Better Knowledge Retention through Metric Learning
This work is significant for researchers and practitioners working on continual learning systems, offering an incremental improvement in knowledge retention.
This paper addresses the problem of catastrophic forgetting in continual learning when new categories are introduced. The proposed method reduces forgetting by 2.3x to 6.9x on CIFAR-10 and by 1.8x to 2.7x on ImageNet compared to baselines.
In continual learning, new categories may be introduced over time, and an ideal learning system should perform well on both the original categories and the new categories. While deep neural nets have achieved resounding success in the classical supervised setting, they are known to forget about knowledge acquired in prior episodes of learning if the examples encountered in the current episode of learning are drastically different from those encountered in prior episodes. In this paper, we propose a new method that can both leverage the expressive power of deep neural nets and is resilient to forgetting when new categories are introduced. We found the proposed method can reduce forgetting by 2.3x to 6.9x on CIFAR-10 compared to existing methods and by 1.8x to 2.7x on ImageNet compared to an oracle baseline.