Is Discriminator a Good Feature Extractor?

no code implementations • 2 Dec 2019 • Xin Mao, Zhaoyu Su, Pin Siang Tan, Jun Kang Chow, Yu-Hsing Wang

From this perspective and combined with further analyses, we found that to avoid mode collapse, the features extracted by the discriminator are not guided to be different for the real samples, but divergence without noise is indeed allowed and occupies a large proportion of the feature space.

Transfer Learning