Distance transform regression for spatially-aware deep semantic segmentation

Abstract : 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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02277621
Contributor : Nicolas Audebert <>
Submitted on : Tuesday, September 3, 2019 - 5:19:19 PM
Last modification on : Sunday, November 3, 2019 - 6:48:31 PM

Identifiers

Citation

Nicolas Audebert, Alexandre Boulch, Bertrand Le Saux, Sébastien Lefèvre. Distance transform regression for spatially-aware deep semantic segmentation. Computer Vision and Image Understanding, Elsevier, 2019, 189, pp.102809. ⟨10.1016/j.cviu.2019.102809⟩. ⟨hal-02277621⟩

Share

Metrics

Record views

63

Files downloads

47