检索结果-内蒙古大学图书馆

AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classes

Remote Sensing 2025年第9期17卷 1556-1556页

作者： Li, Zhenteng Lian, Sheng Pan, Dengfeng Wang, Youlin Liu, Wei College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350002 China Key Laboratory of Intelligent Metro of Universities in Fujian Fuzhou350108 China School of Software and Information Engineering East China Jiaotong University Nanchang330013 China

Object detection in unmanned aerial vehicle (UAV) images poses significant challenges due to complex scale variations and class imbalance among objects. Existing methods often address these challenges separately, overlooking the intricate nature of UAV images and the potential synergy between them. In response, this paper proposes AD-Det, a novel framework employing a coherent coarse-to-fine strategy that seamlessly integrates two pivotal components: adaptive small object enhancement (ASOE) and dynamic class-balanced copy–paste (DCC). ASOE utilizes a high-resolution feature map to identify and cluster regions containing small objects. These regions are subsequently enlarged and processed by a fine-grained detector. On the other hand, DCC conducts object-level resampling by dynamically pasting tail classes around the cluster centers obtained by ASOE, maintaining a dynamic memory bank for each tail class. This approach enables AD-Det to not only extract regions with small objects for precise detection but also dynamically perform reasonable resampling for tail-class objects. Consequently, AD-Det enhances the overall detection performance by addressing the challenges of scale variations and class imbalance in UAV images through a synergistic and adaptive framework. We extensively evaluate our approach on two public datasets, i.e., VisDrone and UAVDT, and demonstrate that AD-Det significantly outperforms existing competitive alternatives. Notably, AD-Det achieves a (Formula presented.) average precision (AP) on the VisDrone dataset, surpassing its counterparts by at least (Formula presented.). © 2025 by the authors.

关键词： Vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

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

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Cross-Domain Code Search without Fine-Tuning

arXiv

引用

arXiv 2025年

作者： Liang, keyu Liu, Zhongxin Liu, Chao Wan, Zhiyuan Lo, David Yang, Xiaohu The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computing and Information Systems Singapore Management University Singapore Singapore

Code search is a crucial task in software engineering, aiming to retrieve code snippets that are semantically relevant to a natural language query. Recently, Pre-trained Language Models (PLMs) have shown remarkable success and are widely adopted for code search tasks. However, PLM-based methods often struggle in cross-domain scenarios. When applied to a new domain, they typically require extensive fine-tuning with substantial data. Even worse, the data scarcity problem in new domains often forces these methods to operate in a zero-shot setting, resulting in a significant decline in performance. RAPID, which generates synthetic data for model fine-tuning, is currently the only effective method for zero-shot cross-domain code search. Despite its effectiveness, RAPID demands substantial computational resources for fine-tuning and needs to maintain specialized models for each domain, underscoring the need for a zero-shot, fine-tuning-free approach for cross-domain code search. The key to tackling zero-shot cross-domain code search lies in bridging the gaps among domains. In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching. We first conduct an empirical study to investigate the effectiveness of these two matching schemas in zero-shot cross-domain code search. Our findings highlight the strong complementarity among the three matching schemas, i.e., query-code, query-comment, and code-code matching. Based on the findings, we propose CodeBridge, a zero-shot, fine-tuning-free approach for cross-domain code search. Specifically, CodeBridge first employs zero-shot prompting to guide Large Language Models (LLMs) to generate a comment for each code snippet in the codebase and produce a code for each query. Subsequently, it encodes queries, code snippets, comments, and the generated code using PLMs and assesses similarities through three matching schemas: query-code, query-comment,

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

CoSIL: software Issue Localization via LLM-Driven Code Repository Graph Searching

arXiv

引用

arXiv 2025年

作者： Jiang, Zhonghao Ren, Xiaoxue Yan, Meng Jiang, Wei Li, Yong Liu, Zhongxin The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China Ant Group Hangzhou China

Large language models (LLMs) have significantly advanced autonomous software engineering, leading to a growing number of software engineering agents that assist developers in automatic program repair. Issue localization forms the basis for accurate patch generation. However, because of limitations caused by the context window length of LLMs, existing issue localization methods face challenges in balancing concise yet effective contexts and adequately comprehensive search spaces. In this paper, we introduce CoSIL, an LLM-driven, simple yet powerful function-level issue localization method without training or indexing. CoSIL reduces the search space through module call graphs, iteratively searches the function call graph to obtain relevant contexts, and uses context pruning to control the search direction and manage contexts effectively. Importantly, the call graph is dynamically constructed by the LLM during search, eliminating the need for pre-parsing. Experiment results demonstrate that CoSIL achieves a Top-1 localization success rate of 43% and 44.6% on SWE-bench Lite and SWE-bench Verified, using Qwen2.5-Coder-32B, respectively, outperforming existing methods by 8.6%–98.2%. When CoSIL is applied to guide the patch generation stage, the resolved rate further improves by 9.3%–31.5%. Copyright © 2025, The Authors. All rights reserved.

关键词： Automatic programming

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Xin Xu, Feng Tao, Feifei Tong, Yao Lyu, Xin Zhong, Jianyi Kaup, André College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9798350368741

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study. © 2025 IEEE.

