Continual Learning Based on OOD Detection and Task Masking

TL;DR

This paper introduces CLOM, a unified continual learning method using OOD detection and task masking, effectively addressing both TIL and CIL problems with superior accuracy.

Contribution

It proposes a novel approach that trains each task as an OOD detection model and employs task masking to prevent forgetting, unifying TIL and CIL solutions.

Findings

CLOM achieves an average accuracy of 87.6% on TIL and 67.9% on CIL.

CLOM outperforms state-of-the-art baselines by large margins.

The method demonstrates robustness across six different experiments.

Abstract

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%.