A Rate-Distortion-Classification Approach for Lossy Image Compression

TL;DR

This paper introduces a unified Rate-Distortion-Classification model for lossy image compression that balances compression rate, image quality, and classification accuracy, with theoretical analysis and practical implications.

Contribution

It proposes a novel RDC framework that integrates semantic classification into the compression process, bridging image compression and visual analysis.

Findings

RDC model shows monotonic and convex properties under certain conditions.

Experimental results on MNIST validate the model's effectiveness.

Insights for human-machine friendly and VCM compression methods.

Abstract

In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized the significance of considering semantic distortion in compressed images. To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion-Classification (RDC) model for lossy image compression, offering a unified framework to optimize the trade-off between rate, distortion, and classification accuracy. The RDC model is extensively analyzed both statistically on a multi-distribution source and experimentally on the widely used MNIST dataset. The findings reveal that the RDC model exhibits desirable properties, including monotonic non-increasing and convex functions, under certain conditions. This work provides insights into the development of human-machine friendly compression methods and Video Coding for Machine (VCM) approaches, paving the way for end-to-end image compression techniques in real-world applications.