· 2017
Pyramid Scene Parsing Network
- 15,565citations
- 2017year
Short summary
The Pyramid Scene Parsing Network (PSPNet) introduces a pyramid pooling module to aggregate global context, achieving state-of-the-art scene parsing performance.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces a pyramid pooling module for global context aggregation in scene parsing.
- PSPNet provides a superior framework for pixel-level prediction tasks.
- Achieved state-of-the-art performance on ImageNet, PASCAL VOC 2012, and Cityscapes benchmarks.
- Set new records with 85.4% mIoU on PASCAL VOC 2012 and 80.2% accuracy on Cityscapes.
AI-generated from the title and abstract; the full text is not read.
Abstract
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.
The authors' abstract, as published at the source., 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science