Deep co-training for semi-supervised image segmentation
Deep co-training for semi-supervised image segmentation
Peng, J and Estrada, G and Pedersoli, M and Desrosiers, C
Pattern Recognition 2020
Abstract : In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting where training is performed with a reduced set of annotated images and additional non-annotated images. We present a method based on an ensemble of deep łdots