Scene Parsing with Global Context Embedding

October 17, 2017 · Entered Twilight · 🏛 IEEE International Conference on Computer Vision

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, context_feats, data, eval.py, get_model.sh, get_prior.sh, models, priors, prototxt, python_layers

Authors Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang arXiv ID 1710.06507 Category cs.CV: Computer Vision Citations 56 Venue IEEE International Conference on Computer Vision Repository https://github.com/hfslyc/GCPNet ⭐ 22 Last Checked 1 month ago

Abstract

We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context network based on scene similarities to generate feature representations for global contexts. In addition, these learned features are utilized to generate global and spatial priors for explicit classes inference. We then design modules to embed the feature representations and the priors into the segmentation network as additional global context cues. We show that the proposed method can eliminate false positives that are not compatible with the global context representations. Experiments on both the MIT ADE20K and PASCAL Context datasets show that the proposed method performs favorably against existing methods.