applied during this process to distinguish inliers and outliers. SPARS3R then performs a second, Semantic Outlier Alignment step, which extracts semantically coherent regions around the outliers and performs local alignment in these regions. Along with several improvements in the evaluation process, we demonstrate that SPARS3R can achieve photorealistic rendering with sparse images and significantly outperforms existing approaches.
Authors: Yuanbin Man, Ying Huang, Chengming Zhang, Bingzhe Li, Wei Niu, Miao Yin
Abstract: The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to processing short-duration videos. Recent attempts to understand long-term videos by extracting and compressing visual features into a fixed memory size. Nevertheless, those methods leverage only visual modality to merge video tokens and overlook the correlation between visual and textual queries, leading to difficulties in effectively handling complex question-answering tasks. To address the challenges of long videos and complex prompts, we propose AdaCM$^2$, which, for the first time, introduces an adaptive cross-modality memory reduction approach to video-text alignment in an auto-regressive manner on video streams. Our extensive experiments on various video understanding tasks, such as video captioning, video question answering, and video classification, demonstrate that AdaCM$^2$ achieves state-of-the-art performance across multiple datasets while significantly reducing memory usage. Notably, it achieves a 4.5% improvement across multiple tasks in the LVU dataset with a GPU memory consumption reduction of up to 65%.
Authors: Ron Keuth, Lasse Hansen, Maren Balks, Ronja J\"ager, Anne-Nele Schr\"oder, Ludger T\"ushaus, Mattias Heinrich
Abstract: Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently introduced Segment Anything Model (SAM) enables prompt-based segmentation and offers zero-shot generalization to unfamiliar objects. In our work, we leverage SAM's abstract object understanding for medical image segmentation to provide pseudo labels for semi-supervised learning, thereby mitigating the need for extensive annotated training data. Our approach refines initial segmentations that are derived from a limited amount of annotated data (comprising up to 43 cases) by extracting bounding boxes and seed points as prompts forwarded to SAM. Thus, it enables the generation of dense segmentation masks as pseudo labels for unlabelled data. The results show that training with our pseudo labels yields an improvement in Dice score from $74.29\,\%$ to $84.17\,\%$ and from $66.63\,\%$ to $74.87\,\%$ for the segmentation of bones of the paediatric wrist and teeth in dental radiographs, respectively. As a result, our method outperforms intensity-based post-processing methods, state-of-the-art supervised learning for segmentation (nnU-Net), and the semi-supervised mean teacher approach. Our Code is available on GitHub.
Authors: Mark Sch\"one, Yash Bhisikar, Karan Bania, Khaleelulla Khan Nazeer, Christian Mayr, Anand Subramoney, David Kappel
Abstract: Handling sparse and unstructured geometric data, such as point clouds or event-based vision, is a pressing challenge in the field of machine vision. Recently, sequence models such as Transformers and state-space models entered the domain of geometric data. These methods require specialized preprocessing to create a sequential view of a set of points. Furthermore, prior works involving sequence models iterate geometric data with either uniform or learned step sizes, implicitly relying on the model to infer the underlying geometric structure. In this work, we propose to encode geometric structure explicitly into the parameterization of a state-space model. State-space models are based on linear dynamics governed by a one-dimensional variable such as time or a spatial coordinate. We exploit this dynamic variable to inject relative differences of coordinates into the step size of the state-space model. The resulting geometric operation computes interactions between all pairs of N points in O(N) steps. Our model deploys the Mamba selective state-space model with a modified CUDA kernel to efficiently map sparse geometric data to modern hardware. The resulting sequence model, which we call STREAM, achieves competitive results on a range of benchmarks from point-cloud classification to event-based vision and audio classification. STREAM demonstrates a powerful inductive bias for sparse geometric data by improving the PointMamba baseline when trained from scratch on the ModelNet40 and ScanObjectNN point cloud analysis datasets. It further achieves, for the first time, 100% test accuracy on all 11 classes of the DVS128 Gestures dataset.
Authors: Zhiwen Shao, Yichen Yuan, Lizhuang Ma, Dit-Yan Yeung, Xiaojia Zhu
Abstract: Automatic Cobb angle measurement from X-ray images is crucial for scoliosis screening and diagnosis. However, most existing regression-based methods and segmentation-based methods struggle with inaccurate spine representations or mask connectivity/fragmentation issues. Besides, landmark-based methods suffer from insufficient training data and annotations. To address these challenges, we propose a novel framework including Self-Generation pipeline and Low-Rank Approximation representation (SG-LRA) for automatic Cobb angle measurement. Specifically, we propose a parameterized spine contour representation based on LRA, which enables eigen-spine decomposition and spine contour reconstruction. We can directly obtain spine contour with only regressed LRA coefficients, which form a more accurate spine representation than rectangular boxes. Also, we combine LRA coefficient regression with anchor box classification to solve inaccurate predictions and mask connectivity issues. Moreover, we develop a data engine with automatic annotation and automatic selection in an iterative manner, which is trained on a private Spinal2023 dataset. With our data engine, we generate the largest scoliosis X-ray dataset named Spinal-AI2024 largely without privacy leaks. Extensive experiments on public AASCE2019, private Spinal2023, and generated Spinal-AI2024 datasets demonstrate that our method achieves state-of-the-art Cobb angle measurement performance. Our code and Spinal-AI2024 dataset are available at https://github.com/Ernestchenchen/SG-LRA and https://github.com/Ernestchenchen/Spinal-AI2024, respectively.
URLs: https://github.com/Ernestchenchen/SG-LRA, https://github.com/Ernestchenchen/Spinal-AI2024,
Authors: Jiaqi Yang, Nitish Mehta, Xiaoling Hu, Chao Chen, Chia-Ling Tsai
Abstract: Accurate segmentation of Optical Coherence Tomography (OCT) images is crucial for diagnosing and monitoring retinal diseases. However, the labor-intensive nature of pixel-level annotation limits the scalability of supervised learning with large datasets. Weakly Supervised Semantic Segmentation (WSSS) provides a promising alternative by leveraging image-level labels. In this study, we propose a novel WSSS approach that integrates structural guidance with text-driven strategies to generate high-quality pseudo labels, significantly improving segmentation performance. In terms of visual information, our method employs two processing modules that exchange raw image features and structural features from OCT images, guiding the model to identify where lesions are likely to occur. In terms of textual information, we utilize large-scale pretrained models from cross-domain sources to implement label-informed textual guidance and synthetic descriptive integration with two textual processing modules that combine local semantic features with consistent synthetic descriptions. By fusing these visual and textual components within a multimodal framework, our approach enhances lesion localization accuracy. Experimental results on three OCT datasets demonstrate that our method achieves state-of-the-art performance, highlighting its potential to improve diagnostic accuracy and efficiency in medical imaging.
Authors: Matteo Toso, Stefano Fiorini, Stuart James, Alessio Del Bue
Abstract: World-wide detailed 2D maps require enormous collective efforts. OpenStreetMap is the result of 11 million registered users manually annotating the GPS location of over 1.75 billion entries, including distinctive landmarks and common urban objects. At the same time, manual annotations can include errors and are slow to update, limiting the map's accuracy. Maps from Motion (MfM) is a step forward to automatize such time-consuming map making procedure by computing 2D maps of semantic objects directly from a collection of uncalibrated multi-view images. From each image, we extract a set of object detections, and estimate their spatial arrangement in a top-down local map centered in the reference frame of the camera that captured the image. Aligning these local maps is not a trivial problem, since they provide incomplete, noisy fragments of the scene, and matching detections across them is unreliable because of the presence of repeated pattern and the limited appearance variability of urban objects. We address this with a novel graph-based framework, that encodes the spatial and semantic distribution of the objects detected in each image, and learns how to combine them to predict the objects' poses in a global reference system, while taking into account all possible detection matches and preserving the topology observed in each image. Despite the complexity of the problem, our best model achieves global 2D registration with an average accuracy within 4 meters (i.e., below GPS accuracy) even on sparse sequences with strong viewpoint change, on which COLMAP has an 80% failure rate. We provide extensive evaluation on synthetic and real-world data, showing how the method obtains a solution even in scenarios where standard optimization techniques fail.
Authors: Luoxi Zhang, Pragyan Shrestha, Yu Zhou, Chun Xie, Itaru Kitahara
Abstract: The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant difficulties in balancing the extraction of global and local features, particularly in diverse and complex environments, leading to insufficient reconstruction precision and quality. We propose M3D, a novel single-view 3D reconstruction framework, to tackle these challenges. This framework adopts a dual-stream feature extraction strategy based on Selective State Spaces to effectively balance the extraction of global and local features, thereby improving scene comprehension and representation precision. Additionally, a parallel branch extracts depth information, effectively integrating visual and geometric features to enhance reconstruction quality and preserve intricate details. Experimental results indicate that the fusion of multi-scale features with depth information via the dual-branch feature extraction significantly boosts geometric consistency and fidelity, achieving state-of-the-art reconstruction performance.
Authors: David Picard, Nicolas Dufour
Abstract: Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly attention patterns, as the requirements both in terms of memory and compute grow quadratically. To alleviate this problem, we propose a drop-in replacement for MHA called the Polynomial Mixer (PoM) that has the benefit of encoding the entire sequence into an explicit state. PoM has a linear complexity with respect to the number of tokens. This explicit state also allows us to generate frames in a sequential fashion, minimizing memory and compute requirement, while still being able to train in parallel. We show the Polynomial Mixer is a universal sequence-to-sequence approximator, just like regular MHA. We adapt several Diffusion Transformers (DiT) for generating images and videos with PoM replacing MHA, and we obtain high quality samples while using less computational resources. The code is available at https://github.com/davidpicard/HoMM.
Authors: Fei Ren, Chao Ren, Tianyi Lyu
Abstract: This study proposes the IoT-Enhanced Pose Optimization Network (IE-PONet) for high-precision 3D pose estimation and motion optimization of track and field athletes. IE-PONet integrates C3D for spatiotemporal feature extraction, OpenPose for real-time keypoint detection, and Bayesian optimization for hyperparameter tuning. Experimental results on NTURGB+D and FineGYM datasets demonstrate superior performance, with AP\(^p50\) scores of 90.5 and 91.0, and mAP scores of 74.3 and 74.0, respectively. Ablation studies confirm the essential roles of each module in enhancing model accuracy. IE-PONet provides a robust tool for athletic performance analysis and optimization, offering precise technical insights for training and injury prevention. Future work will focus on further model optimization, multimodal data integration, and developing real-time feedback mechanisms to enhance practical applications.
Authors: Devakumar GR, JB Kaarthikeyan, Dominic Immanuel T, Sheena Christabel Pravin
Abstract: Understanding the appropriate skin layer thickness in wounded sites is an important tool to move forward on wound healing practices and treatment protocols. Methods to measure depth often are invasive and less specific. This paper introduces a novel method that is non-invasive with deep learning techniques using classifying of skin layers that helps in measurement of wound depth through heatmap analysis. A set of approximately 200 labeled images of skin allows five classes to be distinguished: scars, wounds, and healthy skin, among others. Each image has annotated key layers, namely the stratum cornetum, the epidermis, and the dermis, in the software Roboflow. In the preliminary stage, the Heatmap generator VGG16 was used to enhance the visibility of tissue layers, based upon which their annotated images were used to train ResNet18 with early stopping techniques. It ended up at a very high accuracy rate of 97.67%. To do this, the comparison of the models ResNet18, VGG16, DenseNet121, and EfficientNet has been done where both EfficientNet and ResNet18 have attained accuracy rates of almost 95.35%. For further hyperparameter tuning, EfficientNet and ResNet18 were trained at six different learning rates to determine the best model configuration. It has been noted that the accuracy has huge variations with different learning rates. In the case of EfficientNet, the maximum achievable accuracy was 95.35% at the rate of 0.0001. The same was true for ResNet18, which also attained its peak value of 95.35% at the same rate. These facts indicate that the model can be applied and utilized in actual-time, non-invasive wound assessment, which holds a great promise to improve clinical diagnosis and treatment planning.
Authors: Zhehan Kan, Ce Zhang, Zihan Liao, Yapeng Tian, Wenming Yang, Junyuan Xiao, Xu Li, Dongmei Jiang, Yaowei Wang, Qingmin Liao
Abstract: Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems. Despite previous efforts to mitigate hallucinations, a persistent issue remains: visual defect from vision-language misalignment, creating a bottleneck in visual processing capacity. To address this challenge, we develop Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs (CATCH), based on the Information Bottleneck theory. CATCH introduces Complementary Visual Decoupling (CVD) for visual information separation, Non-Visual Screening (NVS) for hallucination detection, and Adaptive Token-level Contrastive Decoding (ATCD) for hallucination mitigation. CATCH addresses issues related to visual defects that cause diminished fine-grained feature perception and cumulative hallucinations in open-ended scenarios. It is applicable to various visual question-answering tasks without requiring any specific data or prior knowledge, and generalizes robustly to new tasks without additional training, opening new possibilities for advancing LVLM in various challenging applications.
Authors: Zikang Zhou, Hengjian Zhou, Haibo Hu, Zihao Wen, Jianping Wang, Yung-Hui Li, Yu-Kai Huang
Abstract: Anticipating the multimodality of future events lays the foundation for safe autonomous driving. However, multimodal motion prediction for traffic agents has been clouded by the lack of multimodal ground truth. Existing works predominantly adopt the winner-take-all training strategy to tackle this challenge, yet still suffer from limited trajectory diversity and misaligned mode confidence. While some approaches address these limitations by generating excessive trajectory candidates, they necessitate a post-processing stage to identify the most representative modes, a process lacking universal principles and compromising trajectory accuracy. We are thus motivated to introduce ModeSeq, a new multimodal prediction paradigm that models modes as sequences. Unlike the common practice of decoding multiple plausible trajectories in one shot, ModeSeq requires motion decoders to infer the next mode step by step, thereby more explicitly capturing the correlation between modes and significantly enhancing the ability to reason about multimodality. Leveraging the inductive bias of sequential mode prediction, we also propose the Early-Match-Take-All (EMTA) training strategy to diversify the trajectories further. Without relying on dense mode prediction or rule-based trajectory selection, ModeSeq considerably improves the diversity of multimodal output while attaining satisfactory trajectory accuracy, resulting in balanced performance on motion prediction benchmarks. Moreover, ModeSeq naturally emerges with the capability of mode extrapolation, which supports forecasting more behavior modes when the future is highly uncertain.
Authors: Lechao Cheng, Kaifeng Chen, Jiyang Li, Shengeng Tang, Shufei Zhang, Meng Wang
Abstract: Learning from noisy data has become essential for adapting deep learning models to real-world applications. Traditional methods often involve first evaluating the noise and then applying strategies such as discarding noisy samples, re-weighting, or re-labeling. However, these methods can fall into a vicious cycle when the initial noise evaluation is inaccurate, leading to suboptimal performance. To address this, we propose a novel approach that leverages dataset distillation for noise removal. This method avoids the feedback loop common in existing techniques and enhances training efficiency, while also providing strong privacy protection through offline processing. We rigorously evaluate three representative dataset distillation methods (DATM, DANCE, and RCIG) under various noise conditions, including symmetric noise, asymmetric noise, and real-world natural noise. Our empirical findings reveal that dataset distillation effectively serves as a denoising tool in random noise scenarios but may struggle with structured asymmetric noise patterns, which can be absorbed into the distilled samples. Additionally, clean but challenging samples, such as those from tail classes in imbalanced datasets, may undergo lossy compression during distillation. Despite these challenges, our results highlight that dataset distillation holds significant promise for robust model training, especially in high-privacy environments where noise is prevalent.
Authors: Zheng Zhang, Cuong Nguyen, Kevin Wells, Thanh-Toan Do, Gustavo Carneiro
Abstract: Human-AI cooperative classification (HAI-CC) approaches aim to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabilities. Current HAI-CC methods primarily focus on learning-to-defer (L2D), where decisions are deferred to human experts, and learning-to-complement (L2C), where AI and human experts make predictions cooperatively. However, a notable research gap remains in effectively exploring both L2D and L2C under diverse expert knowledge to improve decision-making, particularly when constrained by the cooperation cost required to achieve a target probability for AI-only selection (i.e., coverage). In this paper, we address this research gap by proposing the Coverage-constrained Learning to Defer and Complement with Specific Experts (CL2DC) method. CL2DC makes final decisions through either AI prediction alone or by deferring to or complementing a specific expert, depending on the input data. Furthermore, we propose a coverage-constrained optimisation to control the cooperation cost, ensuring it approximates a target probability for AI-only selection. This approach enables an effective assessment of system performance within a specified budget. Also, CL2DC is designed to address scenarios where training sets contain multiple noisy-label annotations without any clean-label references. Comprehensive evaluations on both synthetic and real-world datasets demonstrate that CL2DC achieves superior performance compared to state-of-the-art HAI-CC methods.
