Evolving and Regularizing Meta-Environment Learner for Fine-Grained Few-Shot Class-Incremental Learning

Recently proposed Fine-Grained Few-Shot Class-Incremental Learning (FG-FSCIL) offers a practical and efficient solution for enabling models to incrementally learn new fine-grained categories under limited data conditions. However, existing methods still settle for the fine-grained feature extraction capabilities learned from the base classes. Unlike conventional datasets, fine-grained categories exhibit subtle inter-class variations, naturally fostering latent synergy among sub-categories. Meanwhile, the incremental learning framework offers an opportunity to progressively strengthen this synergy by incorporating new sub-category data over time. Motivated by this, we theoretically formulate the FSCIL problem and derive a generalization error bound within a shared fine-grained meta-category environment. Guided by our theoretical insights, we design a novel Meta-Environment Learner (MEL) for FG-FSCIL, which evolves fine-grained feature extraction to enhance meta-environment understanding and simultaneously regularizes hypothesis space complexity. Extensive experiments demonstrate that our method consistently and significantly outperforms existing approaches.

Authors

• Li-Jun Zhao Shandong University
• Zhen-Duo Chen Shandong University
• Yongxin Wang
• Xin Luo University of Science and Technology of China
• Xin-Shun Xu Shandong University

Keywords

No keywords are indexed for this paper.