A comprehensive perspective of contrastive self-supervised learning
Songcan CHEN1,2(), Chuanxing GENG1,2
1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China 2. MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing 211106, China
G Hinton, Y LeCunn, Y Bengio. AAAI’2020 keynotes turing award winners event.
2
L Jing, Y Tian. Self-supervised visual feature learning with deep neural networks: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, DOI:10.1109/TPAMI.2020.2992393 https://doi.org/10.1109/TPAMI.2020.2992393
3
I So. Cognitive development in children: piaget development and learning. Journal of Research in Science Teaching, 1964, 2: 176–186 https://doi.org/10.1002/tea.3660020306
4
A Jaiswal, A R Babu, M Z Zadeh, D Banerjee, F Makedon. A survey on contrastive self-supervised learning. Technologies, 2021, 9(1): 2 https://doi.org/10.3390/technologies9010002
5
N Saunshi, O Plevrakis, S Arora, M Khodak, H Khandeparkar. A theoretical analysis of contrastive unsupervised representation learning. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 5628–5637
6
Y H H Tsai, Y Wu, R Salakhutdinov, L P Morency. Self-supervised learning from a multi-view perspective. In: Proceedings of the 8th International Conference on Learning Representations. 2020
7
C Tosh, A Krishnamurthy, D Hsu. Contrastive learning, multi-view redundancy, and linear models. In: Proceedings of the 32nd International Conference on Algorithmic Learning Theory. 2021, 1179–1206
8
T Wang, P Isola. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 9929–9939
9
W Wang, Z H Zhou. Analyzing co-training style algorithms. In: Proceedings of the 18th European Conference on Machine Learning. 2007, 454–465 https://doi.org/10.1007/978-3-540-74958-5_42
10
J S Pan, Q Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2009, 22(10): 1345–1359 https://doi.org/10.1109/TKDE.2009.191