Authors: Sean Wu, Jun Yu Chen, Vahid Mohammadzadeh, Sajad Besharati, Jaewon Lee, Kouros Nouri-Mahdavi, Joseph Caprioli, Zhe Fei, Fabien Scalzo
Abstract: Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression.
Authors: Rahul Garg, Trilok Padhi, Hemang Jain, Ugur Kursuncu, Ugur Kursuncu, Ponnurangam Kumaraguru
Abstract: Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge Distillation (KD) from Large Visual Language Models (LVLMs) and knowledge infusion to enhance the performance of toxicity detection in hateful memes. Our approach extracts sub-knowledge graphs from ConceptNet, a large-scale commonsense Knowledge Graph (KG) to be infused within a compact VLM framework. The relational context between toxic phrases in captions and memes, as well as visual concepts in memes enhance the model's reasoning capabilities. Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines across AU-ROC, F1, and Recall with improvements of 1.1%, 7%, and 35%, respectively. Given the contextual complexity of the toxicity detection task, our approach showcases the significance of learning from both explicit (i.e. KG) as well as implicit (i.e. LVLMs) contextual cues incorporated through a hybrid neurosymbolic approach. This is crucial for real-world applications where accurate and scalable recognition of toxic content is critical for creating safer online environments.
Authors: Zhixiang Wang, Xudong Li, Yizhai Zhang, Fan Zhang, Panfeng
Abstract: Event cameras, when combined with inertial sensors, show significant potential for motion estimation in challenging scenarios, such as high-speed maneuvers and low-light environments. There are many methods for producing such estimations, but most boil down to a synchronous discrete-time fusion problem. However, the asynchronous nature of event cameras and their unique fusion mechanism with inertial sensors remain underexplored. In this paper, we introduce a monocular event-inertial odometry method called AsynEIO, designed to fuse asynchronous event and inertial data within a unified Gaussian Process (GP) regression framework. Our approach incorporates an event-driven frontend that tracks feature trajectories directly from raw event streams at a high temporal resolution. These tracked feature trajectories, along with various inertial factors, are integrated into the same GP regression framework to enable asynchronous fusion. With deriving analytical residual Jacobians and noise models, our method constructs a factor graph that is iteratively optimized and pruned using a sliding-window optimizer. Comparative assessments highlight the performance of different inertial fusion strategies, suggesting optimal choices for varying conditions. Experimental results on both public datasets and our own event-inertial sequences indicate that AsynEIO outperforms existing methods, especially in high-speed and low-illumination scenarios.
Authors: Mahmut S. Gokmen, Jie Zhang, Ge Wang, Jin Chen, Cody Bumgardner
Abstract: Diffusion models have significant impact on wide range of generative tasks, especially on image inpainting and restoration. Although the improvements on aiming for decreasing number of function evaluations (NFE), the iterative results are still computationally expensive. Consistency models are as a new family of generative models, enable single-step sampling of high quality data without the need for adversarial training. In this paper, we introduce the beta noise distribution, which provides flexibility in adjusting noise levels. This is combined with a sinusoidal curriculum that enhances the learning of the trajectory between the noise distribution and the posterior distribution of interest, allowing High Noise Improved Consistency Training (HN-iCT) to be trained in a supervised fashion. Additionally, High Noise Improved Consistency Training with Image Condition (HN-iCT-CN) architecture is introduced, enables to take Low Dose images as a condition for extracting significant features by Weighted Attention Gates (WAG).Our results indicate that unconditional image generation using HN-iCT significantly outperforms basic CT and iCT training techniques with NFE=1 on the CIFAR10 and CelebA datasets. Moreover, our image-conditioned model demonstrates exceptional performance in enhancing low-dose (LD) CT scans.
Authors: Zheng Gong, Zhuo Deng, Run Gan, Zhiyuan Niu, Lu Chen, Canfeng Huang, Jia Liang, Weihao Gao, Fang Li, Shaochong Zhang, Lan Ma
Abstract: The retinal fundus images are utilized extensively in the diagnosis, and their quality can directly affect the diagnosis results. However, due to the insufficient dataset and algorithm application, current fundus image quality assessment (FIQA) methods are not powerful enough to meet ophthalmologists` demands. In this paper, we address the limitations of datasets and algorithms in FIQA. First, we establish a new FIQA dataset, Fundus Quality Score(FQS), which includes 2246 fundus images with two labels: a continuous Mean Opinion Score varying from 0 to 100 and a three-level quality label. Then, we propose a FIQA Transformer-based Hypernetwork (FTHNet) to solve these tasks with regression results rather than classification results in conventional FIQA works. The FTHNet is optimized for the FIQA tasks with extensive experiments. Results on our FQS dataset show that the FTHNet can give quality scores for fundus images with PLCC of 0.9423 and SRCC of 0.9488, significantly outperforming other methods with fewer parameters and less computation complexity.We successfully build a dataset and model addressing the problems of current FIQA methods. Furthermore, the model deployment experiments demonstrate its potential in automatic medical image quality control. All experiments are carried out with 10-fold cross-validation to ensure the significance of the results.
Authors: Nai-Xuan Ye, Tan-Ha Mai, Hsiu-Hsuan Wang, Wei-I Lin, Hsuan-Tien Lin
Abstract: Complementary-label learning (CLL) is a weakly supervised learning paradigm for multiclass classification, where only complementary labels -- indicating classes an instance does not belong to -- are provided to the learning algorithm. Despite CLL's increasing popularity, previous studies highlight two main challenges: (1) inconsistent results arising from varied assumptions on complementary label generation, and (2) high barriers to entry due to the lack of a standardized evaluation platform across datasets and algorithms. To address these challenges, we introduce \texttt{libcll}, an extensible Python toolkit for CLL research. \texttt{libcll} provides a universal interface that supports a wide range of generation assumptions, both synthetic and real-world datasets, and key CLL algorithms. The toolkit is designed to mitigate inconsistencies and streamline the research process, with easy installation, comprehensive usage guides, and quickstart tutorials that facilitate efficient adoption and implementation of CLL techniques. Extensive ablation studies conducted with \texttt{libcll} demonstrate its utility in generating valuable insights to advance future CLL research.
Authors: Zheng Gong, Zhuo Deng, Weihao Gao, Wenda Zhou, Yuhang Yang, Hanqing Zhao, Zhiyuan Niu, Lei Shao, Wenbin Wei, Lan Ma
Abstract: Cataract is one of the most common blinding eye diseases and can be treated by surgery. However, because cataract patients may also suffer from other blinding eye diseases, ophthalmologists must diagnose them before surgery. The cloudy lens of cataract patients forms a hazy degeneration in the fundus images, making it challenging to observe the patient's fundus vessels, which brings difficulties to the diagnosis process. To address this issue, this paper establishes a new cataract image restoration method named Catintell. It contains a cataract image synthesizing model, Catintell-Syn, and a restoration model, Catintell-Res. Catintell-Syn uses GAN architecture with fully unsupervised data to generate paired cataract-like images with realistic style and texture rather than the conventional Gaussian degradation algorithm. Meanwhile, Catintell-Res is an image restoration network that can improve the quality of real cataract fundus images using the knowledge learned from synthetic cataract images. Extensive experiments show that Catintell-Res outperforms other cataract image restoration methods in PSNR with 39.03 and SSIM with 0.9476. Furthermore, the universal restoration ability that Catintell-Res gained from unpaired cataract images can process cataract images from various datasets. We hope the models can help ophthalmologists identify other blinding eye diseases of cataract patients and inspire more medical image restoration methods in the future.
Authors: Teli Ma, Zifan Wang, Jiaming Zhou, Mengmeng Wang, Junwei Liang
Abstract: Inferring affordable (i.e., graspable) parts of arbitrary objects based on human specifications is essential for robots advancing toward open-vocabulary manipulation. Current grasp planners, however, are hindered by limited vision-language comprehension and time-consuming 3D radiance modeling, restricting real-time, open-vocabulary interactions with objects. To address these limitations, we propose GLOVER, a unified Generalizable Open-Vocabulary Affordance Reasoning framework, which fine-tunes the Large Language Models (LLMs) to predict visual affordance of graspable object parts within RGB feature space. We compile a dataset of over 10,000 images from human-object interactions, annotated with unified visual and linguistic affordance labels, to enable multi-modal fine-tuning. GLOVER inherits world knowledge and common-sense reasoning from LLMs, facilitating more fine-grained object understanding and sophisticated tool-use reasoning. To enable effective real-world deployment, we present Affordance-Aware Grasping Estimation (AGE), a non-parametric grasp planner that aligns the gripper pose with a superquadric surface derived from affordance data. In evaluations across 30 real-world scenes, GLOVER achieves success rates of 86.0% in part identification and 76.3% in grasping, with speeds approximately 330 times faster in affordance reasoning and 40 times faster in grasping pose estimation than the previous state-of-the-art.
Authors: Xiaohe Li, Feilong Huang, Zide Fan, Fangli Mou, Leilei Lin, Yingyan Hou, Lijie Wen
Abstract: Trajectory prediction for multi-agents in complex scenarios is crucial for applications like autonomous driving. However, existing methods often overlook environmental biases, which leads to poor generalization. Additionally, hardware constraints limit the use of large-scale data across environments, and continual learning settings exacerbate the challenge of catastrophic forgetting. To address these issues, we propose the Continual Causal Intervention (C$^{2}$INet) method for generalizable multi-agent trajectory prediction within a continual learning framework. Using variational inference, we align environment-related prior with posterior estimator of confounding factors in the latent space, thereby intervening in causal correlations that affect trajectory representation. Furthermore, we store optimal variational priors across various scenarios using a memory queue, ensuring continuous debiasing during incremental task training. The proposed C$^{2}$INet enhances adaptability to diverse tasks while preserving previous task information to prevent catastrophic forgetting. It also incorporates pruning strategies to mitigate overfitting. Comparative evaluations on three real and synthetic complex datasets against state-of-the-art methods demonstrate that our proposed method consistently achieves reliable prediction performance, effectively mitigating confounding factors unique to different scenarios. This highlights the practical value of our method for real-world applications.
Authors: Xiaoteng Zhou, Yusheng Wang, Katsunori Mizuno
Abstract: This letter proposes a novel approach for compensating target height data in 2D seabed mosaicking for low-visibility underwater perception. Acoustic cameras are effective sensors for sensing the marine environments due to their high-resolution imaging capabilities and robustness to darkness and turbidity. However, the loss of elevation angle during the imaging process results in a lack of target height information in the original acoustic camera images, leading to a simplistic 2D representation of the seabed mosaicking. In perceiving cluttered and unexplored marine environments, target height data is crucial for avoiding collisions with marine robots. This study proposes a novel approach for estimating seabed target height using a single acoustic camera and integrates height data into 2D seabed mosaicking to compensate for the missing 3D dimension of seabed targets. Unlike classic methods that model the loss of elevation angle to achieve seabed 3D reconstruction, this study focuses on utilizing available acoustic cast shadow clues and simple sensor motion to quickly estimate target height. The feasibility of our proposal is verified through a water tank experiment and a simulation experiment.
Authors: Catie Cuan, Tianshuang Qiu, Shreya Ganti, Ken Goldberg
Abstract: This paper describes the robot technology behind an original performance that pairs a human dancer (Cuan) with an industrial robot arm for an eight-hour dance that unfolds over the timespan of an American workday. To control the robot arm, we combine a range of sinusoidal motions with varying amplitude, frequency and offset at each joint to evoke human motions common in physical labor such as stirring, digging, and stacking. More motions were developed using deep learning techniques for video-based human-pose tracking and extraction. We combine these pre-recorded motions with improvised robot motions created live by putting the robot into teach-mode and triggering force sensing from the robot joints onstage. All motions are combined with commercial and original music using a custom suite of python software with AppleScript, Keynote, and Zoom to facilitate on-stage communication with the dancer. The resulting performance contrasts the expressivity of the human body with the precision of robot machinery. Video, code and data are available on the project website: https://sites.google.com/playing.studio/breathless
Authors: Lorenzo J. Tardon, Isabel Barbancho, Ana M. Barbancho, Ichiro Fujinaga
Abstract: The automatic analysis of scores has been a research topic of interest for the last few decades and still is since music databases that include musical scores are currently being created to make musical content available to the public, including scores of ancient music. For the correct analysis of music elements and their interpretation, the identification of staff lines is of key importance. In this paper, a scheme to post-process the output of a previous musical object identification system is described. This system allows the reconstruction by means of detection, tracking and interpolation of the staff lines of ancient scores from the digital Salzinnes Database. The scheme developed shows a remarkable performance on the specific task it was created for.
Authors: Hanbeom Chang, Jongseong Brad Choi, Chul Min Yeum
Abstract: Indoor SLAM often suffers from issues such as scene drifting, double walls, and blind spots, particularly in confined spaces with objects close to the sensors (e.g. LiDAR and cameras) in reconstruction tasks. Real-time visualization of point cloud registration during data collection may help mitigate these issues, but a significant limitation remains in the inability to in-depth compare the scanned data with actual physical environments. These challenges obstruct the quality of reconstruction products, frequently necessitating revisit and rescan efforts. For this regard, we developed the LiMRSF (LiDAR-MR-RGB Sensor Fusion) system, allowing users to perceive the in-situ point cloud registration by looking through a Mixed-Reality (MR) headset. This tailored framework visualizes point cloud meshes as holograms, seamlessly matching with the real-time scene on see-through glasses, and automatically highlights errors detected while they overlap. Such holographic elements are transmitted via a TCP server to an MR headset, where it is calibrated to align with the world coordinate, the physical location. This allows users to view the localized reconstruction product instantaneously, enabling them to quickly identify blind spots and errors, and take prompt action on-site. Our blind spot detector achieves an error detection precision with an F1 Score of 75.76% with acceptably high fidelity of monitoring through the LiMRSF system (highest SSIM of 0.5619, PSNR of 14.1004, and lowest MSE of 0.0389 in the five different sections of the simplified mesh model which users visualize through the LiMRSF device see-through glasses). This method ensures the creation of detailed, high-quality datasets for 3D models, with potential applications in Building Information Modeling (BIM) but not limited.
Authors: Anantha S. Rao, Donovan Buterakos, Barnaby van Straaten, Valentin John, C\'ecile X. Yu, Stefan D. Oosterhout, Lucas Stehouwer, Giordano Scappucci, Menno Veldhorst, Francesco Borsoi, Justyna P. Zwolak
Abstract: Arrays of gate-defined semiconductor quantum dots are among the leading candidates for building scalable quantum processors. High-fidelity initialization, control, and readout of spin qubit registers require exquisite and targeted control over key Hamiltonian parameters that define the electrostatic environment. However, due to the tight gate pitch, capacitive crosstalk between gates hinders independent tuning of chemical potentials and interdot couplings. While virtual gates offer a practical solution, determining all the required cross-capacitance matrices accurately and efficiently in large quantum dot registers is an open challenge. Here, we establish a Modular Automated Virtualization System (MAViS) -- a general and modular framework for autonomously constructing a complete stack of multi-layer virtual gates in real time. Our method employs machine learning techniques to rapidly extract features from two-dimensional charge stability diagrams. We then utilize computer vision and regression models to self-consistently determine all relative capacitive couplings necessary for virtualizing plunger and barrier gates in both low- and high-tunnel-coupling regimes. Using MAViS, we successfully demonstrate accurate virtualization of a dense two-dimensional array comprising ten quantum dots defined in a high-quality Ge/SiGe heterostructure. Our work offers an elegant and practical solution for the efficient control of large-scale semiconductor quantum dot systems.
Authors: Yuhao Jin, Qizhong Gao, Xiaohui Zhu, Yong Yue, Eng Gee Lim, Yuqing Chen, Prudence Wong, Yijie Chu
Abstract: While deep learning-based robotic grasping technology has demonstrated strong adaptability, its computational complexity has also significantly increased, making it unsuitable for scenarios with high real-time requirements. Therefore, we propose a low computational complexity and high accuracy model named VMGNet for robotic grasping. For the first time, we introduce the Visual State Space into the robotic grasping field to achieve linear computational complexity, thereby greatly reducing the model's computational cost. Meanwhile, to improve the accuracy of the model, we propose an efficient and lightweight multi-scale feature fusion module, named Fusion Bridge Module, to extract and fuse information at different scales. We also present a new loss function calculation method to enhance the importance differences between subtasks, improving the model's fitting ability. Experiments show that VMGNet has only 8.7G Floating Point Operations and an inference time of 8.1 ms on our devices. VMGNet also achieved state-of-the-art performance on the Cornell and Jacquard public datasets. To validate VMGNet's effectiveness in practical applications, we conducted real grasping experiments in multi-object scenarios, and VMGNet achieved an excellent performance with a 94.4% success rate in real-world grasping tasks. The video for the real-world robotic grasping experiments is available at https://youtu.be/S-QHBtbmLc4.
