Learned Image Compression for Machine Perception

TL;DR

This paper introduces a learned image compression method optimized for both human perception and machine vision tasks, achieving smaller representations with maintained or improved performance on segmentation and detection.

Contribution

It develops a novel framework for compressing images that enhances performance on vision tasks while reducing data size, surpassing traditional JPEGs.

Findings

Outperforms JPEG in segmentation and detection accuracy.

Achieves 4-10x smaller representations with minimal performance loss.

Supports training models directly from compressed representations.

Abstract

Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing applications of computer vision, high quality image reconstruction from a compressible representation is often a secondary objective. Compression that ensures high accuracy on computer vision tasks such as image segmentation, classification, and detection therefore has the potential for significant impact across a wide variety of settings. In this work, we develop a framework that produces a compression format suitable for both human perception and machine perception. We show that representations can be learned that simultaneously optimize for compression and performance on core vision tasks. Our approach allows models to be trained directly from compressed representations, and this approach yields increased performance on new tasks and in low-shot learning settings. We present results that improve upon segmentation and detection performance compared to standard high quality JPGs, but with representations that are four to ten times smaller in terms of bits per pixel. Further, unlike naive compression methods, at a level ten times smaller than standard JEPGs, segmentation and detection models trained from our format suffer only minor degradation in performance.