Continual learning with Bayesian model based on a fixed pre-trained feature extractor
Open Access
- 8 May 2023
- journal article
- research article
- Published by Springer Nature in Visual Intelligence
- Vol. 1 (1) , 1-14
Abstract
Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterized by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge such as 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 reveal that the proposed approach outperforms state-of-the-art approaches that even keep some images of old classes during continual learning of new classes.Keywords
Funding Information
- Innovative Research Group Project of the National Natural Science Foundation of China (62071502, U1811461)
- Special Project for Research and Development in Key areas of Guangdong Province (2020B1111190001)
This publication has 15 references indexed in Scilit:
- SINet: A Scale-Insensitive Convolutional Neural Network for Fast Vehicle DetectionIEEE Transactions on Intelligent Transportation Systems, 2018
- Clinically applicable deep learning for diagnosis and referral in retinal diseaseNature Medicine, 2018
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- A complementary processes account of the development of childhood amnesia and a personal past.Psychological Review, 2015
- Development of allocentric spatial memory abilities in children from 18 months to 5 years of ageCognitive Psychology, 2013
- Memory formation, consolidation and transformationNeuroscience & Biobehavioral Reviews, 2012
- To have and to hold: Episodic memory in 3‐ and 4‐year‐old childrenDevelopmental Psychobiology, 2011
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999