Authors: Rania Briq, Jiangtao Wang, Steffan Kesselheim
Abstract: Data pruning is the problem of identifying a core subset that is most beneficial to training and discarding the remainder. While pruning strategies are well studied for discriminative models like those used in classification, little research has gone into their application to generative models. Generative models aim to estimate the underlying distribution of the data, so presumably they should benefit from larger datasets. In this work we aim to shed light on the accuracy of this statement, specifically answer the question of whether data pruning for generative diffusion models could have a positive impact. Contrary to intuition, we show that eliminating redundant or noisy data in large datasets is beneficial particularly when done strategically. We experiment with several pruning methods including recent-state-of-art methods, and evaluate over CelebA-HQ and ImageNet datasets. We demonstrate that a simple clustering method outperforms other sophisticated and computationally demanding methods. We further exhibit how we can leverage clustering to balance skewed datasets in an unsupervised manner to allow fair sampling for underrepresented populations in the data distribution, which is a crucial problem in generative models.
Authors: Yuke Wu, Xiang Liu, Yunyu Shi, Xinyi Chen, Zhenglei Wang, YuQing Xu, Shuo Hong Wang
Abstract: The irregular and challenging characteristics of lung adenocarcinoma nodules in computed tomography (CT) images complicate staging diagnosis, making accurate segmentation critical for clinicians to extract detailed lesion information. In this study, we propose a segmentation model, S3TU-Net, which integrates multi-dimensional spatial connectors and a superpixel-based visual transformer. S3TU-Net is built on a multi-view CNN-Transformer hybrid architecture, incorporating superpixel algorithms, structured weighting, and spatial shifting techniques to achieve superior segmentation performance. The model leverages structured convolution blocks (DWF-Conv/D2BR-Conv) to extract multi-scale local features while mitigating overfitting. To enhance multi-scale feature fusion, we introduce the S2-MLP Link, integrating spatial shifting and attention mechanisms at the skip connections. Additionally, the residual-based superpixel visual transformer (RM-SViT) effectively merges global and local features by employing sparse correlation learning and multi-branch attention to capture long-range dependencies, with residual connections enhancing stability and computational efficiency. Experimental results on the LIDC-IDRI dataset demonstrate that S3TU-Net achieves a DSC, precision, and IoU of 89.04%, 90.73%, and 90.70%, respectively. Compared to recent methods, S3TU-Net improves DSC by 4.52% and sensitivity by 3.16%, with other metrics showing an approximate 2% increase. In addition to comparison and ablation studies, we validated the generalization ability of our model on the EPDB private dataset, achieving a DSC of 86.40%.
Authors: Ekaterina Shumitskaya, Mikhail Pautov, Dmitriy Vatolin, Anastasia Antsiferova
Abstract: Most modern No-Reference Image-Quality Assessment (NR-IQA) metrics are based on neural networks vulnerable to adversarial attacks. Attacks on such metrics lead to incorrect image/video quality predictions, which poses significant risks, especially in public benchmarks. Developers of image processing algorithms may unfairly increase the score of a target IQA metric without improving the actual quality of the adversarial image. Although some empirical defenses for IQA metrics were proposed, they do not provide theoretical guarantees and may be vulnerable to adaptive attacks. This work focuses on developing a provably robust no-reference IQA metric. Our method is based on Median Smoothing (MS) combined with an additional convolution denoiser with ranking loss to improve the SROCC and PLCC scores of the defended IQA metric. Compared with two prior methods on three datasets, our method exhibited superior SROCC and PLCC scores while maintaining comparable certified guarantees.
Authors: Vitalis Vosylius, Edward Johns
Abstract: Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly (without further training) from just one or two demonstrations, achieving ICIL through two key components. First, we introduce inductive biases through a graph representation and model ICIL as a graph generation problem with a learned diffusion process, enabling structured reasoning over demonstrations, observations, and actions. Second, we show that such a model can be trained using pseudo-demonstrations - arbitrary trajectories generated in simulation - as a virtually infinite pool of training data. Simulated and real experiments show that Instant Policy enables rapid learning of various everyday robot tasks. We also show how it can serve as a foundation for cross-embodiment and zero-shot transfer to language-defined tasks. Code and videos are available at https://www.robot-learning.uk/instant-policy.
Authors: Kazi Hasibul Kabir, Md. Zahiruddin Aqib, Sharmin Sultana, Shamim Akhter
Abstract: Monitoring agricultural activities is important to ensure food security. Remote sensing plays a significant role for large-scale continuous monitoring of cultivation activities. Time series remote sensing data were used for the generation of the cropping pattern. Classification algorithms are used to classify crop patterns and mapped agriculture land used. Some conventional classification methods including support vector machine (SVM) and decision trees were applied for crop pattern recognition. However, in this paper, we are proposing Deep Neural Network (DNN) based classification to improve the performance of crop pattern recognition and make a comparative analysis with two (2) other machine learning approaches including Naive Bayes and Random Forest.
Authors: Dharanidharan S I, Suhitha Renuka S V, Ajishi Singh, Sheena Christabel Pravin
Abstract: In order to support the creation of reliable machine learning models for anomaly detection, this project focuses on preprocessing, enhancing, and organizing a medical imaging dataset. There are two classifications in the dataset: normal and abnormal, along with extra noise fluctuations. In order to improve the photographs' quality, undesirable artifacts, including visible medical equipment at the edges, were eliminated using central cropping. Adjusting the brightness and contrast was one of the additional preprocessing processes. Normalization was then performed to normalize the data. To make classification jobs easier, the dataset was methodically handled by combining several image subsets into two primary categories: normal and pathological. To provide a strong training set that adapts well to real-world situations, sophisticated picture preprocessing techniques were used, such as contrast enhancement and real-time augmentation (including rotations, zooms, and brightness modifications). To guarantee efficient model evaluation, the data was subsequently divided into training and testing subsets. In order to create precise and effective machine learning models for medical anomaly detection, high-quality input data is ensured via this thorough approach. Because of the project pipeline's flexible and scalable design, it can be easily integrated with bigger clinical decision-support systems.
Authors: Ayush Singla, Shakson Isaac, Chirag J. Patel
Abstract: Imaging-based deep learning has transformed healthcare research, yet its clinical adoption remains limited due to challenges in comparing imaging models with traditional non-imaging and tabular data. To bridge this gap, we introduce Barttender, an interpretable framework that uses deep learning for the direct comparison of the utility of imaging versus non-imaging tabular data for tasks like disease prediction. Barttender converts non-imaging tabular features, such as scalar data from electronic health records, into grayscale bars, facilitating an interpretable and scalable deep learning based modeling of both data modalities. Our framework allows researchers to evaluate differences in utility through performance measures, as well as local (sample-level) and global (population-level) explanations. We introduce a novel measure to define global feature importances for image-based deep learning models, which we call gIoU. Experiments on the CheXpert and MIMIC datasets with chest X-rays and scalar data from electronic health records show that Barttender performs comparably to traditional methods and offers enhanced explainability using deep learning models.
Authors: Huy Thong Nguyen, En-Hung Chu, Lenord Melvix, Jazon Jiao, Chunglin Wen, Benjamin Louie
Abstract: We introduce Teacher2Task, a novel framework for multi-teacher learning that eliminates the need for manual aggregation heuristics. Existing multi-teacher methods typically rely on such heuristics to combine predictions from multiple teachers, often resulting in sub-optimal aggregated labels and the propagation of aggregation errors. Teacher2Task addresses these limitations by introducing teacher-specific input tokens and reformulating the training process. Instead of relying on aggregated labels, the framework transforms the training data, consisting of ground truth labels and annotations from N teachers, into N+1 distinct tasks: N auxiliary tasks that predict the labeling styles of the N individual teachers, and one primary task that focuses on the ground truth labels. This approach, drawing upon principles from multiple learning paradigms, demonstrates strong empirical results across a range of architectures, modalities, and tasks.
Authors: Chao Chen, Zegang Cheng, Xinhao Liu, Yiming Li, Li Ding, Ruoyu Wang, Chen Feng
Abstract: Visual place recognition (VPR) using deep networks has achieved state-of-the-art performance. However, most of them require a training set with ground truth sensor poses to obtain positive and negative samples of each observation's spatial neighborhood for supervised learning. When such information is unavailable, temporal neighborhoods from a sequentially collected data stream could be exploited for self-supervised training, although we find its performance suboptimal. Inspired by noisy label learning, we propose a novel self-supervised framework named TF-VPR that uses temporal neighborhoods and learnable feature neighborhoods to discover unknown spatial neighborhoods. Our method follows an iterative training paradigm which alternates between: (1) representation learning with data augmentation, (2) positive set expansion to include the current feature space neighbors, and (3) positive set contraction via geometric verification. We conduct auto-labeling and generalization tests on both simulated and real datasets, with either RGB images or point clouds as inputs. The results show that our method outperforms self-supervised baselines in recall rate, robustness, and heading diversity, a novel metric we propose for VPR. Our code and datasets can be found at https://ai4ce.github.io/TF-VPR/
Authors: Naga VS Raviteja Chappa, Pha Nguyen, Alexander H Nelson, Han-Seok Seo, Xin Li, Page Daniel Dobbs, Khoa Luu
Abstract: This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video were consistent across spatio-temporal domains. Our proposed approach is efficient in using transformer-based encoders to alleviate the weakly supervised setting of group activity recognition. By leveraging the benefits of transformer models, our approach can model long-term relationships along spatio-temporal dimensions. Our proposed SoGAR method achieved state-of-the-art results on three group activity recognition benchmarks, namely JRDB-PAR, NBA, and Volleyball datasets, surpassing the current numbers in terms of F1-score, MCA, and MPCA metrics.
Authors: Linhui Xiao, Xiaoshan Yang, Fang Peng, Ming Yan, Yaowei Wang, Changsheng Xu
Abstract: Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding have been developed to locate regions using pseudo-labels. However, the performance of existing unsupervised methods is highly dependent on the quality of pseudo-labels and these methods always encounter issues with limited diversity. In order to utilize vision and language pre-trained models to address the grounding problem, and reasonably take advantage of pseudo-labels, we propose CLIP-VG, a novel method that can conduct self-paced curriculum adapting of CLIP with pseudo-language labels. We propose a simple yet efficient end-to-end network architecture to realize the transfer of CLIP to the visual grounding. Based on the CLIP-based architecture, we further propose single-source and multi-source curriculum adapting algorithms, which can progressively find more reliable pseudo-labels to learn an optimal model, thereby achieving a balance between reliability and diversity for the pseudo-language labels. Our method outperforms the current state-of-the-art unsupervised method by a significant margin on RefCOCO/+/g datasets in both single-source and multi-source scenarios, with improvements ranging from 6.78$\%$ to 10.67$\%$ and 11.39$\%$ to 14.87$\%$, respectively. The results even outperform existing weakly supervised visual grounding methods. Furthermore, our method is also competitive in fully supervised setting. The code and models are available at https://github.com/linhuixiao/CLIP-VG.
Authors: Mohammad Adiban, Kalin Stefanov, Sabato Marco Siniscalchi, Giampiero Salvi
Abstract: We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with major challenges in video prediction. These include learning spatiotemporal information, handling high dimensional data, combating blurry prediction, and implicit modeling of physical characteristics. Extensive experimental results on four challenging tasks, namely KTH Human Action, TrafficBJ, Human3.6M, and Kitti, demonstrate that our model compares favorably against state-of-the-art video prediction techniques both in quantitative and qualitative evaluations despite a much smaller model size. Finally, we boost S-HR-VQVAE by proposing a novel training method to jointly estimate the HR-VQVAE and AST-PM parameters.
Authors: Sambit Mohapatra, Senthil Yogamani, Varun Ravi Kumar, Stefan Milz, Heinrich Gotzig, Patrick M\"ader
Abstract: LiDAR is crucial for robust 3D scene perception in autonomous driving. LiDAR perception has the largest body of literature after camera perception. However, multi-task learning across tasks like detection, segmentation, and motion estimation using LiDAR remains relatively unexplored, especially on automotive-grade embedded platforms. We present a real-time multi-task convolutional neural network for LiDAR-based object detection, semantics, and motion segmentation. The unified architecture comprises a shared encoder and task-specific decoders, enabling joint representation learning. We propose a novel Semantic Weighting and Guidance (SWAG) module to transfer semantic features for improved object detection selectively. Our heterogeneous training scheme combines diverse datasets and exploits complementary cues between tasks. The work provides the first embedded implementation unifying these key perception tasks from LiDAR point clouds achieving 3ms latency on the embedded NVIDIA Xavier platform. We achieve state-of-the-art results for two tasks, semantic and motion segmentation, and close to state-of-the-art performance for 3D object detection. By maximizing hardware efficiency and leveraging multi-task synergies, our method delivers an accurate and efficient solution tailored for real-world automated driving deployment. Qualitative results can be seen at https://youtu.be/H-hWRzv2lIY.
Authors: Xiaoxiao Ma, Zhixiang Wei, Yi Jin, Pengyang Ling, Tianle Liu, Ben Wang, Junkang Dai, Huaian Chen
Abstract: In this work, we observe that model trained on vast general images via masking strategy, has been naturally embedded with their distribution knowledge, thus spontaneously attains the underlying potential for strong image denoising. Based on this observation, we propose a novel zero-shot denoising paradigm, i.e., Masked Pre-train then Iterative fill (MPI). MPI first trains model via masking and then employs pre-trained weight for high-quality zero-shot image denoising on a single noisy image. Concretely, MPI comprises two key procedures: 1) Masked Pre-training involves training model to reconstruct massive natural images with random masking for generalizable representations, gathering the potential for valid zero-shot denoising on images with varying noise degradation and even in distinct image types. 2) Iterative filling exploits pre-trained knowledge for effective zero-shot denoising. It iteratively optimizes the image by leveraging pre-trained weights, focusing on alternate reconstruction of different image parts, and gradually assembles fully denoised image within limited number of iterations. Comprehensive experiments across various noisy scenarios underscore the notable advances of MPI over previous approaches with a marked reduction in inference time. Code available at https://github.com/krennic999/MPI.
Authors: Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu
Abstract: Current image manipulation primarily centers on static manipulation, such as replacing specific regions within an image or altering its overall style. In this paper, we introduce an innovative dynamic manipulation task, subject repositioning. This task involves relocating a user-specified subject to a desired position while preserving the image's fidelity. Our research reveals that the fundamental sub-tasks of subject repositioning, which include filling the void left by the repositioned subject, reconstructing obscured portions of the subject and blending the subject to be consistent with surrounding areas, can be effectively reformulated as a unified, prompt-guided inpainting task. Consequently, we can employ a single diffusion generative model to address these sub-tasks using various task prompts learned through our proposed task inversion technique. Additionally, we integrate pre-processing and post-processing techniques to further enhance the quality of subject repositioning. These elements together form our SEgment-gEnerate-and-bLEnd (SEELE) framework. To assess SEELE's effectiveness in subject repositioning, we assemble a real-world subject repositioning dataset called ReS. Results of SEELE on ReS demonstrate its efficacy. Code and ReS dataset are available at https://yikai-wang.github.io/seele/.
Authors: Ming Zhong, Yelong Shen, Shuohang Wang, Yadong Lu, Yizhu Jiao, Siru Ouyang, Donghan Yu, Jiawei Han, Weizhu Chen
Abstract: Low-Rank Adaptation (LoRA) is extensively utilized in text-to-image models for the accurate rendition of specific elements like distinct characters or unique styles in generated images. Nonetheless, existing methods face challenges in effectively composing multiple LoRAs, especially as the number of LoRAs to be integrated grows, thus hindering the creation of complex imagery. In this paper, we study multi-LoRA composition through a decoding-centric perspective. We present two training-free methods: LoRA Switch, which alternates between different LoRAs at each denoising step, and LoRA Composite, which simultaneously incorporates all LoRAs to guide more cohesive image synthesis. To evaluate the proposed approaches, we establish ComposLoRA, a new comprehensive testbed as part of this research. It features a diverse range of LoRA categories with 480 composition sets. Utilizing an evaluation framework based on GPT-4V, our findings demonstrate a clear improvement in performance with our methods over the prevalent baseline, particularly evident when increasing the number of LoRAs in a composition. The code, benchmarks, LoRA weights, and all evaluation details are available on our project website: https://maszhongming.github.io/Multi-LoRA-Composition.
URLs: https://maszhongming.github.io/Multi-LoRA-Composition.
