Panoptic segmentation with a joint semantic and instance segmentation network

Research output: Working paperAcademic

18 Downloads (Pure)

Abstract

We present a single network method for panoptic segmentation. This method combines the predictions from a jointly trained semantic and instance segmentation network using heuristics. Joint training is the first step towards an end-to-end panoptic segmentation network and is faster and more memory efficient than training and predicting with two networks, as done in previous work. The architecture consists of a ResNet-50 feature extractor shared by the semantic segmentation and instance segmentation branch. For instance segmentation, a Mask R-CNN type of architecture is used, while the semantic segmentation branch is augmented with a Pyramid Pooling Module. Results for this method are submitted to the COCO and Mapillary Joint Recognition Challenge 2018. Our approach achieves a PQ score of 17.6 on the Mapillary Vistas validation set and 27.2 on the COCO test-dev set.
Original languageEnglish
PublisherarXiv.org
Pages1-6
Number of pages6
Publication statusUnpublished - 6 Sep 2018

Bibliographical note

Technical report

Keywords

  • cs.CV

Fingerprint Dive into the research topics of 'Panoptic segmentation with a joint semantic and instance segmentation network'. Together they form a unique fingerprint.

  • Cite this