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. Our architecture shows a 25% relative meanIoU improvement compared to the best baseline methods for one-shot segmentation on unseen classes in the PASCAL VOC 2012 dataset and is at least 3 times faster.
@article{arxiv.1709.03410,
title = {One-Shot Learning for Semantic Segmentation},
author = {Amirreza Shaban and Shray Bansal and Zhen Liu and Irfan Essa and Byron Boots},
journal= {arXiv preprint arXiv:1709.03410},
year = {2017}
}
Comments
To appear in the proceedings of the British Machine Vision Conference (BMVC) 2017. The code is available at https://github.com/lzzcd001/OSLSM