检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Hongliang Ye Jilin Mei Yu Hu The Research Center for Advanced Computing Systems Zhejiang Lab Hangzhou China The Research Center for Intelligent Computing Systems Institute of Computing Technology Beijing China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Freespace detection is an important part of autonomous driving technology. Compared with structured on-road scenes, unstructured off-road scenes face more challenges. Multi-modal fusion method is a viable solution to these challenges. But existing fusion methods do not fully utilize the multi-modal features. In this paper, we propose an effective multi-modal network named M2F2-Net for freespace detection in unstructured off-road scenes. We propose a multi-modal feature fusion strategy named Multi-modal Cross Fusion (MCF). MCF module is simple but effective in fusing the features of RGB images and surface normal maps. Meanwhile, a multi-modal segmentation decoder module is designed to decouple the segmentation of two modalities, and it further helps the features of both modalities to be fully utilized. In order to solve the problem that the road edge is difficult to extract in the unstructured scenes, we also propose an edge segmentation decoder module. Extensive experiments show that our approach can lead to significant improvements, which brings 6.1% F1 and 10.8% IoU improvements. Our code will be available at https://***/yhl1010/M2F2-Net.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting

arXiv

引用

arXiv 2023年

作者： Zhu, Huilin Yuan, Jingling Zhong, Xian Yang, Zhengwei Wang, Zheng He, Shengfeng School of Computer Science and Artificial Intelligence Wuhan University of Technology China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China School of Computing and Information Systems Singapore Management University Singapore

Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-dataset differences while overlooking the intra-differences within the same dataset, leading to additional learning ambiguities. These domain-agnostic factors, e.g., density, surveillance perspective, and scale, can cause significant in-domain variations, and the misalignment of these factors across domains can lead to a drop in performance in cross-domain crowd counting. To address this issue, we propose a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains. The DAOT consists of three steps. First, individual-level differences in domain-agnostic factors are measured using structural similarity (SSIM). Second, the optimal transfer (OT) strategy is employed to smooth out these differences and find the optimal domain-to-domain misalignment, with outlier individuals removed via a virtual "dustbin" column. Third, knowledge is transferred based on the aligned domain-agnostic factors, and the model is retrained for domain adaptation to bridge the gap across domains. We conduct extensive experiments on five standard crowd-counting benchmarks and demonstrate that the proposed method has strong generalizability across diverse datasets. Our code will be available at: https://***/HopooLinZ/DAOT/. © 2023, CC0.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China The School of Computing Kent Interdisciplinary Research Centre in Cyber Security University of Kent CanterburyCT2 7NF United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The Intelligent Transportation Systems Lab Innopolis University Innopolis Russia The School of Computer Science and Technology Xidian University China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. © 2004-2012 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

FDRA: Fully Distributed Routing Architecture for Private Virtual Network in Public Cloud 11th

FDRA: Fully Distributed Routing Architecture for Private Vir...

引用

11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020

作者： Hu, Zhangfeng Zhang, Hui Sun, Siqing Gao, Chuanji Li, Yanjun Li, Xiong Cloud Computing Research Center Inspur Cloud Service Group Beijing China School of Computer Science and Engineering University of Electronic Science and Technology Chengdu China

ISBN: (纸本)9789811600098

A virtual private cloud (VPC) is often comprised of a set of virtual computing, storage and network resource which is allocated from a public cloud. Public clouds build virtualized resource pools based on physical infrastructure including generic x86 servers, network devices (e.g. switches, routers, firewalls), storage servers and so forth to dynamically provision virtual computing and storage resource to customers, while virtual network is a bridge that connects all the computing resource in a VPC and segregates network traffic between different VPCs. One VPC may contain multiple subnets, which makes private virtual network should provide the capability of communications between virtual computing resources i.e. virtual machines’ communication through Layer-2 switching and Layer-3 routing simultaneously. In this paper we propose a fully distributed routing architecture (FDRA) for private virtual network to fulfill the requirements of public cloud. FDRA splits the VPC traffic into two categories, i.e. the traffic goes inside of a VPC and the traffic goes out of a VPC, and presents two different routing entities to route different traffic issued from virtual machines in a VPC. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Cross-links matter for link prediction: rethinking the debiased GNN from a data perspective 23

