1. Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
2. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results;tarvainen;Advances in neural information processing systems,2017
3. Mixmatch: A holistic approach to semi-supervised learning;berthelot;Advances in neural information processing systems,2019
4. Going deeper with convolutions
5. Unsupervised learning of visual features by contrasting cluster assignments;caron;Advances in neural information processing systems,2020