Saliency Map-Guided End-to-End Image Coding for Machines
IEEE Signal Processing Letters · 2024 · 31 · 1755-1759
DOI: 10.1109/lsp.2024.3420178 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Bo Peng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref). Gefördert von: National Natural Science Foundation of China, Tianjin Research Innovation Project for Postgraduate Students.
Abstract (Originalsprache)
Existing end-to-end image coding for machines (ICM) methods generally use joint training strategies to promote the compression efficiency for machine vision without considering the influence of different regions in the image. To encourage the image compression network to focus on the regions that are critical to the subsequent visual task, this paper proposes a saliency map-guided image compression network (SMIC-Net) for ICM. Specifically, a saliency map-guided transform module (SMTM) is proposed to improve the representation ability of image features for object detection task by exploring the semantic and structural information of the detected object. Besides, a saliency map-guided mean square error (SM-MSE) loss is designed to place more emphasis on the detected object regions. Experimental results demonstrate that the proposed SMIC-Net effectively promotes the compression efficiency for machine vision.
Förderung
- National Natural Science Foundation of China
- Tianjin Research Innovation Project for Postgraduate Students
Zitieren
APA
Peng, B., Lin, T., Jin, D., Pan, Z., & Lei, J. (2024). Saliency Map-Guided End-to-End Image Coding for Machines. IEEE Signal Processing Letters, 31, 1755-1759. https://doi.org/10.1109/lsp.2024.3420178
Vancouver
Peng B, Lin T, Jin D, Pan Z, Lei J. Saliency Map-Guided End-to-End Image Coding for Machines. IEEE Signal Processing Letters. 2024;31:1755-1759. doi:10.1109/lsp.2024.3420178
BibTeX
@article{Peng2024,
author = {Peng, Bo and Lin, Tianxiang and Jin, Dengchao and Pan, Zhaoqing and Lei, Jianjun},
title = {Saliency Map-Guided End-to-End Image Coding for Machines},
journal = {IEEE Signal Processing Letters},
year = {2024},
volume = {31},
pages = {1755--1759},
doi = {10.1109/lsp.2024.3420178}
}
EUVIMED