Gradient Reweighting: Towards Imbalanced Class-Incremental Learning

arXiv:2402.18528v1 Announce Type: new
Abstract: Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge. A major challenge of CIL arises when applying to real-world data characterized by non-uniform distribution, which introduces a dual imbalance problem involving (i) disparities between stored exemplars of old tasks and new class data (inter-phase imbalance), and (ii) severe class imbalances within each individual task (intra-phase imbalance). We show that this dual imbalance issue causes skewed gradient …

abstract arxiv challenge class cs.cv data distribution gradient incremental knowledge major tasks trains type uniform world