How Well Do Self-Supervised Models Transfer?

InsDis MoCo-v1 PCL-v1 PIRL PCL-v2 SimCLR-v1 MoCo-v2 SimCLR-v2 SeLa-v2 InfoMin BYOL DeepCluster-v2 SwAV Supervised Figure 1 . Transfer performance is highly correlated with ImageNet performance for many-shot recognition but increasingly less correlated for few-shot recognition, object detection and dense prediction. On the x-axes we plot ImageNet top-1 accuracy and on the y-axes the average transfer log-odds. The gradients of the regression lines describe the correlation, with confidence intervals in shaded areas. For perfect correlation, the ideal line is a positive slope diagonal. Correlation coefficients (Pearson's r) are shown in the top left of each plot.