BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks

Viet Pham, Satoshi Ito and Tatsuo Kozakaya

Abstract

We present a simple and effective framework for simultaneous semantic segmentation and instance segmentation with Fully Convolutional Networks (FCNs). The method, called BiSeg, predicts instance segmentation as a posterior in Bayesian inference, where semantic segmentation is used as a prior. We extend the idea of position-sensitive score maps used in recent methods to a fusion of multiple score maps at different scales and partition modes, and adopt it as a robust likelihood for instance segmentation inference. As both Bayesian inference and map fusion are performed per pixel, BiSeg is a fully convolutional end-to-end solution that inherits all the advantages of FCNs.

Session

Posters

Files

Paper (PDF)

DOI

10.5244/C.31.60
https://dx.doi.org/10.5244/C.31.60

Citation

Bibtex

            @inproceedings{BMVC2017_60,
                title={BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks},
                author={Viet Pham, Satoshi Ito and Tatsuo Kozakaya},
                year={2017},
                month={September},
                pages={60.1-60.12},
                articleno={60},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.60},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.60}
            }