Region-of-interest guided Supervoxel Inpainting for Self-supervision

TL;DR

This paper introduces a region-of-interest guided supervoxel inpainting method for self-supervised learning in biomedical image segmentation, improving performance over traditional methods by focusing on relevant areas.

Contribution

It proposes a novel inpainting approach using supervoxel-based masking and ROI focus, enhancing semantic learning for segmentation tasks.

Findings

Outperforms supervised CNNs without self-supervision

Better results than conventional inpainting self-supervision

Effective on both large and small datasets

Abstract

Self-supervised learning has proven to be invaluable in making best use of all of the available data in biomedical image segmentation. One particularly simple and effective mechanism to achieve self-supervision is inpainting, the task of predicting arbitrary missing areas based on the rest of an image. In this work, we focus on image inpainting as the self-supervised proxy task, and propose two novel structural changes to further enhance the performance of a deep neural network. We guide the process of generating images to inpaint by using supervoxel-based masking instead of random masking, and also by focusing on the area to be segmented in the primary task, which we term as the region-of-interest. We postulate that these additions force the network to learn semantics that are more attuned to the primary task, and test our hypotheses on two applications: brain tumour and white matter hyperintensities segmentation. We empirically show that our proposed approach consistently outperforms both supervised CNNs, without any self-supervision, and conventional inpainting-based self-supervision methods on both large and small training set sizes.