Divide and not forget: Ensemble of selectively trained experts in Continual Learning

arXiv:2401.10191v3 Announce Type: replace
Abstract: Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation, we introduce a novel approach named SEED. …

abstract arxiv class continual cs.cv cs.lg ensemble expert experts however incremental popular solve together trend type work