Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11838-11847
Abstract
Few-Shot Class-Incremental Learning (FSCIL) aims to continually learn novel classes based on only few training samples, which poses a more challenging task than the well-studied Class-Incremental Learning (CIL) due to data scarcity. While knowledge distillation, a prevailing technique in CIL, can alleviate the catastrophic forgetting of older classes by regularizing outputs between current and previous model, it fails to consider the overfitting risk of novel classes in FSCIL. To adapt the powerful distillation technique for FSCIL, we propose a novel distillation structure, by taking the unique challenge of overfitting into account. Concretely, we draw knowledge from two complementary teachers. One is the model trained on abundant data from base classes that carries rich general knowledge, which can be leveraged for easing the overfitting of current novel classes. The other is the updated model from last incremental session that contains the adapted knowledge of previous novel classes, which is used for alleviating their forgetting. To combine the guidances, an adaptive strategy conditioned on the class-wise semantic similarities is introduced. Besides, for better preserving base class knowledge when accommodating novel concepts, we adopt a two-branch network with an attention-based aggregation module to dynamically merge predictions from two complementary branches. Extensive experiments on 3 popular FSCIL datasets: mini-ImageNet, CIFAR100 and CUB200 validate the effectiveness of our method by surpassing existing works by a significant margin. Code is available at https://github.com/LinglanZhao/BiDistFSCIL.Keywords
This publication has 25 references indexed in Scilit:
- Few-Shot Class-Incremental Learning2020
- Semantic Drift Compensation for Class-Incremental Learning2020
- Adversarial Feature Hallucination Networks for Few-Shot Learning2020
- Learning a Unified Classifier Incrementally via Rebalancing2019
- Low-Shot Learning with Imprinted Weights2018
- Low-Shot Learning from Imaginary Data2018
- Dynamic Few-Shot Visual Learning Without Forgetting2018
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- iCaRL: Incremental Classifier and Representation Learning2017
- Deep Residual Learning for Image Recognition2016