论文标题
一项有关因果代表学习和未来的医学图像分析工作的调查
A Survey on Causal Representation Learning and Future Work for Medical Image Analysis
论文作者
论文摘要
统计机器学习算法已经在基准数据集上取得了最新的结果，在许多任务中表现优于人类。但是，具有不可预测的因果关系的分布数据和混杂因素会大大降低现有模型的性能。因果代表学习（CRL）最近是解决视力理解中因果关系问题的一个有希望的方向。这项调查介绍了CRL视觉的最新进展。首先，我们介绍了因果推断的基本概念。其次，我们分析了CRL理论工作，尤其是在不变风险最小化以及特征理解和转移学习方面的实际工作。最后，我们提出了医学图像分析和CRL一般理论的未来研究方向。
Statistical machine learning algorithms have achieved state-of-the-art results on benchmark datasets, outperforming humans in many tasks. However, the out-of-distribution data and confounder, which have an unpredictable causal relationship, significantly degrade the performance of the existing models. Causal Representation Learning (CRL) has recently been a promising direction to address the causal relationship problem in vision understanding. This survey presents recent advances in CRL in vision. Firstly, we introduce the basic concept of causal inference. Secondly, we analyze the CRL theoretical work, especially in invariant risk minimization, and the practical work in feature understanding and transfer learning. Finally, we propose a future research direction in medical image analysis and CRL general theory.
