Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.10.2024 · 20 (10) · 1-19
DOI: 10.1145/3678471 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 15.10.2024. Verfasst von Hanyue Tu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, GPU cluster built by MCC Lab of Information Science and Technology Institution, USTC.
Abstract (Originalsprache)
Reconstruction-free image compression for machine vision aims to perform machine vision tasks directly on compressed-domain representations instead of reconstructed images. Existing reports have validated the feasibility of compressed-domain machine vision. However, we observe that when using recently learned compression models, the performance gap between compressed-domain and pixel-domain vision tasks is still large due to the lack of some natural inductive biases in pixel-domain convolutional neural networks. In this article, we attempt to address this problem by transferring knowledge from the pixel domain to the compressed domain. A knowledge transfer loss defined at both output level and feature level is proposed to narrow the gap between the compressed domain and the pixel domain. In addition, we modify neural networks for pixel-domain vision tasks to better suit compressed-domain inputs. Experimental results on several machine vision tasks show that the proposed method improves the accuracy of compressed-domain vision tasks significantly, which even outperforms learning on reconstructed images while avoiding the computational cost of image reconstruction.
Förderung
- Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- GPU cluster built by MCC Lab of Information Science and Technology Institution, USTC
Zitieren
APA
Tu, H., Li, L., Zhou, W., & Li, H. (2024). Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(10), 1-19. https://doi.org/10.1145/3678471
Vancouver
Tu H, Li L, Zhou W, Li H. Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(10):1-19. doi:10.1145/3678471
BibTeX
@article{Tu2024,
author = {Tu, Hanyue and Li, Li and Zhou, Wengang and Li, Houqiang},
title = {Reconstruction-Free Image Compression for Machine Vision via Knowledge Transfer},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2024},
volume = {20},
number = {10},
pages = {1--19},
doi = {10.1145/3678471}
}
EUVIMED