Authors: Chenghao Li, Lei Qi, Xin Geng
Abstract: In industrial anomaly detection, model efficiency and mobile-friendliness become the primary concerns in real-world applications. Simultaneously, the impressive generalization capabilities of Segment Anything (SAM) have garnered broad academic attention, making it an ideal choice for localizing unseen anomalies and diverse real-world patterns. In this paper, considering these two critical factors, we propose a SAM-guided Two-stream Lightweight Model for unsupervised anomaly detection (STLM) that not only aligns with the two practical application requirements but also harnesses the robust generalization capabilities of SAM. We employ two lightweight image encoders, i.e., our two-stream lightweight module, guided by SAM's knowledge. To be specific, one stream is trained to generate discriminative and general feature representations in both normal and anomalous regions, while the other stream reconstructs the same images without anomalies, which effectively enhances the differentiation of two-stream representations when facing anomalous regions. Furthermore, we employ a shared mask decoder and a feature aggregation module to generate anomaly maps. Our experiments conducted on MVTec AD benchmark show that STLM, with about 16M parameters and achieving an inference time in 20ms, competes effectively with state-of-the-art methods in terms of performance, 98.26% on pixel-level AUC and 94.92% on PRO. We further experiment on more difficult datasets, e.g., VisA and DAGM, to demonstrate the effectiveness and generalizability of STLM.
Authors: Nikolas Adaloglou, Tim Kaiser, Felix Michels, Markus Kollmann
Abstract: Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis across three different datasets. Given the optimal number of clusters with respect to image synthesis, we show that cluster-conditioning can achieve state-of-the-art performance, with an FID of 1.67 for CIFAR10 and 2.17 for CIFAR100, along with a strong increase in training sample efficiency. We further propose a novel empirical method to estimate an upper bound for the optimal number of clusters. Unlike existing approaches, we find no significant association between clustering performance and the corresponding cluster-conditional FID scores. The code is available at https://github.com/HHU-MMBS/cedm-official-wavc2025.
Authors: Youyuan Zhang, Xuan Ju, James J. Clark
Abstract: Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling in diffusion models poses challenges for efficient video editing. Existing approaches relying on image generation models for video editing suffer from time-consuming one-shot fine-tuning, additional condition extraction, or DDIM inversion, making real-time applications impractical. In this work, we propose FastVideoEdit, an efficient zero-shot video editing approach inspired by Consistency Models (CMs). By leveraging the self-consistency property of CMs, we eliminate the need for time-consuming inversion or additional condition extraction, reducing editing time. Our method enables direct mapping from source video to target video with strong preservation ability utilizing a special variance schedule. This results in improved speed advantages, as fewer sampling steps can be used while maintaining comparable generation quality. Experimental results validate the state-of-the-art performance and speed advantages of FastVideoEdit across evaluation metrics encompassing editing speed, temporal consistency, and text-video alignment.
Authors: Lachlan Thorpe, Lewis Bawden, Karanjot Vendal, John Bronskill, Richard E. Turner
Abstract: We present a transformer decoder based sports simulation engine, SportsNGEN, trained on sports player and ball tracking sequences, that is capable of generating sustained gameplay and accurately mimicking the decision making of real players. By training on a large database of professional tennis tracking data, we demonstrate that simulations produced by SportsNGEN can be used to predict the outcomes of rallies, determine the best shot choices at any point, and evaluate counterfactual or what if scenarios to inform coaching decisions and elevate broadcast coverage. By combining the generated simulations with a shot classifier and logic to start and end rallies, the system is capable of simulating an entire tennis match. We evaluate SportsNGEN by comparing statistics of the simulations with those of real matches between the same players. We show that the model output sampling parameters are crucial to simulation realism and that SportsNGEN is probabilistically well-calibrated to real data. In addition, a generic version of SportsNGEN can be customized to a specific player by fine-tuning on the subset of match data that includes that player. Finally, we show qualitative results indicating the same approach works for football.
Authors: Ziyang Chen, Wei Long, He Yao, Yongjun Zhang, Bingshu Wang, Yongbin Qin, Jia Wu
Abstract: Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at https://github.com/ZYangChen/MoCha-Stereo.
Authors: Ming Li, Taojiannan Yang, Huafeng Kuang, Jie Wu, Zhaoning Wang, Xuefeng Xiao, Chen Chen
Abstract: To enhance the controllability of text-to-image diffusion models, existing efforts like ControlNet incorporated image-based conditional controls. In this paper, we reveal that existing methods still face significant challenges in generating images that align with the image conditional controls. To this end, we propose ControlNet++, a novel approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency between generated images and conditional controls. Specifically, for an input conditional control, we use a pre-trained discriminative reward model to extract the corresponding condition of the generated images, and then optimize the consistency loss between the input conditional control and extracted condition. A straightforward implementation would be generating images from random noises and then calculating the consistency loss, but such an approach requires storing gradients for multiple sampling timesteps, leading to considerable time and memory costs. To address this, we introduce an efficient reward strategy that deliberately disturbs the input images by adding noise, and then uses the single-step denoised images for reward fine-tuning. This avoids the extensive costs associated with image sampling, allowing for more efficient reward fine-tuning. Extensive experiments show that ControlNet++ significantly improves controllability under various conditional controls. For example, it achieves improvements over ControlNet by 11.1% mIoU, 13.4% SSIM, and 7.6% RMSE, respectively, for segmentation mask, line-art edge, and depth conditions. All the code, models, demo and organized data have been open sourced on our Github Repo.
Authors: Yian Li, Wentao Tian, Yang Jiao, Jingjing Chen, Na Zhao, Yu-Gang Jiang
Abstract: Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge. However, whether these MLLMs possess human-like compositional reasoning abilities remains an open problem. To unveil their reasoning behaviors, we first curate a \textbf{M}ultimodal \textbf{A}ssumptive \textbf{R}ea\textbf{s}oning Benchmark (MARS-Bench) in this paper. Interestingly, we find that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning. Besides, we also propose a simple yet effective method, Active Deduction (AD), to encourage the model to actively perform composite deduction before reaching a final decision. Equipped with the proposed AD method, a MLLM demonstrates significant improvements in assumptive reasoning abilities without compromising its general-purpose question-answering performance. We also provide extensive evaluations of both open-source and private MLLMs on MARS-Bench, along with experimental analyses of the AD method.
Authors: Xujie Zhang, Ente Lin, Xiu Li, Yuxuan Luo, Michael Kampffmeyer, Xin Dong, Xiaodan Liang
Abstract: This paper introduces MMTryon, a multi-modal multi-reference VIrtual Try-ON (VITON) framework, which can generate high-quality compositional try-on results by taking a text instruction and multiple garment images as inputs. Our MMTryon addresses three problems overlooked in prior literature: 1) Support of multiple try-on items. Existing methods are commonly designed for single-item try-on tasks (e.g., upper/lower garments, dresses). 2)Specification of dressing style. Existing methods are unable to customize dressing styles based on instructions (e.g., zipped/unzipped, tuck-in/tuck-out, etc.) 3) Segmentation Dependency. They further heavily rely on category-specific segmentation models to identify the replacement regions, with segmentation errors directly leading to significant artifacts in the try-on results. To address the first two issues, our MMTryon introduces a novel multi-modality and multi-reference attention mechanism to combine the garment information from reference images and dressing-style information from text instructions. Besides, to remove the segmentation dependency, MMTryon uses a parsing-free garment encoder and leverages a novel scalable data generation pipeline to convert existing VITON datasets to a form that allows MMTryon to be trained without requiring any explicit segmentation. Extensive experiments on high-resolution benchmarks and in-the-wild test sets demonstrate MMTryon's superiority over existing SOTA methods both qualitatively and quantitatively. MMTryon's impressive performance on multi-item and style-controllable virtual try-on scenarios and its ability to try on any outfit in a large variety of scenarios from any source image, opens up a new avenue for future investigation in the fashion community.
Authors: Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, Chunhui Lin, Wanqing Li, Mohamad Fitri Faiz Bin Mahmood, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang
Abstract: Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding. Nonetheless, most existing TEC-VQA benchmarks have focused on high-resource languages like English and Chinese. Despite pioneering works to expand multilingual QA pairs in non-text-centric VQA datasets through translation engines, the translation-based protocol encounters a substantial "visual-textual misalignment" problem when applied to TEC-VQA. Specifically, it prioritizes the text in question-answer pairs while disregarding the visual text present in images. Moreover, it fails to address complexities related to nuanced meaning, contextual distortion, language bias, and question-type diversity. In this work, we tackle multilingual TEC-VQA by introducing MTVQA, the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. Further, by comprehensively evaluating numerous state-of-the-art Multimodal Large Language Models~(MLLMs), including Qwen2-VL, GPT-4o, GPT-4V, Claude3, and Gemini, on the MTVQA benchmark, it is evident that there is still a large room for performance improvement (Qwen2-VL scoring 30.9 versus 79.7 for human performance), underscoring the value of MTVQA. Additionally, we supply multilingual training data within the MTVQA dataset, demonstrating that straightforward fine-tuning with this data can substantially enhance multilingual TEC-VQA performance. We aspire that MTVQA will offer the research community fresh insights and stimulate further exploration in multilingual visual text comprehension. The project homepage is available at https://bytedance.github.io/MTVQA/.
Authors: Hari Iyer, Neel Macwan, Shenghan Guo, Heejin Jeong
Abstract: The performance of physical workers is significantly influenced by the extent of their motions. However, monitoring and assessing these motions remains a challenge. Recent advancements have enabled in-situ video analysis for real-time observation of worker behaviors. This paper introduces a novel framework for tracking and quantifying upper and lower limb motions, issuing alerts when critical thresholds are reached. Using joint position data from posture estimation, the framework employs Hotelling's $T^2$ statistic to quantify and monitor motion amounts. The results indicate that the correlation between workers' joint motion amounts and Hotelling's $T^2$ statistic is approximately 35\% higher for micro-tasks than macro-tasks, demonstrating the framework's ability to detect fine-grained motion differences. This study highlights the proposed system's effectiveness in real-time applications across various industry settings, providing a valuable tool for precision motion analysis and proactive ergonomic adjustments.
Authors: Beitao Chen, Xinyu Lyu, Lianli Gao, Jingkuan Song, Heng Tao Shen
Abstract: Although Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data, they invariably suffer from hallucinations, leading to a disconnect between the generated text and the corresponding images. Almost all current visual contrastive decoding methods attempt to mitigate these hallucinations by introducing visual uncertainty information that appropriately widens the contrastive logits gap between hallucinatory and targeted ones. However, due to uncontrollable nature of the global visual uncertainty, they struggle to precisely induce the hallucinatory tokens, which severely limits their effectiveness in mitigating hallucinations and may even lead to the generation of undesired hallucinations. To tackle this issue, we conducted the theoretical analysis to promote the effectiveness of contrast decoding. Building on this insight, we introduce a novel optimization strategy named Hallucination-Induced Optimization (HIO). This strategy seeks to amplify the contrast between hallucinatory and targeted tokens relying on a fine-tuned theoretical preference model (i.e., Contrary Bradley-Terry Model), thereby facilitating efficient contrast decoding to alleviate hallucinations in LVLMs. Extensive experimental research demonstrates that our HIO strategy can effectively reduce hallucinations in LVLMs, outperforming state-of-the-art methods across various benchmarks.
Authors: Qiaowei Miao, JinSheng Quan, Kehan Li, Yawei Luo
Abstract: Previous text-to-4D methods have leveraged multiple Score Distillation Sampling (SDS) techniques, combining motion priors from video-based diffusion models (DMs) with geometric priors from multiview DMs to implicitly guide 4D renderings. However, differences in these priors result in conflicting gradient directions during optimization, causing trade-offs between motion fidelity and geometry accuracy, and requiring substantial optimization time to reconcile the models. In this paper, we introduce \textbf{P}ixel-\textbf{L}evel \textbf{A}lignment for text-driven \textbf{4D} Gaussian splatting (PLA4D) to resolve this motion-geometry conflict. PLA4D provides an anchor reference, i.e., text-generated video, to align the rendering process conditioned by different DMs in pixel space. For static alignment, our approach introduces a focal alignment method and Gaussian-Mesh contrastive learning to iteratively adjust focal lengths and provide explicit geometric priors at each timestep. At the dynamic level, a motion alignment technique and T-MV refinement method are employed to enforce both pose alignment and motion continuity across unknown viewpoints, ensuring intrinsic geometric consistency across views. With such pixel-level multi-DM alignment, our PLA4D framework is able to generate 4D objects with superior geometric, motion, and semantic consistency. Fully implemented with open-source tools, PLA4D offers an efficient and accessible solution for high-quality 4D digital content creation with significantly reduced generation time.
Authors: Jiahao Nie, Gongjie Zhang, Wenbin An, Yap-Peng Tan, Alex C. Kot, Shijian Lu
Abstract: Though Multi-modal Large Language Models (MLLMs) have recently achieved significant progress, they often face various problems while handling inter-object relations, i.e., the interaction or association among distinct objects. This constraint largely stems from insufficient training and evaluation data for relation understanding, which has greatly impeded MLLMs in various vision-language generation and reasoning tasks. We attempt to address this challenge by introducing Multi-Modal Relation Understanding (MMRel), a benchmark that features large-scale, high-quality, and diverse data on inter-object relations. MMRel features three distinctive attributes: (i) It contains over 22K question-answer pairs, spanning three distinct domains and covering three relation categories, ensuring both scale and diversity; (ii) it provides manually verified, high-quality labels to ensure exceptional annotation accuracy; (iii) it includes adversarial cases with highly unusual relations, offering a challenging setting for evaluating relation hallucination. These features make MMRel ideal for evaluating MLLMs on relation understanding, as well as for fine-tuning MLLMs to enhance relation comprehension capability. Extensive experiments verify the effectiveness of MMRel in evaluating and enhancing MLLMs' relation understanding capabilities. The benchmark has been released publicly at: https://niejiahao1998.github.io/MMRel/
Authors: Zhaoxu Luo, Bowen Song, Liyue Shen
Abstract: During the acquisition of satellite images, there is generally a trade-off between spatial resolution and temporal resolution (acquisition frequency) due to the onboard sensors of satellite imaging systems. High-resolution satellite images are very important for land crop monitoring, urban planning, wildfire management and a variety of applications. It is a significant yet challenging task to achieve high spatial-temporal resolution in satellite imaging. With the advent of diffusion models, we can now learn strong generative priors to generate realistic satellite images with high resolution, which can be utilized to promote the super-resolution task as well. In this work, we propose a novel diffusion-based fusion algorithm called \textbf{SatDiffMoE} that can take an arbitrary number of sequential low-resolution satellite images at the same location as inputs, and fuse them into one high-resolution reconstructed image with more fine details, by leveraging and fusing the complementary information from different time points. Our algorithm is highly flexible and allows training and inference on arbitrary number of low-resolution images. Experimental results show that our proposed SatDiffMoE method not only achieves superior performance for the satellite image super-resolution tasks on a variety of datasets, but also gets an improved computational efficiency with reduced model parameters, compared with previous methods.
Authors: Zaiyan Zhang, Jining Yan, Yuanqi Liang, Jiaxin Feng, Haixu He, Li Cao
Abstract: Remote sensing images often suffer from substantial data loss due to factors such as thick cloud cover and sensor limitations. Existing methods for imputing missing values in remote sensing images fail to fully exploit spatiotemporal auxiliary information, which restricts the accuracy of their reconstructions. To address this issue, this paper proposes a novel deep learning-based approach called MS2TAN (Multi-Scale Masked Spatial-Temporal Attention Network) for reconstructing time-series remote sensing images. First, we introduce an efficient spatiotemporal feature extractor based on Masked Spatial-Temporal Attention (MSTA) to capture high-quality representations of spatiotemporal neighborhood features surrounding missing regions while significantly reducing the computational complexity of the attention mechanism. Second, a Multi-Scale Restoration Network composed of MSTA-based Feature Extractors is designed to progressively refine missing values by exploring spatiotemporal neighborhood features at different scales. Third, we propose a "Pixel-Structure-Perception" Multi-Objective Joint Optimization method to enhance the visual quality of the reconstructed results from multiple perspectives and to preserve more texture structures. Finally, quantitative experimental results under multi-temporal inputs on two public datasets demonstrate that the proposed method outperforms competitive approaches, achieving a 9.76%/9.30% reduction in Mean Absolute Error (MAE) and a 0.56 dB/0.62 dB increase in Peak Signal-to-Noise Ratio (PSNR), along with stronger texture and structural consistency. Ablation experiments further validate the contribution of the core innovations to imputation accuracy.
