ADIS-GAN: Affine Disentangled GAN

Letao Liu, Martin Saerbeck, Justin Dauwels

Keywords: Deep Learning, Disentangled Representation, Generative Adversarial Network, Computer Vision

Abstract: This paper proposes Affine Disentangled GAN (ADIS-GAN), which is a Generative Adversarial Network that can explicitly disentangle affine transformations in a self-supervised and rigorous manner. The objective is inspired by InfoGAN, where an additional affine regularizer acts as the inductive bias. The affine regularizer is rooted in the affine transformation properties of images, changing some properties of the underlying images, while leaving all other properties invariant. We derive the affine regularizer by decomposing the affine matrix into separate transformation matrices and inferring the transformation parameters by maximum-likelihood estimation. Unlike the disentangled representations learned by existing approaches, the features learned by ADIS-GAN are axis-aligned and scalable, where transformations such as rotation, horizontal and vertical zoom, horizontal and vertical skew, horizontal and vertical translation can be explicitly selected and learned. ADIS-GAN successfully disentangles these features on the MNIST, CelebA, and dSprites datasets.

One-sentence Summary: A Generative Adversarial Network that can explicitly disentangle affine transformations in a self-supervised and rigorous manner.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=jN5K6PG7n-