Abstract | ||
---|---|---|
This paper introduces an explanatory graph representation to reveal object parts encoded inside convolutional layers of a CNN. Given a pre-trained CNN, each filter1 in a conv-layer usually represents a mixture of object parts. We develop a simple yet effective method to learn an explanatory graph, which automatically disentangles object parts from each filter without any part annotation... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TPAMI.2020.2992207 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Feature extraction,Visualization,Neural networks,Semantics,Annotations,Task analysis,Training | Journal | 43 |
Issue | ISSN | Citations |
11 | 0162-8828 | 1 |
PageRank | References | Authors |
0.34 | 18 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Quanshi Zhang | 1 | 288 | 26.67 |
Xin Wang | 2 | 1 | 1.36 |
Ruiming Cao | 3 | 32 | 4.79 |
Ying Nian Wu | 4 | 1652 | 267.72 |
Feng Shi | 5 | 14 | 2.96 |
Song-Chun Zhu | 6 | 6580 | 741.75 |