HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Face Verification On Ijb A

評価指標

TAR @ FAR=0.01

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
TAR @ FAR=0.01
Paper TitleRepository
Deep CNN + COTS matcher73.30%Face Search at Scale: 80 Million Gallery-
All-in-one CNN92.20%An All-In-One Convolutional Neural Network for Face Analysis
FPN90.1%FacePoseNet: Making a Case for Landmark-Free Face Alignment
Triplet probabilistic embedding90%Triplet Probabilistic Embedding for Face Verification and Clustering
Template adaptation93.90%Template Adaptation for Face Verification and Identification-
L2-constrained softmax loss97%L2-constrained Softmax Loss for Discriminative Face Verification
Dual-Agent GANs97.60%Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis-
StyleFNM94.60%Inclusive normalization of face images to passport format-
PFEfuse + match97.5%Probabilistic Face Embeddings
VGG + GANFaces53.507%Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model
SE-GV-4-g197.2%GhostVLAD for set-based face recognition
VGGFace2_ft96.8%VGGFace2: A dataset for recognising faces across pose and age
Synthesis as data augmentation88.60%Do We Really Need to Collect Millions of Faces for Effective Face Recognition?-
DCNN83.80%Unconstrained Face Verification using Deep CNN Features-
Deep multi-pose representations78.70%Face Recognition Using Deep Multi-Pose Representations-
Deep Residual Equivariant Mapping94.40%Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
NAN94.10%Neural Aggregation Network for Video Face Recognition-
0 of 17 row(s) selected.