ParseNet: Looking Wider to See Better

June 15, 2015 · Entered Twilight · 🏛 arXiv.org

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

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

Authors Wei Liu, Andrew Rabinovich, Alexander C. Berg arXiv ID 1506.04579 Category cs.CV: Computer Vision Citations 1.3K Venue arXiv.org Repository https://github.com/weiliu89/caffe/tree/fcn ⭐ 4807 Last Checked 1 month ago

Abstract

We present a technique for adding global context to deep convolutional networks for semantic segmentation. The approach is simple, using the average feature for a layer to augment the features at each location. In addition, we study several idiosyncrasies of training, significantly increasing the performance of baseline networks (e.g. from FCN). When we add our proposed global feature, and a technique for learning normalization parameters, accuracy increases consistently even over our improved versions of the baselines. Our proposed approach, ParseNet, achieves state-of-the-art performance on SiftFlow and PASCAL-Context with small additional computational cost over baselines, and near current state-of-the-art performance on PASCAL VOC 2012 semantic segmentation with a simple approach. Code is available at https://github.com/weiliu89/caffe/tree/fcn .