Authors: Tengbo Wang, Yu Bai
Abstract: How to extract instance-level masks without instance-level supervision is the main challenge of weakly supervised instance segmentation (WSIS). Popular WSIS methods estimate a displacement field (DF) via learning inter-pixel relations and perform clustering to identify instances. However, the resulting instance centroids are inherently unstable and vary significantly across different clustering algorithms. In this paper, we propose Boundary-Assisted Instance Segmentation (BAISeg), which is a novel paradigm for WSIS that realizes instance segmentation with pixel-level annotations. BAISeg comprises an instance-aware boundary detection (IABD) branch and a semantic segmentation branch. The IABD branch identifies instances by predicting class-agnostic instance boundaries rather than instance centroids, therefore, it is different from previous DF-based approaches. In particular, we proposed the Cascade Fusion Module (CFM) and the Deep Mutual Attention (DMA) in the IABD branch to obtain rich contextual information and capture instance boundaries with weak responses. During the training phase, we employed Pixel-to-Pixel Contrast to enhance the discriminative capacity of the IABD branch. This further strengthens the continuity and closedness of the instance boundaries. Extensive experiments on PASCAL VOC 2012 and MS COCO demonstrate the effectiveness of our approach, and we achieve considerable performance with only pixel-level annotations. The code will be available at https://github.com/wsis-seg/BAISeg.
Authors: Zongxiang Hu, Zhaosheng Zhang
Abstract: Visual anomaly detection is essential in industrial manufacturing, yet traditional methods often rely heavily on extensive normal datasets and task-specific models, limiting their scalability. Recent advancements in large-scale vision-language models have significantly enhanced zero- and few-shot anomaly detection. However, these approaches may not fully leverage hierarchical features, potentially overlooking nuanced details crucial for accurate detection. To address this, we introduce a novel window self-attention mechanism based on the CLIP model, augmented with learnable prompts to process multi-level features within a Soldier-Officer Window Self-Attention (SOWA) framework. Our method has been rigorously evaluated on five benchmark datasets, achieving superior performance by leading in 18 out of 20 metrics, setting a new standard against existing state-of-the-art techniques.
Authors: Owen Claxton, Connor Malone, Helen Carson, Jason Ford, Gabe Bolton, Iman Shames, Michael Milford
Abstract: Visual Place Recognition (VPR) systems often have imperfect performance, affecting the `integrity' of position estimates and subsequent robot navigation decisions. Previously, SVM classifiers have been used to monitor VPR integrity. This research introduces a novel Multi-Layer Perceptron (MLP) integrity monitor which demonstrates improved performance and generalizability, removing per-environment training and reducing manual tuning requirements. We test our proposed system in extensive real-world experiments, presenting two real-time integrity-based VPR verification methods: a single-query rejection method for robot navigation to a goal zone (Experiment 1); and a history-of-queries method that takes a best, verified, match from its recent trajectory and uses an odometer to extrapolate a current position estimate (Experiment 2). Noteworthy results for Experiment 1 include a decrease in aggregate mean along-track goal error from ~9.8m to ~3.1m, and an increase in the aggregate rate of successful mission completion from ~41% to ~55%. Experiment 2 showed a decrease in aggregate mean along-track localization error from ~2.0m to ~0.5m, and an increase in the aggregate localization precision from ~97% to ~99%. Overall, our results demonstrate the practical usefulness of a VPR integrity monitor in real-world robotics to improve VPR localization and consequent navigation performance.
Authors: Xiaomeng Chu, Jiajun Deng, Guoliang You, Yifan Duan, Yao Li, Yanyong Zhang
Abstract: The recent advances in query-based multi-camera 3D object detection are featured by initializing object queries in the 3D space, and then sampling features from perspective-view images to perform multi-round query refinement. In such a framework, query points near the same camera ray are likely to sample similar features from very close pixels, resulting in ambiguous query features and degraded detection accuracy. To this end, we introduce RayFormer, a camera-ray-inspired query-based 3D object detector that aligns the initialization and feature extraction of object queries with the optical characteristics of cameras. Specifically, RayFormer transforms perspective-view image features into bird's eye view (BEV) via the lift-splat-shoot method and segments the BEV map to sectors based on the camera rays. Object queries are uniformly and sparsely initialized along each camera ray, facilitating the projection of different queries onto different areas in the image to extract distinct features. Besides, we leverage the instance information of images to supplement the uniformly initialized object queries by further involving additional queries along the ray from 2D object detection boxes. To extract unique object-level features that cater to distinct queries, we design a ray sampling method that suitably organizes the distribution of feature sampling points on both images and bird's eye view. Extensive experiments are conducted on the nuScenes dataset to validate our proposed ray-inspired model design. The proposed RayFormer achieves superior performance of 55.5% mAP and 63.3% NDS, respectively.
Authors: Leina Elansary, Zaki Taha, Walaa Gad
Abstract: A survey is presented focused on using pose estimation techniques in Emotional recognition using various technologies normal cameras, and depth cameras for real-time, and the potential use of VR and inputs including images, videos, and 3-dimensional poses described in vector space. We discussed 19 research papers collected from selected journals and databases highlighting their methodology, classification algorithm, and the used datasets that relate to emotion recognition and pose estimation. A benchmark has been made according to their accuracy as it was the most common performance measurement metric used. We concluded that the multimodal Approaches overall made the best accuracy and then we mentioned futuristic concerns that can improve the development of this research topic.
Authors: Felix Assion, Florens Gressner, Nitin Augustine, Jona Klemenc, Ahmed Hammam, Alexandre Krattinger, Holger Trittenbach, Anja Philippsen, Sascha Riemer
Abstract: High-autonomy vehicle functions rely on machine learning (ML) algorithms to understand the environment. Despite displaying remarkable performance in fair weather scenarios, perception algorithms are heavily affected by adverse weather and lighting conditions. To overcome these difficulties, ML engineers mainly rely on comprehensive real-world datasets. However, the difficulties in real-world data collection for critical areas of the operational design domain (ODD) often means synthetic data is required for perception training and safety validation. Thus, we present A-BDD, a large set of over 60,000 synthetically augmented images based on BDD100K that are equipped with semantic segmentation and bounding box annotations (inherited from the BDD100K dataset). The dataset contains augmented data for rain, fog, overcast and sunglare/shadow with varying intensity levels. We further introduce novel strategies utilizing feature-based image quality metrics like FID and CMMD, which help identify useful augmented and real-world data for ML training and testing. By conducting experiments on A-BDD, we provide evidence that data augmentations can play a pivotal role in closing performance gaps in adverse weather and lighting conditions.
Authors: Chenjie Cao, Chaohui Yu, Fan Wang, Xiangyang Xue, Yanwei Fu
Abstract: Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic 3D assets, which are discouraged from generalizing to challenging in-the-wild scenes and fail to be employed with 2D synthesis directly. Moreover, these methods heavily depended on camera poses, limiting their real-world applications. To overcome these issues, we propose MVInpainter, re-formulating the 3D editing as a multi-view 2D inpainting task. Specifically, MVInpainter partially inpaints multi-view images with the reference guidance rather than intractably generating an entirely novel view from scratch, which largely simplifies the difficulty of in-the-wild NVS and leverages unmasked clues instead of explicit pose conditions. To ensure cross-view consistency, MVInpainter is enhanced by video priors from motion components and appearance guidance from concatenated reference key&value attention. Furthermore, MVInpainter incorporates slot attention to aggregate high-level optical flow features from unmasked regions to control the camera movement with pose-free training and inference. Sufficient scene-level experiments on both object-centric and forward-facing datasets verify the effectiveness of MVInpainter, including diverse tasks, such as multi-view object removal, synthesis, insertion, and replacement. The project page is https://ewrfcas.github.io/MVInpainter/.
Authors: Jin Cao, Yi Cao, Li Pang, Deyu Meng, Xiangyong Cao
Abstract: Image restoration aims to recover a high-quality clean image from its degraded version. Recent progress in image restoration has demonstrated the effectiveness of All-in-One image restoration models in addressing various unknown degradations simultaneously. However, these existing methods typically utilize the same parameters to tackle images with different types of degradation, forcing the model to balance the performance between different tasks and limiting its performance on each task. To alleviate this issue, we propose HAIR, a Hypernetworks-based All-in-One Image Restoration plug-and-play method that generates parameters based on the input image and thus makes the model to adapt to specific degradation dynamically. Specifically, HAIR consists of two main components, i.e., Classifier and Hyper Selecting Net (HSN). The Classifier is a simple image classification network used to generate a Global Information Vector (GIV) that contains the degradation information of the input image, and the HSN is a simple fully-connected neural network that receives the GIV and outputs parameters for the corresponding modules. Extensive experiments demonstrate that HAIR can significantly improve the performance of existing image restoration models in a plug-and-play manner, both in single-task and All-in-One settings. Notably, our proposed model Res-HAIR, which integrates HAIR into the well-known Restormer, can obtain superior or comparable performance compared with current state-of-the-art methods. Moreover, we theoretically demonstrate that to achieve a given small enough error, our proposed HAIR requires fewer parameters in contrast to mainstream embedding-based All-in-One methods. The code is available at https://github.com/toummHus/HAIR.
Authors: Simon Deltadahl, Julian Gilbey, Christine Van Laer, Nancy Boeckx, Mathie Leers, Tanya Freeman, Laura Aiken, Timothy Farren, Matthew Smith, Mohamad Zeina, BloodCounts consortium, James HF Rudd, Concetta Piazzese, Joseph Taylor, Nicholas Gleadall, Carola-Bibiane Sch\"onlieb, Suthesh Sivapalaratnam, Michael Roberts, Parashkev Nachev
Abstract: Accurate classification of haematological cells is critical for diagnosing blood disorders, but presents significant challenges for machine automation owing to the complexity of cell morphology, heterogeneities of biological, pathological, and imaging characteristics, and the imbalance of cell type frequencies. We introduce CytoDiffusion, a diffusion-based classifier that effectively models blood cell morphology, combining accurate classification with robust anomaly detection, resistance to distributional shifts, interpretability, data efficiency, and superhuman uncertainty quantification. Our approach outperforms state-of-the-art discriminative models in anomaly detection (AUC 0.990 vs. 0.918), resistance to domain shifts (85.85% vs. 74.38% balanced accuracy), and performance in low-data regimes (95.88% vs. 94.95% balanced accuracy). Notably, our model generates synthetic blood cell images that are nearly indistinguishable from real images, as demonstrated by an authenticity test in which expert haematologists achieved only 52.3% accuracy (95% CI: [50.5%, 54.2%]) in distinguishing real from generated images. Furthermore, we enhance model explainability through the generation of directly interpretable counterfactual heatmaps. Our comprehensive evaluation framework, encompassing these multiple performance dimensions, establishes a new benchmark for medical image analysis in haematology, ultimately enabling improved diagnostic accuracy in clinical settings. Our code is available at https://github.com/CambridgeCIA/CytoDiffusion.
Authors: Ce Wang, Zhenyu Hu, Wanjie Sun, Zhenzhong Chen
Abstract: Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition media. However, extreme downscaling factors pose significant challenges to the upscaling process due to its highly ill-posed nature, causing existing image rescaling methods to struggle in generating semantically correct structures and perceptual friendly textures. In this work, we propose a novel framework called One-Step Image Rescaling Diffusion (OSIRDiff) for extreme image rescaling, which performs rescaling operations in the latent space of a pre-trained autoencoder and effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model. Specifically, OSIRDiff adopts a pseudo-invertible module to establish the bidirectional mapping between the latent features of the HR image and the target-sized LR image. Then, the rescaled features are refined by a pre-trained diffusion model to generate more faithful and visually pleasing details. The entire model is end-to-end trained to enable the diffusion priors to guide the rescaling process. Considering the spatially non-uniform reconstruction quality of the rescaled latent features, we propose a novel time-step alignment strategy, which can adaptively determine the generative strength of the diffusion model based on the degree of latent reconstruction errors. Extensive experiments demonstrate the superiority of OSIRDiff over previous methods in both quantitative and qualitative evaluations.
Authors: Haoyu Zhao, Hao Wang, Chen Yang, Wei Shen
Abstract: Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail reconstruction, particularly when training with sparse inputs. To address this challenge, we propose CHASE, a novel framework that achieves dense-input-level performance using only sparse inputs through two key innovations: cross-pose intrinsic 3D consistency supervision and 3D geometry contrastive learning. Building upon prior skeleton-driven approaches that combine rigid deformation with non-rigid cloth dynamics, we first establish baseline avatars with fundamental 3D consistency. To enhance 3D consistency under sparse inputs, we introduce a Dynamic Avatar Adjustment (DAA) module, which refines deformed Gaussians by leveraging similar poses from the training set. By minimizing the rendering discrepancy between adjusted Gaussians and reference poses, DAA provides additional supervision for avatar reconstruction. We further maintain global 3D consistency through a novel geometry-aware contrastive learning strategy. While designed for sparse inputs, CHASE surpasses state-of-the-art methods across both full and sparse settings on ZJU-MoCap and H36M datasets, demonstrating that our enhanced 3D consistency leads to superior rendering quality.
Authors: Haoyu Zhao, Chen Yang, Hao Wang, Xingyue Zhao, Wei Shen
Abstract: Reconstructing photo-realistic and topology-aware animatable human avatars from monocular videos remains challenging in computer vision and graphics. Recently, methods using 3D Gaussians to represent the human body have emerged, offering faster optimization and real-time rendering. However, due to ignoring the crucial role of human body semantic information which represents the explicit topological and intrinsic structure within human body, they fail to achieve fine-detail reconstruction of human avatars. To address this issue, we propose SG-GS, which uses semantics-embedded 3D Gaussians, skeleton-driven rigid deformation, and non-rigid cloth dynamics deformation to create photo-realistic human avatars. We then design a Semantic Human-Body Annotator (SHA) which utilizes SMPL's semantic prior for efficient body part semantic labeling. The generated labels are used to guide the optimization of semantic attributes of Gaussian. To capture the explicit topological structure of the human body, we employ a 3D network that integrates both topological and geometric associations for human avatar deformation. We further implement three key strategies to enhance the semantic accuracy of 3D Gaussians and rendering quality: semantic projection with 2D regularization, semantic-guided density regularization and semantic-aware regularization with neighborhood consistency. Extensive experiments demonstrate that SG-GS achieves state-of-the-art geometry and appearance reconstruction performance.
Authors: Junho Moon, Haejun Chung, Ikbeom Jang
Abstract: Facial wrinkle detection plays a crucial role in cosmetic dermatology. Precise manual segmentation of facial wrinkles is challenging and time-consuming, with inherent subjectivity leading to inconsistent results among graders. To address this issue, we propose two solutions. First, we build and release the first public facial wrinkle dataset, 'FFHQ-Wrinkle', an extension of the NVIDIA FFHQ dataset. It includes 1,000 images with human labels and 50,000 images with automatically generated weak labels. This dataset could serve as a foundation for the research community to develop advanced wrinkle detection algorithms. Second, we introduce a simple training strategy utilizing texture maps, applicable to various segmentation models, to detect wrinkles across the face. Our two-stage training strategy first pretrain models on a large dataset with weak labels (N=50k), or masked texture maps generated through computer vision techniques, without human intervention. We then finetune the models using human-labeled data (N=1k), which consists of manually labeled wrinkle masks. The network takes as input a combination of RGB and masked texture map of the image, comprising four channels, in finetuning. We effectively combine labels from multiple annotators to minimize subjectivity in manual labeling. Our strategies demonstrate improved segmentation performance in facial wrinkle segmentation both quantitatively and visually compared to existing pretraining methods. The dataset is available at https://github.com/labhai/ffhq-wrinkle-dataset.
Authors: Siwei Tu, Weidong Yang, Ben Fei
Abstract: Diffusion models have been widely utilized for image restoration. However, previous blind image restoration methods still need to assume the type of degradation model while leaving the parameters to be optimized, limiting their real-world applications. Therefore, we aim to tame generative diffusion prior for universal blind image restoration dubbed BIR-D, which utilizes an optimizable convolutional kernel to simulate the degradation model and dynamically update the parameters of the kernel in the diffusion steps, enabling it to achieve blind image restoration results even in various complex situations. Besides, based on mathematical reasoning, we have provided an empirical formula for the chosen of adaptive guidance scale, eliminating the need for a grid search for the optimal parameter. Experimentally, Our BIR-D has demonstrated superior practicality and versatility than off-the-shelf unsupervised methods across various tasks both on real-world and synthetic datasets, qualitatively and quantitatively. BIR-D is able to fulfill multi-guidance blind image restoration. Moreover, BIR-D can also restore images that undergo multiple and complicated degradations, demonstrating the practical applications.
