Home

Awesome

The COCO-Stuff dataset

Holger Caesar, Jasper Uijlings, Vittorio Ferrari

<img src="http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/cocostuff-examples.png" alt="COCO-Stuff example annotations" width="100%"> Welcome to official homepage of the COCO-Stuff [1] dataset. COCO-Stuff augments all 164K images of the popular COCO [2] dataset with pixel-level stuff annotations. These annotations can be used for scene understanding tasks like semantic segmentation, object detection and image captioning.

Overview

Highlights

Explore COCO-Stuff

You can now use Scale's Nucleus platform to explore the COCO-Stuff dataset. The platform allows you to search for images with specific annotations or using textual image descriptions. You can also identify potential annotation errors by comparing the predictions of an object detector to the ground-truth of COCO-Stuff. Registration is free! You can learn more at the Scale homepage link above.

COCO-Stuff on Nucleus

Research Paper

COCO-Stuff: Thing and Stuff Classes in Context<br /> H. Caesar, J. Uijlings, V. Ferrari,<br /> In Computer Vision and Pattern Recognition (CVPR), 2018.<br /> [paper][bibtex]

Versions of COCO-Stuff

Downloads

FilenameDescriptionSize
train2017.zipCOCO 2017 train images (118K images)18 GB
val2017.zipCOCO 2017 val images (5K images)1 GB
stuffthingmaps_trainval2017.zipStuff+thing PNG-style annotations on COCO 2017 trainval659 MB
stuff_trainval2017.zipStuff-only COCO-style annotations on COCO 2017 trainval543 MB
annotations_trainval2017.zipThing-only COCO-style annotations on COCO 2017 trainval241 MB
labels.mdIndices, names, previews and descriptions of the classes in COCO-Stuff<10 KB
labels.txtMachine readable version of the label list<10 KB
README.mdThis readme<10 KB

To use this dataset you will need to download the images (18+1 GB!) and annotations of the trainval sets. To download earlier versions of this dataset, please visit the COCO 2017 Stuff Segmentation Challenge or COCO-Stuff 10K.

Caffe-compatible stuff-thing maps We suggest using the stuffthingmaps, as they provide all stuff and thing labels in a single .png file per image. Note that the .png files are indexed images, which means they store only the label indices and are typically displayed as grayscale images. To be compatible with most Caffe-based semantic segmentation methods, thing+stuff labels cover indices 0-181 and 255 indicates the 'unlabeled' or void class.

Separate stuff and thing downloads Alternatively you can download the separate files for stuff and thing annotations in COCO format, which are compatible with the COCO-Stuff API. Note that the stuff annotations contain a class 'other' with index 183 that covers all non-stuff pixels.

Setup

Use the following instructions to download the COCO-Stuff dataset and setup the folder structure. The instructions are for Ubuntu and require git, wget and unzip. On other operating systems the commands may differ:

# Get this repo
git clone https://github.com/nightrome/cocostuff.git
cd cocostuff

# Download everything
wget --directory-prefix=downloads http://images.cocodataset.org/zips/train2017.zip
wget --directory-prefix=downloads http://images.cocodataset.org/zips/val2017.zip
wget --directory-prefix=downloads http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/stuffthingmaps_trainval2017.zip

# Unpack everything
mkdir -p dataset/images
mkdir -p dataset/annotations
unzip downloads/train2017.zip -d dataset/images/
unzip downloads/val2017.zip -d dataset/images/
unzip downloads/stuffthingmaps_trainval2017.zip -d dataset/annotations/

Results

Below we present results on different releases of COCO-Stuff. If you would like to see your results here, please contact the first author.

Results on the val set of COCO-Stuff:

MethodSourceClass accuracyPixel accuracyMean IOUFW IOU
Deeplab VGG-16 (no CRF) [4][1]45.1%63.6%33.2%47.6%

Note that the results between the 10K dataset and the full dataset are not direclty comparable, as different train and val images are used. Furthermore, on the full dataset we train Deeplab for 100K iterations [1], compared to 20K iterations on the 10K dataset [1b].

Results on the val set of the COCO 2017 Stuff Segmentation Challenge:

We show results on the val set of the challenge. Please refer to the official leaderboard for results on the test-dev and test-challenge sets. Note that these results are not comparable to other COCO-Stuff results, as the challenge only includes a single thing class 'other'.

