Rethinking Class-Incremental Learning From a Dynamic Imbalanced Learning Perspective
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2025.3632688
Abstract: Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and… read more here.
Keywords: rethinking class; class incremental; learning dynamic; incremental learning ... See more keywords