检索结果-内蒙古大学图书馆

TGAS-ReID: Efficient architecture search for person re-identification via greedy decisions with topological order

APPLIED INTELLIGENCE 2023年第7期53卷 7343-7354页

作者： Chen, Shengbo Jiang, Kai Liu, Xianrui Yang, Kangkang Lei, Zhou Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Key Lab Comp Software Testing & Evaluati Shanghai 201112 Peoples R China

Person Re-Identification (Re-ID) technology is being developed rapidly due to the successful application of deep convolutional neural networks. However, the prevailing Re-ID models are usually built upon manually design backbones. In this paper, we propose using the TGAS-ReID which is automatically designed convolutional network backbones for Re-ID to substitute the backbones originally designed for classification such as ResNet and VGG. In the Re-ID tasks to search for a cell structure, greedy decisions are made instead of deriving the architecture after comprehensive training. In other words, at each decision epoch, according to the topological order, we first decide the candidates' pool of the edges to progressively reduce the coupling of the internal nodes of the DAG. An edge is then selected based on edge importance, edge certainty, and selection stability. We then make a greedy optimal choice for the selected edge and prune the relevant parameters. To further improve the backbone's representation capability of the features, we further introduce the triplet loss with batch hard mining as the retrieval loss. Extensive experiments demonstrate that the searched structure of the backbones reaches a performance level close to the previous work with a 20.8% shorter searching time. The proposed method also prevents the final CNNs network from suffering the well-known performance collapse by avoiding aggregation of the skip-connections.

关键词： Architecture search Person re-ID Greedy decisions AutoML One-shot

来源：评论

学校读者我要写书评

暂无评论

Multi-domain mixup for scenario-universal face anti-spoofing

引用

compUTERS & GRAPHICS-UK 2023年 116卷 327-335页

作者： Lu, Shitao Liu, Shice Zhang, keyue Chen, Mingang Tan, Xin Ma, Lizhuang East China Normal Univ Shanghai Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai Peoples R China Tencent Youtu Lab Shenzhen Peoples R China

Recently, disentangled representation learning has been commonly used in face anti-spoofing (FAS). However, such method has limited generalization ability due to the lack of data domains in the training phase. To overcome this issue, we devise a novel disentangling framework, which contains Progressive Refinement Disentangling (PRD) module and Multi-Domain Mixup (MDM) module. Concretely, face images are well disentangled into liveness features and domain features via the PRD module. The MDM module aims to produce more diverse domain features to generate faces of brand-new domains. The generated faces could improve the generalization ability of model in a data augmentation manner. Moreover, our disentangling framework is capable of tapping the potential of unlabeled data so it is universal in semi-supervised, domain generalization and adaption scenarios. Extensive experiments demonstrate the effectiveness of our method on public datasets.(c) 2023 Published by Elsevier Ltd.

关键词： Face anti-spoofing Disentangling Generative model

来源：评论

学校读者我要写书评

暂无评论

Time-cost efficient memory configuration for serverless workflow applications

引用

CONCURRENCY AND compUTATION-PRACTICE & EXPERIENCE 2022年第27期34卷

作者： Li, Zengpeng Yu, Huiqun Fan, Guisheng East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

Recently, workflow applications are increasingly migrated to Function-as-a-Service platforms which are easy to manage, highly-scalable, and pay-as-you-go. Meanwhile, users face challenges in migration of serverless applications because of the lack of efficient algorithm for workflow memory configuration to optimize the performance. To this end, this article proposes a heuristic urgency-based algorithm UWC and a meta-heuristic hybrid algorithm BPSO to tackle the time-cost tradeoff. UWC sorts functions and allocates each function an appropriate memory size by greedy strategy. BPSO hybridizes particle swarm optimization as well as beetle antennae search algorithm to guide particles to search directionally and utilizes nonlinear inertia weight to avoid local premature convergence. Extensive experiments with classical serverless application demonstrate that UWC and BPSO are very competitive in comparison with existing algorithms as they can find the optimal workflow memory configuration.

关键词： constrained optimization performance modeling serverless computing workflow memory configuration

来源：评论

学校读者我要写书评

暂无评论

A Combining Method for Wireless Protocol Conformance testing: A Empirical Case

引用

WIRELESS COMMUNICATIONS & MOBILE compUTING 2021年第1期2021卷 p1-14页

作者： Wei-Wei, Lin Hong-Wei, Zeng Kim, Jung Yoon Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China Gachon Univ Grad Sch Game Seongnam South Korea

Ensuring the consistency of protocol implementation and protocol specification is the basic premise of wireless communication. With the application of wireless communication in more and more fields, the wireless communication environment becomes more and more complex, and the fault coverage of wireless protocol conformance testing is also facing more and more challenges. To solve this problem, this paper uses Finite State Machine (FSM) as a formal description tool for wireless protocols and presents a combining test method based on two test methods with complementary characteristics in the test technologies based on structural coverage and state identification. Then, the paper evaluates the effectiveness of the method based on 14 empirical cases. The experimental results show that the fault coverage of each empirical case can be effectively improved to 100% when the average test cost is only increased by 17.99%.

