Deep Watershed Transform for Instance Segmentation

Min Bai, Raquel Urtasun; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 5221-5229

Abstract


Most contemporary approaches to instance segmentation use complex pipelines involving conditional random fields, recurrent neural networks, object proposals, or template matching schemes. In this paper, we present a simple yet powerful end-to-end convolutional neural network to tackle this task. Our approach combines intuitions from the classical watershed transform and modern deep learning to produce an energy map of the image where object instances are unambiguously represented as energy basins. We then perform a cut at a single energy level to directly yield connected components corresponding to object instances. Our model achieves more than double the performance over the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Bai_2017_CVPR,
author = {Bai, Min and Urtasun, Raquel},
title = {Deep Watershed Transform for Instance Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}