Accuracy: 86.7
Papers with Code · CC BY-SA 4.0
Unsupervised Image Classification
Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing the ground truth labels.
<span style="color:grey; opacity: 0.6"> Image credit: ImageNet clustering results of SCAN: Learning to Classify Images without Labels (ECCV 2020) </span>
논문
Accuracy: 80.90
Accuracy: 56.92NMI: 56.76ARI: 41.15
Accuracy: 61.00
Accuracy : 80.91
Accuracy: 99.7
Accuracy: 66.50
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
Accuracy: 89.67
Accuracy: 85.11
Accuracy (%): 6.53±0.19ARI: 1.59±0.04
Accuracy: 93
Accuracy: 71.6NMI: 73.2
Accuracy: 56.1
Accuracy: 85.7