关键词： testing

来源：评论

学校读者我要写书评

暂无评论

A graph algorithm for the time constrained shortest path

引用

CONNECTION SCIENCE 2022年第1期34卷 1500-1518页

作者： Liu, Pan Huang, Wulan Shanghai Business Sch Fac Business Informat Shanghai Peoples R China Shanghai Key Lab Comp Software Testing & Evaluat Shanghai Peoples R China

Highly efficient algorithms for solving the time constrained shortest path problem have been highlighted over the past decades to reduce the cost of vehicle travel in the road network. The paper presents a novel graph algorithm comprising three stages to acquire a time constrained shortest path between any two nodes on the map. In the first stage, the undirected graph is transformed into a directed graph (DT graph) by deleting edges that must not be included in any of the time constrained shortest paths. A variant DT tree with the destination as the root and the source as the leaf is then constructed from the DT graph in the second stage. By finding the minimal difference value between leaves and the root of the variant DT tree, we can eventually obtain a time constrained shortest path from the variant DT tree in the third stage. Experimental results show that our algorithm not only requires less running time than some classical graph algorithms but also can work immediately in the first stage without knowing the information of both the destination and a specific time constraint.

关键词： Time constrained shortest path graph algorithm DT graph variant DT tree

来源：评论

学校读者我要写书评

暂无评论

Security-based code smell definition, detection, and impact quantification in Android

引用

software-PRACTICE & EXPERIENCE 2023年第11期53卷 2296-2321页

作者： Zhong, Yi Shi, Mengyu He, Jiawei Fang, Chunrong Chen, Zhenyu Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai Peoples R China Nanjing Univ Shenzhen Res Inst Shenzhen Peoples R China

Android's high market share and extensive functionality make its security a significant concern. Research reveals that many security issues are caused by insecure coding practices. As a poor design indicator, code smell threatens the safety and quality assurance of Android applications (apps). Although previous works revealed specific problems associated with code smells, the field still lacks research reflecting Android features. Moreover, the cost and time limit developers to repairing numerous smells timely. We conducted a study, including Definition, Detection, and Impact Quantification for Android code smell (DefDIQ): (1) define 15 novel code smells in Android from a security programming perspective and provide suggestions on how to eliminate or mitigate them;(2) implement DACS (Detect Android Code Smell) to automatically detect the custom code smells based on ASTs;(3) investigate the correlation between individual smells with DACS detection results, select suitable code smells to construct fault counting models, then quantify their impact on quality, and thereby generating code smell repair priorities. We conducted experiments on 4575 open-source apps, and the findings are: (i) Lin's CCC between DACS and manual detection results reaches 0.9994, verifying the validity;(ii) the fault counting model constructed by zero-inflated negative binomial is superior to negative binomial (AIC = 517.32, BIC = 522.12);some smells do indicate fault-proneness, and we identify such avoidable poor designs;(iii) different code smells have different levels of importance and the repair priorities constructed provide a practical guideline for researchers and inexperienced developers.

关键词： Android code smell quality assurance repair priority security

来源：评论

学校读者我要写书评

暂无评论

Pattern Mining-Based Warning Prioritization by Refining Abstract Syntax Tree

引用

INTERNATIONAL JOURNAL OF software ENGINEERING AND KNOWLEDGE ENGINEERING 2024年第10期34卷 1593-1619页

作者： Ge, Xiuting Li, Xuanye Sun, Yuanyuan Qing, Mingshuang Zheng, Haitao Zhang, Huibin Wu, Xianyu GuangDong Tops Soft Pk co LTD Guangzhou Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

Static code analysis tools (SATs) are widely used to detect potential defects in software projects. However, the usability of SATs is seriously hindered by a large number of unactionable warnings. Currently, many warning prioritization approaches are proposed to improve the usability of SATs. These approaches mainly extract different warning features to capture the statistical or historical information of warnings, thereby ranking actionable warnings in front of unactionable warnings. Such features are extracted by extremely relying on domain knowledge. However, the precise domain knowledge is difficult to be acquired. Also, the domain knowledge obtained in a project cannot be directly applied to other projects due to different application scenarios among different projects. To address the above problem, we propose a pattern mining-based warning prioritization approach based on the warning-related Abstract Syntax Tree (AST). To automatically mine actionable warning patterns, our approach leverages an advanced technique to collect actionable warnings, designs an algorithm to extract the warning-related AST, and mines patterns from ASTs of all actionable warnings. To prioritize the newly reported warnings, our approach combines exact and fuzzing matching techniques to calculate the similarity score between patterns of the newly reported warnings and the mined actionable warning patterns. We compare our approach with four typical baselines on five open-source and large-scale Java projects. The results show that our approach outperforms four baselines and achieves the maximum MAP (0.76) and MRR (2.19). Besides, a case study on Defect4J dataset demonstrates that our approach can discover 83% of true defects in the top 10 warnings.

