PSPNet

Pyramid Scene Parsing Network

Introduction

Official Repo

Code Snippet

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 tasks. 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 new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.

Citation

@inproceedings{zhao2017pspnet,
  title={Pyramid Scene Parsing Network},
  author={Zhao, Hengshuang and Shi, Jianping and Qi, Xiaojuan and Wang, Xiaogang and Jia, Jiaya},
  booktitle={CVPR},
  year={2017}
}

@article{wightman2021resnet,
  title={Resnet strikes back: An improved training procedure in timm},
  author={Wightman, Ross and Touvron, Hugo and J{\'e}gou, Herv{\'e}},
  journal={arXiv preprint arXiv:2110.00476},
  year={2021}
}

Results and models

Cityscapes

ADE20K

Pascal VOC 2012 + Aug

Pascal Context

Pascal Context 59

Dark Zurich and Nighttime Driving

We support evaluation results on these two datasets using models above trained on Cityscapes training set.

COCO-Stuff 10k

COCO-Stuff 164k

LoveDA

Potsdam

Vaihingen

iSAID

Note:

• FP16 means Mixed Precision (FP16) is adopted in training.
• 896x896 is the Crop Size of iSAID dataset, which is followed by the implementation of PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
• rsb is short for 'Resnet strikes back'.
• The b in R-50b means ResNetV1b, which is a standard ResNet backbone. In MMSegmentation, default backbone is ResNetV1c, which usually performs better in semantic segmentation task.