检索结果-内蒙古大学图书馆

IEEE International Conference on Data Mining (ICDM)

作者： Xin Gao Zhengye Zhu Xu Chu Yasha Wang Wenjie Ruan Junfeng Zhao Key Lab of High Confidence Software Technologies Ministry of Education School of Computer Science Peking University School of Computer Science Peking University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China University of Exeter Exeter UK

Despite the success of deep neural networks on text classification, their large capacity also leads to capturing task-irrelevant patterns such as label noise. label noise is usually introduced into the data during label collection and causes nontrivial declines in performance due to the memorization effect. Though effort has been devoted to combating the label noise in other systems such as image classification, high-quality input features are necessary for discovering task-relevant patterns before memorizing the label noise. However, such a high-quality input feature requirement is hard to be satisfied for text classification due to the nature of natural language. To combat the label noise with low-quality input features in the text classification, we propose a novel framework that exploits external category descriptions to construct prototypes that can be used to denoise the input representation and alleviate the over-fitting. However, there still remains a challenge that the external category descriptions from other corpora could be semantically discrepant with the underlying task-specific classes in the training corpus. To align their semantics, we propose two regularizers that penalize sample-wise semantic-based deviations at the local level and class-wise structure-based deviations at the global level, respectively. Our extensive experiments across two open datasets and one real-world case study demonstrate that our method is superior to state-of-the-art baselines under various settings of label noise.

关键词： Training Deep learning Text categorization Semantics Neural networks Natural languages Prototypes

来源：评论

学校读者我要写书评

暂无评论

SGBA: A Stealthy Scapegoat Backdoor Attack against Deep Neural Networks

arXiv

引用

arXiv 2021年

作者： He, Ying Shen, Zhili Xia, Chang Hua, Jingyu Tong, Wei Zhong, Sheng The Computer Science and Technology Department Nanjing University Nanjing210023 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled correctly while those carrying a specific trigger are falsely given a target label. Due to the severity of such attacks, many backdoor detection and containment systems have recently, been proposed for deep neural networks. One major category among them are various model inspection schemes, which hope to detect backdoors before deploying models from non-trusted third-parties. In this paper, we show that such state-of-the-art schemes can be defeated by a so-called Scapegoat Backdoor Attack, which introduces a benign scapegoat trigger in data poisoning to prevent the defender from reversing the real abnormal trigger. In addition, it confines the values of network parameters within the same variances of those from clean model during training, which further significantly enhances the difficulty of the defender to learn the differences between legal and illegal models through machine-learning approaches. Our experiments on 3 popular datasets show that it can escape detection by all five state-of-the-art model inspection schemes. Moreover, this attack brings almost no side-effects on the attack effectiveness and guarantees the universal feature of the trigger compared with original patch-based trojan attacks. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-View Panorama Image Synthesis

arXiv

引用

arXiv 2022年

作者： Wu, Songsong Tang, Hao Jing, Xiao-Yuan Zhao, Haifeng Qian, Jianjun Sebe, Nicu Yan, Yan The School of Computer Science Guangdong University of Petrochemical Technology Maoming525000 China The Department of Information Technology and Electrical Engineering ETH Zurich Zurich8092 Switzerland The School of Computer Science Wuhan University Wuhan430072 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China The School of Software Engineering Jinling Institute of Technology Nanjing211169 China Jiangsu Hoperun Software Co. Ltd. Nanjing210012 China The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Trento Trento38123 Italy The Department of Computer Science Illinois Institute of Technology Chicago60616 United States

