RPGAN: GANs Interpretability via Random Routing
arXiv:1912.10920
Abstract
In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) -- an alternative design of GANs that can serve as a tool for generative model analysis. While the latent space of a typical GAN consists of input vectors, randomly sampled from the standard Gaussian distribution, the latent space of RPGAN consists of random paths in a generator network. As we show, this design allows to understand factors of variation, captured by different generator layers, providing their natural interpretability. With experiments on standard benchmarks, we demonstrate that RPGAN reveals several interesting insights about the roles that different layers play in the image generation process. Aside from interpretability, the RPGAN model also provides competitive generation quality and allows efficient incremental learning on new data.
References in corpus (8)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Axiomatic Attribution for Deep Networks
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
- Assessing Generative Models via Precision and Recall
- Video-to-Video Synthesis
- Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis