Device Interoperability for Learned Image Compression with Weights and Activations Quantization

TL;DR

This paper proposes a quantization method for learned image compression networks that ensures device interoperability with minimal performance loss, enabling error-free encoding and decoding across different hardware platforms.

Contribution

It introduces a simple quantization approach for entropy networks that guarantees cross-platform compatibility with negligible performance degradation.

Findings

Achieves 0.3% BD-rate deviation with quantization

Enables error-free encoding/decoding across CPUs and GPUs

Maintains state-of-the-art compression performance

Abstract

Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy parameters. We suggest a simple method which can ensure cross-platform encoding and decoding, and can be implemented quickly with minor performance deviation, of 0.3% BD-rate, from floating point model results.