Authors: Hyo Jong Chung, Byungkon Kang, Yoonseok Yang
Abstract: Driver motion recognition is a principal factor in ensuring the safety of driving systems. This paper presents a novel system for learning and predicting driver motions and an event-based high-resolution (1280x720) dataset, N-DriverMotion, newly collected to train on a neuromorphic vision system. The system comprises an event-based camera that generates the first high-resolution driver motion dataset representing spike inputs and efficient spiking neural networks (SNNs) that are effective in training and predicting the driver's gestures. The event dataset consists of 13 driver motion categories classified by direction (front, side), illumination (bright, moderate, dark), and participant. A novel simplified four-layer convolutional spiking neural network (CSNN) that we proposed was directly trained using the high-resolution dataset without any time-consuming preprocessing. This enables efficient adaptation to on-device SNNs for real-time inference on high-resolution event-based streams. Compared with recent gesture recognition systems adopting neural networks for vision processing, the proposed neuromorphic vision system achieves comparable accuracy, 94.04\%, in recognizing driver motions with the CSNN architecture. Our proposed CSNN and the dataset can be used to develop safer and more efficient driver monitoring systems for autonomous vehicles or edge devices requiring an efficient neural network architecture.
Authors: Reza Kakavand, Reza Ahmadi, Atousa Parsaei, W. Brent Edwards, Amin Komeili
Abstract: Markerless motion capture offers several benefits over traditional marker-based systems by eliminating the need for physical markers, which are prone to misplacement and artifacts. Utilizing computer vision and deep learning algorithms, markerless systems can directly detect human body landmarks, reducing manual processing and errors associated with marker placement. These systems are adaptable, able to track user-defined features, and practical for real-world applications using consumer-grade devices such as smartphone cameras. This study compares the performance of OpenCap, a markerless motion capture system, with traditional marker-based systems in assessing cycling biomechanics. Ten healthy adults participated in experiments to capture sagittal hip, knee, and ankle kinematics and dynamics using both methods. OpenCap used videos from smartphones and integrated computer vision and musculoskeletal simulations to estimate 3D kinematics. Results showed high agreement between the two systems, with no significant differences in kinematic and kinetic measurements for the hip, knee, and ankle. The correlation coefficients exceeded 0.98, indicating very strong consistency. Errors were minimal, with kinematic errors under 4 degrees and kinetic errors below 5 Nm. This study concludes that OpenCap is a viable alternative to marker-based motion capture, offering comparable precision without extensive setup for hip (flexion/extension), knee (flexion/extension), and ankle (dorsiflexion/plantarflexion) joints. Future work should aim to enhance the accuracy of ankle joint measurements and extend analyses to 3D kinematics and kinetics for comprehensive biomechanical assessments.
Authors: Qingyao Tian, Zhen Chen, Huai Liao, Xinyan Huang, Lujie Li, Sebastien Ourselin, Hongbin Liu
Abstract: Single-image depth estimation is essential for endoscopy tasks such as localization, reconstruction, and augmented reality. Most existing methods in surgical scenes focus on in-domain depth estimation, limiting their real-world applicability. This constraint stems from the scarcity and inferior labeling quality of medical data for training. In this work, we present EndoOmni, the first foundation model for zero-shot cross-domain depth estimation for endoscopy. To harness the potential of diverse training data, we refine the advanced self-learning paradigm that employs a teacher model to generate pseudo-labels, guiding a student model trained on large-scale labeled and unlabeled data. To address training disturbance caused by inherent noise in depth labels, we propose a robust training framework that leverages both depth labels and estimated confidence from the teacher model to jointly guide the student model training. Moreover, we propose a weighted scale-and-shift invariant loss to adaptively adjust learning weights based on label confidence, thus imposing learning bias towards cleaner label pixels while reducing the influence of highly noisy pixels. Experiments on zero-shot relative depth estimation show that our EndoOmni improves state-of-the-art methods in medical imaging for 33\% and existing foundation models for 34\% in terms of absolute relative error on specific datasets. Furthermore, our model provides strong initialization for fine-tuning metric depth estimation, maintaining superior performance in both in-domain and out-of-domain scenarios. The source code is publicly available at https://github.com/TianCuteQY/EndoOmni.
Authors: Kun Fang, Qinghua Tao, Zuopeng Yang, Xiaolin Huang, Jie Yang
Abstract: Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or from OoD. Diffusion Models (DMs) are recently utilized in OoD detection by using the perceptual distances between the given image and its DM generation. DM-based methods bring fresh insights to the field, yet remain under-explored. In this work, we point out two main limitations in DM-based OoD detection methods: (i) the perceptual metrics on the disparities between the given sample and its generation are devised only at human-perceived levels, ignoring the abstract or high-level patterns that help better reflect the intrinsic disparities in distribution; (ii) only the raw image contents are taken to measure the disparities, while other representations, i.e., the features and probabilities from the classifier-under-protection, are easy to access at hand but are ignored. To this end, our proposed detection framework goes beyond the perceptual distances and looks into the deep representations from the classifier-under-protection with our novel metrics devised correspondingly, leading to more informative disparity assessments between InD and OoD. An anomaly-removal strategy is integrated to remove the abnormal OoD information in the generation, further enhancing the distinctiveness of disparities. Our work has demonstrated state-of-the-art detection performances among DM-based methods in extensive experiments.
Authors: Ming Li, Jike Zhong, Chenxin Li, Liuzhuozheng Li, Nie Lin, Masashi Sugiyama
Abstract: Recent advances in fine-tuning Vision-Language Models (VLMs) have witnessed the success of prompt tuning and adapter tuning, while the classic model fine-tuning on inherent parameters seems to be overlooked. It is believed that fine-tuning the parameters of VLMs with few-shot samples corrupts the pre-trained knowledge since fine-tuning the CLIP model even degrades performance. In this paper, we revisit this viewpoint, and propose a new perspective: fine-tuning the specific parameters instead of all will uncover the power of classic model fine-tuning on VLMs. Through our meticulous study, we propose ClipFit, a simple yet effective method to fine-tune CLIP without introducing any overhead of extra parameters. We demonstrate that by only fine-tuning the specific bias terms and normalization layers, ClipFit can improve the performance of zero-shot CLIP by 7.27\% average harmonic mean accuracy. Lastly, to understand how fine-tuning in CLIPFit affects the pre-trained models, we conducted extensive experimental analyses w.r.t. changes in internal parameters and representations. We found that low-level text bias layers and the first layer normalization layer change much more than other layers. The code is available at \url{https://github.com/minglllli/CLIPFit}.
Authors: Shiben Liu, Qiang Wang, Huijie Fan, Weihong Ren, Baojie Fan, Yandong Tang
Abstract: Lifelong person re-identification (LReID) exhibits a contradictory relationship between intra-domain discrimination and inter-domain gaps when learning from continuous data. Intra-domain discrimination focuses on individual nuances (e.g. clothing type, accessories, etc.), while inter-domain gaps emphasize domain consistency. Achieving a trade-off between maximizing intra-domain discrimination and minimizing inter-domain gaps is a crucial challenge for improving LReID performance. Most existing methods aim to reduce inter-domain gaps through knowledge distillation to maintain domain consistency. However, they often ignore intra-domain discrimination. To address this challenge, we propose a novel domain consistency representation learning (DCR) model that explores global and attribute-wise representations as a bridge to balance intra-domain discrimination and inter-domain gaps. At the intra-domain level, we explore the complementary relationship between global and attribute-wise representations to improve discrimination among similar identities. Excessive learning intra-domain discrimination can lead to catastrophic forgetting. We further develop an attribute-oriented anti-forgetting (AF) strategy that explores attribute-wise representations to enhance inter-domain consistency, and propose a knowledge consolidation (KC) strategy to facilitate knowledge transfer. Extensive experiments show that our DCR model achieves superior performance compared to state-of-the-art LReID methods. Our code will be available soon.
Authors: Tingzhang Luo, Yichao Liu, Yuanyuan Liu, Andi Zhang, Xin Wang, Yibing Zhan, Chang Tang, Leyuan Liu, Zhe Chen
Abstract: We introduce a novel task, Generalized Facial Expression Category Discovery (G-FACE), that discovers new, unseen facial expressions while recognizing known categories effectively. Even though there are generalized category discovery methods for natural images, they show compromised performance on G-FACE. We identified two biases that affect the learning: implicit bias, coming from an underlying distributional gap between new categories in unlabeled data and known categories in labeled data, and explicit bias, coming from shifted preference on explicit visual facial change characteristics from known expressions to unknown expressions. By addressing the challenges caused by both biases, we propose a Debiased G-FACE method, namely DIG-FACE, that facilitates the debiasing of both implicit and explicit biases. In the implicit debiasing process of DIG-FACE, we devise a novel learning strategy that aims at estimating and minimizing the upper bound of implicit bias. In the explicit debiasing process, we optimize the model's ability to handle nuanced visual facial expression data by introducing a hierarchical category-discrimination refinement strategy: sample-level, triplet-level, and distribution-level optimizations. Extensive experiments demonstrate that our DIG-FACE significantly enhances recognition accuracy for both known and new categories, setting a first-of-its-kind standard for the task.
Authors: Tianshu Kuai, Sina Honari, Igor Gilitschenski, Alex Levinshtein
Abstract: Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a handcrafted image degradation pipeline. The models trained on such synthetic degradations, however, cannot deal with inputs of unseen degradations. In this paper, we address this issue by using only a set of input images, with unknown degradations and without ground truth targets, to fine-tune a restoration model that learns to map them to clean and contextually consistent outputs. We utilize a pre-trained diffusion model as a generative prior through which we generate high quality images from the natural image distribution while maintaining the input image content through consistency constraints. These generated images are then used as pseudo targets to fine-tune a pre-trained restoration model. Unlike many recent approaches that employ diffusion models at test time, we only do so during training and thus maintain an efficient inference-time performance. Extensive experiments show that the proposed approach can consistently improve the perceptual quality of pre-trained blind face restoration models while maintaining great consistency with the input contents. Our best model also achieves the state-of-the-art results on both synthetic and real-world datasets.
Authors: Haoran Hao, Jiaming Han, Changsheng Li, Yu-Feng Li, Xiangyu Yue
Abstract: The development of large language models (LLMs) has significantly enhanced the capabilities of multimodal LLMs (MLLMs) as general assistants. However, lack of user-specific knowledge still restricts their application in human's daily life. In this paper, we introduce the Retrieval Augmented Personalization (RAP) framework for MLLMs' personalization. Starting from a general MLLM, we turn it into a personalized assistant in three steps. (a) Remember: We design a key-value database to store user-related information, e.g., user's name, avatar and other attributes. (b) Retrieve: When the user initiates a conversation, RAP will retrieve relevant information from the database using a multimodal retriever. (c) Generate: The input query and retrieved concepts' information are fed into MLLMs to generate personalized, knowledge-augmented responses. Unlike previous methods, RAP allows real-time concept editing via updating the external database. To further improve generation quality and alignment with user-specific information, we design a pipeline for data collection and create a specialized dataset for personalized training of MLLMs. Based on the dataset, we train a series of MLLMs as personalized multimodal assistants. By pretraining on large-scale dataset, RAP-MLLMs can generalize to infinite visual concepts without additional finetuning. Our models demonstrate outstanding flexibility and generation quality across a variety of tasks, such as personalized image captioning, question answering and visual recognition. The code, data and models are available at https://github.com/Hoar012/RAP-MLLM.
Authors: Florian Wulff, Bernd Schaeufele, Julian Pfeifer, Ilja Radusch
Abstract: Automated vehicles rely on an accurate and robust perception of the environment. Similarly to automated cars, highly automated trains require an environmental perception. Although there is a lot of research based on either camera or LiDAR sensors in the automotive domain, very few contributions for this task exist yet for automated trains. Additionally, no public dataset or described approach for a 3D LiDAR semantic segmentation in the railway environment exists yet. Thus, we propose an approach for a point-wise 3D semantic segmentation based on the 2DPass network architecture using scans and images jointly. In addition, we present a semi-automated intelligent data annotation approach, which we use to efficiently and accurately label the required dataset recorded on a railway track in Germany. To improve performance despite a still small number of labeled scans, we apply an active learning approach to intelligently select scans for the training dataset. Our contributions are threefold: We annotate rail data including camera and LiDAR data from the railway environment, transfer label the raw LiDAR point clouds using an image segmentation network, and train a state-of-the-art 3D LiDAR semantic segmentation network efficiently leveraging active learning. The trained network achieves good segmentation results with a mean IoU of 71.48% of 9 classes.
Authors: Chenhang Cui, An Zhang, Yiyang Zhou, Zhaorun Chen, Gelei Deng, Huaxiu Yao, Tat-Seng Chua
Abstract: The recent advancements in large language models (LLMs) and pre-trained vision models have accelerated the development of vision-language large models (VLLMs), enhancing the interaction between visual and linguistic modalities. Despite their notable success across various domains, VLLMs face challenges in modality alignment, which can lead to issues like hallucinations and unsafe content generation. Current alignment techniques often rely on coarse feedback and external datasets, limiting scalability and performance. In this paper, we propose FiSAO (Fine-Grained Self-Alignment Optimization), a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment without the need for additional data. By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data. Through both theoretical analysis and experimental validation, we demonstrate that FiSAO effectively addresses the misalignment problem in VLLMs, marking the first instance of token-level rewards being applied to such models.
Authors: Stefanos Pasios, Nikos Nikolaidis
Abstract: Simulators are indispensable for research in autonomous systems such as self-driving cars, autonomous robots and drones. Despite significant progress in various simulation aspects, such as graphical realism, an evident gap persists between the virtual and real-world environments. Since the ultimate goal is to deploy the autonomous systems in the real world, closing the sim2real gap is of utmost importance. In this paper, we employ a state-of-the-art approach to enhance the photorealism of simulated data, aligning them with the visual characteristics of real-world datasets. Based on this, we developed CARLA2Real, an easy-to-use, publicly available tool (plug-in) for the widely used and open-source CARLA simulator. This tool enhances the output of CARLA in near real-time, achieving a frame rate of 13 FPS, translating it to the visual style and realism of real-world datasets such as Cityscapes, KITTI, and Mapillary Vistas. By employing the proposed tool, we generated synthetic datasets from both the simulator and the enhancement model outputs, including their corresponding ground truth annotations for tasks related to autonomous driving. Then, we performed a number of experiments to evaluate the impact of the proposed approach on feature extraction and semantic segmentation methods when trained on the enhanced synthetic data. The results demonstrate that the sim2real gap is significant and can indeed be reduced by the introduced approach.
Authors: Xueyang Yu, Xinlei Chen, Yossi Gandelsman
Abstract: We show that useful video representations can be learned from synthetic videos and natural images, without incorporating natural videos in the training. We propose a progression of video datasets synthesized by simple generative processes, that model a growing set of natural video properties (e.g., motion, acceleration, and shape transformations). The downstream performance of video models pre-trained on these generated datasets gradually increases with the dataset progression. A VideoMAE model pre-trained on our synthetic videos closes 97.2\% of the performance gap on UCF101 action classification between training from scratch and self-supervised pre-training from natural videos, and outperforms the pre-trained model on HMDB51. Introducing crops of static images to the pre-training stage results in similar performance to UCF101 pre-training and outperforms the UCF101 pre-trained model on 11 out of 14 out-of-distribution datasets of UCF101-P. Analyzing the low-level properties of the datasets, we identify correlations between frame diversity, frame similarity to natural data, and downstream performance. Our approach provides a more controllable and transparent alternative to video data curation processes for pre-training.
Authors: Yuka Ogino, Yuho Shoji, Takahiro Toizumi, Atsushi Ito
Abstract: We propose an image-adaptive object detection method for adverse weather conditions such as fog and low-light. Our framework employs differentiable preprocessing filters to perform image enhancement suitable for later-stage object detections. Our framework introduces two differentiable filters: a B\'ezier curve-based pixel-wise (BPW) filter and a kernel-based local (KBL) filter. These filters unify the functions of classical image processing filters and improve performance of object detection. We also propose a domain-agnostic data augmentation strategy using the BPW filter. Our method does not require data-specific customization of the filter combinations, parameter ranges, and data augmentation. We evaluate our proposed approach, called Enhanced Robustness by Unified Image Processing (ERUP)-YOLO, by applying it to the YOLOv3 detector. Experiments on adverse weather datasets demonstrate that our proposed filters match or exceed the expressiveness of conventional methods and our ERUP-YOLO achieved superior performance in a wide range of adverse weather conditions, including fog and low-light conditions.
Authors: Shuchang Lyu, Qi Zhao, Guangliang Cheng, Yiwei He, Zheng Zhou, Guangbiao Wang, Zhenwei Shi
Abstract: Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation (UDA-RSSeg) addresses the challenge of adapting a model trained on source domain data to target domain samples, thereby minimizing the need for annotated data across diverse remote sensing scenes. This task presents two principal challenges: (1) severe inconsistencies in feature representation across different remote sensing domains, and (2) a domain gap that emerges due to the representation bias of source domain patterns when translating features to predictive logits. To tackle these issues, we propose a joint-optimized adversarial network incorporating the "Segment Anything Model (SAM) (SAM-JOANet)" for UDA-RSSeg. Our approach integrates SAM to leverage its robust generalized representation capabilities, thereby alleviating feature inconsistencies. We introduce a finetuning decoder designed to convert SAM-Encoder features into predictive logits. Additionally, a feature-level adversarial-based prompted segmentor is employed to generate class-agnostic maps, which guide the finetuning decoder's feature representations. The network is optimized end-to-end, combining the prompted segmentor and the finetuning decoder. Extensive evaluations on benchmark datasets, including ISPRS (Potsdam/Vaihingen) and CITY-OSM (Paris/Chicago), demonstrate the effectiveness of our method. The results, supported by visualization and analysis, confirm the method's interpretability and robustness. The code of this paper is available at https://github.com/CV-ShuchangLyu/SAM-JOANet.
