检索结果-内蒙古大学图书馆

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Hui Li, Nan Yao, Pengjuan Dong, Kexin Guo, Yuhan Hong, Danfeng Zhang, Ying Wen, Congcong China Academy of Electronics and Information Technology Beijing100846 China National Satellite Meteorological Center Innovation Center for FengYun Meteorological Satellite China Meteorological Administration Beijing100081 China State Key Laboratory of Hydroscience and Engineering Department of Hydraulic Engineering Tsinghua University Beijing100084 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi United Arab Emirates

Object detection is a fundamental task in computer vision that involves accurately locating and classifying objects within images or video frames. In remote sensing, this task is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced approaches for effective object detection in such environments. While deep learning methods have achieved remarkable success in remote sensing object detection, they typically rely on large amounts of labeled data. Acquiring sufficient labeled data, particularly for novel or rare objects, is both challenging and time-consuming in remote sensing scenarios, limiting the generalization capabilities of existing models. To address these challenges, few-shot learning (FSL) has emerged as a promising approach, aiming to enable models to learn new classes from limited labeled examples. Building on this concept, few-shot object detection (FSOD) specifically targets object detection challenges in data-limited conditions. However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments. In this paper, we propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing FSOD tasks. Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN) for enhanced multi-scale feature representation, the Multi-Stage Refinement Region Proposal Network (MRRPN) for more accurate region proposals, and the Generalized Classification Loss (GCL) for improved classification performance in few-shot scenarios. GE-FSOD demonstrates superior robustness and accuracy in remote sensing FSOD tasks through these enhancements. Extensive experiments on the DIOR and NWPU VHR-10 datasets show that our

关键词： Labeled data

Implicit Multi-Scale Swin Transformer Network for Image Denoising

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Qi Ding, Yuwei Zhang, Weiqi Zhu, Yian Zhang, Bob Lin, Jerry Chun-Wei Harbin Institute of Technology at Weihai School of Economics and Management Weihai China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Northwestern Polytechnical University School of Computer Science Xi’an China Northwestern Polytechnical University Yangtze River Delta Research Institute Taicang China University of Macau PAMI Research Group Department of Computer and Information Science Taipa China Department of Distributed Systems and IT Devices Electrical Engineering and Mathematical Sciences Silesian university of technology Poland

Image denoising has been used in various edge computing scenarios such as consumer electronics to improve the image quality and user experience. Existing image denoising methods based on Convolutional Neural Networks (CNNs) and vision Transformers achieve good performance by empirically utilizing residual neural network (ResNet) as basic component. However, ResNet lacks interpretability in network design and also long-term memory of features, potentially restricting the performance of denoising networks. In this paper, we propose an Implicit Multi-scale Swin Transformer Network (IMSNet) for image denoising, which introduces the implicit Euler scheme from the feature memory perspective. Specifically, densely connected implicit feature extraction blocks (IFEBs) are designed to learn the residual mapping between noisy and clean images. The IFEB reformulates the initial skip connection of ResNet based on the implicit Euler discretization, providing both network interpretability and long-term memory. In IFEB, the multi-scale swin Transformer block (MSB) is designed as the implicit layer to capture spatial details and non-local contextual information at different scales. Additionally, a cross-layer feature fusion block (CLFF) is proposed to further improve feature reuse capabilities. Compared to existing denoising networks, the extensive experiments demonstrate the superior performance of our IMSNet in various image denoising tasks, and the flexibility in the practical applications with proposed light model on resource-restricted platforms such as consumer electronic devices. © 1975-2011 IEEE.

关键词： Image denoising

Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson’s Disease Screening in OCT

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Xiaoqing Shi, Hanfeng Li, Xiangyu Ye, Haili Xu, Tao Li, Na Hu, Yan Lv, Fan Chen, Jiangfan Liu, Jiang Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China State Key Laboratory of Ophthalmology Optometry and Vision Science Wenzhou Medical University Wenzhou China Centre for Computational Science and Mathematical Modelling Coventry University Coventry United Kingdom School of Computer Science University of Nottingham Ningbo China Ningbo315100 China School of Ophthalmology and Optometry Wenzhou Medical University Wenzhou325035 China Department of Electronic and Information Engineering Changchun University Changchun130022 China

Parkinson’s disease (PD) is a prevalent neurodegenerative disorder globally. The eye’s retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness. © 2025, CC BY-NC-SA.

