HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Face Identification On Megaface

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	Paper Title	Repository
GhostFaceNetV2-1	98.64%	GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations
CosFace	82.72%	CosFace: Large Margin Cosine Loss for Deep Face Recognition	-
Cos+UNPG	99.27%	Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition	-
PartialFC + Glint360K + R100	99.10%	Partial FC: Training 10 Million Identities on a Single Machine	-
SphereFace (3-patch ensemble)	75.766%	SphereFace: Deep Hypersphere Embedding for Face Recognition	-
Mag+UNPG	98.03%	Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition	-
ArcFace + MS1MV2 + R100 + R	98.35%	ArcFace: Additive Angular Margin Loss for Deep Face Recognition	-
Prodpoly	98.78%	Deep Polynomial Neural Networks	-
FaceNet	70.49%	FaceNet: A Unified Embedding for Face Recognition and Clustering	-
Light CNN-29	73.749%	A Light CNN for Deep Face Representation with Noisy Labels	-
SV-AM-Softmax	97.2%	Support Vector Guided Softmax Loss for Face Recognition	-
SphereFace (single model)	72.729%	SphereFace: Deep Hypersphere Embedding for Face Recognition	-
Arc+UNPG	98.82%	Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition	-

0 of 13 row(s) selected.

Face Identification On Megaface | SOTA | HyperAI초신경