English

Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning

Computer Vision and Pattern Recognition 2025-01-28 v1 Artificial Intelligence Machine Learning

Abstract

Class-incremental learning in the context of limited personal labeled samples (few-shot) is critical for numerous real-world applications, such as smart home devices. A key challenge in these scenarios is balancing the trade-off between adapting to new, personalized classes and maintaining the performance of the model on the original, base classes. Fine-tuning the model on novel classes often leads to the phenomenon of catastrophic forgetting, where the accuracy of base classes declines unpredictably and significantly. In this paper, we propose a simple yet effective mechanism to address this challenge by controlling the trade-off between novel and base class accuracy. We specifically target the ultra-low-shot scenario, where only a single example is available per novel class. Our approach introduces a Novel Class Detection (NCD) rule, which adjusts the degree of forgetting a priori while simultaneously enhancing performance on novel classes. We demonstrate the versatility of our solution by applying it to state-of-the-art Few-Shot Class-Incremental Learning (FSCIL) methods, showing consistent improvements across different settings. To better quantify the trade-off between novel and base class performance, we introduce new metrics: NCR@2FOR and NCR@5FOR. Our approach achieves up to a 30% improvement in novel class accuracy on the CIFAR100 dataset (1-shot, 1 novel class) while maintaining a controlled base class forgetting rate of 2%.

Keywords

Cite

@article{arxiv.2501.15998,
  title  = {Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning},
  author = {Kirill Paramonov and Mete Ozay and Eunju Yang and Jijoong Moon and Umberto Michieli},
  journal= {arXiv preprint arXiv:2501.15998},
  year   = {2025}
}

Comments

ICASSP 2025

R2 v1 2026-06-28T21:19:28.644Z