Class-Incremental Learning (CIL) faces challenges with imbalanced data distribution, leading to skewed gradient updates and catastrophic forgetting. The proposed method reweights gradients to balance optimization and mitigate forgetting. Distribution-aware knowledge distillation loss aligns output logits with lost training data distribution. Experimental results show consistent improvements across various datasets and evaluation protocols.
Naar een andere taal
vanuit de broninhoud
arxiv.org
Belangrijkste Inzichten Gedestilleerd Uit
by Jiangpeng He... om arxiv.org 02-29-2024
https://arxiv.org/pdf/2402.18528.pdfDiepere vragen