MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning

TL;DR

This paper introduces a multi-grained slow versus fast framework for few-shot class-incremental learning, balancing knowledge retention and adaptation through intra-space and inter-space strategies, achieving superior performance.

Contribution

It proposes a novel multi-grained SvF learning strategy with frequency-aware regularization and feature space composition for improved FSCIL.

Findings

Outperforms state-of-the-art methods significantly

Effective balance between old knowledge retention and new knowledge adaptation

Demonstrates robustness across different FSCIL scenarios

Abstract

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 vs. 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.