This paradigm uses the idea that model predictions on an unlabeled image should remain the same even after adding noise. We could use input noise such as Image Augmentation and Gaussian noise. Noise can also be incorporated into the architecture itself using Dropout.
0) Overview:
Dataset:
Metrics:
1) Papers:
Consistency Regularization
[π-model] [Temporal Ensembling] , “Temporal Ensembling for Semi-Supervised Learning”
[Mean Teacher] , “Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results”
[Virtual Adversarial Training] , “Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning”
[Unsupervised Data Augmentation] , “Unsupervised data augmentation for consistency training”
