检索结果-内蒙古大学图书馆

TS-CGNet: Temporal-Spatial Fusion Meets Centerline-Guided Diffusion for BEV Mapping

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hong, Xinying Li, Siyu Zeng, Kang Shi, Hao Peng, Bomin Yang, Kailun Li, Zhiyong The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China

Bird’s Eye View (BEV) perception technology is crucial for autonomous driving, as it generates top-down 2D maps for environment perception, navigation, and decision-making. Nevertheless, the majority of current BEV map generation studies focusing on visual map generation lack depth-aware reasoning capabilities. They exhibit limited efficacy in managing occlusions and handling complex environments, with a notable decline in perceptual performance under adverse weather conditions or low-light scenarios. Therefore, this paper proposes TS-CGNet, which leverages Temporal-Spatial fusion with Centerline-Guided diffusion. This visual framework, grounded in prior knowledge, is designed for integration into any existing network for building BEV maps. Specifically, this framework is decoupled into three parts: Local mapping system involves the initial generation of semantic maps using purely visual information;The Temporal-Spatial Aligner Module (TSAM) integrates historical information into mapping generation by applying transformation matrices;The Centerline-Guided Diffusion Model (CGDM) is a prediction module based on the diffusion model. CGDM incorporates centerline information through spatial-attention mechanisms to enhance semantic segmentation reconstruction. We construct BEV semantic segmentation maps by our methods on the public nuScenes and the robustness benchmarks under various corruptions. Our method improves 1.90%, 1.73%, and 2.87% for perceived ranges of 60×30m, 120×60m, and 240×60m in the task of BEV HD mapping. TS-CGNet attains an improvement of 1.92% for perceived ranges of 100×100m in the task of BEV semantic mapping. Moreover, TS-CGNet achieves an average improvement of 2.92% in detection accuracy under varying weather conditions and sensor interferences in the perception range of 240×60m. The source code will be publicly available at https://***/krabs-H/TS-CGNet. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

Horizontal-to-vertical video conversion

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Tun Zhang, Daoxin Hu, Yao Wang, Tianran Jiang, Xiaolong Zhu, Jianke Li, Jiawei The College of Computer Science Zhejiang University Hangzhou310027 China The Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Company of Alibaba Youku Cognitive and Intelligent Lab

At this blooming age of social media and mobile platform, mass consumers are migrating from horizontal video to vertical contents delivered on hand-held devices. Accordingly, revitalizing the exposure of horizontal video becomes vital and urgent, which is hereby tackled by our automated horizontal-to-vertical (abbreviated as H2V) video conversion framework. Essentially, the H2V framework performs subject-preserving video cropping instantiated in the proposed Rank-SS module. Rank-SS incorporates object detection to discover the candidate subjects, from which we select the primary subject-to-preserve leveraging location, appearance, and salient cues in a convolutional neural network. In addition to converting horizontal videos vertically by cropping around the selected subject, automatic shot detection and multi-object tracking are integrated into the H2V framework to accommodate long and complex videos. To develop H2V systems, we collect an H2V-142K dataset containing 125 videos (132K frames) and 9,500 cover images annotated with primary subject bounding boxes. On H2V-142K and public object detection datasets, our method demonstrates promising results on the subject selection comparing to the related solutions. Furthermore, our H2V framework is industrially deployed hosting millions of daily active users and exhibits favorable H2V conversion performance. By making this dataset as well as our approach publicly available, we wish to pave the way for more horizontal-to-vertical video conversion research. Our collected H2V-142K dataset is available at H2V-142K website. © 2021, CC BY.

关键词： Video signal processing

Efficient Medical Image Segmentation Based on Knowledge Distillation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qin, Dian Bu, Jia-Jun Liu, Zhe Shen, Xin Zhou, Sheng Gu, Jing-Jun Wang, Zhi-Hua Wu, Lei Dai, Hui-Fen Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Ningbo Research Institute School of Software Technology Zhejiang University The Fourth Affiliated Hospital Zhejiang University School of Medicine

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Jinyin Mu, Wenbo Zhang, Luxin Huang, Guohan Zheng, Haibin Cheng, Yao The Institute of Cyberspace Security The College of Information Engineering Zhejiang University of Technology Hangzhou310023 China The College of Information Engineering Zhejiang University of Technology Hangzhou310023 China National Key Laboratory of Electromagnetic Space Security Jiaxing China The College of Computer Science and Technology The Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China The Digital Service TÜV SÜD Asia Pacific Pte. Ltd. 609937 Singapore

Graph neural network (GNN) has captured wide attention due to its capability of graph representation learning for graph-structured data. However, the distributed data silos limit the performance of GNN. Vertical federated learning (VFL), an emerging technique to process distributed data, successfully makes GNN possible to handle the distributed graph-structured data. Despite the prosperous development of vertical federated graph learning (VFGL), the robustness of VFGL against the adversarial attack has not been explored yet. Although numerous adversarial attacks against centralized GNNs are proposed, their attack performance is challenged in the VFGL scenario. To the best of our knowledge, this is the first work to explore the adversarial attack against VFGL. A query-efficient hybrid adversarial attack framework is proposed to significantly improve the centralized adversarial attacks against VFGL, denoted as NA2, short for Neuron-based Adversarial Attack. Specifically, a malicious client manipulates its local training data to improve its contribution in a stealthy fashion. Then a shadow model is established based on the manipulated data to simulate the behavior of the server model in VFGL. As a result, the shadow model can improve the attack success rate of various centralized attacks with a few queries. Extensive experiments on five real-world benchmarks demonstrate that NA2 improves the performance of the centralized adversarial attacks against VFGL, achieving state-of-the-art performance even under potential adaptive defense where the defender knows the attack method. Additionally, we provide interpretable experiments of the effectiveness of NA2 via sensitive neurons identification and visualization of t-SNE. The code and datasets are available at https://***/hgh0545/NA2. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Siyu Cao, Yihong Shi, Hao Zang, Yongsheng He, Xuan Yang, Kailun Li, Zhiyong School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Hunan Vanguard Group Corporation Limited Changsha410100 China

