DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning

arXiv:2402.08963v1 Announce Type: new
Abstract: Recent machine learning algorithms have been developed using well-curated datasets, which often require substantial cost and resources. On the other hand, the direct use of raw data often leads to overfitting towards frequently occurring class information. To address class imbalances cost-efficiently, we propose an active data filtering process during self-supervised pre-training in our novel framework, Duplicate Elimination (DUEL). This framework integrates an active memory inspired by human working memory and introduces distinctiveness information, which measures …

abstract algorithms arxiv class cost cs.ai cs.lg data datasets duplicate information leads machine machine learning machine learning algorithms memory overfitting raw resources type