Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we propose a few-shot class incremental learning (FSCIL) method referred to as \emph{Soft-SubNetworks (SoftNet)}. Our objective is to learn a sequence of sessions incrementally, where each session only includes a few training instances per class while preserving the knowledge of the previously learned ones. SoftNet jointly learns the model weights and adaptive non-binary soft masks at a base training session in which each mask consists of the major and minor subnetwork; the former aims to minimize catastrophic forgetting during training, and the latter aims to avoid overfitting to a few samples in each new training session. We provide comprehensive empirical validations demonstrating that our SoftNet effectively tackles the few-shot incremental learning problem by surpassing the performance of state-of-the-art baselines over benchmark datasets.
@article{arxiv.2209.07529,
title = {On the Soft-Subnetwork for Few-shot Class Incremental Learning},
author = {Haeyong Kang and Jaehong Yoon and Sultan Rizky Hikmawan Madjid and Sung Ju Hwang and Chang D. Yoo},
journal= {arXiv preprint arXiv:2209.07529},
year = {2023}
}
Comments
The Eleventh International Conference on Learning Representations (ICLR, 2023)