Authors: Yuanyuan Liu, Lin Wei, Kejun Liu, Yibing Zhan, Zijing Chen, Zhe Chen, Shiguang Shan
Abstract: Emotion Recognition (ER) is the process of identifying human emotions from given data. Currently, the field heavily relies on facial expression recognition (FER) because facial expressions contain rich emotional cues. However, it is important to note that facial expressions may not always precisely reflect genuine emotions and FER-based results may yield misleading ER. To understand and bridge this gap between FER and ER, we introduce eye behaviors as an important emotional cues for the creation of a new Eye-behavior-aided Multimodal Emotion Recognition (EMER) dataset. Different from existing multimodal ER datasets, the EMER dataset employs a stimulus material-induced spontaneous emotion generation method to integrate non-invasive eye behavior data, like eye movements and eye fixation maps, with facial videos, aiming to obtain natural and accurate human emotions. Notably, for the first time, we provide annotations for both ER and FER in the EMER, enabling a comprehensive analysis to better illustrate the gap between both tasks. Furthermore, we specifically design a new EMERT architecture to concurrently enhance performance in both ER and FER by efficiently identifying and bridging the emotion gap between the two.Specifically, our EMERT employs modality-adversarial feature decoupling and multi-task Transformer to augment the modeling of eye behaviors, thus providing an effective complement to facial expressions. In the experiment, we introduce seven multimodal benchmark protocols for a variety of comprehensive evaluations of the EMER dataset. The results show that the EMERT outperforms other state-of-the-art multimodal methods by a great margin, revealing the importance of modeling eye behaviors for robust ER. To sum up, we provide a comprehensive analysis of the importance of eye behaviors in ER, advancing the study on addressing the gap between FER and ER for more robust ER performance.
Authors: Weijie Ma, Jingwei Jiang, Yang Yang, Zehui Chen, Hao Chen
Abstract: With the attention gained by camera-only 3D object detection in autonomous driving, methods based on Bird-Eye-View (BEV) representation especially derived from the forward view transformation paradigm, i.e., lift-splat-shoot (LSS), have recently seen significant progress. The BEV representation formulated by the frustum based on depth distribution prediction is ideal for learning the road structure and scene layout from multi-view images. However, to retain computational efficiency, the compressed BEV representation such as in resolution and axis is inevitably weak in retaining the individual geometric details, undermining the methodological generality and applicability. With this in mind, to compensate for the missing details and utilize multi-view geometry constraints, we propose LSSInst, a two-stage object detector incorporating BEV and instance representations in tandem. The proposed detector exploits fine-grained pixel-level features that can be flexibly integrated into existing LSS-based BEV networks. Having said that, due to the inherent gap between two representation spaces, we design the instance adaptor for the BEV-to-instance semantic coherence rather than pass the proposal naively. Extensive experiments demonstrated that our proposed framework is of excellent generalization ability and performance, which boosts the performances of modern LSS-based BEV perception methods without bells and whistles and outperforms current LSS-based state-of-the-art works on the large-scale nuScenes benchmark.
Authors: Qihang Fan, Huaibo Huang, Ran He
Abstract: The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications. In contrast, linear attention provides a far more efficient solution by reducing the complexity to linear levels. However, compared to Softmax attention, linear attention often experiences significant performance degradation. Our experiments indicate that this performance drop is due to the low-rank nature of linear attention's feature map, which hinders its ability to adequately model complex spatial information. In this paper, to break the low-rank dilemma of linear attention, we conduct rank analysis from two perspectives: the KV buffer and the output features. Consequently, we introduce Rank-Augmented Linear Attention (RALA), which rivals the performance of Softmax attention while maintaining linear complexity and high efficiency. Based on RALA, we construct the Rank-Augmented Vision Linear Transformer (RAVLT). Extensive experiments demonstrate that RAVLT achieves excellent performance across various vision tasks. Specifically, without using any additional labels, data, or supervision during training, RAVLT achieves an 84.4% Top-1 accuracy on ImageNet-1k with only 26M parameters and 4.6G FLOPs. This result significantly surpasses previous linear attention mechanisms, fully illustrating the potential of RALA. Code will be available at https://github.com/qhfan/RALA.
Authors: Xuyang Cao, Guoxin Wang, Sheng Shi, Jun Zhao, Yang Yao, Jintao Fei, Minyu Gao
Abstract: Audio-driven portrait animation has made significant advances with diffusion-based models, improving video quality and lipsync accuracy. However, the increasing complexity of these models has led to inefficiencies in training and inference, as well as constraints on video length and inter-frame continuity. In this paper, we propose JoyVASA, a diffusion-based method for generating facial dynamics and head motion in audio-driven facial animation. Specifically, in the first stage, we introduce a decoupled facial representation framework that separates dynamic facial expressions from static 3D facial representations. This decoupling allows the system to generate longer videos by combining any static 3D facial representation with dynamic motion sequences. Then, in the second stage, a diffusion transformer is trained to generate motion sequences directly from audio cues, independent of character identity. Finally, a generator trained in the first stage uses the 3D facial representation and the generated motion sequences as inputs to render high-quality animations. With the decoupled facial representation and the identity-independent motion generation process, JoyVASA extends beyond human portraits to animate animal faces seamlessly. The model is trained on a hybrid dataset of private Chinese and public English data, enabling multilingual support. Experimental results validate the effectiveness of our approach. Future work will focus on improving real-time performance and refining expression control, further expanding the applications in portrait animation. The code is available at: https://github.com/jdh-algo/JoyVASA.
Authors: Qiang Li, George Teodoro, Yi Jiang, Jun Kong
Abstract: Neoadjuvant chemotherapy (NAC) response prediction for triple negative breast cancer (TNBC) patients is a challenging task clinically as it requires understanding complex histology interactions within the tumor microenvironment (TME). Digital whole slide images (WSIs) capture detailed tissue information, but their giga-pixel size necessitates computational methods based on multiple instance learning, which typically analyze small, isolated image tiles without the spatial context of the TME. To address this limitation and incorporate TME spatial histology interactions in predicting NAC response for TNBC patients, we developed a histology context-aware transformer graph convolution network (NACNet). Our deep learning method identifies the histopathological labels on individual image tiles from WSIs, constructs a spatial TME graph, and represents each node with features derived from tissue texture and social network analysis. It predicts NAC response using a transformer graph convolution network model enhanced with graph isomorphism network layers. We evaluate our method with WSIs of a cohort of TNBC patient (N=105) and compared its performance with multiple state-of-the-art machine learning and deep learning models, including both graph and non-graph approaches. Our NACNet achieves 90.0% accuracy, 96.0% sensitivity, 88.0% specificity, and an AUC of 0.82, through eight-fold cross-validation, outperforming baseline models. These comprehensive experimental results suggest that NACNet holds strong potential for stratifying TNBC patients by NAC response, thereby helping to prevent overtreatment, improve patient quality of life, reduce treatment cost, and enhance clinical outcomes, marking an important advancement toward personalized breast cancer treatment.
Authors: Yongjin Lee, Hyeon-Mun Jeong, Yurim Jeon, Sanghyun Kim
Abstract: Multi-modal sensor fusion in bird's-eye-view (BEV) representation has become the leading approach in 3D object detection. However, existing methods often rely on depth estimators or transformer encoders for view transformation, incurring substantial computational overhead. Furthermore, the lack of precise geometric correspondence between 2D and 3D spaces leads to spatial and ray-directional misalignments, restricting the effectiveness of BEV representations. To address these challenges, we propose a novel 3D object detector via efficient view transformation (EVT), which leverages a well-structured BEV representation to enhance accuracy and efficiency. EVT focuses on two main areas. First, it employs Adaptive Sampling and Adaptive Projection (ASAP), using LiDAR guidance to generate 3D sampling points and adaptive kernels. The generated points and kernels are then used to facilitate the transformation of image features into BEV space and refine the BEV features. Second, EVT includes an improved transformer-based detection framework, which contains a group-wise query initialization method and an enhanced query update framework. It is designed to effectively utilize the obtained multi-modal BEV features within the transformer decoder. By leveraging the geometric properties of object queries, this framework significantly enhances detection performance, especially in a multi-layer transformer decoder structure. EVT achieves state-of-the-art performance on the nuScenes test set with real-time inference speed.
Authors: Yunlong Tang, Junjia Guo, Hang Hua, Susan Liang, Mingqian Feng, Xinyang Li, Rui Mao, Chao Huang, Jing Bi, Zeliang Zhang, Pooyan Fazli, Chenliang Xu
Abstract: The advancement of Multimodal Large Language Models (MLLMs) has enabled significant progress in multimodal understanding, expanding their capacity to analyze video content. However, existing evaluation benchmarks for MLLMs primarily focus on abstract video comprehension, lacking a detailed assessment of their ability to understand video compositions, the nuanced interpretation of how visual elements combine and interact within highly compiled video contexts. We introduce VidComposition, a new benchmark specifically designed to evaluate the video composition understanding capabilities of MLLMs using carefully curated compiled videos and cinematic-level annotations. VidComposition includes 982 videos with 1706 multiple-choice questions, covering various compositional aspects such as camera movement, angle, shot size, narrative structure, character actions and emotions, etc. Our comprehensive evaluation of 33 open-source and proprietary MLLMs reveals a significant performance gap between human and model capabilities. This highlights the limitations of current MLLMs in understanding complex, compiled video compositions and offers insights into areas for further improvement. The leaderboard and evaluation code are available at https://yunlong10.github.io/VidComposition/.
Authors: Tiancheng Lin, Jinglei Zhang, Yi Xu, Kai Chen, Rui Zhang, Chang-Wen Chen
Abstract: Context-aware methods have achieved remarkable advancements in supervised scene text recognition by leveraging semantic priors from words. Considering the heterogeneity of text and background in STR, we propose that such contextual priors can be reinterpreted as the relations between textual elements, serving as effective self-supervised labels for representation learning. However, textual relations are restricted to the finite size of the dataset due to lexical dependencies, which causes over-fitting problem, thus compromising the representation quality. To address this, our work introduces a unified framework of Relational Contrastive Learning and Masked Image Modeling for STR (RCMSTR), which explicitly models the enriched textual relations. For the RCL branch, we first introduce the relational rearrangement module to cultivate new relations on the fly. Based on this, we further conduct relational contrastive learning to model the intra- and inter-hierarchical relations for frames, sub-words and words. On the other hand, MIM can naturally boost the context information via masking, where we find that the block masking strategy is more effective for STR. For the effective integration of RCL and MIM, we also introduce a novel decoupling design aimed at mitigating the impact of masked images on contrastive learning. Additionally, to enhance the compatibility of MIM with CNNs, we propose the adoption of sparse convolutions and directly sharing the weights with dense convolutions in training. The proposed RCMSTR demonstrates superior performance in various evaluation protocols for different STR-related downstream tasks, outperforming the existing state-of-the-art self-supervised STR techniques. Ablation studies and qualitative experimental results further validate the effectiveness of our method. The code and pre-trained models will be available at https://github.com/ThunderVVV/RCMSTR .
Authors: Jikang Cheng, Zhiyuan Yan, Ying Zhang, Li Hao, Jiaxin Ai, Qin Zou, Chen Li, Zhongyuan Wang
Abstract: The rapid advancement of face forgery techniques has introduced a growing variety of forgeries. Incremental Face Forgery Detection (IFFD), involving gradually adding new forgery data to fine-tune the previously trained model, has been introduced as a promising strategy to deal with evolving forgery methods. However, a naively trained IFFD model is prone to catastrophic forgetting when new forgeries are integrated, as treating all forgeries as a single ''Fake" class in the Real/Fake classification can cause different forgery types overriding one another, thereby resulting in the forgetting of unique characteristics from earlier tasks and limiting the model's effectiveness in learning forgery specificity and generality. In this paper, we propose to stack the latent feature distributions of previous and new tasks brick by brick, $\textit{i.e.}$, achieving $\textbf{aligned feature isolation}$. In this manner, we aim to preserve learned forgery information and accumulate new knowledge by minimizing distribution overriding, thereby mitigating catastrophic forgetting. To achieve this, we first introduce Sparse Uniform Replay (SUR) to obtain the representative subsets that could be treated as the uniformly sparse versions of the previous global distributions. We then propose a Latent-space Incremental Detector (LID) that leverages SUR data to isolate and align distributions. For evaluation, we construct a more advanced and comprehensive benchmark tailored for IFFD. The leading experimental results validate the superiority of our method.
Authors: R\"uveyda Yilmaz, Kaan Keven, Yuli Wu, Johannes Stegmaier
Abstract: Automated cell segmentation in microscopy images is essential for biomedical research, yet conventional methods are labor-intensive and prone to error. While deep learning-based approaches have proven effective, they often require large annotated datasets, which are scarce due to the challenges of manual annotation. To overcome this, we propose a novel framework for synthesizing densely annotated 2D and 3D cell microscopy images using cascaded diffusion models. Our method synthesizes 2D and 3D cell masks from sparse 2D annotations using multi-level diffusion models and NeuS, a 3D surface reconstruction approach. Following that, a pretrained 2D Stable Diffusion model is finetuned to generate realistic cell textures and the final outputs are combined to form cell populations. We show that training a segmentation model with a combination of our synthetic data and real data improves cell segmentation performance by up to 9\% across multiple datasets. Additionally, the FID scores indicate that the synthetic data closely resembles real data. The code for our proposed approach will be available at https://github.com/ruveydayilmaz0/cascaded_diffusion.
Authors: Danny Barash, Emilie Manning, Aidan Van Vleck, Omri Hirsch, Kyi Lei Aye, Jingxi Li, Philip O. Scumpia, Aydogan Ozcan, Sumaira Aasi, Kerri E. Rieger, Kavita Y. Sarin, Oren Freifeld, Yonatan Winetraub
Abstract: Noninvasive optical imaging modalities can probe patient's tissue in 3D and over time generate gigabytes of clinically relevant data per sample. There is a need for AI models to analyze this data and assist clinical workflow. The lack of expert labelers and the large dataset required (>100,000 images) for model training and tuning are the main hurdles in creating foundation models. In this paper we introduce FoundationShift, a method to apply any AI model from computational pathology without retraining. We show our method is more accurate than state of the art models (SAM, MedSAM, SAM-Med2D, CellProfiler, Hover-Net, PLIP, UNI and ChatGPT), with multiple imaging modalities (OCT and RCM). This is achieved without the need for model retraining or fine-tuning. Applying our method to noninvasive in vivo images could enable physicians to readily incorporate optical imaging modalities into their clinical practice, providing real time tissue analysis and improving patient care.
Authors: Taiming Lu, Tianmin Shu, Alan Yuille, Daniel Khashabi, Jieneng Chen
Abstract: Planning with partial observation is a central challenge in embodied AI. A majority of prior works have tackled this challenge by developing agents that physically explore their environment to update their beliefs about the world state. In contrast, humans can $\textit{imagine}$ unseen parts of the world through a mental exploration and $\textit{revise}$ their beliefs with imagined observations. Such updated beliefs can allow them to make more informed decisions, without necessitating the physical exploration of the world at all times. To achieve this human-like ability, we introduce the $\textit{Generative World Explorer (Genex)}$, an egocentric world exploration framework that allows an agent to mentally explore a large-scale 3D world (e.g., urban scenes) and acquire imagined observations to update its belief. This updated belief will then help the agent to make a more informed decision at the current step. To train $\textit{Genex}$, we create a synthetic urban scene dataset, Genex-DB. Our experimental results demonstrate that (1) $\textit{Genex}$ can generate high-quality and consistent observations during long-horizon exploration of a large virtual physical world and (2) the beliefs updated with the generated observations can inform an existing decision-making model (e.g., an LLM agent) to make better plans.
