papers AI Learner
The Github is limit! Click to go to the new site.

Semi-Supervised Learning with IPM-based GANs: an Empirical Study

2017-12-07
Tom Sercu, Youssef Mroueh

Abstract

We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning. IPM-based GANs like Wasserstein GAN, Fisher GAN and Sobolev GAN have desirable properties in terms of theoretical understanding, training stability, and a meaningful loss. In this work we investigate how the design of the critic (or discriminator) influences the performance in semi-supervised learning. We distill three key take-aways which are important for good SSL performance: (1) the K+1 formulation, (2) avoiding batch normalization in the critic and (3) avoiding gradient penalty constraints on the classification layer.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1712.02505

PDF

https://arxiv.org/pdf/1712.02505


Similar Posts

Comments