A Rate-Distortion-Classification Approach for Lossy Image Compression
This work addresses the need for compression methods that consider semantic distortion for visual analysis applications, such as classification tasks, which is an incremental advancement in bridging image compression and machine vision.
The paper tackles the problem of lossy image compression by proposing a Rate-Distortion-Classification (RDC) model to optimize trade-offs between bit rate, distortion, and classification accuracy, with experimental validation on the MNIST dataset showing desirable properties like monotonic non-increasing and convex functions under certain conditions.
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.