Semantic Instance Segmentation for Autonomous Driving
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 478-480
- https://doi.org/10.1109/cvprw.2017.66
Abstract
Semantic instance segmentation remains a challenge. We propose to tackle the problem with a discriminative loss function, operating at pixel level, that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step. Our approach of combining an off-the-shelf network with a principled loss function inspired by a metric learning objective is conceptually simple and distinct from recent efforts in instance segmentation and is well-suited for real-time applications. In contrast to previous works, our method does not rely on object proposals or recurrent mechanisms and is particularly well suited for tasks with complex occlusions. A key contribution of our work is to demonstrate that such a simple setup without bells and whistles is effective and can perform on-par with more complex methods. We achieve competitive performance on the Cityscapes segmentation benchmark.Keywords
This publication has 8 references indexed in Scilit:
- Instance-Aware Semantic Segmentation via Multi-task Network CascadesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- The Cityscapes Dataset for Semantic Urban Scene UnderstandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Monocular Object Instance Segmentation and Depth Ordering with CNNsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- FaceNet: A unified embedding for face recognition and clusteringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Multi-instance object segmentation with occlusion handlingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Large scale metric learning from equivalence constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Learning a Similarity Metric Discriminatively, with Application to Face VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The estimation of the gradient of a density function, with applications in pattern recognitionIEEE Transactions on Information Theory, 1975