Face Verification On Labeled Faces In The
Metrics
Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| ArcFace + MS1MV2 + R100, | 99.83% | ArcFace: Additive Angular Margin Loss for Deep Face Recognition |
| FaceNet | 99.63% | FaceNet: A Unified Embedding for Face Recognition and Clustering |
| Dlib | 99.38% | Dlib-ml: A Machine Learning Toolkit |
| VGG-Face | 98.78% | Deep Face Recognition |
| DeepFace | 98.37% | DeepFace: Closing the Gap to Human-Level Performance in Face Verification |
| DeepID | 97.05% | Deep Learning Face Representation from Predicting 10,000 Classes |
| OpenFace | 92.92% | OpenFace: A general-purpose face recognition library with mobile applications |
0 of 7 row(s) selected.