检索结果-内蒙古大学图书馆

?-net: Dual supervised medical image segmentation with multi-dimensional self-attention and diversely-connected multi-scale convolution

引用

NEUROCOMPUTING 2022年 500卷 177-190页

作者： Xu, Zhenghua Liu, Shijie Yuan, Di Wang, Lei Chen, Junyang Lukasiewicz, Thomas Fu, Zhigang Zhang, Rui State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology China Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health Hebei University of Technology China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science University of Oxford United Kingdom Department of Health Management Center 983 Hospital of Joint Logistics Support Force China www.ruizhang.info

Although U-Net and its variants have achieved some great successes in medical image segmentation tasks, their segmentation performances for small objects are still unsatisfactory. Therefore, in this work, a new deep model, co-Net, is proposed to achieve more accurate medical image segmentations. The advancements of co-Net are mainly threefold: First, it incorporates an additional expansive path into U-Net to import an extra supervision signal and obtain a more effective and robust image segmentation by dual supervision. Then, a multi-dimensional self-attention mechanism is further developed to highlight salient features and suppress irrelevant ones consecutively in both spatial and channel dimensions. Finally, to reduce semantic disparity between the feature maps of the contracting and expansive paths, we further propose to integrate diversely-connected multi-scale convolution blocks into the skip connections, where several multi-scale convolutional operations are connected in both series and parallel. Extensive experimental results on three abdominal CT segmentation tasks show that (i) co-Net greatly outperforms the state-of-the-art image segmentation methods in medical image segmentation tasks;(ii) the proposed three advancements are all effective and essential for co-Net to achieve the superior performances;and (iii) the proposed multi-dimensional self-attention (resp., diversely-connected multi scale convolution) is more effective than the state-of-the-art attention mechanisms (resp., multi-scale solutions) for medical image segmentations. The code will be released online after this paper is formally accepted. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Medical image segmentation Dual supervision Multi-dimensional self-attention Diversely-connected multi-scale convolution

来源：评论

学校读者我要写书评

暂无评论

Constant Optimization Driven Database System Testing

arXiv

引用

arXiv 2025年

作者： Zhang, Chi Rigger, Manuel State Key Laboratory for Novel Software Technology School of Computer Science Nanjing University Nanjing China National University of Singapore Singapore

Logic bugs are bugs that can cause database management systems (DBMSs) to silently produce incorrect results for given queries. Such bugs are severe, because they can easily be overlooked by both developers and users, and can cause applications that rely on the DBMSs to malfunction. In this work, we propose Constant-Optimization-Driven Database Testing (CODDTest) as a novel approach for detecting logic bugs in DBMSs. This method draws inspiration from two well-known optimizations in compilers: constant folding and constant propagation. Our key insight is that for a certain database state and query containing a predicate, we can apply constant folding on the predicate by replacing an expression in the predicate with a constant, anticipating that the results of this predicate remain unchanged;any discrepancy indicates a bug in the DBMS. We evaluated CODDTest on five mature and extensively-tested DBMSs–SQLite, MySQL, CockroachDB, DuckDB, and TiDB–and found 45 unique, previously unknown bugs in them. Out of these, 24 are unique logic bugs. Our manual analysis of the state-of-the-art approaches indicates that 11 logic bugs are detectable only by CODDTest. We believe that CODDTest is easy to implement, and can be widely adopted in practice. © 2025, CC BY.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Single-Phase Fault Detection Based on GCN-TCN Sparse-Attention Model 12

Single-Phase Fault Detection Based on GCN-TCN Sparse-Attenti...

引用

12th International Conference on Advanced computer Information Technologies, ACIT 2022

作者： Yong, Ouyang Dou, Wan Rong, Gao Zhiwei, Ye Kochan, Orest Hubei University of Technology School of Computer Science China Hubei University of Technology Nanjing University School of Computer Science State Key Laboratory for Novel Software Technology China University Hubei University of Technology China School of Computer Science Lviv Polytechnic National Lviv Ukraine

ISBN: (数字)9781665410502

ISBN: (纸本)9781665466479

Effective extraction of fault current features is the problem facing single phase fault detection in distribution networks. We propose a hybrid neural network model based on the GCN-TCN sparse attention mechanism (GTHNN-SA) to solve this problem. Specifically, this model uses the convolutional graph network (GCN) to perform graph convolution operation on the graph data established by the fault line transient zero-sequence current, extract the spatial characteristics of the zero-sequence current data with the fault location relationship, use the temporal convolution network (TCN) to extract the temporal characteristics both of threephase currents and new data generated by GAN. Then fuse and input the three feature matrices to the sparse attention mechanism to highlight essential features of current data. Finally, the output of parse-attention is input to the entire connected layer for classification. This model enables us to learn the current data relationship between different waveform faults more comprehensively, and the proposed method has a good effect on single-phase fault detection in distribution networks. © 2022 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Driven Inference Testing for Question Answering software

Knowledge Graph Driven Inference Testing for Question Answer...

