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. |
Year | DOI | Venue |
---|---|---|
2017 | 10.5244/c.31.167 | BMVC |
DocType | Volume | Citations |
Conference | abs/1709.03410 | 13 |
PageRank | References | Authors |
0.53 | 27 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Amirreza Shaban | 1 | 48 | 5.60 |
Shray Bansal | 2 | 44 | 2.57 |
Zhen Liu | 3 | 40 | 5.01 |
Irfan A. Essa | 4 | 4876 | 580.85 |
Byron Boots | 5 | 471 | 50.73 |