참고

1. Modern batch contrastive approaches subsume or significantly outperform traditional contrastive losses such as triplet*, max-margin* and the N-pairs loss.* / Recently, several approaches based on contrastive loss [22] have been proposed for self-supervised visual representation learning [9, 10, 14, 24, 35, 57, 60]. These approaches treat each instance as a class and use contrastive loss-based instance discrimination for representation learning.
2. [2004.11362] Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. Supervised Contrastive Learning CoRR, abs/2004.11362, 2020.