.png){kind=icon}
.png){kind=icon}
Return
Rethinking Class-Incremental Learning From a Dynamic Imbalanced Learning Perspective
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2025.3632688.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 new task data contributes to forgetting of the old tasks. Moreover, the increasing imbalance ratio during incremental learning further aggravates the problem. To address the dynamic imbalance issue, we propose Uniform Prototype Contrastive Learning (UPCL), where uniform and compact features are learned. Specifically, we generate a set of non-learnable uniform prototypes before each task starts. Then we assign these uniform prototypes to each class and guide the feature learning through prototype contrastive learning. We also dynamically adjust the relative margin between old and new classes so that the feature distribution will be maintained balanced and compact. Finally, we demonstrate through extensive experiments that the proposed method achieves state-of-the-art performance on several benchmark including CIFAR-100, ImageNet-100, TinyImageNet, Food-101, and CUB-200. Experimental results show that our approach not only effectively addresses the issue of imbalanced old data in memory but also tackles the problem of imbalanced new data distributions.
Keywords:
Class-incremental learning
imbalanced learning
prototype learning
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W
View more organizations