Tempered Adversarial Networks
Mehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, and Bernhard Sch\"olkopf

TL;DR
This paper introduces a simple, generic modification to GAN training that balances the learning process by controlling the real data exposure, leading to improved stability and quality across various GAN architectures.
Contribution
A novel tempered learning approach that adjusts the exposure of real data to the discriminator, enhancing GAN training stability and performance.
Findings
Improved stability across multiple GAN variants.
Faster convergence in training.
Enhanced quality of generated samples.
Abstract
Generative adversarial networks (GANs) have been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset. We propose a simple modification that gives the generator control over the real samples which leads to a tempered learning process for both generator and discriminator. The real data distribution passes through a lens before being revealed to the discriminator, balancing the generator and discriminator by gradually revealing more detailed features necessary to produce high-quality results. The proposed module automatically…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Digital Media Forensic Detection · Advanced Image Processing Techniques
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings · *Communicated@Fast*How Do I Communicate to Expedia? · Batch Normalization · Dense Connections · HuMan(Expedia)||How do I get a human at Expedia? · GAN Least Squares Loss · LSGAN · Convolution · Dogecoin Customer Service Number +1-833-534-1729