The exploration of Bird’s-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. Furthermore, this paper introduces intra-domain feature exchange data augmentation to enhance the efficiency of domain adaptation learning. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. It demonstrates competitive perfo

关键词： Birds

An End-to-End OCR Text Re-organization Sequence Learning for Rich-Text Detail Image Comprehension 1

学校读者我要写书评

暂无评论

16th European Conference on computer Vision, ECCV 2020

作者： Li, Liangcheng Gao, Feiyu Bu, Jiajun Wang, Yongpan Yu, Zhi Zheng, Qi Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China Alibaba Group Hangzhou China Alibaba-Zhejiang University Joint Institute of Frontier Technologies Hangzhou China Ningbo Research Institute Zhejiang University Ningbo China

ISBN: (数字)9783030585952

ISBN: (纸本)9783030585945

Nowadays the description of detailed images helps users know more about the commodities. With the help of OCR technology, the description text can be detected and recognized as auxiliary information to remove the visually impaired users’ comprehension barriers. However, for lack of proper logical structure among these OCR text blocks, it is challenging to comprehend the detailed images accurately. To tackle the above problems, we propose a novel end-to-end OCR text reorganizing model. Specifically, we create a Graph Neural Network with an attention map to encode the text blocks with visual layout features, with which an attention-based sequence decoder inspired by the Pointer Network and a Sinkhorn global optimization will reorder the OCR text into a proper sequence. Experimental results illustrate that our model outperforms the other baselines, and the real experiment of the blind users’ experience shows that our model improves their comprehension. © 2020, Springer Nature Switzerland AG.

关键词： Global optimization

A transactional-behavior-based hierarchical gated network for credit card fraud detection

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年

作者： Xie, Yu Zhou, MengChu Liu, Guanjun Wei, Lifei Zhu, Honghao De Meo, Pasquale College of Information Engineering Shanghai Maritime University Shanghai201306 China School of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou310018 China Helen and John C. Hartmann Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science Tongji University Shanghai201804 China College of Computer Science and Information Engineering Bengbu University Bengbu233030 China Department of Ancient and Modern Civilizations University of Messina Messina98166 Italy

The task of detecting fraud in credit card transactions is crucial to ensure the security and stability of a financial system, as well as to enforce customer confidence in digital payment systems. Historically, credit card companies have used rule-based approaches to detect fraudulent transactions, but these have proven inadequate due to the complexity of fraud strategies and have been replaced by much more powerful solutions based on machine learning or deep learning algorithms. Despite significant progress, the current approaches to fraud detection suffer from a number of limitations: for example, it is unclear whether some transaction features are more effective than others in discriminating fraudulent transactions, and they often neglect possible correlations among transactions, even though they could reveal illicit behaviour. In this paper, we propose a novel credit card fraud detection (CCFD) method based on a transaction behaviour-based hierarchical gated network. First, we introduce a feature-oriented extraction module capable of identifying key features from original transactions, and such analysis is effective in revealing the behavioural characteristics of fraudsters. Second, we design a transaction-oriented extraction module capable of capturing the correlation between users' historical and current transactional behaviour. Such information is crucial for revealing users' sequential behaviour patterns. Our approach, called transactional-behaviour-based hierarchical gated network model (TbHGN), extracts two types of new transactional features, which are then combined in a feature interaction module to learn the final transactional representations used for CCFD. We have conducted extensive experiments on a real-world credit card transaction dataset with an increase in average F1 between 1.42% and 6.53% and an improvement in average AUC between 0.63% and 2.78% over the state of the art. © 2025 Institute of Electrical and Electronics Engineers Inc.. All right

关键词： Deep learning

Simultaneous Communication and Localization for Double-RIS Aided Multi-UE ISAC Systems

学校读者我要写书评

暂无评论

Simultaneous Communication and Localization for Double-RIS A...

International Conference on Communication Technology (ICCT)

作者： Xu Gan Chongwen Huang Zhaohui Yang Caijun Zhong Xiaoming Chen Jiguang He Zhaoyang Zhang Qinghua Guo Chau Yuen Mérouane Debbah College of Information Science and Electronic Engineering Zhejiang University State Key Laboratory of Integrated Service Networks Xidian University Technology Innovation Institute Abu Dhabi United Arab Emirates School of Electrical Computer and Telecommunications Engineering University of Wollongong School of Electrical and Electronics Engineering Nanyang Technological University Khalifa University of Science and Technology

Reconfigurable intelligent surface (RIS) has great potential to improve the performance of integrated sensing and communication (ISAC) systems, especially in scenarios where line-of-sight paths between the base station and users are blocked. However, the spectral efficiency of RIS-aided ISAC uplink transmissions may be drastically reduced by the heavy burden of pilot overhead for realizing sensing capabilities. In this paper, we tackle this bottleneck by proposing a superimposed symbol scheme, which superimposes sensing pilots onto data symbols over the same time-frequency resources. Specifically, a low-complexity simultaneous communication and localization algorithm is proposed, which employs the unitary approximate message passing in the Bayesian learning framework for initial angle estimate, followed by iterative refinements through reduced-dimension matrix calculations. Moreover, the sparse code multiple access technology is incorporated into this iterative framework for accurate data detection which also facilitates localization. Numerical results show that the proposed superimposed symbol-based scheme empowered by the developed algorithm can achieve centimeter-level localization and provide an effective throughput improvement over 143%.

关键词：