Expert with Outlier Exposure for Continual Learning of New Diseases
Authors:
- 6 December 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1768-1772
Abstract
Current intelligent diagnosis systems struggle to continually learn to diagnose more and more diseases due to catastrophic forgetting of old knowledge when learning new knowledge. Although storing small old data for subsequent continual learning can effectively help alleviate the forgetting issue, the heavy data imbalance between old classes and to-be-learned new classes in classifier training often causes biased prediction towards the new classes just learned by the updated classifier. In this study, an outlier detection technique is novelly applied to train an additional expert classifier for new classes to help alleviate the class imbalance issue and discriminate the learned new classes from old classes during inference (instead of the training phase). Specially, the stored small data of old classes are considered as outliers during training the expert classifier, such that the output probability distributions from the expert classifier are expected to be obviously different between test data of the old classes and those of the new classes. Such difference between old classes and new classes can be used to fine-tune the original output from the updated classifier which is responsible for prediction of all learned (old and new) classes. During inference, a novel ensemble strategy is proposed to combine the predictions from the updated classifier, the expert classifier, and the previously learned old classifier. The proposed learning and inference framework can be easily combined with existing continual learning strategies. Empirical evaluations on three medical image datasets and one natural image dataset show that the proposed framework can effectively improve continual learning performance.Keywords
Funding Information
- Research and Development
This publication has 20 references indexed in Scilit:
- Large Scale Incremental Learning2019
- Continual lifelong learning with neural networks: A reviewNeural Networks, 2019
- The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionsScientific Data, 2018
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- iCaRL: Incremental Classifier and Representation Learning2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- A Benchmark for Automatic Visual Classification of Clinical Skin Disease Images2016
- Using Noise to Compute Error Surfaces in Connectionist Networks: A Novel Means of Reducing Catastrophic ForgettingNeural Computation, 2002
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999
- Catastrophic Forgetting, Rehearsal and PseudorehearsalConnection Science, 1995