Self-paced and self-consistent co-training for semi-supervised image segmentation

Abstract

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method. To help distillate information from unlabeled images, we first design a self-paced learning strategy for co-training that lets jointly-trained neural networks focus on easier-to-segment regions first, and then gradually consider harder ones.This is achieved via an end-to-end differentiable loss inthe form of a generalized Jensen Shannon Divergence(JSD). Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy. The robustness of individual models is further improved using a self-ensembling loss that enforces their prediction to be consistent across different training iterations. We demonstrate the potential of our method on three challenging image segmentation problems with different image modalities, using small fraction of labeled data. Results show clear advantages in terms of performance compared to the standard co-training baselines and recently proposed state-of-the-art approaches for semi-supervised segmentation

References in corpus (13)

• SGDR: Stochastic Gradient Descent with Warm Restarts
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Temporal Ensembling for Semi-Supervised Learning
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• A Survey on Multi-view Learning
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Semi-Supervised Learning with Ladder Networks
• Semantic Segmentation using Adversarial Networks
• Adversarial Learning for Semi-Supervised Semantic Segmentation
• Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
• Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
• Improving Semantic Segmentation via Self-Training

Cited by in corpus (5)

• Nuclei Segmentation with Point Annotations from Pathology Images via Self-Supervised Learning and Co-Training
• Segmentation with mixed supervision: Confidence maximization helps knowledge distillation
• Adaptive Mix for Semi-Supervised Medical Image Segmentation
• Diversified Multi-prototype Representation for Semi-supervised Segmentation
• Fully Differentiable Bidirectional Dual-Task Synergistic Learning for Semi-Supervised 3D Medical Image Segmentation