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.
Para outro idioma
do conteúdo fonte
arxiv.org
Principais Insights Extraídos De
by Jiangpeng He... às arxiv.org 02-29-2024
https://arxiv.org/pdf/2402.18528.pdfPerguntas Mais Profundas