A5088528442- Face recognition and analysis
- Face and Expression Recognition
- Biometric Identification and Security
- Advanced Image and Video Retrieval Techniques
ITMO University
2022-2023
Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, its usual "full softmax" form is not suitable for millions persons. Several methods, based on "sampled were proposed to remove this limitation. These however, have set disadvantages. One them problem "prototype obsolescence": classifier weights (prototypes) rarely sampled classes receive too scarce...
Prototype Memory is a powerful model for face representation learning. It enables the training of recognition models using datasets any size, with on-the-fly generation prototypes (classifier weights) and efficient ways their utilization. demonstrated strong results in many benchmarks. However, algorithm prototype generation, used it, prone to problems imperfectly calculated case low-quality or poorly recognizable faces images, selected creation. All images same person, presented mini-batch,...