1. SGDR: Stochastic gradient descent with warm restarts;loshchilov,2016
2. Large batch training of convolutional networks;you,2017
3. Learning a nonlinear embedding by preserving class neighbourhood structure;salakhutdinov;Artificial Intelligence and Statistics,2007
4. Exploring simple siamese representation learning;chen,2020
5. Selflabelling via simultaneous clustering and representation learning;asano,2019