A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification

Documenti analoghi

• Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning
  di: Wu, Jiaqi, et al.
  Pubblicazione: (2025)
• Decorrelating Structure via Adapters Makes Ensemble Learning Practical for Semi-supervised Learning
  di: Wu, Jiaqi, et al.
  Pubblicazione: (2024)
• Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization
  di: Deng, Jiaxin, et al.
  Pubblicazione: (2024)
• Bilateral Sharpness-Aware Minimization for Flatter Minima
  di: Deng, Jiaxin, et al.
  Pubblicazione: (2024)
• In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training
  di: Pang, Junbiao, et al.
  Pubblicazione: (2024)