# Scene Parsing with Global Context Embedding

arXiv: https://arxiv.org/abs/1710.06507 · HTML: https://mlsanity.com/paper/1710.06507/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2017.

## Built on by (most cited first, 7 of 7)

- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [Semi-supervised Multi-task Learning for Semantics and Depth](https://mlsanity.com/paper/2110.07197/) (2021)
- [ORDNet: Capturing Omni-Range Dependencies for Scene Parsing](https://mlsanity.com/paper/2101.03929/) (2021)
- [Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS](https://mlsanity.com/paper/2211.01999/) (2022)
- [Contextual Information Enhanced Convolutional Neural Networks for Retinal Vessel Segmentation in Color Fundus Images](https://mlsanity.com/paper/2103.13622/) (2021)
- [Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining](https://mlsanity.com/paper/2604.11195/) (2026)
- [Hybrid supervised instance segmentation by learning label noise suppression](https://mlsanity.com/paper/2610.20412/) (2026)

## Abstract (arXiv)

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.