papers AI Learner
The Github is limit! Click to go to the new site.

Inducing Sparse Coding and And-Or Grammar from Generator Network

2019-01-20
Xianglei Xing, Song-Chun Zhu, Ying Nian Wu

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.11494

PDF

http://arxiv.org/pdf/1901.11494


Similar Posts

Comments