HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Face Verification On Megaface

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name
Accuracy
Paper TitleRepository
ElasticFace-Arc98.81%ElasticFace: Elastic Margin Loss for Deep Face Recognition-
PFEfuse + match92.51%Probabilistic Face Embeddings-
Dynamic AdaCos97.41%AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations-
SV-AM-Softmax97.38%Support Vector Guided Softmax Loss for Face Recognition-
SphereFace (3-patch ensemble)89.142%SphereFace: Deep Hypersphere Embedding for Face Recognition-
Prodpoly98.95%Deep Polynomial Neural Networks-
CosFace96.65%CosFace: Large Margin Cosine Loss for Deep Face Recognition-
DiscFace97.44%DiscFace: Minimum Discrepancy Learning for Deep Face Recognition-
GhostFaceNetV2-198.72%GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations
ArcFace + MS1MV2 + R100 + R98.48%ArcFace: Additive Angular Margin Loss for Deep Face Recognition-
SphereFace (single model)85.561%SphereFace: Deep Hypersphere Embedding for Face Recognition-
Light CNN-2985.133%A Light CNN for Deep Face Representation with Noisy Labels-
0 of 12 row(s) selected.
Face Verification On Megaface | SOTA | HyperAI