检索结果-内蒙古大学图书馆

LLDB: Efficient Low-Light Image Enhancement with Difffusion Bridge

学校读者我要写书评

暂无评论

LLDB: Efficient Low-Light Image Enhancement with Difffusion ...

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Junlong Ma Conghan Yue Zhengwei Peng Dongyu Zhang Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper investigates a low-light image enhancement method based on the diffusion bridge framework. Currently, low-light image enhancement tasks still face challenges in noise reduction and detail restoration, and existing diffusion model methods are time-consuming and have unstable diffusion processes. We conducted an in-depth study of diffusion bridge theory, integrating the advantages of the end-to-end paradigm of diffusion bridge theory and employing a nonlinear activation network to further enhance the performance of low-light image enhancement tasks. Additionally, we used a Gamma correction module for fine-tuning low-light images, significantly improving performance with almost no extra computational cost. Experiments show that Low-Light image enhancement with Difffusion Bridge (LLDB) far surpasses other methods on LOLv1 and LOLv2 datasets. Code is available at https://***/M-Chase/LLDB

关键词： Bridges Computational modeling Noise reduction Diffusion processes Speech enhancement Signal processing Diffusion models Image restoration Image enhancement Faces

Enhanced Control for Diffusion Bridge in Image Restoration

学校读者我要写书评

暂无评论

Enhanced Control for Diffusion Bridge in Image Restoration

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Conghan Yue Zhengwei Peng Junlong Ma Dongyu Zhang Sun Yat-Sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Image restoration refers to the process of restoring a damaged low-quality image back to its corresponding high-quality image. Recently, a special type of diffusion bridge model has achieved more advanced results in image restoration. It can transform the direct mapping from low-quality to high-quality images into a diffusion process, restoring low-quality images through a reverse process. However, the current diffusion bridge restoration models do not emphasize the idea of conditional control, which may affect performance. This paper introduces the ECDB model enhancing the control of the diffusion bridge with low-quality images as conditions. Moreover, in response to the characteristic of diffusion models having low denoising level at larger values of t, we also propose a Conditional Fusion Schedule, which more effectively handles the conditional feature information of various modules. Experimental results prove that the ECDB model has achieved state-of-the-art results in many image restoration tasks, including deraining, inpainting and super-resolution. Code is avaliable at https://***/Hammour-steak/ECDB.

关键词： Bridges Schedules Noise reduction Superresolution Diffusion processes Transforms Predictive models Feature extraction Image restoration Speech processing

Graph-Enhanced Multi-Scale Contrastive Learning for Graph Anomaly Detection with Adaptive Diffusion Models

学校读者我要写书评

暂无评论

IEEE Transactions on big data 2025年

作者： Xiao, Chunjing Tong, Yao Lu, Jiahui Xue, Yuxia Tai, Wenxin Cheng, Zhangtao Zhou, Fan The Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China The University of Electronic Science and Technology of China Chengdu610054 China

Graph anomaly detection has gained significant research interest across various domains. Due to the lack of labeled data, contrastive learning has been applied in detecting anomalies and various contrastive strategies have been initiated. However, these methods might force two instances (e.g., node-level and subgraph-level representations) with different category labels to be consistent during model training, which can adversely impact the model robustness. Also, they extract node-level representations only based on node attributes, which are inadequate in reflecting the information of the structural anomaly. To tackle this problem, we present a Graph-enhanced multi-scale Contrastive Learning framework for Anomaly Detection, GCLAD. In this framework, we design a diffusion probabilistic model-based graph enhancement module to adaptively manipulate neighbors to generate enhanced graphs, which can efficiently enhance subgraph-level representations and alleviate the inconsistent problem. Further, we present a multi-scale contrastive module where we introduce meta-paths to exploit a few relevant neighbors to boost node-level representations, and build the multi-scale contrastive losses to promote anomaly detection performance. Experimental results demonstrate the superiority of GCLAD compared with state-of-the-art baselines. © 2015 IEEE. All rights reserved.

关键词： Contrastive Learning

Anima2: Cross-Species Animal Animation through Image-to-Video Synthesis with Subject Alignment

学校读者我要写书评

暂无评论

Anima2: Cross-Species Animal Animation through Image-to-Vide...

