1. ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification
2. Decoupled weight decay regularization;loshchilov;Proc Int’l Conf Learning Representations,2019
3. Learning multiple layers of features from tiny images;krizhevsky;Technical Report,2009
4. Mixup: Beyond empirical risk minimization;zhang;Proc Int’l Conf Learning Representations,2018
5. An image is worth 16x16 words: Transformers for image recognition at scale;dosovitskiy;Proc Int’l Conf Learning Representations,2021