Asymptotic Feature Pyramid Network for Labeling Pixels and Regions
IEEE Transactions on Circuits and Systems for Video Technology · 2024-09 · 34 (9) · 7820-7829
DOI: 10.1109/tcsvt.2024.3376773 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-09. Verfasst von Guoyu Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 105-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Zhejiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
Multi-scale features are crucial in encoding objects with varying scales in vision tasks. The classic top-down and bottom-up feature pyramid networks are a common strategy for multi-scale feature extraction. However, these approaches suffer from the loss or degradation of feature information, which impairs the fusion effect of non-adjacent levels. In this paper, we propose an Asymptotic Feature Pyramid Network (AFPN) that supports direct interaction between non-adjacent levels. AFPN starts by fusing two adjacent low-level features and asymptotic incorporates higher-level features into the fusion process. This fusion way avoids the significant semantic gap between non-adjacent levels. Adaptive spatial fusion operation is further used to mitigate potential multi-object information conflicts during feature fusion at each spatial location. To reduce parameters, computational requirements, and inference speed, we propose a Lightweight Asymptotic Feature Pyramid Network (LightAFPN) that uses the concept of reparametrization. We evaluate the proposed method on the MS-COCO 2017, PASCAL VOC and Cityscapes datasets in both object detection and semantic segmentation frameworks. Experimental evaluation shows that our method achieves more competitive results than other state-of-the-art feature pyramid networks. The code is available at https://github.com/gyyang23/AFPN.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Zhejiang Provincial Natural Science Foundation of China
Zitieren
APA
Yang, G., Lei, J., Tian, H., Feng, Z., & Liang, R. (2024). Asymptotic Feature Pyramid Network for Labeling Pixels and Regions. IEEE Transactions on Circuits and Systems for Video Technology, 34(9), 7820-7829. https://doi.org/10.1109/tcsvt.2024.3376773
Vancouver
Yang G, Lei J, Tian H, Feng Z, Liang R. Asymptotic Feature Pyramid Network for Labeling Pixels and Regions. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(9):7820-7829. doi:10.1109/tcsvt.2024.3376773
BibTeX
@article{Yang2024,
author = {Yang, Guoyu and Lei, Jie and Tian, Hao and Feng, Zunlei and Liang, Ronghua},
title = {Asymptotic Feature Pyramid Network for Labeling Pixels and Regions},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {34},
number = {9},
pages = {7820--7829},
doi = {10.1109/tcsvt.2024.3376773}
}
EUVIMED