Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning

TL;DR

This paper analyzes the separate performances of base and novel classes in few-shot class-incremental learning, proposing a simple normalized prototype classifier method that achieves competitive results without additional training.

Contribution

It introduces a parameter decomposition analysis for FSCIL and proposes NoNPC, a training-free normalized prototype classifier for incremental learning.

Findings

NoNPC achieves comparable performance to state-of-the-art methods.

Parameter tendencies for base and novel performances vary significantly with updates.

Decomposition analysis provides insights into FSCIL performance dynamics.

Abstract

Few-shot class-incremental learning (FSCIL) has addressed challenging real-world scenarios where unseen novel classes continually arrive with few samples. In these scenarios, it is required to develop a model that recognizes the novel classes without forgetting prior knowledge. In other words, FSCIL aims to maintain the base performance and improve the novel performance simultaneously. However, there is little study to investigate the two performances separately. In this paper, we first decompose the entire model into four types of parameters and demonstrate that the tendency of the two performances varies greatly with the updated parameters when the novel classes appear. Based on the analysis, we propose a simple method for FSCIL, coined as NoNPC, which uses normalized prototype classifiers without further training for incremental novel classes. It is shown that our straightforward method has comparable performance with the sophisticated state-of-the-art algorithms.