In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a topview aerial image, which is a challenging problem due to the large gap between the two image domains with different viewpoints. Instead of learning cross-view mapping in a feedforward pass, we propose a novel adversarial feedback GAN framework named PanoGAN with two key components: an adversarial feedback module and a dual branch discrimination strategy. First, the aerial image is fed into the generator to produce a target panorama image and its associated segmentation map in favor of model training with layout semantics. Second, the feature responses of the discriminator encoded by our adversarial feedback module are fed back to the generator to refine the intermediate representations, so that the generation performance is continually improved through an iterative generation process. Third, to pursue high-fidelity and semantic consistency of the generated panorama image, we propose a pixel-segmentation alignment mechanism under the dual branch discrimiantion strategy to facilitate cooperation between the generator and the discriminator. Extensive experimental results on two challenging cross-view image datasets show that PanoGAN enables highquality panorama image generation with more convincing details than state-of-the-art approaches. The source code and trained models are available at https://***/sswuai/PanoGAN. Copyright © 2022, The Authors. All rights reserved.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

keywords-driven web APIs group recommendation for automatic app service creation process

Keywords-driven web APIs group recommendation for automatic ...

引用

作者： Gong, Wenwen Lv, Chao Duan, Yucong Liu, Zengguang Khosravi, Mohammad R. Qi, Lianyong Dou, Wanchun College of Information and Electrical Engineering China Agricultural University Beijing China China Telecom Smart Home Competence Center Nanjing China E-Surfing Smart Home Technology Co. Ltd Nanjing China School of Computer Science and Cyberspace Security Hainan University Haikou China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Department of Computer Engineering Persian Gulf University Bushehr Iran Telecommunications Group Department of Electrical and Electronic Engineering Shiraz University of Technology Shiraz Iran School of Information Science and Engineering Qufu Normal University Rizhao China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

With the ever-increasing popularity of web application programming interfaces (APIs) sharing communities, it is becoming a promising way for software developers to design and create their interesting Apps through composing a set of selected web APIs that can collectively fulfill the App functions expected by the App developer. However, the App developer's web APIs selection decision-makings are often nontrivial due to the massive candidate APIs as well as their diverse functions. Furthermore, it is difficult to guarantee that the selected web APIs are compatible enough. Moreover, traditional web APIs recommendation approaches only return a recommended APIs list, which are often not sufficient to accommodate the App developer's undetermined and fuzzy personalized preferences. Considering the above challenges, a novel keywords-driven web APIs recommendation approach called keywords-driven and compatibility-aware multiple API group recommendation is proposed in this article for green and compatible software, which cannot only satisfy the App developer's functional requirements, but also return a group of web APIs recommended lists. Each returned list includes a set of compatible web APIs. Finally, we design a series of experiments based on a real-world web APIs dataset, that is, PW dataset crawled from ***. Experimental reports compared with other competitive approaches in existing literatures indicate the effectiveness and efficiency of our proposal in this work. © 2020 John Wiley & Sons Ltd

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Hero: On the Chaos When PATH Meets Modules

Hero: On the Chaos When PATH Meets Modules

引用

International Conference on software Engineering (ICSE)

作者： Ying Wang Liang Qiao Chang Xu Yepang Liu Shing-Chi Cheung Na Meng Hai Yu Zhiliang Zhu Software College Northeastern University China State Key Laboratory for Novel Software Technology and Department of Computer Science and Technology Nanjing University China Southern University of Science and Technology China The Hong Kong University of Science and Technology China Virginia Tech USA

Ever since its first release in 2009, the Go programming language (Golang) has been well received by software communities. A major reason for its success is the powerful support of library-based development, where a Golang project can be conveniently built on top of other projects by referencing them as libraries. As Golang evolves, it recommends the use of a new library-referencing mode to overcome the limitations of the original one. While these two library modes are incompatible, both are supported by the Golang ecosystem. The heterogeneous use of library-referencing modes across Golang projects has caused numerous dependency management (DM) issues, incurring reference inconsistencies and even build failures. Motivated by the problem, we conducted an empirical study to characterize the DM issues, understand their root causes, and examine their fixing solutions. Based on our findings, we developed Hero, an automated technique to detect DM issues and suggest proper fixing solutions. We applied Hero to 19,000 popular Golang projects. The results showed that Hero achieved a high detection rate of 98.5% on a DM issue benchmark and found 2,422 new DM issues in 2,356 popular Golang projects. We reported 280 issues, among which 181 (64.6%) issues have been confirmed, and 160 of them (88.4%) have been fixed or are under fixing. Almost all the fixes have adopted our fixing suggestions.

