组合等变表示学习
Compositionally Equivariant Representation Learning
AI总结：
本文提出组合等变表示学习，利用可学习vMF核建模医学图像分割中的组合结构，在无/弱/半监督下提升表示的可解释性与泛化性，并在半监督域泛化分割任务上取得最优性能。
摘要：
深度学习模型通常需要足够的监督（即标记数据）才能有效训练。相比之下，人类可以凭借最少的指导，迅速学会识别MRI和CT扫描等医学图像中的重要解剖结构。这种识别能力很容易泛化到来自不同医疗设施的新图像以及不同环境中的新任务。这种快速且可泛化的学习能力很大程度上归功于人脑中图像模式的组合结构，而当前医学模型并未很好地表征这种结构。在本文中，我们研究了利用组合性来学习更具可解释性和泛化性的医学图像分割表示。总体而言，我们提出用于生成医学图像的潜在生成因子满足组合等变性质，其中每个因子是组合的（例如，对应于人体解剖结构），并且对任务也是等变的。因此，一个能很好逼近真实因子的良好表示必须是组合等变的。通过使用可学习的von-Mises-Fisher（vMF）核来建模组合表示，我们探讨了如何利用不同的设计和学习偏差，在无监督、弱监督和半监督设置下强制表示更具组合等变性。大量结果表明，在半监督域泛化医学图像分割任务上，我们的方法在多个强基线上取得了最佳性能。代码将在录用后公开于https://github.com/vios-s。
英文摘要：
Deep learning models often need sufficient supervision (i.e. labelled data) in order to be trained effectively. By contrast, humans can swiftly learn to identify important anatomy in medical images like MRI and CT scans, with minimal guidance. This recognition capability easily generalises to new images from different medical facilities and to new tasks in different settings. This rapid and generalisable learning ability is largely due to the compositional structure of image patterns in the human brain, which are not well represented in current medical models. In this paper, we study the utilisation of compositionality in learning more interpretable and generalisable representations for medical image segmentation. Overall, we propose that the underlying generative factors that are used to generate the medical images satisfy compositional equivariance property, where each factor is compositional (e.g. corresponds to the structures in human anatomy) and also equivariant to the task. Hence, a good representation that approximates well the ground truth factor has to be compositionally equivariant. By modelling the compositional representations with learnable von-Mises-Fisher (vMF) kernels, we explore how different design and learning biases can be used to enforce the representations to be more compositionally equivariant under un-, weakly-, and semi-supervised settings. Extensive results show that our methods achieve the best performance over several strong baselines on the task of semi-supervised domain-generalised medical image segmentation. Code will be made publicly available upon acceptance at https://github.com/vios-s.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