Cross-links matter for link prediction: rethinking the debia...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zihan Luo Hong Huang Jianxun Lian Xiran Song Xing Xie Hai Jin National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China

Recently, the bias-related issues in GNN-based link prediction have raised widely spread concerns. In this paper, we emphasize the bias on links across different node clusters, which we call cross-links, after considering its significance in both easing information cocoons and preserving graph connectivity. Instead of following the objective-oriented mechanism in prior works with compromised utility, we empirically find that existing GNN models face severe data bias between internal-links (links within the same cluster) and cross-links, and this inspires us to rethink the bias issue on cross-links from a data perspective. Specifically, we design a simple yet effective twin-structure framework, which can be easily applied to most GNNs to mitigate the bias as well as boost their utility in an end-to-end manner. The basic idea is to generate debiased node embeddings as demonstrations and fuse them into the embeddings of original GNNs. In particular, we learn debiased node embeddings with the help of augmented supervision signals, and a novel dynamic training strategy is designed to effectively fuse debiased node embeddings with the original node embeddings. Experiments on three datasets with six common GNNs show that our framework can not only alleviate the bias between internal-links and cross-links but also boost the overall accuracy. Comparisons with other state-of-the-art methods also verify the superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Kernel Calibration

Deep Kernel Calibration

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zunlei Feng Wenxiang Xu Tian Qiu Jie Lei Huiqiong Wang Zhongle Xie School of Software Technology Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China Ningbo Innovation Center Zhejiang University Ningbo China Institute of Computing Innovation Zhejiang University Hangzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Korbinian Brodmann argued that the brain regions with different cytoarchitectures exhibited different cognitive functions, which are widely recognized as "Brodmann areas" in neuroscience. Inspired by this theory, we observe from experiments that the different well-trained convolutional kernels also hold their unique functionalities, indicated by their output activations that highly concentrate on the "different certain ranges". This discovery motivates us to devise a deep kernel-by-kernel feature calibration mechanism that "calibrates" the output distribution of a pre-trained convolutional kernel for a more concentrated activation interval, by eliminating the outlier activations. Towards this end, we develop two dedicated Brodmann calibration forms, termed as Hard Kernel Calibration (HKC) and Soft Kernel Calibration (SKC) that simply filters the overrange activations, or adaptively condense the activations in a weighted manner, respectively. As a flexible plug-and-play module, the proposed calibration demonstrates encouraging results on five benchmarks across sixteen network architectures and also triggers the functionality of significantly enhanced model robustness against adversarial attacks. The developed code is publicly available at https://***/tcmyxc/DKC.

关键词： Convolutional codes Neuroscience Filters Convolution Network architecture Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

The Span-Based Transformer Classifier for Named Entity Recognition

The Span-Based Transformer Classifier for Named Entity Recog...

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Li, Yangfan Sun, Xin Li, Hongao Yang, Kaige Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Southeast Academy of Information Technology Fujian Putian351100 China

ISBN: (纸本)9789811694912

Named entity recognition is a basic task in the field of natural language processing. The existing named entity recognition model has the problem of poor recognition effect on specific domain data sets. Aiming at the inconsistency of sequence labeling caused by the shortcomings of the traditional BIO (B-begin, I-inside, O-outside) annotation method, a named entity recognition model based on transformer is proposed, which uses the feature extraction of encoder in transformer and the labeling method of limited interval. Firstly, the BERT pre-training model is used to perform word-level dynamic vector representation of the input text. Then the vector representation of the text is intercepted by the span-based labeling method, and the feature of text and candidate named entity is extracted by self-attention mechanism. The results of experiment on the dataset in the industrial informatization field show the effectiveness of the model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