关键词： Chaos computer languages Ecosystems Benchmark testing Libraries software software engineering

来源：评论

学校读者我要写书评

暂无评论

Visual Tuning

arXiv

引用

arXiv 2023年

作者： Yu, Bruce X.B. Chang, Jianlong Wang, Haixin Liu, Lingbo Wang, Shijie Wang, Zhiyu Lin, Junfan Xie, Lingxi Li, Haojie Lin, Zhouchen Tian, Qi Chen, Chang Wen Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University China Huawei China National Engineering Research Center for Software Engineering Peking University China Peng Cheng Laboratory China College of Computer Science and Engineering Shandong University of Science and Technology China National Key Lab of General AI School of Intelligence Science and Technology Peking University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: fine-tuning, prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning. Copyright © 2023, The Authors. All rights reserved.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

Targeting Requirements Violations of Autonomous Driving Systems by Dynamic Evolutionary Search 36

Targeting Requirements Violations of Autonomous Driving Syst...

引用

36th IEEE/ACM International Conference on Automated software Engineering, ASE 2021

作者： Luo, Yixing Zhang, Xiao-Yi Arcaini, Paolo Jin, Zhi Zhao, Haiyan Ishikawa, Fuyuki Wu, Rongxin Xie, Tao Peking University Ministry of Education Key Lab. of High-Confidence Software Technologies Beijing China Department of Computer Science and Technology School of EECS Peking University Beijing China National Institute of Informatics Tokyo Japan Xiamen University School of Informatics Xiamen China

ISBN: (纸本)9781665403375

Autonomous Driving Systems (ADSs) are complex systems that must satisfy multiple requirements such as safety, compliance to traffic rules, and comfortableness. However, satisfying all these requirements may not always be possible due to emerging environmental conditions. Therefore, the ADSs may have to make trade-offs among multiple requirements during the ongoing operation, resulting in one or more requirements violations. For ADS engineers, it is highly important to know which combinations of requirements violations may occur, as different combinations can expose different types of failures. However, there is currently no testing approach that can generate scenarios to expose different combinations of requirements violations. To address this issue, in this paper, we introduce the notion of requirements violation pattern to characterize a specific combination of requirements violations. Based on this notion, we propose a testing approach named EMOOD that can effectively generate test scenarios to expose as many requirements violation patterns as possible. EMOOD uses a prioritization technique to sort all possible patterns to search for, from the most to the least critical ones. Then, EMOOD iteratively includes an evolutionary many-objective optimization algorithm to find different combinations of requirements violations. In each iteration, the targeted pattern is determined by a dynamic prioritization technique to give preferences to those patterns with higher criticality and higher likelihood to occur. We apply EMOOD to an industrial ADS under two common traffic situations. Evaluation results show that EMOOD outperforms three baseline approaches in generating test scenarios by discovering more requirements violation patterns. © 2021 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Context-aware Multi-level Question Embedding Fusion for visual question answering

引用

Information Fusion 2024年 102卷

作者： Li, Shengdong Gong, Chen Zhu, Yuqing Luo, Chuanwen Hong, Yi Lv, Xueqiang School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Zhejiang Lab Zhejiang Hangzhou311121 China Department of Computer Science California State University Los Angeles CA90032 United States School of Information Science and Technology Beijing Forestry University Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration 100083 China Beijing Key Laboratory of Internet Culture and Digital Dissemination Research Beijing Information Science and Technology University 100101 China

