Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers

• Published in: Proceedings / IEEE Workshop on Applications of Computer Vision pp. 6289 - 6299
• Main Authors: Phan, Hai, Le, Cindy X., Le, Vu, He, Yihui, Nguyen, Anh Totti
• Format: Conference Proceeding
• Language: English
• Published: IEEE 03.01.2024
• Subjects: Algorithms; Biometrics; body pose; Computational modeling; Computer vision; Data models; Data visualization; face; gesture; Image recognition and understanding; Neural networks; Training; Transformers
• ISSN: 2642-9381
• DOI: 10.1109/WACV57701.2024.00618

Most face identification approaches employ a Siamese neural network to compare two images at the image embedding level. Yet, this technique can be subject to occlusion (e.g., faces with masks or sunglasses) and out-of-distribution data. DeepFace-EMD [40] reaches state-of-the-art accuracy on out-of-d...