Pyramid Scene Parsing Network

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)....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 6230 - 6239
Hlavní autoři: Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.07.2017
Témata:
Automobiles
Convolution
Feature extraction
Image segmentation
Neural networks
Semantics
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2017.660