引用

International Conference on software Engineering (ICSE)

作者： Jun Wang Yanhui Li Zhifei Chen Lin Chen Xiaofang Zhang Yuming Zhou State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Nanjing University of Science and Technology China School of Computer Science and Technology Soochow University China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

In the wake of developments in the field of Natural Language Processing, Question Answering (QA) software has penetrated our daily lives. Due to the data-driven programming paradigm, QA software inevitably contains bugs, i.e., misbehaving in real-world applications. Current testing techniques for testing QA software include two folds, reference-based testing and metamorphic testing. This paper adopts a different angle to achieve testing for QA software: we notice that answers to questions would have inference relations, i.e., the answers to some questions could be logically inferred from the answers to other questions. If these answers on QA software do not satisfy the inference relations, an inference bug is detected. To generate the questions with the inference relations automatically, we propose a novel testing method Knowledge Graph driven Inference Testing (KGIT), which employs facts in the Knowledge Graph (KG) as the seeds to logically construct test cases containing questions and contexts with inference relations. To evaluate the effectiveness of KGIT, we conduct an extensive empirical study with more than 2.8 million test cases generated from the large-scale KG YAGO4 and three QA models based on the state-of-the-art QA model structure. The experimental results show that our method (a) could detect a considerable number of inference bugs in all three studied QA models and (b) is helpful in retraining QA models to improve their inference ability.

关键词： computer bugs Knowledge graphs Programming software Question answering (information retrieval) Testing software engineering

来源：评论

学校读者我要写书评

暂无评论

EXPLORING LEARNING COMPLEXITY FOR EFFICIENT DOWNSTREAM DATASET PRUNING

arXiv

引用

arXiv 2024年

作者： Jiang, Wenyu Liu, Zhenlong Xie, Zejian Zhang, Songxin Jing, Bingyi Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China State Key Laboratory for Novel Software Technology Nanjing University China

The ever-increasing fine-tuning cost of large-scale pre-trained models gives rise to the importance of dataset pruning, which aims to reduce dataset size while maintaining task performance. However, existing dataset pruning methods require training on the entire dataset, which is impractical for large-scale pre-trained models. In this paper, we propose a straightforward, novel, and training-free hardness score named Distorting-based Learning Complexity (DLC), to identify informative images and instructions from the downstream dataset efficiently. Our method is motivated by the observation that easy samples learned faster can also be learned with fewer parameters. Specifically, we define the Learning Complexity to quantify sample hardness and utilize a lightweight weights masking process for fast estimation, instead of the costly SGD optimization. Based on DLC, we further design a flexible under-sampling with randomness (dubbed FlexRand), replacing the top-K strategy, to alleviate the severe subset distribution shift. Extensive experiments with downstream image and instructions dataset pruning benchmarks demonstrate the effectiveness and efficiency of the proposed approach. In the images pruning benchmark, DLC significantly reduces the pruning time by 35× while establishing state-of-the-art performance with FlexRand. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Duplicate Vulnerability Records Across Databases

SSRN

引用

SSRN 2025年

作者： Zhu, Kangliang Yang, Wenhua Pan, Minxue Zhou, Yu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Vulnerability databases are critical repositories that aggregate information about known security vulnerabilities across various software products. However, the existence of multiple, heterogeneous databases often leads to duplicate vulnerability records, necessitating significant manual effort by maintainers to identify and consolidate these duplicates. This study addresses the challenge of detecting duplicate vulnerabilities across different databases by proposing a combined method that integrates cosine similarity measures with a fine-tuned BERT-based language model. We constructed a comprehensive duplicate vulnerability dataset by analyzing records from prominent databases such as CVE, OSV, and the GitHub Advisory Database. Our method was evaluated against several baseline techniques, including similarity-based and deep learning-based approaches, demonstrating superior performance across multiple metrics, including Hit Rate@N, Mean Reciprocal Rank (MRR), Mean Rank, and Median Rank. Additionally, our method proved effective in practical scenarios involving ongoing database maintenance, showcasing its ability to generalize to unseen data. The findings highlight the potential of integrating traditional similarity measures with advanced language models to enhance the accuracy and efficiency of duplicate vulnerability detection, thereby facilitating more reliable vulnerability management. © 2025, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Multi-View Incongruity Learning for Multimodal Sarcasm Detection 31

Multi-View Incongruity Learning for Multimodal Sarcasm Detec...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Guo, Diandian Cao, Cong Yuan, Fangfang Liu, Yanbing Zeng, Guangjie Yu, Xiaoyan Peng, Hao Yu, Philip S. Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Technology Beijing Institute of Technology China Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9798891761964

Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model's generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL's advancement in mitigating the effect of spurious correlation. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Amplified locality-sensitive hashing-based recommender systems with privacy protection

Amplified locality-sensitive hashing-based recommender syste...

