Deep Generative Models for Distribution-Preserving Lossy Compression
arXiv:1805.11057
Abstract
We propose and study the problem of distribution-preserving lossy compression. Motivated by recent advances in extreme image compression which allow to maintain artifact-free reconstructions even at very low bitrates, we propose to optimize the rate-distortion tradeoff under the constraint that the reconstructed samples follow the distribution of the training data. The resulting compression system recovers both ends of the spectrum: On one hand, at zero bitrate it learns a generative model of the data, and at high enough bitrates it achieves perfect reconstruction. Furthermore, for intermediate bitrates it smoothly interpolates between learning a generative model of the training data and perfectly reconstructing the training samples. We study several methods to approximately solve the proposed optimization problem, including a novel combination of Wasserstein GAN and Wasserstein Autoencoder, and present an extensive theoretical and empirical characterization of the proposed compression systems.
arXiv commentNIPS 2018. Code: https://github.com/mitscha/dplc . Changes w.r.t. v1: Some clarifications in the text and additional numerical results
References in corpus (20)
- Auto-Encoding Variational Bayes
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Improved Training of Wasserstein GANs
- Variational image compression with a scale hyperprior
- End-to-end Optimized Image Compression
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Toward Multimodal Image-to-Image Translation
- Adversarial Feature Learning
- Adversarially Learned Inference
- Autoencoding beyond pixels using a learned similarity metric
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Lossy Image Compression with Compressive Autoencoders
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Variable Rate Image Compression with Recurrent Neural Networks
- Real-Time Adaptive Image Compression
- Towards Image Understanding from Deep Compression without Decoding
- Towards Conceptual Compression
- Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
- Video Compression through Image Interpolation