Supervised contrastive learning. (arXiv 2020)

  • 저자 : Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., ... & Krishnan, D.
  • 연구기관 : Google, MIT

SimCLR (A simple framework for contrastive learning of visual representations, PMLR 2020) 후속 논문이다. SimCLR의 단점을 보완하였다고 볼 수 있다.




Popular Posts

Show, attend and tell: Neural image caption generation with visual attention (ICML 2015)

Multiple object recognition with visual attention (arXiv 2014)

Towards Accurate Multi-person Pose Estimation in the Wild (CVPR 2017)

DeepPose: Human pose estimation via deep neural networks (CVPR 2014)

Recurrent models of visual attention (NIPS 2014)

Pose machines: Articulated pose estimation via inference machines (ECCV 2014)