Contrastive pretraining is well-known to improve downstream task performance
and model generalisation, especially in limited label settings. However, it is
sensitive to the choice of augmentation pipeline. Positive pairs should
preserve semantic information while destroying domain-specific information.
Standard augmentation pipelines emulate domain-specific changes with
pre-defined photometric transformations, but what if we could simulate
realistic domain changes instead? In this work, we show how to utilise recent
progress in counterfactual image generation to this effect. We propose
CF-SimCLR, a counterfactual contrastive learning approach which leverages
approximate counterfactual inference for positive pair creation. Comprehensive
evaluation across five datasets, on chest radiography and mammography,
demonstrates that CF-SimCLR substantially improves robustness to acquisition
shift with higher downstream performance on both in- and out-of-distribution
data, particularly for domains which are under-represented during training.

利用计数事实图像生成的最新进展，我们提出了 CF-SimCLR，一种反事实对比学习方法，利用近似的反事实推理用于正样本对的创建，在胸部放射学和乳房 X 线检查的五个数据集上进行综合评估，证明 CF-SimCLR 可以显著提高对获得偏移的稳健性，在内部和外部分布的数据上都能获得更高的下游性能，特别是对于在训练过程中少见的领域。