Deep Image Compression Toward Machine Vision: A Unified Optimization Framework
IEEE Transactions on Circuits and Systems for Video Technology · 2023-06 · 33 (6) · 2979-2989
DOI: 10.1109/tcsvt.2022.3230843 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-06. Verfasst von Shurun Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hong Kong Research Grants Council, General Research Fund, Alibaba Innovative Research.
Abstract (Originalsprache)
There has been an increasing consensus that the machine vision is gradually replacing human vision in numerous tasks, with the demonstrated success of artificial intelligence. In this paper, we propose a deep image compression scheme towards machine vision, with the principle of “begin with the end in mind”. In particular, a unified optimization scheme for end-to-end image compression towards machine vision is proposed, accompanied with the dedicated variable bitrate coding and generalized rate-accuracy optimization. The presented framework, which jointly optimizes the compression and the machine vision networks, exploits the utmost potential of robust machine vision for compressed images. The variable bitrate modules towards machine vision, which effectively shrink the storage space for model parameters, are further developed to accommodate to the real-world applications. Moreover, an iterative algorithm is presented to achieve the optimality in terms of the generalized rate-accuracy towards machine vision. Experimental results show that the proposed framework achieves the state-of-the-art object detection performance among the end-to-end image compression methods: in the exploration of Video Coding for Machines (VCM) in Moving Picture Experts Group (MPEG), and the proposed framework achieves 31.69% and 23.96% BD-rate gains compared with the VCM official test datasets, the Open Images dataset and the TVD dataset respectively, which are generated using the state-of-the-art standard Versatile Video Coding (VVC) standard. The generalization capability of the proposed framework is also verified with instance segmentation under various scenarios.
Förderung
- National Natural Science Foundation of China
- Hong Kong Research Grants Council, General Research Fund
- Alibaba Innovative Research
Zitieren
APA
Wang, S., Wang, Z., Wang, S., & Ye, Y. (2023). Deep Image Compression Toward Machine Vision: A Unified Optimization Framework. IEEE Transactions on Circuits and Systems for Video Technology, 33(6), 2979-2989. https://doi.org/10.1109/tcsvt.2022.3230843
Vancouver
Wang S, Wang Z, Wang S, Ye Y. Deep Image Compression Toward Machine Vision: A Unified Optimization Framework. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(6):2979-2989. doi:10.1109/tcsvt.2022.3230843
BibTeX
@article{Wang2023,
author = {Wang, Shurun and Wang, Zhao and Wang, Shiqi and Ye, Yan},
title = {Deep Image Compression Toward Machine Vision: A Unified Optimization Framework},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2023},
volume = {33},
number = {6},
pages = {2979--2989},
doi = {10.1109/tcsvt.2022.3230843}
}
EUVIMED