Shallow Feature-driven Dual-edges Localization Network for Weakly Supervised Localization
文献类型：期刊论文
| 作者 | Wenjun Hui1,2; Guanghua Gu1,2; Bo Wang1,2 |
| 刊名 | Machine Intelligence Research
 |
| 出版日期 | 2023 |
| 卷号 | 20期号:6页码:923-936 |
| 关键词 | Weakly supervised object localization, edge feature mining, edge of shallow feature map, edge of shallow gradients, similarity measurement |
| ISSN号 | 2731-538X |
| DOI | 10.1007/s11633-022-1368-6 |
| 英文摘要 | Weakly supervised object localization mines the pixel-level location information based on image-level annotations. The traditional weakly supervised object localization approaches exploit the last convolutional feature map to locate the discriminative regions with abundant semantics. Although it shows the localization ability of classification network, the process lacks the use of shallow edge and texture features, which cannot meet the requirement of object integrity in the localization task. Thus, we propose a novel shallow feature-driven dual-edges localization (DEL) network, in which dual kinds of shallow edges are utilized to mine entire target object regions. Specifically, we design an edge feature mining (EFM) module to extract the shallow edge details through the similarity measurement between the original class activation map and shallow features. We exploit the EFM module to extract two kinds of edges, named the edge of the shallow feature map and the edge of shallow gradients, for enhancing the edge details of the target object in the last convolutional feature map. The total process is proposed during the inference stage, which does not bring extra training costs. Extensive experiments on both the ILSVRC and CUB-200-2011 datasets show that the DEL method obtains consistency and substantial performance improvements compared with the existing methods. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/56019]  |
| 专题 | 自动化研究所_学术期刊_International Journal of Automation and Computing |
| 作者单位 | 1.Hebei Key Laboratory of Information Transmission and Signal Processing, Qinhuangdao 066000, China 2.School of Information Science and Engineering, Yanshan University, Qinhuangdao 066000, China |
| 推荐引用方式 GB/T 7714 | Wenjun Hui,Guanghua Gu,Bo Wang. Shallow Feature-driven Dual-edges Localization Network for Weakly Supervised Localization[J]. Machine Intelligence Research,2023,20(6):923-936. |
| APA | Wenjun Hui,Guanghua Gu,&Bo Wang.(2023).Shallow Feature-driven Dual-edges Localization Network for Weakly Supervised Localization.Machine Intelligence Research,20(6),923-936. |
| MLA | Wenjun Hui,et al."Shallow Feature-driven Dual-edges Localization Network for Weakly Supervised Localization".Machine Intelligence Research 20.6(2023):923-936. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。