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yuanfeng Xu Yuhao Chen Zhongzhan Huang Zijian He Guangrun Wang Liang Lin Sun Yat-Sen University China Guangdong Key Laboratory of Big Data Analysis and Processing China Peng Cheng Laboratory China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent video editing advancements rely on accurate pose sequences to animate human actors. However, these efforts are not suitable for cross-species animation due to pose misalignment between species (for example, the poses of a cat differ greatly from that of a pig due to their distinct body structures). In this paper, we present Anima 2 , a zero-shot diffusion-based video generator to address this issue, aiming to accurately ANIMAte ANIMAls while preserving the background. The key technique involves two-fold subject alignment. First, we improve appearance feature extraction by integrating a Laplacian detail booster and a prompt-tuning identity extractor. They capture essential appearance information, including identity and fine details. Second, we align shape features and address conflicts from differing animals by introducing a scale-information remover and an adaptive rescaling module. They both enhance subject alignment for accurate cross-species animation. Additionally, we introduce two high-quality animal video datasets with diverse species to benchmark cross-species animation. Trained on these extensive datasets, our model directly generates videos with accurate movements, consistent appearances, and high-fidelity frames, eliminating the need for test-time training. Extensive experiments demonstrate our method’s superiority in cross-species animation, showcasing robust adaptability and generality.

关键词： Training Accuracy Laplace equations Animals Shape Signal processing Animation Feature extraction Information leakage Speech processing

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Junjia Yan, Pengxiang Cai, Jinhang Liu, Jiyang Wang, Zhao Wang, Yitong Wu, Xinglong Li, Guanbin Sun Yat-sen University China ByteDance Intelligent Creation Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation and multi-layer compositions. However, existing approaches often fail to provide a thorough exploration of multi-layer structures, leading to inconsistent inter-layer interactions, such as occlusion relationships, spatial layout, and shadowing. In this paper, we introduce DreamLayer, a novel framework that enables coherent text-driven generation of multiple image layers, by explicitly modeling the relationship between transparent foreground and background layers. DreamLayer incorporates three key components, i.e., Context-Aware Cross-Attention (CACA) for global-local information exchange, Layer-Shared Self-Attention (LSSA) for establishing robust inter-layer connections, and Information Retained Harmonization (IRH) for refining fusion details at the latent level. By leveraging a coherent full-image context, DreamLayer builds inter-layer connections through attention mechanisms and applies a harmonization step to achieve seamless layer fusion. To facilitate research in multi-layer generation, we construct a high-quality, diverse multi-layer dataset including 400k samples. Extensive experiments and user studies demonstrate that DreamLayer generates more coherent and well-aligned layers, with broad applicability, including latent-space image editing and image-to-layer decomposition. Copyright © 2025, The Authors. All rights reserved.

关键词： Image fusion

GraphSparseNet: a Novel Method for Large Scale Trafffic Flow Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kong, Weiyang Wu, Kaiqi Zhang, Sen Liu, Yubao Sun Yat-Sen University Guangzhou China Sun Yat-Sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Traffic flow forecasting is a critical spatio-temporal data mining task with wide-ranging applications in intelligent route planning and dynamic traffic management. Recent advancements in deep learning, particularly through Graph Neural Networks (GNNs), have significantly enhanced the accuracy of these forecasts by capturing complex spatio-temporal dynamics. However, the scalability of GNNs remains a challenge due to their exponential growth in model complexity with increasing nodes in the graph. Existing methods to address this issue, including sparsification, decomposition, and kernel-based approaches, either do not fully resolve the complexity issue or risk compromising predictive accuracy. This paper introduces GraphSparseNet (GSNet), a novel framework designed to improve both the scalability and accuracy of GNN-based traffic forecasting models. GraphSparseNet is comprised of two core modules: the Feature Extractor and the Relational Compressor. These modules operate with linear time and space complexity, thereby reducing the overall computational complexity of the model to a linear scale. Our extensive experiments on multiple real-world datasets demonstrate that GraphSparseNet not only significantly reduces training time by 3.51x compared to state-of-the-art linear models but also maintains high predictive performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Scalability

Aerial Vision-and-Language Navigation with Grid-based View Selection and Map Construction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Ganlong Li, Guanbin Pan, Jia Yu, Yizhou The University of Hong Kong Hong Kong Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing China Peng Cheng Laboratory China

