Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training

arXiv:2403.03728v1 Announce Type: new
Abstract: This study addresses the integration of diversity-based and uncertainty-based sampling strategies in active learning, particularly within the context of self-supervised pre-trained models. We introduce a straightforward heuristic called TCM that mitigates the cold start problem while maintaining strong performance across various data levels. By initially applying TypiClust for diversity sampling and subsequently transitioning to uncertainty sampling with Margin, our approach effectively combines the strengths of both strategies. Our experiments demonstrate that TCM consistently outperforms existing …

abstract active learning arxiv cold start context cs.ai cs.cv cs.lg data diversity integration performance pre-trained models pre-training sampling strategies study training type uncertainty