One-Shot Learning for Semantic Segmentation

September 11, 2017 · Entered Twilight · 🏛 British Machine Vision Conference

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .Doxyfile, .gitignore, .travis.yml, CMakeLists.txt, CONTRIBUTING.md, CONTRIBUTORS.md, INSTALL.md, LICENSE, Makefile, Makefile.config.example, OSLSM, README.md, caffe.cloc, cmake, config.sh, docker, docs, examples, include, matlab, python, scripts, src, tools

Authors Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa, Byron Boots arXiv ID 1709.03410 Category cs.CV: Computer Vision Citations 838 Venue British Machine Vision Conference Repository https://github.com/lzzcd001/OSLSM ⭐ 119 Last Checked 1 month ago

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.