DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic Surgery

Yuning Zhou, Henry Badgery, Matthew Read, James Bailey, Catherine Davey

Keywords: differentiable augmentation search, contrastive learning, representation learning, laparoscopic imaging

Abstract: Self-supervised learning (SSL) enables effective representation learning from unlabeled data. There has been significant interest in transitioning SSL techniques to medical imaging analysis. An important consideration in SSL is the choice of data augmentation, which often depends on the specific domain. It is unclear whether commonly used augmentation policies for general image types are suitable for surgical applications. In this work, we automate the search for suitable augmentation policies through a new method called Dimensionality Driven Augmentation Search (DDA). DDA leverages the local dimensionality of deep representations as a proxy target, and searches for suitable data augmentation policies in contrastive learning. We demonstrate the effectiveness and efficiency of DDA in navigating a large search space and successfully identifying an appropriate data augmentation policy for laparoscopic surgery. We systematically evaluate DDA across three laparoscopic image classification and segmentation tasks, where it significantly improves over existing baselines. Furthermore, DDA’s optimised set of augmentations provides insight into domain-specific dependencies when applying contrastive learning in medical applications. For example, while hue is an effective augmentation for natural images, it is not advantageous for laparoscopic images.

Submission Number: 17