Authors: Sheng Sun, Armando Marino, Wenze Shui, Zhongwen Hu
Abstract: In this work we explore the performance of DCNNs on semantic segmentation using spaceborne polarimetric synthetic aperture radar (PolSAR) datasets. The semantic segmentation task using PolSAR data can be categorized as weakly supervised learning when the characteristics of SAR data and data annotating procedures are factored in. Datasets are initially analyzed for selecting feasible pre-training images. Then the differences between spaceborne and airborne datasets are examined in terms of spatial resolution and viewing geometry. In this study we used two dual-polarimetric images acquired by TerraSAR-X DLR. A novel method to produce training dataset with more supervised information is developed. Specifically, a series of typical classified images as well as intensity images serve as training datasets. A field survey is conducted for an area of about 20 square kilometers to obtain a ground truth dataset used for accuracy evaluation. Several transfer learning strategies are made for aforementioned training datasets which will be combined in a practicable order. Three DCNN models, including SegNet, U-Net, and LinkNet, are implemented next.
Authors: Xingting Yao, Qinghao Hu, Fei Zhou, Tielong Liu, Zitao Mo, Zeyu Zhu, Zhengyang Zhuge, Jian Cheng
Abstract: In this paper, we propose SpikingNeRF, which aligns the temporal dimension of spiking neural networks (SNNs) with the radiance rays, to seamlessly accommodate SNNs to the reconstruction of neural radiance fields (NeRF). Thus, the computation turns into a spike-based, multiplication-free manner, reducing energy consumption and making high-quality 3D rendering, for the first time, accessible to neuromorphic hardware. In SpikingNeRF, each sampled point on the ray is matched to a particular time step and represented in a hybrid manner where the voxel grids are maintained as well. Based on the voxel grids, sampled points are determined whether to be masked out for faster training and inference. However, this masking operation also incurs irregular temporal length, making it intractable for hardware processors, e.g., GPUs, to conduct parallel training. To address this problem, we develop the temporal padding strategy to tackle the masked samples to maintain regular temporal length, i.e., regular tensors, and further propose the temporal condensing strategy to form a denser data structure for hardware-friendly computation. Experiments on various datasets demonstrate that our method can reduce energy consumption by an average of 70.79\% and obtain comparable synthesis quality with the ANN baseline. Verification on the neuromorphic hardware accelerator also shows that SpikingNeRF can further benefit from neuromorphic computing over the ANN baselines on energy efficiency. Codes and the appendix are in \url{https://github.com/Ikarosy/SpikingNeRF-of-CASIA}.
Authors: Chenqi Kong, Anwei Luo, Shiqi Wang, Haoliang Li, Anderson Rocha, Alex C. Kot
Abstract: Digital image forensics plays a crucial role in image authentication and manipulation localization. Despite the progress powered by deep neural networks, existing forgery localization methodologies exhibit limitations when deployed to unseen datasets and perturbed images (i.e., lack of generalization and robustness to real-world applications). To circumvent these problems and aid image integrity, this paper presents a generalized and robust manipulation localization model through the analysis of pixel inconsistency artifacts. The rationale is grounded on the observation that most image signal processors (ISP) involve the demosaicing process, which introduces pixel correlations in pristine images. Moreover, manipulating operations, including splicing, copy-move, and inpainting, directly affect such pixel regularity. We, therefore, first split the input image into several blocks and design masked self-attention mechanisms to model the global pixel dependency in input images. Simultaneously, we optimize another local pixel dependency stream to mine local manipulation clues within input forgery images. In addition, we design novel Learning-to-Weight Modules (LWM) to combine features from the two streams, thereby enhancing the final forgery localization performance. To improve the training process, we propose a novel Pixel-Inconsistency Data Augmentation (PIDA) strategy, driving the model to focus on capturing inherent pixel-level artifacts instead of mining semantic forgery traces. This work establishes a comprehensive benchmark integrating 15 representative detection models across 12 datasets. Extensive experiments show that our method successfully extracts inherent pixel-inconsistency forgery fingerprints and achieve state-of-the-art generalization and robustness performances in image manipulation localization.
Authors: Yafei Dong, Kuang Gong
Abstract: Head and neck (H&N) cancers are among the most prevalent types of cancer worldwide, and [18F]F-FDG PET/CT is widely used for H&N cancer management. Recently, the diffusion model has demonstrated remarkable performance in various image-generation tasks. In this work, we proposed a 3D diffusion model to accurately perform H&N tumor segmentation from 3D PET and CT volumes. The 3D diffusion model was developed considering the 3D nature of PET and CT images acquired. During the reverse process, the model utilized a 3D UNet structure and took the concatenation of PET, CT, and Gaussian noise volumes as the network input to generate the tumor mask. Experiments based on the HECKTOR challenge dataset were conducted to evaluate the effectiveness of the proposed diffusion model. Several state-of-the-art techniques based on U-Net and Transformer structures were adopted as the reference methods. Benefits of employing both PET and CT as the network input as well as further extending the diffusion model from 2D to 3D were investigated based on various quantitative metrics and the uncertainty maps generated. Results showed that the proposed 3D diffusion model could generate more accurate segmentation results compared with other methods. Compared to the diffusion model in 2D format, the proposed 3D model yielded superior results. Our experiments also highlighted the advantage of utilizing dual-modality PET and CT data over only single-modality data for H&N tumor segmentation.
Authors: Jonathan Heek, Emiel Hoogeboom, Tim Salimans
Abstract: Diffusion models are relatively easy to train but require many steps to generate samples. Consistency models are far more difficult to train, but generate samples in a single step. In this paper we propose Multistep Consistency Models: A unification between Consistency Models (Song et al., 2023) and TRACT (Berthelot et al., 2023) that can interpolate between a consistency model and a diffusion model: a trade-off between sampling speed and sampling quality. Specifically, a 1-step consistency model is a conventional consistency model whereas a $\infty$-step consistency model is a diffusion model. Multistep Consistency Models work really well in practice. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples, while retaining much of the sampling speed benefits. Notable results are 1.4 FID on Imagenet 64 in 8 step and 2.1 FID on Imagenet128 in 8 steps with consistency distillation, using simple losses without adversarial training. We also show that our method scales to a text-to-image diffusion model, generating samples that are close to the quality of the original model.
Authors: Felix Wagner, Wentian Xu, Pramit Saha, Ziyun Liang, Daniel Whitehouse, David Menon, Virginia Newcombe, Natalie Voets, J. Alison Noble, Konstantinos Kamnitsas
Abstract: Segmentation models for brain lesions in MRI are typically developed for a specific disease and trained on data with a predefined set of MRI modalities. Such models cannot segment the disease using data with a different set of MRI modalities, nor can they segment other types of diseases. Moreover, this training paradigm prevents a model from using the advantages of learning from heterogeneous databases that may contain scans and segmentation labels for different brain pathologies and diverse sets of MRI modalities. Additionally, the confidentiality of patient data often prevents central data aggregation, necessitating a decentralized approach. Is it feasible to use Federated Learning (FL) to train a single model on client databases that contain scans and labels of different brain pathologies and diverse sets of MRI modalities? We demonstrate promising results by combining appropriate, simple, and practical modifications to the model and training strategy: Designing a model with input channels that cover the whole set of modalities available across clients, training with random modality drop, and exploring the effects of feature normalization methods. Evaluation on 7 brain MRI databases with 5 different diseases shows that this FL framework can train a single model achieving very promising results in segmenting all disease types seen during training. Importantly, it can segment these diseases in new databases that contain sets of modalities different from those in training clients. These results demonstrate, for the first time, the feasibility and effectiveness of using FL to train a single 3D segmentation model on decentralised data with diverse brain diseases and MRI modalities, a necessary step towards leveraging heterogeneous real-world databases. Code: https://github.com/FelixWag/FedUniBrain
Authors: Xuanyu Tian, Zhuoya Dong, Xiyue Lin, Yue Gao, Hongjiang Wei, Yanhang Ma, Jingyi Yu, Yuyao Zhang
Abstract: High-resolution electron microscopy (HREM) imaging technique is a powerful tool for directly visualizing a broad range of materials in real-space. However, it faces challenges in denoising due to ultra-low signal-to-noise ratio (SNR) and scarce data availability. In this work, we propose Noise2SR, a zero-shot self-supervised learning (ZS-SSL) denoising framework for HREM. Within our framework, we propose a super-resolution (SR) based self-supervised training strategy, incorporating the Random Sub-sampler module. The Random Sub-sampler is designed to generate approximate infinite noisy pairs from a single noisy image, serving as an effective data augmentation in zero-shot denoising. Noise2SR trains the network with paired noisy images of different resolutions, which is conducted via SR strategy. The SR-based training facilitates the network adopting more pixels for supervision, and the random sub-sampling helps compel the network to learn continuous signals enhancing the robustness. Meanwhile, we mitigate the uncertainty caused by random-sampling by adopting minimum mean squared error (MMSE) estimation for the denoised results. With the distinctive integration of training strategy and proposed designs, Noise2SR can achieve superior denoising performance using a single noisy HREM image. We evaluate the performance of Noise2SR in both simulated and real HREM denoising tasks. It outperforms state-of-the-art ZS-SSL methods and achieves comparable denoising performance with supervised methods. The success of Noise2SR suggests its potential for improving the SNR of images in material imaging domains.
Authors: Wael Mattar, Idan Levy, Nir Sharon, Shai Dekel
Abstract: In this paper, we take a new approach to autoregressive image generation that is based on two main ingredients. The first is wavelet image coding, which allows to tokenize the visual details of an image from coarse to fine details by ordering the information starting with the most significant bits of the most significant wavelet coefficients. The second is a variant of a language transformer whose architecture is re-designed and optimized for token sequences in this 'wavelet language'. The transformer learns the significant statistical correlations within a token sequence, which are the manifestations of well-known correlations between the wavelet subbands at various resolutions. We show experimental results with conditioning on the generation process.
Authors: Sina Derakhshandeh, Ali Mahloojifar
Abstract: Segmentation is one of the most significant steps in image processing. Segmenting an image is a technique that makes it possible to separate a digital image into various areas based on the different characteristics of pixels in the image. In particular, segmentation of breast ultrasound images is widely used for cancer identification. As a result of image segmentation, it is possible to make early diagnoses of a diseases via medical images in a very effective way. Due to various ultrasound artifacts and noises, including speckle noise, low signal-to-noise ratio, and intensity heterogeneity, the process of accurately segmenting medical images, such as ultrasound images, is still a challenging task. In this paper, we present a new method to improve the accuracy and effectiveness of breast ultrasound image segmentation. More precisely, we propose a Neural Network (NN) based on U-Net and an encoder-decoder architecture. By taking U-Net as the basis, both encoder and decoder parts are developed by combining U-Net with other Deep Neural Networks (Res-Net and MultiResUNet) and introducing a new approach and block (Co-Block), which preserve as much as possible the low-level and the high-level features. Designed network is evaluated using the Breast Ultrasound Images (BUSI) Dataset. It consists of 780 images and the images are categorized into three classes, which are normal, benign, and malignant. According to our extensive evaluations on a public breast ultrasound dataset, designed network segments the breast lesions more accurately than other state-of-the-art deep learning methods. With only 8.88M parameters, our network (CResU-Net) obtained 82.88%, 77.5%, 90.3%, and 98.4% in terms of Dice similarity coefficients (DSC), Intersection over Union (IoU), Area under curve (AUC), and global accuracy (ACC), respectively, on BUSI dataset.
Authors: Jiawei Du, Xin Zhang, Juncheng Hu, Wenxin Huang, Joey Tianyi Zhou
Abstract: The sharp increase in data-related expenses has motivated research into condensing datasets while retaining the most informative features. Dataset distillation has thus recently come to the fore. This paradigm generates synthetic datasets that are representative enough to replace the original dataset in training a neural network. To avoid redundancy in these synthetic datasets, it is crucial that each element contains unique features and remains diverse from others during the synthesis stage. In this paper, we provide a thorough theoretical and empirical analysis of diversity within synthesized datasets. We argue that enhancing diversity can improve the parallelizable yet isolated synthesizing approach. Specifically, we introduce a novel method that employs dynamic and directed weight adjustment techniques to modulate the synthesis process, thereby maximizing the representativeness and diversity of each synthetic instance. Our method ensures that each batch of synthetic data mirrors the characteristics of a large, varying subset of the original dataset. Extensive experiments across multiple datasets, including CIFAR, Tiny-ImageNet, and ImageNet-1K, demonstrate the superior performance of our method, highlighting its effectiveness in producing diverse and representative synthetic datasets with minimal computational expense. Our code is available at https://github.com/AngusDujw/Diversity-Driven-Synthesis.https://github.com/AngusDujw/Diversity-Driven-Synthesis.
Authors: Mingyu Yu, Haonan Miao, Zhengping Jin, Sujuan Qin
Abstract: Typical steganography embeds secret information into images by exploiting their redundancy. Since the visual imperceptibility of secret information is a key factor in scheme evaluation, conventional methods aim to balance this requirement with embedding capacity. Consequently, integrating emerging image generation models and secret transmission has been extensively explored to achieve a higher embedding capacity. Previous works mostly focus on generating stego-images with Generative Adversarial Networks (GANs) and usually rely on pseudo-keys, namely conditions or parameters involved in the generation process, which are related to secret images. However, studies on diffusion-based coverless steganography remain insufficient. In this work, we leverage the Denoising Diffusion Implicit Model (DDIM) to generate high-quality stego-images without introducing pseudo-keys, instead employing real keys to enhance security. Furthermore, our method offers low-image-correlation real-key protection by incorporating chaotic encryption. Another core innovation is that our method requires only one-time negotiation for multiple communications, unlike prior methods that necessitate negotiation for each interaction.
Authors: Abdurahman Ali Mohammed, Catherine Fonder, Donald S. Sakaguchi, Wallapak Tavanapong, Surya K. Mallapragada, Azeez Idris
Abstract: We present a new annotated microscopic cellular image dataset to improve the effectiveness of machine learning methods for cellular image analysis. Cell counting is an important step in cell analysis. Typically, domain experts manually count cells in a microscopic image. Automated cell counting can potentially eliminate this tedious, time-consuming process. However, a good, labeled dataset is required for training an accurate machine learning model. Our dataset includes microscopic images of cells, and for each image, the cell count and the location of individual cells. The data were collected as part of an ongoing study investigating the potential of electrical stimulation to modulate stem cell differentiation and possible applications for neural repair. Compared to existing publicly available datasets, our dataset has more images of cells stained with more variety of antibodies (protein components of immune responses against invaders) typically used for cell analysis. The experimental results on this dataset indicate that none of the five existing models under this study are able to achieve sufficiently accurate count to replace the manual methods. The dataset is available at https://figshare.com/articles/dataset/Dataset/21970604.
URLs: https://figshare.com/articles/dataset/Dataset/21970604.
Authors: F. Adetunji, A. Karukayil, P. Samant, S. Shabana, F. Varghese, U. Upadhyay, R. A. Yadav, A. Partridge, E. Pendleton, R. Plant, Y. Petillot, M. Koskinopoulou
Abstract: This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm. Industry 4.0, driven by data, connectivity, analytics, and robotics, promises enhanced accessibility and sustainability throughout the value chain. The integration of autonomous systems, including collaborative robots (cobots), into industrial processes is pivotal for efficiency and safety. The proposed solution employs advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs), to identify transparent plastic bags under varying lighting and background conditions. Tracking algorithms and depth sensing technologies are utilized for 3D spatial awareness during pick and placement. The system addresses challenges in grasping and manipulation, considering optimal points, compliance control with vacuum gripping technology, and real-time automation for safe interaction in dynamic environments. The system's successful testing and validation in the lab with the FRANKA robot arm, showcases its potential for widespread industrial applications, while demonstrating effectiveness in automating the unpacking and cutting of transparent plastic bags for an 8-stack bulk-loader based on specific requirements and rigorous testing.
Authors: Daphn\'e Chopard, Sonia Laguna, Kieran Chin-Cheong, Annika Dietz, Anna Badura, Sven Wellmann, Julia E. Vogt
Abstract: General movements (GMs) are spontaneous, coordinated body movements in infants that offer valuable insights into the developing nervous system. Assessed through the Prechtl GM Assessment (GMA), GMs are reliable predictors for neurodevelopmental disorders. However, GMA requires specifically trained clinicians, who are limited in number. To scale up newborn screening, there is a need for an algorithm that can automatically classify GMs from infant video recordings. This data poses challenges, including variability in recording length, device type, and setting, with each video coarsely annotated for overall movement quality. In this work, we introduce a tool for extracting features from these recordings and explore various machine learning techniques for automated GM classification.
Authors: Maria Monzon, Thomas Iff, Ender Konukoglu, Catherine R. Jutzeler
Abstract: This study introduces a diffusion-based framework for robust and accurate segmenton of vertebrae, intervertebral discs (IVDs), and spinal canal from Magnetic Resonance Imaging~(MRI) scans of patients with low back pain (LBP), regardless of whether the scans are T1w or T2-weighted. The results showed that SpineSegDiff achieved comparable outperformed non-diffusion state-of-the-art models in the identification of degenerated IVDs. Our findings highlight the potential of diffusion models to improve LBP diagnosis and management through precise spine MRI analysis.