Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation

TL;DR

This paper introduces RepGAN, an unsupervised adversarial network that learns disentangled representations capable of semantic generation, clustering, and reconstruction, demonstrating state-of-the-art results on multiple datasets.

Contribution

It proposes a novel symmetric adversarial framework for joint learning of data-to-representation mappings, enabling multiple tasks simultaneously in an unsupervised manner.

Findings

Achieves high unsupervised classification accuracy on MNIST.

Demonstrates low reconstruction error across datasets.

Shows competitive performance in generation and clustering tasks.

Abstract

A good representation for arbitrarily complicated data should have the capability of semantic generation, clustering and reconstruction. Previous research has already achieved impressive performance on either one. This paper aims at learning a disentangled representation effective for all of them in an unsupervised way. To achieve all the three tasks together, we learn the forward and inverse mapping between data and representation on the basis of a symmetric adversarial process. In theory, we minimize the upper bound of the two conditional entropy loss between the latent variables and the observations together to achieve the cycle consistency. The newly proposed RepGAN is tested on MNIST, fashionMNIST, CelebA, and SVHN datasets to perform unsupervised classification, generation and reconstruction tasks. The result demonstrates that RepGAN is able to learn a useful and competitive representation. To the author's knowledge, our work is the first one to achieve both a high unsupervised classification accuracy and low reconstruction error on MNIST. Codes are available at https://github.com/yzhouas/RepGAN-tensorflow.