Curriculum semi-supervised segmentation

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.

arXiv commentAccepted as paper as MICCAI 2O19

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• A Survey on Deep Learning in Medical Image Analysis
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Constrained-CNN losses for weakly supervised segmentation
• Semi-Supervised Deep Learning for Fully Convolutional Networks
• Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning

Cited by in corpus (8)

• FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• Curriculum learning for improved femur fracture classification: scheduling data with prior knowledge and uncertainty
• Constrained domain adaptation for Image segmentation
• Discretely-constrained deep network for weakly supervised segmentation
• Exploring the parameter reusability of CNN
• MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labels