Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation

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.

[1]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[2]  Alexei A. Efros,et al.  Toward Multimodal Image-to-Image Translation , 2017, NIPS.

[3]  Stefano Ermon,et al.  InfoVAE: Balancing Learning and Inference in Variational Autoencoders , 2019, AAAI.

[4]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[5]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[6]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.

[7]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[8]  Yuandong Tian,et al.  Channel-Recurrent Variational Autoencoders , 2017, ArXiv.

[9]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[10]  Huachun Tan,et al.  Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering , 2016, IJCAI.

[11]  Andrew Brock,et al.  Neural Photo Editing with Introspective Adversarial Networks , 2016, ICLR.

[12]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[13]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[14]  Ali Farhadi,et al.  Unsupervised Deep Embedding for Clustering Analysis , 2015, ICML.

[15]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[16]  Lawrence Carin,et al.  ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching , 2017, NIPS.

[17]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[18]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[19]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[20]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[21]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[22]  Lior Wolf,et al.  Unsupervised Cross-Domain Image Generation , 2016, ICLR.

[23]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[24]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[25]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[26]  Yuandong Tian,et al.  Channel-Recurrent Autoencoding for Image Modeling , 2018, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[27]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[28]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[29]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .