Deep Co-Training for Semi-Supervised Image Segmentation
arXiv:1903.11233
Abstract
In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images. We present a method based on an ensemble of deep segmentation models. Each model is trained on a subset of the annotated data, and uses the non-annotated images to exchange information with the other models, similar to co-training. Even if each model learns on the same non-annotated images, diversity is preserved with the use of adversarial samples. Our results show that this ability to simultaneously train models, which exchange knowledge while preserving diversity, leads to state-of-the-art results on two challenging medical image datasets.
References in corpus (10)
- A Survey on Deep Learning in Medical Image Analysis
- Temporal Ensembling for Semi-Supervised Learning
- A Survey on Multi-view Learning
- A large annotated medical image dataset for the development and evaluation of segmentation algorithms
- Semantic Segmentation using Adversarial Networks
- 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study
- Semi-Supervised Deep Learning for Fully Convolutional Networks
- Data Distillation: Towards Omni-Supervised Learning
- Deep Co-Training for Semi-Supervised Image Recognition
- A Two-Stream Mutual Attention Network for Semi-supervised Biomedical Segmentation with Noisy Labels