Pyramid Scene Parsing Network (2016-12-04T00:00:00.000000Z)

TL;DR

This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.

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.

Authors

Xiaogang Wang

21 papers

Jiaya Jia

23 papers

Jianping Shi

9 papers

TL;DR

Abstract

Authors

References47 items

Back Propagation

Convolutional Scale Invariance for Semantic Segmentation

Semantic Understanding of Scenes Through the ADE20K Dataset

Gaussian Conditional Random Field Network for Semantic Segmentation

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Bridging Category-level and Instance-level Semantic Image Segmentation

Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation

The Cityscapes Dataset for Semantic Urban Scene Understanding

Deep Residual Learning for Image Recognition

Higher Order Conditional Random Fields in Deep Neural Networks

Multi-Scale Context Aggregation by Dilated Convolutions

Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net

Attention to Scale: Scale-Aware Semantic Image Segmentation

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Semantic Image Segmentation via Deep Parsing Network

Towards Good Practices for Very Deep Two-Stream ConvNets

ParseNet: Looking Wider to See Better

Learning Deconvolution Network for Semantic Segmentation

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Conditional Random Fields as Recurrent Neural Networks

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Object Detectors Emerge in Deep Scene CNNs

Scalable, High-Quality Object Detection

Feedforward semantic segmentation with zoom-out features

Hypercolumns for object segmentation and fine-grained localization

Fully convolutional networks for semantic segmentation

Deeply-Supervised Nets

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

The Role of Context for Object Detection and Semantic Segmentation in the Wild

Caffe: Convolutional Architecture for Fast Feature Embedding

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Microsoft COCO: Common Objects in Context

ImageNet classification with deep convolutional neural networks

Nonparametric Scene Parsing via Label Transfer

Are spatial and global constraints really necessary for segmentation?

Semantic contours from inverse detectors

Nonparametric scene parsing: Label transfer via dense scene alignment

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

International Journal of Computer Vision manuscript No. (will be inserted by the editor) The PASCAL Visual Object Classes (VOC) Challenge

Methods pre-trained on MS-COCO are marked with ' †'. Method road swalk build. wall fence pole tlight sign veg. terrain sky person rider car truck bus train mbike bike mIoU CRF-RNN

Method aero bike bird boat bottle bus car cat chair cow table dog horse mbike person plant sheep sofa train tv mIoU

Visual comparison on PASCAL VOC 2012 data. (a) Image. (b) Ground Truth

Methods trained using both fine and coarse set are marked with

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names