Aerial Vision-and-Language Navigation (Aerial VLN) aims to obtain an unmanned aerial vehicle agent to navigate aerial 3D environments following human instruction. Compared to ground-based VLN, aerial VLN requires the agent to decide the next action in both horizontal and vertical directions based on the first-person view observations. Previous methods struggle to perform well due to the longer navigation path, more complicated 3D scenes, and the neglect of the interplay between vertical and horizontal actions. In this paper, we propose a novel grid-based view selection framework that formulates aerial VLN action prediction as a grid-based view selection task, incorporating vertical action prediction in a manner that accounts for the coupling with horizontal actions, thereby enabling effective altitude adjustments. We further introduce a grid-based bird’s eye view map for aerial space to fuse the visual information in the navigation history, provide contextual scene information, and mitigate the impact of obstacles. Finally, a cross-modal transformer is adopted to explicitly align the long navigation history with the instruction. We demonstrate the superiority of our method in extensive experiments. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

Out-of-Distribution Fault Diagnosis of Industrial Cyber-Physical Systems Based on Orthogonal Anchor Clustering With Adaptive Balance

学校读者我要写书评

暂无评论

IEEE Transactions on Industrial Cyber-Physical Systems

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 48-60页

作者： Liu, Ruonan Hu, Puyuan Zhao, Siheng Sun, Zhijian Han, Te Pang, Zhibo Zhang, Weidong Shanghai Jiao Tong University Department of Automation Shanghai200240 China National Key Laboratory of Marine Engine Science and Technology Shanghai201108 China Crossocean of Suzhou Technology Suzhou215121 China Beijing Institute of Technology Center for Energy and Environmental Policy Research School of Management Beijing100081 China ABB Corporate Research Sweden Department of Automation Technology Vasteras722 26 Sweden KTH Royal Institute of Technology Department of Intelligent Systems Stockholm114 28 Sweden Henan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng475001 China Shanghai Jiaotong University Department of Automation Shanghai200240 China

Given the critical role of rotating machinery in industrial cyber-physical systems (ICPS), ensuring their reliable operation is essential for the stability and safety of ICPS. Deep neural networks have demonstrated competitive results for intelligent fault diagnosis, which are usually trained via the historical data of all fault modes. However, in real engineering, it is usually difficult to collect samples and exhaust all failures during the training stage. As a result, out-of-distribution fault diagnosis (OOD-FD) becomes a more realistic problem that requires the methods to not only accurately diagnose the known faults, but also effectively recognize unknown ones. Therefore, a novel orthogonal anchor clustering with focal attention (FA-OAC) is proposed in this paper for OOD-FD. Firstly, an orthogonal anchor clustering (OAC) algorithm is proposed to fix the class center of each fault mode orthogonally and distinguish the known and unknown faults at the class level. Then, because the identifiability of different fault modes changes a lot in OOD-FD, the focal attention mechanism is applied to dynamically adjust the attention to different fault modes according to the distance loss of OAC, thus addressing the identifiability imbalance problem. To verify the effectiveness of the proposed method, different OOD-FD tasks are designed based on two rotating machinery datasets. The experimental results and comparison with state-of-the-art fault diagnosis methods have demonstrated that the proposed method has improved the OOD-FD performance greatly and therefore provides an effective tool in real engineering. © 2023 IEEE.

关键词： Rotating machinery

A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Zhongzhan Zhong, Shanshan Zhou, Pan Gao, Shanghua Zitnik, Marinka Lin, Liang Sun Yat-sen University China Singapore Management University Singapore Harvard University United States Guangdong Key Laboratory of Big Data Analysis and Processing and Peng Cheng Laboratory China

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern multimodal LLMs and benefits from a rich repository of high-quality, human-annotated creative responses, making it an ideal platform for studying LLM creativity. Next, beyond using the Oogiri game for standard evaluations like ranking and selection, we propose LoTbench, an interactive, causality-aware evaluation framework, to further address some intrinsic risks in standard evaluations, such as information leakage and limited interpretability. The proposed LoTbench not only quantifies LLM creativity more effectively but also visualizes the underlying creative thought processes. Our results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable. Furthermore, we observe a strong correlation between results from the multimodal cognition benchmark MMMU and LoTbench, but only a weak connection with traditional creativity metrics. This suggests that LoTbench better aligns with human cognitive theories, highlighting cognition as a critical foundation in the early stages of creativity and enabling the bridging of diverse concepts. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking