Skip to main content
. Author manuscript; available in PMC: 2022 Jun 9.
Published in final edited form as: Mach Learn Med Imaging. 2021 Sep 21;12966:692–702. doi: 10.1007/978-3-030-87589-3_71

Fig. 5:

Fig. 5:

Self-supervised pre-training extracted more transferable features compared with supervised pre-training. The blue and red dashed lines represent supervised pre-training and learning from scratch with standard deviation (shaded), respectively. 6 out of 14 SSL methods (in green) outperformed the supervised pre-training. All the reported methods had ResNet50 as the backbone.