Deeply Explain CNN Via Hierarchical Decomposition
文献类型：期刊论文
| 作者 | Cheng, Ming-Ming3; Jiang, Peng-Tao3; Han, Ling-Hao3; Wang, Liang2 ; Torr, Philip1
|
| 刊名 | INTERNATIONAL JOURNAL OF COMPUTER VISION
 |
| 出版日期 | 2023-01-11 |
| 页码 | 15 |
| 关键词 | Explaining CNNs Hierarchical decomposition |
| ISSN号 | 0920-5691 |
| DOI | 10.1007/s11263-022-01746-x |
| 通讯作者 | Cheng, Ming-Ming(cmm@nankai.edu.cn) |
| 英文摘要 | In computer vision, some attribution methods for explaining CNNs attempt to study how the intermediate features affect network prediction. However, they usually ignore the feature hierarchies among the intermediate features. This paper introduces a hierarchical decomposition framework to explain CNN's decision-making process in a top-down manner. Specifically, we propose a gradient-based activation propagation (gAP) module that can decompose any intermediate CNN decision to its lower layers and find the supporting features. Then we utilize the gAP module to iteratively decompose the network decision to the supporting evidence from different CNN layers. The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process. Moreover, gAP is effort-free for understanding CNN-based models without network architecture modification and extra training processes. Experiments show the effectiveness of the proposed method. The data and source code will be publicly available at https://mmcheng.net/hdecomp/. |
| 资助项目 | Major Project for New Generation of AI ; NSFC ; Fundamental Research Funds for the Central Universities (Nankai University) ; [2018AAA0100400] ; [61922046] ; [63223050] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000919320600002 |
| 出版者 | SPRINGER |
| 资助机构 | Major Project for New Generation of AI ; NSFC ; Fundamental Research Funds for the Central Universities (Nankai University) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/51350]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Cheng, Ming-Ming |
| 作者单位 | 1.Univ Oxford, Oxford, England 2.NLPR, Beijing, Peoples R China 3.Nankai Univ, TMCC, Tianjin, Peoples R China |
| 推荐引用方式 GB/T 7714 | Cheng, Ming-Ming,Jiang, Peng-Tao,Han, Ling-Hao,et al. Deeply Explain CNN Via Hierarchical Decomposition[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2023:15. |
| APA | Cheng, Ming-Ming,Jiang, Peng-Tao,Han, Ling-Hao,Wang, Liang,&Torr, Philip.(2023).Deeply Explain CNN Via Hierarchical Decomposition.INTERNATIONAL JOURNAL OF COMPUTER VISION,15. |
| MLA | Cheng, Ming-Ming,et al."Deeply Explain CNN Via Hierarchical Decomposition".INTERNATIONAL JOURNAL OF COMPUTER VISION (2023):15. |
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。