ID 原文 译文
25165 方法以生成对抗网络为框架，设计了包含 11 个卷积模块和 5 个池化层的鉴别器网络以及不包含池化层，仅包含 15 个卷积模块和 5 个转置卷积模块的小型生成器网络。 The method uses the generative adversarial network as the framework, designs a discriminator network consisting of 11 convolution modules and 5 pool layers, as well as a small generator network that does not contain the pool layer, including only 15 convolution modules and 5 transposed convolution modules．
25166 其中，小型生成器网络大小仅 2。 4M，参数量仅 67 万左右。 Among them, the size of the small generator network is only 2. 4M, and the amount of parameters is only about 670，000.
25167 将训练好的小型生成器用于显著性检测，并与 LMB(融合背景块再选取过程的显著性检测)算法通过设计的融合算法进行融合，从而得到最终结果。 A trained small generator is used for saliency detection and fused with the LMB (Salient object detection based on background block reselection method) algorithm through the designed fusion algorithm to get the final result.
25168 通过大量的实验对比分析表明，提出的方法在 F 值和 MAE(Mean Absolute Error)值上均取得大幅提升。 A large number of experiments and comparative analysis show that the proposed method has achieved significant improvements in both F value and MAE (Mean Absolute Error) value．
25169 缺陷数据分析正成为软件工程领域的热点，现有缺陷分析技术无法有效处理复杂和冗余的缺陷数据，以高效地辅助缺陷修复工作。 Bug data analysis is becoming a hotspot in the software engineering domain. The accumulation of bug knowledge requires redefinition of a new search method to effectively process complex and redundant bug data to efficiently assist bug fixing．
25170 本文提出一种多特征匹配搜索算法———MMSBK (Multi-feature Matching Search Algorithmfor Bug Knowledge)。 This paper proposes a multi-feature matching search algorithm for bug knowledge (MMSBK)．
25171 首先对缺陷问题进行分析，抽取其包含的缺陷实体及关系; First, we analyze the bug question and extract the bug entities and relations.
25172 然后，基于实体和关系匹配将缺陷问题与缺陷知识图谱关联，通过知识图谱的关联性和可视化帮助软件开发搜索缺陷知识; Then, based on bug entity and relation matching,the bug question is associated with the bug knowledge graph.
25173 最后，基于匹配算法生成的缺陷关系三元组生成搜索结果子图。 Finally, the search sub-graph is generated based on the bug triples generated by the matching algorithm．
25174 实验验证了 MMSBK 算法的有效性。 The experiment shows the effectiveness of MMSBK．