Name
Abstract | ||
|---|---|---|
We introduce an explainable generative model by applying sparse operation on the feature maps of the generator network. Meaningful hierarchical representations are obtained using the proposed generative model with sparse activations. The convolutional kernels from the bottom layer to the top layer of the generator network can learn primitives such as edges and colors, object parts, and whole objects layer by layer. From the perspective of the generator network, we propose a method for inducing both sparse coding and the AND-OR grammar for images. Experiments show that our method is capable of learning meaningful and explainable hierarchical representations. |
Year | Venue | DocType |
|---|---|---|
2019 | arXiv: Learning | Journal |
Volume | Citations | PageRank |
abs/1901.11494 | 0 | 0.34 |
References | Authors | |
3 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xianglei Xing | 1 | 96 | 10.51 |
| Song-Chun Zhu | 2 | 6580 | 741.75 |
| Ying Nian Wu | 3 | 1652 | 267.72 |