Adaptive Shortcut Debiasing for Online Continual Learning
This work addresses the problem of shortcut bias for researchers and practitioners in online continual learning, offering an adaptive solution that is incremental in improving existing methods.
The paper tackles shortcut bias in online continual learning by proposing DropTop, a framework that adaptively debiases features based on activation levels, resulting in up to a 10.4% increase in average accuracy and a 63.2% decrease in forgetting across five benchmark datasets.
We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By the observed high-attention property of the shortcut bias, highly-activated features are considered candidates for debiasing. More importantly, resolving the limitation of the online environment where prior knowledge and auxiliary data are not ready, two novel techniques -- feature map fusion and adaptive intensity shifting -- enable us to automatically determine the appropriate level and proportion of the candidate shortcut features to be dropped. Extensive experiments on five benchmark datasets demonstrate that, when combined with various OCL algorithms, DropTop increases the average accuracy by up to 10.4% and decreases the forgetting by up to 63.2%.