Continual Learning Based on OOD Detection and Task Masking
It addresses a gap in continual learning by providing a unified solution for both TIL and CIL, which is incremental as it builds on existing techniques.
The paper tackles the problem of unifying task incremental learning (TIL) and class incremental learning (CIL) in continual learning by proposing CLOM, which uses out-of-distribution detection and task masking, resulting in average TIL/CIL accuracies of 87.6%/67.9% compared to baseline 82.4%/55.0%.
Existing continual learning techniques focus on either task incremental learning (TIL) or class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the task-id is provided for each test sample during testing for TIL, but not provided for CIL. Continual learning methods intended for one problem have limitations on the other problem. This paper proposes a novel unified approach based on out-of-distribution (OOD) detection and task masking, called CLOM, to solve both problems. The key novelty is that each task is trained as an OOD detection model rather than a traditional supervised learning model, and a task mask is trained to protect each task to prevent forgetting. Our evaluation shows that CLOM outperforms existing state-of-the-art baselines by large margins. The average TIL/CIL accuracy of CLOM over six experiments is 87.6/67.9% while that of the best baselines is only 82.4/55.0%.