ECCV 2020 ChaLearn Looking at People Fair Face Recognition Workshop and Challenge

ChaLearn FairFaceRec Challenge 2020


Computer Graphics Computer Vision & Pattern Recognition



We cordially invite you to participate to our
ECCV 2020 ChaLearn Looking at People Fair Face Recognition Workshop and Challenge
For additional details and important dates, please check the following channels of communication:
Workshop: http://chalearnlap.cvc.uab.es/workshop/37/description/
Challenge: http://chalearnlap.cvc.uab.es/challenge/38/description/
Workshop: The workshop will focus on bias analysis and mitigation methodologies, which will result in more fair face recognition and analysis systems. These advances will have a direct impact within society's equality of opportunity. In this proposal we plan to provide a comprehensive up to date review on fair face recognition and analysis research. We find of crucial interest to centralize ideas, discuss them and push the field to advance towards more fair systems for the good of society. Complementary to that, we will also contribute pushing research in the field by releasing a large annotated dataset for fair face verification and running an associated challenge.
Challenge: We present a new collected dataset with 15k images from 3k new subjects along with a reannotated version of IJB-C database (140k images from 3.5k subjects), totalling 155k facial images from 6.5k unique identities. Both databases have been accurately annotated for gender and skin colour (protected attributes) as well as for age group, eyeglasses, head pose, image source and face size. We will evaluate submitted models for bias in terms of total causal effect of the protected attributes (including their combination) to the verification accuracy while adjusting for the other attributes. The final ranking of each model will depend both on its bias and accuracy with the emphasis on bias.
Preliminary (tentative) Schedule:
Workshop:
- Paper submission: July 7th, 2020
- Notification to authors: July 28th, 2020
- Camera-ready: September 4th, 2020
Challenge
- Start of the challenge (development phase): April 7th, 2020
- Start of test phase: June 22th, 2020
- End of the challenge: July 1st, 2020
- Fact sheets and code submission: July 4th, 2020
- Release of final results: July 12th, 2020
ORGANIZATION & SPONSORS
Sergio Escalera, Computer Vision Center (UAB) and University of Barcelona, Spain
Rama Chellappa, University of Maryland, United States of America
Eduard Vazquez, Anyvision, Belfast, Northern Ireland
Neil Robertson, Queen’s University Belfast / Anyvision, Belfast, Northern Ireland
Pau Buch-Cardona, Computer Vision Center (UAB) and University of Barcelona, Spain
Tomas Sixta, Belfast, Northern Ireland
Julio C. S. Jacques Junior, Universitat Oberta de Catalunya (UOC) and Computer Vision Center (CVC/UAB), Spain
This event is sponsored by ChaLearn and Anyvision.