Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (12) · 13581-13589
DOI: 10.1609/aaai.v38i12.29262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Mengke Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref).
Abstract (Originalsprache)
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.
Zitieren
APA
Li, M., HU, Z., Lu, Y., Lan, W., Cheung, Y., & Huang, H. (2024). Feature Fusion from Head to Tail for Long-Tailed Visual Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 38(12), 13581-13589. https://doi.org/10.1609/aaai.v38i12.29262
Vancouver
Li M, HU Z, Lu Y, Lan W, Cheung Y, Huang H. Feature Fusion from Head to Tail for Long-Tailed Visual Recognition. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(12):13581-13589. doi:10.1609/aaai.v38i12.29262
BibTeX
@article{Li2024,
author = {Li, Mengke and HU, Zhikai and Lu, Yang and Lan, Weichao and Cheung, Yiu-ming and Huang, Hui},
title = {Feature Fusion from Head to Tail for Long-Tailed Visual Recognition},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {12},
pages = {13581--13589},
doi = {10.1609/aaai.v38i12.29262}
}
EUVIMED