Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
arXiv:2404.10378 · doi:10.1109/CVPRW63382.2024.00323
Abstract
Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new sub-tasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.
arXiv admin note: text overlap with arXiv:2311.10476
References in corpus (8)
- Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
- Learning Face Representation from Scratch
- Deep Face Recognition: A Survey
- SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
- How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability
- Efficient Image Generation with Variadic Attention Heads
- Prototype Memory for Large-scale Face Representation Learning
- Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers