Soft then Hard: Rethinking the Quantization in Neural Image Compression
Abstract
Quantization is one of the core components in lossy image compression. For neural image compression, end-to-end optimization requires differentiable approximations of quantization, which can generally be grouped into three categories: additive uniform noise, straight-through estimator and soft-to-hard annealing. Training with additive uniform noise approximates the quantization error variationally but suffers from the train-test mismatch. The other two methods do not encounter this mismatch but, as shown in this paper, hurt the rate-distortion performance since the latent representation ability is weakened. We thus propose a novel soft-then-hard quantization strategy for neural image compression that first learns an expressive latent space softly, then closes the train-test mismatch with hard quantization. In addition, beyond the fixed integer quantization, we apply scaled additive uniform noise to adaptively control the quantization granularity by deriving a new variational upper bound on actual rate. Experiments demonstrate that our proposed methods are easy to adopt, stable to train, and highly effective especially on complex compression models.
Keywords
Cite
@article{arxiv.2104.05168,
title = {Soft then Hard: Rethinking the Quantization in Neural Image Compression},
author = {Zongyu Guo and Zhizheng Zhang and Runsen Feng and Zhibo Chen},
journal= {arXiv preprint arXiv:2104.05168},
year = {2024}
}
Comments
Updated with a description on the high-rate assumption