An Information-Theoretic Regularizer for Lossy Neural Image Compression

TL;DR

This paper introduces an information-theoretic regularizer for neural image compression that improves model regularization and reduces bit rates by leveraging a novel entropy-based insight, without increasing inference complexity.

Contribution

It proposes a new regularization method based on conditional source entropy, enhancing neural image compression performance and generalization.

Findings

Regularizer improves compression efficiency across models.

Enhances model generalization to unseen domains.

No additional inference overhead introduced.

Abstract

Lossy image compression networks aim to minimize the latent entropy of images while adhering to specific distortion constraints. However, optimizing the neural network can be challenging due to its nature of learning quantized latent representations. In this paper, our key finding is that minimizing the latent entropy is, to some extent, equivalent to maximizing the conditional source entropy, an insight that is deeply rooted in information-theoretic equalities. Building on this insight, we propose a novel structural regularization method for the neural image compression task by incorporating the negative conditional source entropy into the training objective, such that both the optimization efficacy and the model's generalization ability can be promoted. The proposed information-theoretic regularizer is interpretable, plug-and-play, and imposes no inference overheads. Extensive experiments demonstrate its superiority in regularizing the models and further squeezing bits from the latent representation across various compression structures and unseen domains.