Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor

TL;DR

This paper introduces a Bayesian generative model using a fixed pre-trained feature extractor to enable continual learning without catastrophic forgetting, especially effective in medical and natural image classification tasks.

Contribution

It presents a novel Bayesian approach that models old classes with statistical distributions, avoiding sensitivity to the continual learning process and supporting data-incremental learning.

Findings

Outperforms state-of-the-art methods in medical and natural image classification

Effectively prevents forgetting of old classes during continual learning

Applicable to both class-incremental and data-incremental scenarios

Abstract

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly in intelligent diagnosis systems where initially only training data of a limited number of diseases are available. In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning built on a fixed pre-trained feature extractor. In this model, knowledge of each old class can be compactly represented by a collection of statistical distributions, e.g. with Gaussian mixture models, and naturally kept from forgetting in continual learning over time. Unlike existing class-incremental learning methods, the proposed approach is not sensitive to the continual learning process and can be additionally well applied to the data-incremental learning scenario. Experiments on multiple medical and natural image classification tasks showed that the proposed approach outperforms state-of-the-art approaches which even keep some images of old classes during continual learning of new classes.