Self-Supervised GANs via Auxiliary Rotation Loss

Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labeled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs. In particular, we allow the networks to collaborate on the task of representation learning, while being adversarial with respect to the classic GAN game. The role of self-supervision is to encourage the discriminator to learn meaningful feature representations which are not forgotten during training. We test empirically both the quality of the learned image representations, and the quality of the synthesized images. Under the same conditions, the self-supervised GAN attains a similar performance to state-of-the-art conditional counterparts. Finally, we show that this approach to fully unsupervised learning can be scaled to attain an FID of 23.4 on unconditional ImageNet generation.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation CelebA-HQ 128x128 SS-GAN (sBN) FID 24.36 # 6
Image Generation CIFAR-10 SS-GAN (sBN) FID 15.65 # 66
Image Generation ImageNet 128x128 SS-GAN (sBN) FID 43.87 # 12
Image Generation LSUN Bedroom 256 x 256 SS-GAN (sBN) FID 13.3 # 12