MoCo v2

Introduced by Chen et al. in Improved Baselines with Momentum Contrastive Learning

MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Improvements include:

  • Replacing the 1-layer fully connected layer with a 2-layer MLP head.
  • Including blur augmentation (the same used in SimCLR).
Source: Improved Baselines with Momentum Contrastive Learning

Latest Papers

PAPER DATE
Parametric Instance Classification for Unsupervised Visual Feature Learning
Yue CaoZhenda XieBin LiuYutong LinZheng ZhangHan Hu
2020-06-25
Improved Baselines with Momentum Contrastive Learning
| Xinlei ChenHaoqi FanRoss GirshickKaiming He
2020-03-09

Tasks

TASK PAPERS SHARE
Self-Supervised Image Classification 1 50.00%
unsupervised learning 1 50.00%

Categories