Referring Expression Datasets API
The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
This API is able to load all 4 referring expression datasets, i.e., RefClef, RefCOCO, RefCOCO+ and RefCOCOg. They are with different train/val/test split by UNC, Google and UC Berkeley respectively. We provide all kinds of splits here.
If you used the following three datasets RefClef, RefCOCO and RefCOCO+ that were collected by UNC, please consider cite our EMNLP2014 paper; if you want to compare with our recent results, please check our ECCV2016 paper.
bash Kazemzadeh, Sahar, et al. "ReferItGame: Referring to Objects in Photographs of Natural Scenes." EMNLP 2014. Yu, Licheng, et al. "Modeling Context in Referring Expressions." ECCV 2016.
Run "make" before using the code. It will generate
external/folder. These mask-related codes are copied from mscoco API.
Download the cleaned data and extract them into "data" folder - 1) http://bvisionweb1.cs.unc.edu/licheng/referit/data/refclef.zip - 2) http://bvisionweb1.cs.unc.edu/licheng/referit/data/refcoco.zip - 3) http://bvisionweb1.cs.unc.edu/licheng/referit/data/refcoco+.zip - 4) http://bvisionweb1.cs.unc.edu/licheng/referit/data/refcocog.zip
Besides, add "mscoco" into the
data/imagesfolder, which can be from mscoco COCO's images are used for RefCOCO, RefCOCO+ and refCOCOg. For RefCLEF, please add
data/imagesfolder. We extracted the related 19997 images to our cleaned RefCLEF dataset, which is a subset of the original imageCLEF. Download the subset and unzip it to
The "refer.py" is able to load all 4 datasets with different kinds of data split by UNC, Google, UMD and UC Berkeley. Note for RefCOCOg, we suggest use UMD's split which has train/val/test splits and there is no overlap of images between different split. ```bash
refer = REFER(dataroot, dataset='refclef', splitBy='unc') refer = REFER(dataroot, dataset='refclef', splitBy='berkeley') # 2 train and 1 test images missed refer = REFER(dataroot, dataset='refcoco', splitBy='unc') refer = REFER(dataroot, dataset='refcoco', splitBy='google') refer = REFER(dataroot, dataset='refcoco+', splitBy='unc') refer = REFER(dataroot, dataset='refcocog', splitBy='google') # test split not released yet refer = REFER(data_root, dataset='refcocog', splitBy='umd') # Recommended, including train/val/test ```