The 4th Look Into Person (LIP) Challenge - Track 1 Multi-Person Human Parsing Challenge

Organized by ZhenyuXie - Current server time: July 9, 2020, 7:31 a.m. UTC

First phase

Final
Feb. 20, 2020, midnight UTC

End

Competition Ends
June 6, 2020, midnight UTC

Overview

This task aims to predict the semantic part segmentation map and instance-level human parsing map of an image which contains multiple persons.

Data Description

To stimulate the multiple-human parsing research, we collect the images with multiple person instances to establish the first standard and comprehensive benchmark for instance-level human parsing. Our Crowd Instance-level Human Parsing Dataset (CIHP) contains 28280 training, 5000 validation and 5000 test images, in which there are 38280 multiple-person images in total.

You can download the dataset at CIHP(Google Drive) or CIHP(Baidu Drive).

Class Definition

Class ID012345
Class Name Background Hat Hair Glove Sunglasses Upper-clothes
Class ID67891011
Class Name Dress Coat Socks Pants Tosor-skin Scarf
Class ID121314151617
Class Name Skirt Face Left-arm Right-arm Left-leg Right-leg
Class ID1819
Class Name Left-shoe Right-shoe

Dataset Examples

Evaluation Metrics

For this task, we use two metrics for multi-human parsing evaluation. The final score is the average of the results of these two metrics.

  • Mean IoU(%) for semantic part segmentation, reported by the FCN paper.
  • APr for instance-level human parsing, first introduced in Simultaneous Detection and Segmentation. The details show APr at various IoU thresholds.

Submission Format

The results should be pack into a single zip file. Example zip file is available in mp_results.zip.

Specifically, the zip file contains two 2 sub-folders in it:

1.global_parsing
A folder of png images, named as "global_parsing". The content of id.png is the global human parsing results (instance-agnostic) for the image with exactly the same size.

2.instance_parsing
Named as "instance_parsing", this folder consist of two things:
1) An indexed-png image with the segmentation. Here, each number belongs to a unique part. 0 is always assumed to be the background label.
2) A text file. Each line is of the format < class_id score >. The first line of this file corresponds to 1 in the indexed png, the second line corresponds to 2 in the indexed png and so on.

After uploading you results, please wait for 40 to 50 minutes and refrash your page to see the scores.

Terms and Conditions

General Rules

  • Each entry is required to be associated to a team and its affiliation.
  • Using multiple accounts to increase the number of submissions is strictly prohibited.
  • Results should follow the correct format and must be uploaded to the evaluation server through the CodaLab competition site. Detailed information about how results will be evaluated is represented on the evaluation page.
  • The best entry of each team will be public in the leaderboard at all time.
  • The organizer reserves the absolute right to disqualify entries which is incomplete or illegible, late entries or entries that violate the rules.

Datasets

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.

Concate Us

For more information, please concate us at xiezhy6@mail2.sysu.edu.cn or donghy7@mail2.sysu.edu.cn.

Final

Start: Feb. 20, 2020, midnight

Competition Ends

June 6, 2020, midnight

You must be logged in to participate in competitions.

Sign In