This task aims to predict the segmentation map of an image containing dark complexion portrait.
To stimulate the dark complexion portrait segmentation research, we collect the images with dark complexion portrait to establish the benchmark for dark complexion portrait segmentation. Our Dark Complexion Portrait Segmentation Dataset (DCPS) contains 12165 training and 2570 test images, in which there are 14735 dark complexion portrait images in total.
For this task, we use Mean IoU(%) for dark complexion portrait segmentation evaluation.
The results should be pack into a single zip file. Example zip file is available in example_results.zip.
Specifically, the zip file contains one sub-folder in it:
A folder of png images, named as "segmentation". The content of id.png is the segmentation results for the image with exactly the same size.
After uploading you results, please wait for 10 to 20 minutes and refrash your page to see the scores.
The datasets are released for academic research only and it is free to researchers from educational or research institutions for non-commercial purposes. When downloading the dataset you agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purposes, any portion of the images and any portion of derived data.
For more information, please concate us at firstname.lastname@example.org or email@example.com.
Start: March 20, 2020, midnight
Sept. 30, 2020, midnight
You must be logged in to participate in competitions.Sign In