Title | ||
---|---|---|
Mining Interpretable AOG Representations From Convolutional Networks via Active Question Answering |
Abstract | ||
---|---|---|
In this paper, we present a method to mine object-part patterns from conv-layers of a pre-trained convolutional neural network (CNN). The mined object-part patterns are organized by an And-Or graph (AOG). This interpretable AOG representation consists of a four-layer semantic hierarchy, i.e., semantic parts, part templates, latent patterns, and neural units. The AOG associates each object part wit... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TPAMI.2020.2993147 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Semantics,Visualization,Head,Magnetic heads,Neural networks,Information filters | Journal | 43 |
Issue | ISSN | Citations |
11 | 0162-8828 | 0 |
PageRank | References | Authors |
0.34 | 18 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Quanshi Zhang | 1 | 288 | 26.67 |
Jie Ren | 2 | 0 | 0.34 |
Ge Huang | 3 | 2 | 3.07 |
Ruiming Cao | 4 | 32 | 4.79 |
Ying Nian Wu | 5 | 1652 | 267.72 |
Song-Chun Zhu | 6 | 6580 | 741.75 |