Improved Baselines with Momentum Contrastive Learning

9 Mar 2020Xinlei ChenHaoqi FanRoss GirshickKaiming He

Contrastive unsupervised learning has recently shown encouraging progress, e.g., in Momentum Contrast (MoCo) and SimCLR. In this note, we verify the effectiveness of two of SimCLR's design improvements by implementing them in the MoCo framework... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Self-Supervised Image Classification ImageNet MoCo v2 (ResNet-50) Top 1 Accuracy 71.1% # 4
Self-Supervised Image Classification ImageNet MoCo v2 (ResNet-50) Top 5 Accuracy 90.1% # 3
Self-Supervised Image Classification ImageNet MoCo v2 (ResNet-50) Number of Params 24M # 1