Adversarial Feature Learning
Jeff Donahue, Philipp Krähenbühl, Trevor Jackson Darrell · arXiv (Cornell University) · 2016
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the data distribution. Intuitively, models trained to predict these semantic latent representations given data may serve as useful feature representations for auxiliary problems where semantics are relevant. However, in their existing form, GANs have no means of learning the inverse mapping -- projecting data back into the latent space. We propose Bidirectional Generative Adversarial Networks (BiGANs) as a means of learning this inverse mapping, and demonstrate that the resulting learned feature representation is useful for auxiliary supervised discrimination tasks, competitive with contemporary approaches to unsupervised and self-supervised feature learning.
Cited by 616 works. doi:10.48550/arxiv.1605.09782 Open-access PDF
Authors
References
- Gradient-based learning applied to document recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- ImageNet Large Scale Visual Recognition Challenge
- Fully convolutional networks for semantic segmentation
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- A Fast Learning Algorithm for Deep Belief Nets
- Reducing the Dimensionality of Data with Neural Networks
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Visualizing and Understanding Convolutional Networks
- Sequence to Sequence Learning with Neural Networks