SCAN: Learning to Classify Images without Labels

ECCV 2020 Wouter Van GansbekeSimon VandenhendeStamatios GeorgoulisMarc ProesmansLuc Van Gool

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision... (read more)

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Unsupervised Image Classification CIFAR-10 SCAN Accuracy 88.3 # 1
Unsupervised Image Classification CIFAR-20 SCAN Accuracy 50.7 # 1
Unsupervised Image Classification ImageNet SCAN (ResNet-50) Accuracy (%) 39.9 # 2
ARI 27.5 # 1
Semi-Supervised Image Classification ImageNet - 1% labeled data SCAN (ResNet-50|Unsupervised) Top 5 Accuracy 60.0% # 18
Top 1 Accuracy 39.90% # 16
Unsupervised Image Classification STL-10 SCAN Accuracy 80.90 # 1

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