MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-03 · 46 (3) · 1576-1588
DOI: 10.1109/tpami.2021.3133897 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-03. Verfasst von Hanbin Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 115-mal zitiert (Crossref) und nennt 98 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge. In this paper, we concentrate on this "slow versus fast" (SvF) dilemma to determine which knowledge components to be updated in a slow fashion or a fast fashion, and thereby balance old-knowledge preservation and new-knowledge adaptation. We propose a multi-grained SvF learning strategy to cope with the SvF dilemma from two different grains: intra-space (within the same feature space) and inter-space (between two different feature spaces). The proposed strategy designs a novel frequency-aware regularization to boost the intra-space SvF capability, and meanwhile develops a new feature space composition operation to enhance the inter-space SvF learning performance. With the multi-grained SvF learning strategy, our method outperforms the state-of-the-art approaches by a large margin.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
- Key Scientific Technological Innovation Research Project
- Zhejiang University K.P.Chao's High Technology Development Foundation
- Zhejiang Lab's Open Fund
- Zhejiang Laboratory
Zitieren
APA
Zhao, H., Fu, Y., Kang, M., Tian, Q., Wu, F., & Li, X. (2024). MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(3), 1576-1588. https://doi.org/10.1109/tpami.2021.3133897
Vancouver
Zhao H, Fu Y, Kang M, Tian Q, Wu F, Li X. MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(3):1576-1588. doi:10.1109/tpami.2021.3133897
BibTeX
@article{Zhao2024,
author = {Zhao, Hanbin and Fu, Yongjian and Kang, Mintong and Tian, Qi and Wu, Fei and Li, Xi},
title = {MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {3},
pages = {1576--1588},
doi = {10.1109/tpami.2021.3133897}
}
EUVIMED