Quality-based Regularization for Iterative Deep Image Segmentation

Traditional image segmentation algorithms operate by iteratively working over an image, as if refining a segmentation until a stopping criterion is met. Deep learning has replaced traditional approaches, achieving state-of-the-art performance in many problems, one of them being image segmentation. However, the concept of segmentation refinement is not present anymore, since usually the images are segmented in a single step. This work focuses on the refinement of image segmentations using deep convolutional neural networks, with the addition of a quality prediction output. The output from a state-of-the-art base segmenter is refined, simultaneously improving it and trying to predict its quality. We show that the quality concept can be used as a regularizer while training a network for direct segmentation refinement.