A Super-Resolution-Based Feature Map Compression for Machine-Oriented Video Coding
Lists
Only you see this
Abstract
Recently, video and image compression methods using neural networks have received much attention. In MPEG standardization, Video Coding for Machine (VCM) is a newly arising topic which attempts to compress features/images for the purpose of machine vision tasks. Especially, compressing features has advantages in terms of privacy protection and computation off-loading. In this paper, we propose an effective feature compression method equipped with a super-resolution (SR) module for features. Our main motivation comes from the observation that features are somewhat robust to spatial distortions (e.g., AWGN, blur, quantization distortions, coding artifacts), which leads us to integrating an SR module into the compression framework. We also further explore the best training strategy of the proposed method, i.e., finding the best combination of various losses and proper input feature shapes. Our comprehensive experiments show that the proposed method outperforms the baseline in the original VCM anchor scenario on various QP values with Versatile Video Coding (VVC). Specifically, the proposed framework achieved up to 50% BD-rate reduction compared to the conventional P-layer feature map compression method for the object detection task on the OpenImage dataset.
BibTeX
@inproceedings{kang2023super,
author = {Jung Heum Kang and Muhammad Salman Ali and Hye-Won Jeong and Chang-Kyun Choi and Younhee Kim and Se-Yoon Jeong and Sung-Ho Bae and Hui Yong Kim},
title = {{A Super-Resolution-Based Feature Map Compression for Machine-Oriented Video Coding}},
booktitle = {IEEE Access},
year = {2023},
url = {https://openreview.net/forum?id=DIDCh2izxY},
}Loading related content...