Semantic Understanding of Scenes through the ADE20K Dataset

Bolei Zhou, Hang Zhao, Xavier Puig, Tete Xiao, Sanja Fidler +2 more
8/18/2016
cs.CV

Official code: CSAILVision/semantic-segmentation-pytorch (5,083 stars, BSD-3-Clause, PyTorch, last commit 2024-01-15).

Abstract

Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision. Despite the community's efforts in data collection, there are still few image datasets covering a wide range of scenes and object categories with dense and detailed annotations for scene parsing. In this paper, we introduce and analyze the ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. A generic network design called Cascade Segmentation Module is then proposed to enable the segmentation networks to parse a scene into stuff, objects, and object parts in a cascade. We evaluate the proposed module integrated within two existing semantic segmentation networks, yielding significant improvements for scene parsing. We further show that the scene parsing networks trained on ADE20K can be applied to a wide variety of scenes and objects.

View on arXivView PDF

Code Implementations(1)

CSAILVision/semantic-segmentation-pytorchOfficial100%
PyTorchBSD-3-Clause

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

5,0831,095Shell, PythonOct 7, 20172 years agoBSD-3-Clause
ade20kpytorchscene-recognitionsemantic-segmentation

Similar Papers

MacFormer: Semantic Segmentation with Fine Object Boundaries

83% match2024

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

83% match1 repo2822016

Unified Semantic Transformer for 3D Scene Understanding

83% match2025

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

82% match1 repo4902016

Unified Perceptual Parsing for Scene Understanding

82% match1 repo4282018

DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

82% match1 repo5712021

Cite this paper

@article{zhou2016semantic,
  title  = {Semantic Understanding of Scenes through the ADE20K Dataset},
  author = {Bolei Zhou and Hang Zhao and Xavier Puig and Tete Xiao and Sanja Fidler and Adela Barriuso and Antonio Torralba},
  year   = {2016},
  eprint = {1608.05442},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1608.05442}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1608.05442.svg)](https://codeofpaper.com/paper/1608.05442)

Discussion