One-Shot Learning for Semantic Segmentation
2017-09-11Code Available1· sign in to hype
Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa, Byron Boots
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/lzzcd001/OSLSMOfficialIn papernone★ 0
- github.com/chunbolang/DCPpytorch★ 35
- github.com/zwzheng98/qclnetpytorch★ 5
- github.com/vamsirk/OneShotSemanticSegmentationnone★ 0
- github.com/vamsirk/FewShotLearningnone★ 0
- github.com/RogerQi/pascal-5ipytorch★ 0
- github.com/ml4ai/mliistf★ 0
- github.com/woaixuexixuexi/PSANetpytorch★ 0
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. 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.