Reducing The Amortization Gap of Entropy Bottleneck In End-to-End Image Compression

TL;DR

This paper introduces an instance-based parameterization method to reduce the amortization gap in entropy bottleneck models for end-to-end image compression, achieving a 1% bitrate improvement with minimal cost.

Contribution

It proposes a novel, simple method applicable to existing models to improve compression efficiency by reducing the amortization gap.

Findings

Achieves 1% bitrate reduction in image compression.

Applicable to any end-to-end compression method.

Minimal impact on reconstruction quality.

Abstract

End-to-end deep trainable models are about to exceed the performance of the traditional handcrafted compression techniques on videos and images. The core idea is to learn a non-linear transformation, modeled as a deep neural network, mapping input image into latent space, jointly with an entropy model of the latent distribution. The decoder is also learned as a deep trainable network, and the reconstructed image measures the distortion. These methods enforce the latent to follow some prior distributions. Since these priors are learned by optimization over the entire training set, the performance is optimal in average. However, it cannot fit exactly on every single new instance, hence damaging the compression performance by enlarging the bit-stream. In this paper, we propose a simple yet efficient instance-based parameterization method to reduce this amortization gap at a minor cost. The proposed method is applicable to any end-to-end compressing methods, improving the compression bitrate by 1% without any impact on the reconstruction quality.