Partner learning: A comprehensive knowledge transfer for vehicle re-identification | |
Wen Qian1,2![]() ![]() ![]() | |
发表期刊 | Neurocomputing
![]() |
2022-04 | |
期号 | 40页码:89-98 |
摘要 | The intra-class variability and inter-class similarity challenges caused by diverse viewpoints, illumination, and similar appearances are crucial in Re-Identification (Re-ID). Previous vehicle Re-ID methods propose to mine more discriminate and fine-grained clues for alleviating the problem, which costs extra computation and time during inference since the use of additional modules, e.g., detection modules, segmentation modules, or attention modules. We propose a multi-branch architecture to mining the discriminative and fine-grained information without additional time and computation cost during inference. Specifically, we focus on three problems: 1) how can knowledge transfer among multi-branches; 2) what knowledge should be utilized for more effective and more functional transfer; 3) where can be used as the input of multi-branches? For the first problem, we introduce a novel complementary learning scheme named partner learning which transfers the knowledge between global and local branches, and thus we only need the global branch during inference. For the second problem, we propose a hierarchical structural knowledge transfer (HSKT) approach to mine knowledge from partners in three different levels hierarchically. For the last problem, to effectively mine more fine-grained clues, we propose two local specifications: one supervised with the specification of the window area being discriminatively crucial as an expert knowledge while the other unsupervised with horizontal stripe cuts. Extensive ablation studies and experimental result discussions show the effectiveness of the proposed method. |
关键词 | 车辆重识别 |
收录类别 | SCI |
七大方向——子方向分类 | 人工智能+安防 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51911 |
专题 | 智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队 |
通讯作者 | Silong Peng |
作者单位 | 1.自动化所 2.中国科学院大学 |
推荐引用方式 GB/T 7714 | Wen Qian,Chen Chen,Silong Peng. Partner learning: A comprehensive knowledge transfer for vehicle re-identification[J]. Neurocomputing,2022(40):89-98. |
APA | Wen Qian,Chen Chen,&Silong Peng.(2022).Partner learning: A comprehensive knowledge transfer for vehicle re-identification.Neurocomputing(40),89-98. |
MLA | Wen Qian,et al."Partner learning: A comprehensive knowledge transfer for vehicle re-identification".Neurocomputing .40(2022):89-98. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
partner learing.pdf(4550KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论