GAN Doctor: Diagnosing and Treating Inherent Semantic Errors

GAN Doctor: Diagnosing and Treating Inherent Semantic Errors

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chengji Shen Zunlei Feng Zhongle Xie Jie Lei Huiqiong Wang Mingli Song College of Computer Science and Technology Zhejiang University Hangzhou China School of Software Technology Zhejiang University Ningbo China Institute of Computing Innovation Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China Ningbo Innovation Center Zhejiang University Ningbo China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Generative Adversarial Network (GAN), as a popular generative model in the field of Artificial Intelligence Generated Content (AIGC), has been intensively developed in previous research, with significant improvements in the quality and diversity of image generation. However, there are still many cases where the results are not satisfactory. A primary concern pertains to the chaotic and blurred local details within the generated images. In this work, through the diagnosis and analysis of high-quality and low-quality images produced by the GAN model, we identified that this issue stems from inherent semantic errors of the GAN, that is, convolutional kernels responsible for certain semantics are not properly involved in the generation process of corresponding image regions. To this end, we propose a straightforward yet effective treatment method, which constrains each image region to be generated by its corresponding semantic convolutional kernels. Experimental results demonstrate that our proposed optimization method can improve the issue of chaotic and blurred local regions in generated images and enhance the overall generation quality. Our work pioneers a novel paradigm for diagnosing and treating GANs, driving the research development and practical application of AIGC image generation technology.

关键词： Analytical models Image synthesis Semantics Neural networks Optimization methods Medical services Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification

arXiv

引用

arXiv 2023年

作者： Ma, Leilei Sun, Dengdi Wang, Lei Zhao, Haifeng Luo, Bin School of Computer Science and Technology Anhui University China School of Artificial Intelligence Anhui University China School of Computer Science and Engineering Nanjing University of Science and Technology China Anhui Provincial key Laboratory of Multimodal Cognitive Computing Anhui University China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on modeling label relationships with graph and understanding object regions using class activation maps (CAM). However, these methods ignore the complex intra- and inter-category relationships among specific semantic features, and CAM is prone to generate noisy information. To this end, we propose a novel semantic-aware dual contrastive learning framework that incorporates sample-to-sample contrastive learning (SSCL) as well as prototype-to-sample contrastive learning (PSCL). Specifically, we leverage semantic-aware representation learning to extract category-related local discriminative features and construct category prototypes. Then based on SSCL, label-level visual representations of the same category are aggregated together, and features belonging to distinct categories are separated. Meanwhile, we construct a novel PSCL module to narrow the distance between positive samples and category prototypes and push negative samples away from the corresponding category prototypes. Finally, the discriminative label-level features related to the image content are accurately captured by the joint training of the above three parts. Experiments on five challenging large-scale public datasets demonstrate that our proposed method is effective and outperforms the state-of-the-art methods. Code and supplementary materials are released on https://***/yu-gi-oh-leilei/SADCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Denoising Method for Distant Supervised Relation Extraction Based on Deep Clustering

A Denoising Method for Distant Supervised Relation Extractio...

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Li, Hongao Sun, Xin Yang, Kaige Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Southeast Academy of Information Technology Fujian Putian351100 China

ISBN: (纸本)9789811694912

Distant supervision for relation extraction uses an external knowledge base as supervision signals to automatically label corpus and has attracted more and more attention. However, this method has an ideal hypothesis that all instances containing the same entity pairs represent the same relation, which will lead to a lot of noisy data and affect the training effect of classifier. Aiming at the noise problem of distant supervised dataset, we propose a denoising method based on deep clustering. First, the deep clustering method is used to train the text features and clustering centers, and the effect of clustering is improved by using the information of mask entity pairs. Then high quality training samples are obtained by removing the noisy data, so as to achieve the effect of denoising. Experimental results show that the proposed model can effectively improve the performance of relation extraction by comparing with the traditional denoising methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Knowledge based systems

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：