Question model has been widely concerned as the cornerstone of constructing Visual Question Answering (VQA) models. Existing question models attempt to exploit word context to extract multi-level concepts for modeling multi-level questions. However, they still have many defects. For example, most question models utilize simple fusion methods to fuse shallow modules and extract parameter-unshared low-level concepts, leading to poor modeling of multi-level questions;although some question models use deep bidirectional Transformer encoder in external knowledge transfer and BERT for multi-level questions, their complexity is still high. To solve these issues, we propose a novel low-complex multi-level contextual question model, termed Context-aware Multi-level Question Embedding Fusion (CMQEF). We formalize its concepts and theories, deduce its modeling process, optimization process and feature extraction process, analyze its low complexity and high expressiveness, and prove that it defines a new way to solve parameter non-sharing for extracting parameter-shared multi-level concepts and optimize the tradeoff between expressiveness and complexity in question models. Extensive experiments on VQAv2 and VQA-CPv2 validate that comparing with the state-of-the-art, our CMQEF outperforms it on SANs and UpDn, reduces the language priors of SANs and UpDn, and has preferable interpretability and applicability. Our code is available at https://***/lsdruc/CMQEF-for-VQA. © 2023 The Author(s)

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A New DCT-FFT Fusion Based Method for Caption and Scene Text Classification in Action Video Images 1

引用

2nd International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2020

作者： Nandanwar, Lokesh Shivakumara, Palaiahnakote Manna, Suvojit Pal, Umapada Lu, Tong Blumenstein, Michael Faculty of Computer Science and Information Technology University of Malayasia Kuala Lumpur Malaysia Department of Computer Science and Engineering Jalpaiguri Government Engineering College Jalpaiguri India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China University of Technology Sydney Ultimo Australia

ISBN: (数字)9783030598303

ISBN: (纸本)9783030598297

Achieving better recognition rate for text in video action images is challenging due to multi-type texts with unpredictable backgrounds. We propose a new method for the classification of captions (which is edited text) and scene texts (which is part of an image in video images of Yoga, Concert, Teleshopping, Craft, and Recipe classes). The proposed method introduces a new fusion criterion-based on DCT and Fourier coefficients to extract features that represent good clarity and visibility of captions to separate them from scene texts. The variances for coefficients of corresponding pixels of DCT and Fourier images are computed to derive the respective weights. The weights and coefficients are further used to generate a fused image. Furthermore, the proposed method estimates sparsity in Canny edge image of each fused image to derive rules for classifying caption and scene texts. Lastly, the proposed method is evaluated on images of five above-mentioned action image classes to validate the derived rules. Comparative studies with the state-of-the-art methods on the standard databases show that the proposed method outperforms the existing methods in terms of classification. The recognition experiments before and after classification show that the recognition performance rate improves significantly after classification. © 2020, Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep symmetric adaptation network for cross-modality medical image segmentation

arXiv

引用

arXiv 2021年

作者： Han, Xiaoting Qi, Lei Yu, Qian Zhou, Ziqi Zheng, Yefeng Shi, Yinghuan Gao, Yang The State Key Laboratory for Novel Software Technology The National Institute for Healthcare Data Science The Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing University China Southeast University China The School of Data and Computer Science Shandong Women’s University China The Tencent Jarvis Lab China

Unsupervised domain adaptation (UDA) methods have shown their promising performance in the cross-modality medical image segmentation tasks. These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images. However, when there exists a large domain shift between source and target domains, we argue that this asymmetric structure could not fully eliminate the domain gap. In this paper, we present a novel deep symmetric architecture of UDA for medical image segmentation, which consists of a segmentation sub-network, and two symmetric source and target domain translation sub-networks. To be specific, based on two translation sub-networks, we introduce a bidirectional alignment scheme via a shared encoder and private decoders to simultaneously align features 1) from source to target domain and 2) from target to source domain, which helps effectively mitigate the discrepancy between domains. Furthermore, for the segmentation sub-network, we train a pixel-level classifier using not only original target images and translated source images, but also original source images and translated target images, which helps sufficiently leverage the semantic information from the images with different styles. Extensive experiments demonstrate that our method has remarkable advantages compared to the state-of-the-art methods in both cross-modality Cardiac and BraTS segmentation tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

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：