Online Meta Adaptation for Variable-Rate Learned Image Compression

TL;DR

This paper proposes an online meta-learning approach for learned image compression that enables variable-rate compression and reduces train-test mismatch, improving adaptability and performance with minimal overhead.

Contribution

It introduces an online meta-learning framework within LIC that adaptively tunes compression quality and bridges the gap between training and true quantization.

Findings

Enhanced compression performance across state-of-the-art LIC methods.

Effective adaptation to different image qualities with minimal additional computation.

Reduced train-test mismatch in learned image compression.

Abstract

This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization. We introduce an online meta-learning (OML) setting for LIC, which combines ideas from meta learning and online learning in the conditional variational auto-encoder (CVAE) framework. By treating the conditional variables as meta parameters and treating the generated conditional features as meta priors, the desired reconstruction can be controlled by the meta parameters to accommodate compression with variable qualities. The online learning framework is used to update the meta parameters so that the conditional reconstruction is adaptively tuned for the current image. Through the OML mechanism, the meta parameters can be effectively updated through SGD. The conditional reconstruction is directly based on the quantized latent representation in the decoder network, and therefore helps to bridge the gap between the training estimation and true quantized latent distribution. Experiments demonstrate that our OML approach can be flexibly applied to different state-of-the-art LIC methods to achieve additional performance improvements with little computation and transmission overhead.