Revisiting Self-Supervised Visual Representation Learning

CVPR 2019 Alexander KolesnikovXiaohua ZhaiLucas Beyer

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised techniques achieves superior performance on many challenging benchmarks... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Self-Supervised Image Classification ImageNet Revisited Rotation (RevNet-50 ×4) Top 1 Accuracy 55.4% # 37
Top 5 Accuracy 77.9% # 21
Self-Supervised Image Classification ImageNet Revisited Rel.Patch.Loc (ResNet50v1 ×2) Top 1 Accuracy 51.4% # 39
Top 5 Accuracy 74.0% # 23
Self-Supervised Image Classification ImageNet Revisited Exemplar (ResNet-50v1 ×3) Top 1 Accuracy 46.0% # 42
Top 5 Accuracy 68.8% # 25
Self-Supervised Image Classification ImageNet Revisited Jigsaw (ResNet50v1 ×2) Top 1 Accuracy 44.6% # 43
Top 5 Accuracy 68.0% # 26

Methods used in the Paper