# Curriculum semi-supervised segmentation

## TL;DR

This paper introduces a curriculum semi-supervised segmentation method using a regression network to incorporate image-level information, improving unlabeled data utilization in CNN segmentation tasks.

## Contribution

It proposes a novel curriculum strategy that employs inequality constraints and a regression network to enhance semi-supervised CNN segmentation performance.

## Key findings

- Achieves competitive results close to fully supervised methods.
- Effectively leverages unlabeled data through inequality constraints.
- Outperforms standard proposal-based semi-supervision strategies.

## Abstract

This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region. These regressions are used to effectively regularize the segmentation network, constraining softmax predictions of the unlabeled images to match the inferred label distributions. Our framework is based on inequality constraints that tolerate uncertainties with inferred knowledge, e.g., regressed region size, and can be employed for a large variety of region attributes. We evaluated our proposed strategy for left ventricle segmentation in magnetic resonance images (MRI), and compared it to standard proposal-based semi-supervision strategies. Our strategy leverages unlabeled data in more efficiently, and achieves very competitive results, approaching the performance of full-supervision.