MethodSourceClass accuracyPixel accuracyMean IOUFW IOU
Inplace-ABN sync[8]--24.9%-

Results on the val set of COCO-Stuff 10K:

MethodSourceClass accuracyPixel accuracyMean IOUFW IOU
FCN-16s [3][1b]34.0%52.0%22.7%-
Deeplab VGG-16 (no CRF) [4][1b]38.1%57.8%26.9%-
FCN-8s [3][6]38.5%60.4%27.2%-
SCA VGG-16 [7][7]42.5%61.6%29.1%-
DAG-RNN + CRF [6][6]42.8%63.0%31.2%-
DC + FCN+ [5][5]44.6%65.5%33.6%50.6%
Deeplab ResNet (no CRF) [4]-45.5%65.1%34.4%50.4%
CCL ResNet-101 [10][10]48.8%66.3%35.7%-
DSSPN ResNet finetune [9][9]48.1%69.4%37.3%-
* OHE + DC + FCN+ [5][5]45.8%66.6%34.3%51.2%
* W2V + DC + FCN+ [5][5]45.1%66.1%34.7%51.0%
* DSSPN ResNet universal [9][9]50.3%70.7%38.9%-

* Results not comparable as they use external data

Labels

Label Names & Indices

To be compatible with COCO, COCO-Stuff has 91 thing classes (1-91), 91 stuff classes (92-182) and 1 class "unlabeled" (0). Note that 11 of the thing classes of COCO do not have any segmentation annotations (blender, desk, door, eye glasses, hair brush, hat, mirror, plate, shoe, street sign, window). The classes desk, door, mirror and window could be either stuff or things and therefore occur in both COCO and COCO-Stuff. To avoid confusion we add the suffix "-stuff" or "-other" to those classes in COCO-Stuff. The full list of classes and their descriptions can be found here.

Label Hierarchy

This figure shows the label hierarchy of COCO-Stuff including all stuff and thing classes: <img src="https://github.com/nightrome/cocostuff10k/blob/master/dataset/cocostuff-labelhierarchy.png?raw=true" alt="COCO-Stuff label hierarchy" width="100%">

Semantic Segmentation Models (stuff+things)

PyTorch model

We recommend this third party re-implementation of Deeplab v2 in PyTorch. Contrary to our Caffe model, it supports ResNet and CRFs. The authors provide setup routines and models for COCO-Stuff 164K. Please file any issues or questions on the project's GitHub page.

Caffe model

Here we provide the Caffe-based segmentation model used in the COCO-Stuff paper. However, for users not familiar with Caffe we recommend the above PyTorch model. Before using the semantic segmentation model, please setup the dataset. The commands below download and install Deeplab (incl. Caffe), download or train the model and predictions and evaluate the performance. The results should be the same as in the table. Due to several issues, we do not provide the Deeplab ResNet101 model, but some code for it can be found in this folder.

# Get and install Deeplab (you may need to change settings)
# We use a special version of Deeplab v2 that supports CuDNN v5, but others may work as well.
git submodule update --init models/deeplab/deeplab-v2
cd models/deeplab/deeplab-v2
cp Makefile.config.example Makefile.config
make all -j8

# Create symbolic links to the images and annotations
cd models/deeplab/cocostuff/data && ln -s ../../../../dataset/images images && ln -s ../../../../dataset/annotations annotations && cd ../../../..

# Option 1: Download the initial model
# wget --directory-prefix=models/deeplab/cocostuff/model/deeplabv2_vgg16 http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/deeplabv2_vgg16_init.caffemodel

# Option 2: Download the trained model
# wg --directory-prefix=downloads http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/deeplab_cocostuff_trainedmodel.zip
# zip downloads/deeplab_cocostuff_trainedmodel.zip -d models/deeplab/cocostuff/model/deeplabv2_vgg16/model120kimages/

# Option 3: Run training & test
# cd models/deeplab && ./run_cocostuff_vgg16.sh && cd ../..

# Option 4 (fastest): Download predictions
wget --directory-prefix=downloads http://calvin.inf.ed.ac.uk/wp-content/uploads/data/cocostuffdataset/deeplab_predictions_cocostuff_val2017.zip
unzip downloads/deeplab_predictions_cocostuff_val2017.zip -d models/deeplab/cocostuff/features/deeplabv2_vgg16/model120kimages/val/fc8/

# Evaluate performance
python models/deeplab/evaluate_performance.py

The table below summarizes the files used in these instructions:

FilenameDescriptionSize
deeplabv2_vgg16_init.caffemodelDeeplab VGG-16 pretrained model (original link)152 MB
deeplab_cocostuff_trainedmodel.zipDeeplab VGG-16 trained on COCO-Stuff286 MB
deeplab_predictions_cocostuff_val2017.zipDeeplab VGG-16 predictions on COCO-Stuff54 MB

Note that the Deeplab predictions need to be rotated and cropped, as shown in this script.

Annotation Tool

For the Matlab annotation tool used to annotate the initial 10K images, please refer to this repository.

Misc

References

Licensing

COCO-Stuff is a derivative work of the COCO dataset. The authors of COCO do not in any form endorse this work. Different licenses apply:

Acknowledgements

This work is supported by the ERC Starting Grant VisCul. The annotations were done by the crowdsourcing startup Mighty AI, and financed by Mighty AI and the Common Visual Data Foundation.

Contact

If you have any questions regarding this dataset, please contact us at holger-at-it-caesar.com.