[2006.02595] Image Augmentations for GAN Trainingopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Data augmentations have been widely studied to improve the accuracy and robustness of classifiers. However, the potential of image augmentation in improving GAN models for image synthesis has not been thoroughly investigated in previous studies. In this work, we systematically study the effectiveness of various existing augmentation techniques for GAN training in a variety of settings. We provide insights and guidelines on how to augment images for both vanilla GANs and GANs with regularizations, improving the fidelity of the generated images substantially. Surprisingly, we find that vanilla GANs attain generation quality on par with recent state-of-the-art results if we use augmentations on both real and generated images. When this GAN training is combined with other augmentation-based regularization techniques, such as contrastive loss and consistency regularization, the augmentations further improve the quality of generated images. We provide new state-of-the-art results for conditi

1 mentions: @oct_path
Keywords: gan
Date: 2020/09/15 12:59

Referring Tweets

@oct_path GANの学習時にContrastive Loss等々を組み込む研究は見つけた t.co/4ArBiXxWpn

Related Entries

Read more [2002.04672] Object Detection as a Positive-Unlabeled Problemcontact arXivarXiv Twitter
0 users, 1 mentions 2020/02/14 20:21
Read more Google Cloud & NCAA® ML Competition 2020-NCAAM | Kaggle
0 users, 1 mentions 2020/02/18 23:21
Read more ALASKA2 Image Steganalysis | Kaggle
0 users, 1 mentions 2020/04/27 21:51
Read more [1607.07590] Simultaneous Estimation of Noise Variance and Number of Peaks in Bayesian Spectral Deco...
0 users, 1 mentions 2020/06/07 02:21
Read more SIIM-ISIC Melanoma Classification | Kaggle
0 users, 1 mentions 2020/08/09 02:21