关键词： Neurodegenerative diseases

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods ...

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Li, Yawei Zhang, Yulun Timofte, Radu Van Gool, Luc Yu, Lei Li, Youwei Li, Xinpeng Jiang, Ting Wu, Qi Han, Mingyan Lin, Wenjie Jiang, Chengzhi Luo, Jinting Fan, Haoqiang Liu, Shuaicheng Wang, Yucong Cai, Minjie Li, Mingxi Zhang, Yuhang Fan, Xian-Jun Sheng, Yankai Mao, Yanyu Zhang, Nihao Wang, Qian Zheng, Mingjun Sun, Long Pan, Jinshan Dong, Jiangxin Tang, Jinhui Yang, Zhongbao Wang, Yan Pan, Erlin Cai, Qixuan Dai, Xinan Zhussip, Magauiya Kalyazin, Nikolay Vyal, Dmitry Zou, Xueyi Yan, Youliang Chung, Heaseo Zhang, Jin Yu, Gaocheng Zhang, Feng Wang, Hongbin Liao, Bohao Du, Zhibo Wu, Yu-Liang Shi, Gege Peng, Long Wang, Yang Cao, Yang Zha, Zhengjun Huang, Zhi-Kai Chen, Yi-Chung Chiang, Yuan-Chun Yang, Hao-Hsiang Chen, Wei-Ting Chang, Hua-En Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Liu, Xin Pan, Jiahao Yu, Hongyuan Yu, Weichen Ge, Lin Dong, Jiahua Zou, Yajun Wu, Zhuoyuan Han, Binnan Zhang, Xiaolin Zhang, Heng Yin, Xuanwu Zuo, Kunlong Deng, Weijian Yuan, Hongjie Lu, Zengtong Ouyang, Mingyu Ma, Wenzhuo Liu, Nian Zheng, Hanyou Zhang, Yuantong Zhang, Junxi Chen, Zhenzhong Gendy, Garas Sabor, Nabil Hou, Jingchao He, Guanghui Zhu, Yurui Wang, Xi Fu, Xueyang Zha, Zheng-Jun Yin, Daheng Liu, Mengyang Chen, Baijun Li, Ao Luo, Lei Jin, Kangjun Zhu, Ce Zhang, Xiaoming Xie, Chengxing Li, Linze Meng, Haiteng Zhang, Tianlin Li, Tianrui Zhao, Xiaole Zhang, Zhao Li, Baiang Zheng, Huan Zhao, Suiyi Gao, Yangcheng Ren, Jiahuan Hu, Kang Shi, Jingpeng Wu, Zhijian Huang, Dingjiang Zhu, Jinchen Li, Hui Xv, Qianru Liu, Tianle Weng, Shizhuang Wu, Gang Jiang, Junpeng Liu, Xianming Jiang, Junjun Zhang, Mingjian Hu, Jing Wu, Chengxu Fan, Qinrui Feng, Chengming Luo, Ziwei Hu, Shu Lyu, Siwei Wu, Xi Wang, Xin Computer Vision Lab ETH Zurich Switzerland Computer Vision Lab University of Würzburg Germany Megvii Technology China MicroBT China College of Computer Science and Electronic Engineering Hunan University China Attrsense Xian University of Posts and Telecommunications Xi'an China National Engineering Laboratory for Cyber Event Warning and Control Technologies China Nanjing University of Science and Technology China Nankai University China University of Electronic Science and Technology of China China Tianjin University China Noah's Ark Lab Huawei Technologies McMaster University Canada Espresomedia Korea Republic of AntGroup China University of Science and Technology of China China Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan ServiceNow United States China Mobile Research Institute China Chongqing University of Technology China Multimedia Department Xiaomi Inc. China Institute of Automation Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences China School of Information and Communication Engineering Communication University of China China Smart Classroom Division Ruijie Networks Co. Ltd. China School of Remote Sensing and Information Engineering Wuhan University China Micro-Nano Electronics Department Shanghai Jiao Tong University Shanghai200240 China Electrical Engineering Department Faculty of Engineering Assiut University Assiut71516 Egypt Southeast University China University of Electronic Science and Technology of China Chengdu China Chongqing University of Posts and Telecommunications Chongqing China Information Technology Co. Ltd Hangzhou China Southwest Jiaotong University China National Space Science Center Chinese Academy of Science China Hefei University of Technology Hefei China Anhui University China Fried Ric

ISBN: (纸本)9798350302493

This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution. © 2023 IEEE.

关键词： Optical resolving power

CONIC10K: A Challenging Math Problem Understanding and Reasoning Dataset

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Haoyi Hui, Wenyang Chen, Yezeng Wu, Weiqi Tu, Kewei Zhou, Yi School of Information Science and Technology ShanghaiTech University China Shanghai Engineering Research Center of Intelligent Vision and Imaging China School of Information Science and Technology University of Science and Technology of China China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application China Key Laboratory of Brain Cognition and Education Sciences Ministry of Education China Shanghai Innovation Center for Processor Technologies China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Mathematical understanding and reasoning are crucial tasks for assessing the capabilities of artificial intelligence (AI). However, existing benchmarks either require just a few steps of reasoning, or only contain a small amount of data in one specific topic, making it hard to analyse AI's behaviour with reference to different problems within a specific topic in detail. In this work, we propose CONIC10K, a challenging math problem dataset on conic sections in Chinese senior high school education. Our dataset contains various problems with different reasoning depths, while only the knowledge from conic sections is required. Since the dataset only involves a narrow range of knowledge, it is easy to separately analyse the knowledge a model possesses and the reasoning ability it has. For each problem, we provide a high-quality formal representation, the reasoning steps, and the final solution. Experiments show that existing large language models, including GPT-4, exhibit weak performance on complex reasoning. We hope that our findings could inspire more advanced techniques for precise natural language understanding and reasoning. Our dataset and codes are available at https://***/whyNLP/Conic10K. © 2023, CC BY.

关键词：

Effective dual-region augmentation for reduced reliance on large amounts of labeled data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pulakurthi, Prasanna Reddy Rabbani, Majid de Melo, Celso M. Dianat, Sohail A. Rao, Raghuveer M. Rochester Institute of Technology Department of Electrical and Computer Engineering United States DEVCOM U.S. Army Research Laboratory United States

This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks, including source-free domain adaptation (SFDA) and person re-identification (ReID). Our method performs targeted data transformations by applying random noise perturbations to foreground objects and spatially shuffling background patches. This effectively increases the diversity of the training data, improving model robustness and generalization. Evaluations on the PACS dataset for SFDA demonstrate that our augmentation strategy consistently outperforms existing methods, achieving significant accuracy improvements in both single-target and multi-target adaptation settings. By augmenting training data through structured transformations, our method enables model generalization across domains, providing a scalable solution for reducing reliance on manually annotated datasets. Furthermore, experiments on Market-1501 and DukeMTMC-reID datasets validate the effectiveness of our approach for person ReID, surpassing traditional augmentation techniques. The code is available at ***/PrasannaPulakurthi/Foreground-Background-Augmentation. © 2025, CC BY.

关键词：

pFedLVM: A Large vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

Improving OCT Image Reconstruction Through Multi-Input GANs with Gated Attention

学校读者我要写书评

暂无评论

Improving OCT Image Reconstruction Through Multi-Input GANs ...

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Maryam Mehdizadeh Cara MacNish David Alonso-Caneiro Ashley Gillman Sajib Saha Fred K. Chen Australian e-Health Research Centre (AEHRC) Commonwealth Scientific and Industrial Research Organisation (CSIRO) Perth Western Australia Australia School of Computer Science & Software Engineering University of Western Australia (UWA) Perth Western Australia Australia School of Science Technology and Engineering University of Sunshine Coast Petrie Queensland Australia Contact Lens and Visual Optics Laboratory Optometry and Vision Science Centre for Vision and Eye Research Queensland University of Technology Brisbane Queensland Australia Centre for Ophthalmology and Visual Science (Lions Eye Institute) The University of Western Australia (UWA) Perth Western Australia Australia Department of Surgery Ophthalmology University of Melbourne (UoM) Melbourne Victoria Australia

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Optical Coherence Tomography (OCT) is a crucial ophthalmic imaging technique that is subject to speckle noise which can obscure pathological features and hinder accurate segmentation. A standard approach to OCT image noise is to capture and average multiple (typically 30) B-scans at the same tissue location. However this is not always possible, particularly for children and patients with pathology who have more difficulty fixating during the scanning process. In the worst scenario, the OCT scanner will stop before achieving the target scans as the exposure time is too long. It is important therefore to seek ways of synthesising better quality images that rely on fewer scans. This paper frames the OCT image reconstruction problem as a multiple-input extension of the image-to-image translation problem. The goal is to match the perceptual quality of the “gold standard” averaged image by synthesising a new image from between 1 and 8 B-scan slides. Building on previous work, we propose a multi-input conditional GAN-based architecture that incorporates a lightweight U-Net generator with a PatchGAN discriminator. Additionally, we examine the impact of a gated attention (GA) mechanism within the U-Net architecture, and the impact of increasing depth of filters. Experiments were conducted with varying numbers of input slices, comparing the results to averaged images derived from the same number of slices as well as the gold standard averaged over 30 B-scans. There is no single reliable metric for image quality. Therefore this paper compares images over a range of indicative metrics including peak-signal-to-noise-ratio (PSNR), structural similarity (SSIM), texture preservation (TP) and edge preservation (EP), as well as three no-reference image sharpness metrics: just noticeable blur (JNB), perceptual similarity index(PSI) and spectral and spatial sharpness (S3). We found that GAN networks with GA generally outperformed those without GA and traditional averaging on PSNR, TP a

关键词： Measurement Pathology Attention mechanisms Translation Image edge detection Noise Logic gates Generative adversarial networks Retina Image reconstruction

学校读者我要写书评

暂无评论

水管理对干旱区盐渍化与土地退化中和的影响

Science Bulletin 2023年第24期68卷 3240-3251,M0006页

作者：施海洋罗格平 Edwin H.Sutanudjaja Olaf Hellwich 陈曦丁建丽吴世新何秀凤陈春波 Friday U.Ochege 王渊刚凌青艾里西尔·库尔班 Philippe De Maeyer Tim Van de Voorde State Key Laboratory of Desert and Oasis Ecology Xinjiang Institute of Ecology and GeographyChinese Academy of SciencesUrumqi 830011China College of Resources and Environment University of Chinese Academy of SciencesBeijing 100049China Research Centre for Ecology and Environment of Central Asia Chinese Academy of SciencesUrumqi 830011China Department of Geography Ghent UniversityGhent 9000Belgium College of Resources and Environment Sciences Xinjiang UniversityUrumqi 830046China Department of Physical Geography Utrecht UniversityUtrecht 3584Netherlands Department of Computer Vision&Remote Sensing Technical University of BerlinBerlin 10587Germany Sino-Belgian Joint Laboratory of Geo-Information Ghent 9000Belgium School of Earth Sciences and Engineering Hohai UniversityNanjing 211100China Department of Geography and Environmental Management University of Port HarcourtPort Harcourt 500004Nigeria

通过优化灌溉和水资源管理以减少耕地土壤盐渍化对实现土地退化中和至关重要.各种灌溉和水资源管理措施对流域尺度盐渍化的缓解作用的有效性和可持续性尚不明确.本研究利用遥感技术估算了1984-2021年干旱区耕地的表层土壤盐度.然后,利... 详细信息

通过优化灌溉和水资源管理以减少耕地土壤盐渍化对实现土地退化中和至关重要.各种灌溉和水资源管理措施对流域尺度盐渍化的缓解作用的有效性和可持续性尚不明确.本研究利用遥感技术估算了1984-2021年干旱区耕地的表层土壤盐度.然后,利用贝叶斯网络分析比较了十个大型干旱区流域(尼罗河、底格里斯-幼发拉底河、印度河、塔里木河、阿姆河、伊犁河、锡尔河、准格尔盆地、科罗拉多河和圣华金河流域)的土壤表层盐度对水资源管理(如各种灌溉和排水方式)的时空响应.在开发水平较高的流域,管理者采用滴灌和地下水灌溉,通过降低地下水水位有效地控制了土壤盐度.对于仍采用传统漫灌的流域,经济发展和政策支持对于建立“改善灌溉系统——降低盐度——增加农业收入”的良性循环至关重要.这也是实现土地退化中和目标的关键.

关键词： Soil salinization Land degradation neutralization Irrigation Water management Bayesian networks Drylands