论文阅读《When Semi-Supervised Learning Meets Transfer Learning》

好的又是一个被想到的Idea

Posted by tianchen on November 21, 2019

🌟 When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets

  • Combine The Semi scheme in Finetuning from the Pretrained Model
  • Incorporate SSL Into Finetune
  • Did Comprehensive Empirical analysis 3 Conclusion:
    • The SSL Gain from full-supervised baseline(with fewer label) is smalller
    • When Domain Shifts, SSL Better
    • Some SSL Methods can outperform full-label training
  • SSL
    • Consistency-Regularization-based
      • Ladder Network
      • Pi-Model
      • Mean-Teacher
    • GANs & Adversarial Training
      • VAT - Virtual Adversrail Loss
    • Entropy-based SSL
      • Entropy-Minmization
    • Co-Training
      • Tri-Learning - Relabelling
  • Transfer Learning
    • Finetune

Datasets

  • Transfer from Imagenet
    • Indoor (67 Scene, 6700)
    • CUB200
    • MURA (医学图像-骨骼的CT?)

Experiments

    • 20 - Epochs
    • 1k labels
    • F+T Augmentation
      • F - HorizontalFlip
      • T - RandomTranslation
      • N - Gaussian Noise

## Conclusion

  • when you have enough labeled images,better pre-trained models seem to counteract the influenceof SSL methods.