Face Verification On Youtube Faces Db
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| SphereFace | 95.0% | SphereFace: Deep Hypersphere Embedding for Face Recognition | - |
| QAN | 96.17% | Quality Aware Network for Set to Set Recognition | - |
| Light CNN-29 | 95.54% | A Light CNN for Deep Face Representation with Noisy Labels | - |
| 3DMM face shape parameters + CNN | 88.80% | Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network | - |
| ArcFace + MS1MV2 + R100, | 98.02% | ArcFace: Additive Angular Margin Loss for Deep Face Recognition | - |
| CosFace | 97.6% | CosFace: Large Margin Cosine Loss for Deep Face Recognition | - |
| VGG-Face | 97.40% | Deep Face Recognition | |
| FaceNet | 95.12% | FaceNet: A Unified Embedding for Face Recognition and Clustering | - |
| Git Loss | 95.30% | Git Loss for Deep Face Recognition | - |
| DeepId2+ | 93.2% | Deeply learned face representations are sparse, selective, and robust | - |
| PFEfuse+match | 97.36% | Probabilistic Face Embeddings | - |
| SeqFace, 1 ResNet-64 | 98.12% | SeqFace: Make full use of sequence information for face recognition | - |
0 of 12 row(s) selected.