SceneUnderstanding/ADE20K
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Xavier Puig 2021-02-28 11:54:11 -05:00 committed by GitHub
parent d39b854b78
commit b1c8808dd1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -1,17 +1,23 @@
# ADE20K Dataset
This is the repository for the [ADE20K](http://groups.csail.mit.edu/vision/datasets/ADE20K/) dataset. We provide some [starter code](notebooks/ade20k_starter.ipynb) to analyze the dataset, basic statistics of the data and links to existing projects using ADE20K.
<img src="assets/slider.png" style="height: 200px; width: 50%">
This is the repository for the [ADE20K](https://groups.csail.mit.edu/vision/datasets/ADE20K/) dataset. We provide some [starter code](./notebooks/ade20k_starter.ipynb) to analyze the dataset, basic statistics of the data and links to existing projects using ADE20K.
## Overview
write
This dataset is composed of more than 25K images from the SUN and Places databases. Images are fully annotated with objects, spanning over 3K object categories. Many of the images also contain object parts, and parts of parts. We also provide the original annotated polygons, as well as object instances for amodal segmentation.
## Download dataset
To download the dataset, register in [this link](http://groups.csail.mit.edu/vision/datasets/ADE20K/request_data/). Once you are approved you will be able to download the data, following the [terms of use](http://groups.csail.mit.edu/vision/datasets/ADE20K/terms).
## Download
To download the dataset, register in [this link](http://groups.csail.mit.edu/vision/datasets/ADE20K/request_data/). Once you are approved you will be able to download the data, following the [Terms of Use](http://groups.csail.mit.edu/vision/datasets/ADE20K/terms).
## ADE20K related projects
Here is a list of existing challenges and projects using ADE20K data. Contact us if you would like to include the dataset in a new benchmark.
* [MIT Scene Parsing Benchmark](https://github.com/CSAILVision/sceneparsing): A semantic segmentation benchmark, using a subset of 250 classes from ADE20K
* [Robust Vision Challenge](http://www.robustvision.net/): A challenge to evaluate the robustness of models to multiple datasets and tasks, including semantic and instance segmentation, depth prediction, optical flow, etc.
## Terms
The data can be used under the following [Terms of Use](http://groups.csail.mit.edu/vision/datasets/ADE20K/terms).
## Citation
If you use this data, please cite the following paper: