What makes for good views for contrastive learning

20 May 2020Yonglong TianChen SunBen PooleDilip KrishnanCordelia SchmidPhillip Isola

Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Self-Supervised Image Classification ImageNet InfoMin (ResNet-50) Top 1 Accuracy 73.0% # 12
Top 5 Accuracy 91.1% # 9
Number of Params 24M # 11
Self-Supervised Image Classification ImageNet InfoMin (ResNeXt-152) Top 1 Accuracy 75.2% # 9
Number of Params 120M # 7

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet