Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models

Documenti analoghi

• ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data
  di: Song, Steven, et al.
  Pubblicazione: (2026)
• On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
  di: Yu, Bing, et al.
  Pubblicazione: (2020)
• Designing Pre-training Datasets from Unlabeled Data for EEG Classification with Transformers
  di: Bary, Tim, et al.
  Pubblicazione: (2024)
• PUAL: A Classifier on Trifurcate Positive-Unlabeled Data
  di: Wang, Xiaoke, et al.
  Pubblicazione: (2024)
• Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model
  di: Shi, Jiang-Xin, et al.
  Pubblicazione: (2024)