Distance transform regression for spatially-aware deep semantic segmentation

• Published in: Computer vision and image understanding 2019-12, Vol.189, p.102809, Article 102809
• Main Authors: Audebert, Nicolas, Boulch, Alexandre, Le Saux, Bertrand, Lefèvre, Sébastien
• Format: Article
• Language: English
• Subjects: Computer Science; Computer Vision and Pattern Recognition; Neural and Evolutionary Computing
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2019.102809

Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks. However, due to the nature of the networks, predictions often suffer from blurry boundaries and ill-segmented shapes, fueling the need for post-processing. This work introduces a new semantic segmentation regularization based on the regression of a distance transform. After computing the distance transform on the label masks, we train a FCN in a multi-task setting in both discrete and continuous spaces by learning jointly classification and distance regression. This requires almost no modification of the network structure and adds a very low overhead to the training process. Learning to approximate the distance transform back-propagates spatial cues that implicitly regularizes the segmentation. We validate this technique with several architectures on various datasets, and we show significant improvements compared to competitive baselines. •We introduce a multi-task scheme to spatially regularize predictions in the semantic segmentation setting based on distance transform.•The method is simple to implement and can be applied to all fully convolutional networks from the state of the art.•The method does not require any additional annotation.•The method is thoroughly validated on several remote sensing and computer vision datasets and various deep models.