Autoencoder based image compression: can the learning be quantization independent?
Image and Video Processing
2018-02-27 v1 Machine Learning
Signal Processing
Machine Learning
Abstract
This paper explores the problem of learning transforms for image compression via autoencoders. Usually, the rate-distortion performances of image compression are tuned by varying the quantization step size. In the case of autoen-coders, this in principle would require learning one transform per rate-distortion point at a given quantization step size. Here, we show that comparable performances can be obtained with a unique learned transform. The different rate-distortion points are then reached by varying the quantization step size at test time. This approach saves a lot of training time.
Cite
@article{arxiv.1802.09371,
title = {Autoencoder based image compression: can the learning be quantization independent?},
author = {Thierry Dumas and Aline Roumy and Christine Guillemot},
journal= {arXiv preprint arXiv:1802.09371},
year = {2018}
}
Comments
International Conference on Acoustics, Speech and Signal Processing ICASSP, Apr 2018, Calgary, Canada. 2018