Class Balance Matters to Active Class-Incremental Learning

TL;DR

This paper introduces Active Class-Incremental Learning (ACIL), a method that selects the most informative and class-balanced samples from unlabeled data to improve incremental learning performance, addressing class imbalance issues.

Contribution

The paper proposes a novel Class-Balanced Selection (CBS) strategy that ensures class balance and informativeness in sample selection for ACIL, enhancing incremental learning effectiveness.

Findings

CBS outperforms random and SOTA active learning methods across five datasets.

The clustering-based selection maintains class balance and informativeness.

ACIL with CBS improves incremental learning performance significantly.

Abstract

Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may not always cover the most informative samples, which largely restricts the capability of incremental learner. We aim to start from a pool of large-scale unlabeled data and then annotate the most informative samples for incremental learning. Based on this premise, this paper introduces the Active Class-Incremental Learning (ACIL). The objective of ACIL is to select the most informative samples from the unlabeled pool to effectively train an incremental learner, aiming to maximize the performance of the resulting model. Note that vanilla active learning algorithms suffer from class-imbalanced distribution among annotated samples, which restricts the ability of incremental learning. To achieve both class balance and informativeness in chosen samples, we propose Class-Balanced Selection (CBS) strategy. Specifically, we first cluster the features of all unlabeled images into multiple groups. Then for each cluster, we employ greedy selection strategy to ensure that the Gaussian distribution of the sampled features closely matches the Gaussian distribution of all unlabeled features within the cluster. Our CBS can be plugged and played into those CIL methods which are based on pretrained models with prompts tunning technique. Extensive experiments under ACIL protocol across five diverse datasets demonstrate that CBS outperforms both random selection and other SOTA active learning approaches. Code is publicly available at https://github.com/1170300714/CBS.