Self-supervised Pretraining of Visual Features in the Wild

Open paper
Benchmark Model Rank Results
image-classification-on-places205SEER#6Top 1 Accuracy: 66.0
image-classification-on-places205RegNetY-128GF (Supervised)#9Top 1 Accuracy: 62.7
self-supervised-image-classification-on-imagenetSEER#48Top 1 Accuracy: 77.5%Number of Params: 1300M
self-supervised-image-classification-on-imagenet-finetunedSEER (RegNetY-256GF)#33Top 1 Accuracy: 84.2%Number of Params: 1.3B
self-supervised-image-classification-on-imagenet-finetunedSEER (RegNetY-128GF)#42Top 1 Accuracy: 83.8%Number of Params: 693M
semi-supervised-image-classification-on-imagenet-1-labeled-dataSEER Large (RegNetY-256GF)#33Top 1 Accuracy: 60.5%
semi-supervised-image-classification-on-imagenet-1-labeled-dataSEER Small (RegNetY-128GF)#38Top 1 Accuracy: 57.5%
semi-supervised-image-classification-on-imagenet-10-labeled-dataSEER Large (RegNetY-256GF)#13Top 1 Accuracy: 77.9%
semi-supervised-image-classification-on-imagenet-10-labeled-dataSEER Small (RegNetY-128GF)#17Top 1 Accuracy: 76.7%

Rank counts only results with a code link.