Learning-Based Image Compression for Machines

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gupta, Kartik, Faria, Kimberley, Mehta, Vikas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914959777071104
author Gupta, Kartik
Faria, Kimberley
Mehta, Vikas
author_facet Gupta, Kartik
Faria, Kimberley
Mehta, Vikas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19184
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning-Based Image Compression for Machines
Gupta, Kartik
Faria, Kimberley
Mehta, Vikas
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
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.
title Learning-Based Image Compression for Machines
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2409.19184