Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

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

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Publication Information:
      OpenReview
    • Publication Date:
      2024
    • Collection:
      ETH Zürich Research Collection
    • 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.
    • File Description:
      application/application/pdf
    • Relation:
      http://hdl.handle.net/20.500.11850/665016
    • Accession Number:
      10.3929/ethz-b-000665016
    • Online Access:
      https://doi.org/20.500.11850/66501610.3929/ethz-b-000665016
      https://hdl.handle.net/20.500.11850/665016
    • Rights:
      info:eu-repo/semantics/openAccess ; http://creativecommons.org/licenses/by/4.0/ ; Creative Commons Attribution 4.0 International
    • Accession Number:
      edsbas.594A58B