Few-shot Class-Incremental Learning via Generative Co-Memory Regularization

TL;DR

This paper introduces a generative co-memory regularization method for few-shot class-incremental learning, enhancing model adaptability and reducing forgetting of old classes with a novel memory-regularized training process.

Contribution

It proposes a new approach combining generative domain adaptation, co-memory regularization, and incremental training to improve FSCIL performance.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively mitigates catastrophic forgetting in incremental learning.

Enhances recognition accuracy with limited data.

Abstract

Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervision to avoid catastrophic forgetting on old classes and overfitting to novel classes. This work proposes a generative co-memory regularization approach to facilitate FSCIL. In the approach, the base learning leverages generative domain adaptation finetuning to finetune a pretrained generative encoder on a few examples of base classes by jointly incorporating a masked autoencoder (MAE) decoder for feature reconstruction and a fully-connected classifier for feature classification, which enables the model to efficiently capture general and adaptable representations. Using the finetuned encoder and learned classifier, we construct two class-wise memories: representation memory for storing the mean features for each class, and weight memory for storing the classifier weights. After that, the memory-regularized incremental learning is performed to train the classifier dynamically on the examples of few-shot classes in each incremental session by simultaneously optimizing feature classification and co-memory regularization. The memories are updated in a class-incremental manner and they collaboratively regularize the incremental learning. In this way, the learned models improve recognition accuracy, while mitigating catastrophic forgetting over old classes and overfitting to novel classes. Extensive experiments on popular benchmarks clearly demonstrate that our approach outperforms the state-of-the-arts.