End-to-End Optimization of JPEG-Based Deep Learning Process for Image Classification

TL;DR

This paper presents an end-to-end trainable model that optimizes JPEG image compression specifically for deep learning classification tasks, improving accuracy under bandwidth constraints.

Contribution

It introduces a novel integrated model combining JPEG compression and deep learning classification, optimizing JPEG settings for better DL task performance.

Findings

Improved validation accuracy on CIFAR-100 and ImageNet datasets.

Optimized JPEG settings enhance classification accuracy under bandwidth constraints.

Demonstrated effectiveness of end-to-end training for compression and classification.

Abstract

Among major deep learning (DL) applications, distributed learning involving image classification require effective image compression codecs deployed on low-cost sensing devices for efficient transmission and storage. Traditional codecs such as JPEG designed for perceptual quality are not configured for DL tasks. This work introduces an integrative end-to-end trainable model for image compression and classification consisting of a JPEG image codec and a DL-based classifier. We demonstrate how this model can optimize the widely deployed JPEG codec settings to improve classification accuracy in consideration of bandwidth constraint. Our tests on CIFAR-100 and ImageNet also demonstrate improved validation accuracy over preset JPEG configuration.