MagFace

2000년 도입 · 논문 7편에서 사용

MagFace is a category of losses for face recognition that learn a universal feature embedding whose magnitude can measure the quality of a given face. Under the new loss, it can be proven that the magnitude of the feature embedding monotonically increases if the subject is more likely to be recognized. In addition, MagFace introduces an adaptive mechanism to learn a well-structured within-class feature distributions by pulling easy samples to class centers while pushing hard samples away. For face recognition, MagFace helps prevent model overfitting on noisy and low-quality samples by an adaptive mechanism to learn well-structured within-class feature distributions -- by pulling easy samples to class centers while pushing hard samples away.

출처: MagFace: A Universal Representation for Face Recognition and Quality Assessment

소개 논문: MagFace: A Universal Representation for Face Recognition and Quality Assessment