One-Shot Learning for Semantic Segmentation

Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa and Byron Boots

Abstract

Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images, produces parameters for a Fully Convolutional Network (FCN). We use this FCN to perform dense pixel-level prediction on a test image for the new semantic class.

Session

Posters

Files

PDF iconPaper (PDF)
PDF iconSupplementary (PDF)

DOI

10.5244/C.31.167
https://dx.doi.org/10.5244/C.31.167

Citation

Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa and Byron Boots. One-Shot Learning for Semantic Segmentation. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 167.1-167.13. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_167,
                title={One-Shot Learning for Semantic Segmentation},
                author={Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa and Byron Boots},
                year={2017},
                month={September},
                pages={167.1-167.13},
                articleno={167},
                numpages={13},
                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.31.167},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.167}
            }