[1910.12027] Consistency Regularization for Generative Adversarial Networks

Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization---a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of the discriminator to these augmentations. We conduct a series of experiments to demonstrate that consistency regularization works effectively with spectral normalization and various GAN architectures, loss functions and optimizer settings. Our method achieves the best FID scores for unconditional image generation compared to other regularization methods on CIFAR-10 and CelebA. Moreover, Our consis

5 mentions: @gstsdn@AkiraTOSEI@roadrunning01@gstsdn
Date: 2019/11/06 12:52

Referring Tweets

@AkiraTOSEI t.co/IgT1THqGCy 画像に変換を加える前後でDiscriminatorの出力値が変化しないように制約をかける(Consistency Regularization)それにより、GANの学習を安定/高性能化させることが可能。実装もシンプルならが効果も強力。 t.co/wwQ3Dw0ApF
@gstsdn @Han_Zhang_ has new research (w/ @ZizhaoZhang, @honglaklee and me) that sets a new state-of-the art in conditional image synthesis by using consistency regularization on GANs: t.co/5sNofjuUWa. Thread follows: t.co/FLjLk4R4TL
@roadrunning01 Consistency Regularization for Generative Adversarial Networks pdf: t.co/i4Sl32KsaT abs: t.co/avsHXYN6gk t.co/PfKhPVek6B

Related Entries

Read more Generative Adversarial Networksの基礎と応用について
1 users, 3 mentions 2019/10/24 15:49
Read more StyleGAN: A Style-Based Generator Architecture for Generative Adversarial Networksの実装 - 機械学習奮闘記
5 users, 2 mentions 2019/03/06 11:14
Read more [1811.11264] Synthesizing Tabular Data using Generative Adversarial Networks
1 users, 1 mentions 2019/08/18 11:16
Read more Data Synthesis based on Generative Adversarial Networks (VLDB 2018) 読んだ - 糞糞糞ネット弁慶
0 users, 0 mentions 2019/08/25 10:49
Read more Generative Adversarial Networks @ ICML 2019
5 users, 2 mentions 2019/07/21 11:16