关键词： Warning prioritization pattern mining actionable warnings

来源：评论

学校读者我要写书评

暂无评论

Enhancing code summarization with action word prediction

引用

NEUROcompUTING 2024年 563卷

作者： Li, Mingchen Yu, Huiqun Fan, Guisheng Zhou, Ziyi Huang, Zijie East China Univ Sci & Technol Dept Comp Sci & Engn Shanghai Peoples R China Shanghai Engn Res Ctr Smart Energy Shanghai Peoples R China Shanghai Comp Software Tech Dev Ctr Shanghai Key Lab Comp Software Evaluating & Testin Shanghai Peoples R China

Code summarization refers to automatically generating concise description in natural language from a code snippet. Good code summaries could effectively facilitate program comprehension and software maintenance. In recent years, various learning-based code summarization techniques have achieved impressive performance. Most of these models treat code summarization as an end-to-end model and directly generate the summaries, which ignores the fact that action words are crucial to code summaries. An essential characteristic of code summaries is the concentration of action word distribution. For instance, in the Funcom dataset, the top forty most-common action words account for 72% of all samples. To incorporate this valuable prior domain knowledge into code summarization models, we develop a method for assisting code summarization through an additional action word prediction module, where an action predictor is employed to predict the primary action in the code summary, which is then used as a prompt to enhance the performance of the summary generation model. Our approach can be conveniently integrated into the existing models. We evaluate our approach on two Java datasets and a C/C++ dataset. The results show that our approach can efficiently improve the performance of the code summarization models. Furthermore, our action word prediction module can enhance the performance of a large pre-trained language model by prompting it with the predicted action words. This work suggests that a precise action word prediction model can significantly improve the performance of code summarization through the proposed action word guidance mechanism.

关键词： Code summarization Action word prediction Multi-task learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

ClassSum: a deep learning model for class-level code summarization

引用

NEURAL compUTING & APPLICATIONS 2023年第4期35卷 3373-3393页

作者： Li, Mingchen Yu, Huiqun Fan, Guisheng Zhou, Ziyi Huang, Jiawen East China Univ Sci & Technol Dept Comp Sci & Engn Shanghai Peoples R China Shanghai Engn Res Ctr Smart Energy Shanghai Peoples R China Shanghai Comp Software Tech Dev Ctr Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

Code summaries are clear and concise natural language descriptions of program entities. Meaningful code summaries assist developers in better understanding. Code summarization refers to the task of generating a natural language summary from a code snippet. Most researches on code summarization focus on automatically generating summaries for methods or functions. However, in an object-oriented language such as Java, class is the basic programming unit rather than method. To fill this gap, in this paper, we investigate how to generate summaries for Java classes utilizing deep learning-based approaches. We propose a novel encoder-decoder model called ClassSum to generate functionality descriptions for Java classes and build a dataset containing 172,639 pairs from 3185 repositories hosted on Github. Since the code of class is much longer and more complicated, encoding a whole class via neural network is more challenging than encoding a method. On the other hand, the content within a class may be incomplete. To overcome this difficulty, we reduce the code of a class by only keeping its key elements, namely class signatures, method signatures and attribute names. To utilize both lexical and structural information of code, our model takes token sequence and abstract syntax tree of the reduced class content as inputs. ClassSum and five baselines (designed for method-level code summarization) are evaluated on our dataset. Experiment results show that summaries generated by ClassSum are more accurate and readable than those generated by baselines. Our dataset is available at https://***/classsum/ClassSum.

关键词： Program comprehension Code summarization Class documentation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Neural 3D face rendering conditioned on 2D appearance via GAN disentanglement method

引用

compUTERS & GRAPHICS-UK 2023年 116卷 336-344页

作者： Chen, Ruizhao Yi, Ran Wang, Tuanfeng Yang Ma, Lizhuang Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai 201112 Peoples R China Adobe Res San Jose CA USA

Previewing the shaded output of 3D models has been a long-standing requirement in the field. Typically, this is achieved by applying common materials;however, this approach is often laborintensive and can yield only rough results in the trial stage. Conventional 2D style transfer methods are unsuitable for 3D-to-2D cross-domain conversion, and they cannot accurately reflect the mesh's geometry. Inspired by StyleGAN2's related research, we propose a method for rendering 2D images of 3D face meshes directly controlled by a single 2D reference image, using GAN disentanglement. Our approach involves an input of a 3D mesh and a reference image, where encoders extract geometric features from the mesh and appearance features from the reference image. These features control the StyleGAN2 generator to obtain a generated image that preserves the 3D mesh's geometry and the reference image's appearance. Our experiments demonstrate that this method performs well in generating images while maintaining geometric consistency.

关键词： Neural rendering GAN disentanglement Conditional generation

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：