Oral
High-Fidelity Image Generation With Fewer Labels
Mario Lucic · Michael Tschannen · Marvin Ritter · Xiaohua Zhai · Olivier Bachem · Sylvain Gelly

Tue Jun 11th 02:25 -- 02:30 PM @ Hall A

Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images at high resolution, they rely on a vast quantity of labeled data. In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform state-of-the-art on both unsupervised ImageNet synthesis, as well as in the conditional setting. In particular, the proposed approach is able to match the sample quality (as measured by FID) of the current state-of-the art conditional model BigGAN on ImageNet using only 10% of the labels and outperform it using 20% of the labels.

Author Information

Mario Lucic (Google Brain)
Michael Tschannen (Google Brain)
Marvin Ritter (Google Brain)
Xiaohua Zhai (Google Brain)
Olivier Bachem (Google Brain)
Sylvain Gelly (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors