. Author manuscript; available in PMC: 2022 Oct 28.

Published in final edited form as: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2022 Sep 27;2022:20792–20802. doi: 10.1109/cvpr52688.2022.02016

Table 2. Comparison with fully-supervised transfer learning:

DiRA models outperform fully-supervised pre-trained models on ImageNet and ChestX-ray14 in three downstream tasks. The best methods are bolded while the second best are underlined. ↑ and ↑ present the statistically significant (p < 0.05) improvement compared with supervised ImageNet and ChestX-ray14 baselines, respectively, while * and * presents the statistically equivalent performances accordingly. For supervised ChestX-ray14 model, transfer learning to ChestX-ray14 is not applicable since pre-training and downstream tasks are the same, denoted by “−”.

Method	Pretraining Dataset	Classification [AUC (%)]		Segmentation [Dice (%)]
Method	Pretraining Dataset	ChestX-ray14	CheXpert	SIIM-ACR	Montgomery
Random	-	80.31±0.10	86.62±0.15	67.54±0.60	97.55±0.36
Supervised	ImageNet	81.70±0.15	87.17±0.22	67.93±1.45	98.19±0.13
Supervised	ChestX-ray14	-	87.40±0.26	68.92±0.98	98.16±0.05
DiRA_MoCo-v2	ChestX-ray14	81.12±0.17	87.59±0.28 ↑ ↑	69.24±0.41 ↑ *	98.24±0.09 * ↑
DiRA_{Barlow Twins}	ChestX-ray14	80.88±0.30	87.50±0.27 ↑ *	69.87±0.68 ↑ ↑	98.16±0.06 * *
DiRA_SimSiam	ChestX-ray14	80.44±0.29	86.04±0.43	68.76±0.69 * *	98.17±0.11 * *