Learning-Based Image Compression for Machines

TL;DR

This paper explores how to adapt learning-based image compression techniques to better serve machine learning tasks by incorporating task-specific features and finetuning methods.

Contribution

It introduces methods to fine-tune pretrained compression pipelines to retain salient features for downstream vision tasks, addressing standardization and feature retention issues.

Findings

Improved performance of vision tasks using compression-based pipelines.

Effective finetuning strategies for pretrained compression models.

Enhanced retention of salient features in compressed images.

Abstract

While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient features needed for such tasks. Decompression of images have taken a back seat in recent years while the focus has shifted to an image's utility in performing machine learning based analysis on top of them. Thus the demand for compression pipelines that incorporate such features from images has become ever present. The methods outlined in the report build on the recent work done on learning based image compression techniques to incorporate downstream tasks in them. We propose various methods of finetuning and enhancing different parts of pretrained compression encoding pipeline and present the results of our investigation regarding the performance of vision tasks using compression based pipelines.