pith. sign in

arxiv: 2403.03728 · v2 · pith:FDQWIGWWnew · submitted 2024-03-06 · 💻 cs.LG · cs.AI· cs.CV

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

classification 💻 cs.LG cs.AIcs.CV
keywords samplingacrossactivedatadiversitylearningself-supervisedstrategies
0
0 comments X
read the original 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 methods across various datasets in both low and high data regimes.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.