关键词： frequency transformer remote sensing images Semantic segmentation spectrum enhancement

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

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

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Decoupled Prototype Learning for Reliable Test-Time Adaptation

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Guowei Ding, Changxing Tan, Wentao Tan, Mingkui South China University of Technology School of Electronic and Information Engineering 381 Wushan Road Tianhe District Guangzhou510000 China Pazhou Lab Guangzhou510330 China South China University of Technology School of Future Technology 381 Wushan Road Tianhe District Guangzhou510000 China South China University of Technology School of Software Engineering Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. However, its performance is significantly affected by noisy pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. To address this issue, we propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation. First, we decouple the optimization of class prototypes. For each class prototype, we reduce its distance with positive samples and enlarge its distance with negative samples in a contrastive manner. This strategy prevents the model from overfitting to noisy pseudo-labels. Second, we propose a memory-based strategy to enhance DPL's robustness for the small batch sizes often encountered in TTA. We update each class's pseudo-feature from a memory in a momentum manner and insert an additional DPL loss. Finally, we introduce a consistency regularization-based approach to leverage samples with unconfident pseudo-labels. This approach transfers feature styles of samples with unconfident pseudo-labels to those with confident pseudo-labels. Thus, more reliable samples for TTA are created. The experimental results demonstrate that our methods achieve state-of-the-art performance on domain generalization benchmarks, and reliably improve the performance of self-training-based methods on image corruption benchmarks. The code will be released. © 1999-2012 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling Under Continuous Representation 15th

RobNODDI: Robust NODDI Parameter Estimation with Adaptive S...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Xiao, Taohui Cheng, Jian Fan, Wenxin Yang, Jing Li, Cheng Dong, Enqing Wang, Shanshan School of Mechanical Electrical and Information Engineering Shandong University Weihai264209 China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Peng Cheng Laboratory Guangdong Shenzhen China

ISBN: (纸本)9783031869198

Neurite Orientation Dispersion and Density Imaging (NODDI) is an important imaging technology used to evaluate the microstructure of brain tissue, which is of great significance for the discovery and treatment of various neurological diseases. Current deep learning-based methods perform parameter estimation through diffusion magnetic resonance imaging (dMRI) with a small number of diffusion gradients. These methods speed up parameter estimation and improve accuracy. However, the diffusion directions used by most existing deep learning models during testing needs to be strictly consistent with the diffusion directions during training. This results in poor generalization and robustness of deep learning models in dMRI parameter estimation. In this work, we first verify that the parameter estimation performance of current mainstream methods will significantly decrease when the testing diffusion directions and the training diffusion directions are inconsistent. A robust NODDI parameter estimation method with adaptive sampling under continuous representation (RobNODDI) is proposed. Furthermore, long short-term memory (LSTM) units and fully connected layers are selected to learn continuous representation signals. To this end, we use a total of 100 subjects to conduct experiments based on the Human Connectome Project (HCP) dataset, of which 60 are used for training, 20 are used for validation, and 20 are used for testing. The test results indicate that RobNODDI improves the generalization performance and robustness of the deep learning model, enhancing the stability and flexibility of deep learning NODDI parameter estimatimation applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

End-to-end robust and transparent image watermarking method for screen-shooting scenarios

引用

Journal of Electronic Imaging 2025年第2期34卷

作者： Yang, Nana Chen, Yi Wang, Hongxia Shen, Guowei Guo, Chun Cui, Yunhe Liu, Yong Wu, Hanzhou Guizhou University College of Computer Science and Technology State Key Laboratory of Public Big Data Guiyang China Guizhou University Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guiyang China Sichuan University School of Cyber Science and Engineering Chengdu China Hubei University of Automotive Technology School of Electrical and Information Engineering Shiyan China Shanghai University School of Communication and Information Engineering Shanghai China

Screen-shooting robust image watermarking techniques are the primary means for copyright protection and leakage traceability of screen content. However, existing image watermarking methods generate watermarked images with visible artifacts and are not robust enough against attacks. Therefore, we propose an end-to-end robust and transparent image watermarking method for protecting copyright in screen-shooting scenarios. In this method, we introduce scaling distortion to combine with color distortion, moiré distortion, Gaussian noise, and JPEG compression to design a new noise layer. In the noise layer, we propose two ways to simulate real moiré distortion. We also propose a training strategy adding five distortions in stages during end-to-end adversarial training. Both the noise layer and training strategy can help improve robustness. In addition, we propose an edge-aware loss function to guide the encoder to focus on modifying the edge regions of the cover image, thereby enhancing transparency. The experimental results show that, under different shooting conditions, the watermark extraction accuracy exceeds 97%, indicating the high robustness of our proposed method. In terms of transparency, the peak signal-to-noise ratio reaches 38.51 dB, which is 1.34 dB higher than the state-of-the-art deep learning-based screen-shooting watermarking method, PIMoG. © 2025 SPIE and IS&T.

关键词： edge-aware loss image watermarking noise layer screen-shooting training strategy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：