Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning
This work addresses a practical limitation in few-shot incremental learning by broadening the scope of unlabeled data, which is incremental but improves applicability for real-world scenarios.
The paper tackles the problem of Semi-supervised Few-shot Class-Incremental Learning (Semi-FSCIL) by redefining it as Generalized Semi-FSCIL (GSemi-FSCIL) to include unlabeled data from both base and novel classes, and proposes an Ambiguity-guided Learnable Distribution Calibration (ALDC) strategy to address the challenge of distinguishing between these classes, achieving state-of-the-art results on three benchmark datasets.
Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have started to leverage unlabeled samples to assist models in learning from few-shot samples, giving rise to the field of Semi-supervised Few-shot Class-Incremental Learning (Semi-FSCIL). However, these studies often assume that the source of unlabeled data is only confined to novel classes of the current session, which presents a narrow perspective and cannot align well with practical scenarios. To better reflect real-world scenarios, we redefine Semi-FSCIL as Generalized Semi-FSCIL (GSemi-FSCIL) by incorporating both base and all the ever-seen novel classes in the unlabeled set. This change in the composition of unlabeled samples poses a new challenge for existing methods, as they struggle to distinguish between unlabeled samples from base and novel classes. To address this issue, we propose an Ambiguity-guided Learnable Distribution Calibration (ALDC) strategy. ALDC dynamically uses abundant base samples to correct biased feature distributions for few-shot novel classes. Experiments on three benchmark datasets show that our method outperforms existing works, setting new state-of-the-art results.