← Back to papers
2020 WACV WACV 2020

CoachGAN

Abstract

CoachGAN provides an inference time method to improve outputs from GAN generator models. Similar to creating adversarial examples to fool neural network classifiers, CoachGAN exploits gradient information, in this case from a pretrained discriminator model. Unlike the process of generating adversarial examples, which uses gradient descent to alter outputs directly, CoachGAN alters the inputs of generator models. This allows for output enhancements at test time without any additional model training. CoachGAN adapts easily to existing algorithms and does not depend on specific model architectures. In addition to qualitative samples, we quantitatively demonstrate the ability of CoachGAN to improve IS and FID scores across a variety of GAN architectures and tasks.

🚀 Conference Pioneer — WACV 2020
🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — generator model
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Mike Brodie

Topics

Machine Learning > Learning Types > Adversarial Learning Deep Learning > Models > Generative Models

Keywords

gradient descent generative adversarial network adversarial example inference time generator model discriminator model
Download PDF

Related papers

Global Co-occurrence Feature Learning and Active Coordinate System Conversion for Skeleton-based Action Recognition 2020
A one-and-half stage pedestrian detector 2020
ImaGINator: Conditional Spatio-Temporal GAN for Video Generation 2020
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion 2020
Active Learning for Imbalanced Datasets 2020