引用

作者： Chi, Xiaoxiao Yan, Chao Wang, Hao Rafique, Wajid Qi, Lianyong School of Information Science and Engineering Qufu Normal University Rizhao China Department of Computer Science Norwegian University of Science and Technology Gjøvik Norway State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

With the advent of Internet of Things (IoT) age, the variety and volume of web services have been increasing at a fast speed. This often leads to users' selections for web services more complicated. Under the circumstance, a variety of methods such as collaborative filtering are adopted to deal with this challenging situation. While traditional collaborative filtering method has some shortcomings, one of which is that only centralized user-service data are considered while distributed quality data from multiple platform are ignored. Generally, service recommendation across different platforms often involves data communication among multiple platforms, during which user privacy may be disclosed and much computational time is required. Considering these challenges, a unique amplified locality-sensitive hashing (LSH)-based service recommendation method, that is, SRAmplified-LSH, is proposed in the article. SRAmplified-LSH can guarantee a good balance between accuracy and efficiency of recommendation and user privacy information. Finally, extensive experiments deployed on WS-DREAM dataset validate the feasibility of our proposed method. © 2020 John Wiley & Sons, Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

XRL-SHAP-Cache:an explainable reinforcement learning approach for intelligent edge service caching in content delivery networks

引用

science China(Information sciences) 2024年第7期67卷 46-71页

作者： Xiaolong XU Fan WU Muhammad BILAL Xiaoyu XIA Wanchun DOU Lina YAO Weiyi ZHONG School of Software Nanjing University of Information Science and Technology School of Computing and Communications Lancaster University School of Computing Technologies Royal Melbourne Institute of Technology State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering University of New South Wales Data 61 Commonwealth Scientific and Industrial Research Organization School of Computer Science Qufu Normal University

Content delivery networks(CDNs) play a pivotal role in the modern internet infrastructure by enabling efficient content delivery across diverse geographical regions. As an essential component of CDNs, the edge caching scheme directly influences the user experience by determining the caching and eviction of content on edge servers. With the emergence of 5G technology, traditional caching schemes have faced challenges in adapting to increasingly complex and dynamic network environments. Consequently, deep reinforcement learning(DRL) offers a promising solution for intelligent zero-touch network governance. However, the blackbox nature of DRL models poses challenges in understanding and making trusting decisions. In this paper,we propose an explainable reinforcement learning(XRL)-based intelligent edge service caching approach,namely XRL-SHAP-Cache, which combines DRL with an explainable artificial intelligence(XAI) technique for cache management in CDNs. Instead of focusing solely on achieving performance gains, this study introduces a novel paradigm for providing interpretable caching strategies, thereby establishing a foundation for future transparent and trustworthy edge caching solutions. Specifically, a multi-level cache scheduling framework for CDNs was formulated theoretically, with the D3QN-based caching scheme serving as the targeted interpretable model. Subsequently, by integrating Deep-SHAP into our framework, the contribution of each state input feature to the agent's Q-value output was calculated, thereby providing valuable insights into the decision-making process. The proposed XRL-SHAP-Cache approach was evaluated through extensive experiments to demonstrate the behavior of the scheduling agent in the face of different environmental *** results demonstrate its strong explainability under various real-life scenarios while maintaining superior performance compared to traditional caching schemes in terms of cache hit ratio, quality of service(QoS),a

关键词： deep reinforcement learning (DRL) explainable artificial intelligence (XAI) multi-level cache content delivery network (CDN) D3QN algorithm Deep-SHAP

来源：评论

学校读者我要写书评

暂无评论

PredRacer: Predictively Detecting Data Races in Android Applications

PredRacer: Predictively Detecting Data Races in Android Appl...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Xin Guo Xiaofang Qi Yanhui Li Chao Wu School of Computer Science and Engineering Southeast University China State Key Laboratory for Novel Software Technology Nanjing University China

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Android platform offers a hybrid concurrency model encompassing multi-threading and asynchronous messaging for concurrent programming. The model is powerful but complex, making it difficult for developers to analyze concurrent behaviors. Data race, a prevalent concurrency defect in real-world Android applications, often results in abnormal executions of mobile applications, even crashes. Despite quite a few studies on detecting data races, it still suffers from high false positives with static analysis techniques and high false negatives with dynamic analysis techniques. To address this issue, this paper presents a predictive approach, PredRacer, for detecting data races in Android applications. It first captures an execution trace of an Android application, and then reorders the events within the trace based on partial orders. Finally, it checks the feasibility of the generated event sequence, which contains a potential data race. PredRacer increases the search scope and reduces false negatives while mitigating false positives by incorporating the happen-before relations specific to the Android concurrency model. The effectiveness of PredRacer is evaluated using the BenchERoid data set. Experimental results demonstrate that PredRacer achieves high precision, recall, and F1 score, outperforming the state-of-the-art techniques. A collection of 20 open-source Android applications is further utilized to assess the effectiveness of PredRacer, and an evaluation of 300 wild apps is conducted to assess its efficiency and scalability.

关键词： Concurrent computing Java Operating systems Scalability Static analysis Predictive models Programming

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：