Synthetic Data for Face Recognition (SDFR) Competition at FG 2024

Home
Competition Session at FG 2024

The competition session will be held at 2:00pm - 3:30pm on Monday, 27 May 2024, in Room 2.

Agenda

2:00pm - 2:10pm Introduction to SDFR Competition
2:10pm - 3:00pm Keynote (Dr. Naser Damer)
3:00pm - 3:15pm Overview of the SDFR Competition
3:15pm - 3:20pm Winner of Task 1
3:20pm - 3:25pm Winner of Task 2
3:25pm - 3:30pm Closing Notes

Keynote

The invited keynote talk for the competition session will be given by Dr. Naser Damer, Fraunhofer IGD, Germany:

Title: Training Strategies for Synthetic-based Face Recognition Models

Abstract: Training face recognition model requires large and diverse data to optimize the huge number of deep learning model parameters while avoiding extreme overfitting. Given the technical, legal, and ethical challenges, collecting and sharing such data is extremely challenging. This motivated the recent move towards generating and using synthetic face data to develop face recognition models and systems. Such synthetic faces can be used to train these models in different manners depending on the goal of the training, as well as the available resources. For example, the knowledge of previously trained face recognition models might be less challenging to share than the data used to train it. However, such models might not be suitable for certain use cases, but their embedded knowledge is still valuable. Training face recognition models, not necessarily only on synthetic data, but with limited authentic-based resources, will be the focus of this talk. This will be also supported by shortly discussing the generation processes and the relation between authentic and synthetic face data.

Pineapple

Biography: Dr. Naser Damer is a senior researcher at the competence center Smart Living & Biometric Technologies, Fraunhofer IGD. He received his master of science degree in electrical engineering from the Technische Universität Kaiserslautern (2010) and his PhD in computer science from the Technischen Universität Darmstadt (2018). He is a researcher at Fraunhofer IGD since 2011 performing applied research, scientific consulting, and system evaluation. His main research interests lie in the fields of biometrics, machine learning and information fusion. He published more than 50 scientific papers in these fields. Dr. Damer is a Principal Investigator at the National Research Center for Applied Cybersecurity CRISP in Darmstadt, Germany. He serves as a reviewer for a number of journals and conferences and as an associate editor for the Visual Computer journal. He represents the German Institute for Standardization (DIN) in ISO/IEC SC37 biometrics standardization committee.