Deep learning-based feature compression for video coding for machine

Jihoon Do; Jooyoung Lee; Younhee Kim; Se Yoon Jeong; Jin Soo Choi

doi:10.1117/12.2626099

30 April 2022 Deep learning-based feature compression for video coding for machine

Jihoon Do, Jooyoung Lee, Younhee Kim, Se Yoon Jeong, Jin Soo Choi

Proceedings Volume 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022; 121773B (2022) https://doi.org/10.1117/12.2626099
Event: International Workshop on Advanced Imaging Technology 2022 (IWAIT 2022), 2022, Hong Kong, China

Abstract

We previously trained the compression network via optimization of bit-rate and distortion (feature domain MSE) [1]. In this paper, we propose feature map compression method for video coding for machine (VCM) based on deep learning-based compression network that joint training for optimizing both compressed bit rate and machine vision task performance. We use bmshij2018-hyperporior model in the CompressAI [2] as the compression network, and compress the feature map which is the output of stem layer in the Faster R-CNN X101-FPN network of Detectron2 [3]. We evaluated the proposed method by evaluation framework for MPEG VCM. The proposed method shows the better results than VVC of MPEG VCM anchor.

Citation Download Citation

Jihoon Do, Jooyoung Lee, Younhee Kim, Se Yoon Jeong, and Jin Soo Choi "Deep learning-based feature compression for video coding for machine", Proc. SPIE 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022, 121773B (30 April 2022); https://doi.org/10.1117/12.2626099

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Video

Video compression

Machine vision

Distortion

Image compression

Signal processing

Video coding

Show All Keywords

Keywords/Phrases

Search In:

Publication Years