Papers with Code · CC BY-SA 4.0

Heterogeneous Face Recognition

Facial Recognition and Modelling › Heterogeneous Face Recognition 5 평가 기록 3 datasets

Heterogeneous face recognition is the task of matching face images acquired from different sources (i.e., different sensors or different wavelengths) for identification or verification.

<span style="color:grey; opacity: 0.6">( Image credit: Pose Agnostic Cross-spectral Hallucination via Disentangling Independent Factors )</span>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode

Disguised Faces in the Wild

A-LINK

GAR @0.1% FAR Impersonation: 75.38GAR @0.1% FAR Obfuscation: 72.13GAR @0.1% FAR Overall: 72.72GAR @1% FAR Impersonation: 95.73

논문 코드

Disguised Faces in the Wild 2019

A2-LINK

GAR @0.1% FAR Impersonation: 79.2GAR @0.1% FAR Obfuscation: 99.00GAR @0.1% FAR Plastic Surgery: 98.80GAR @0.1% FAR Overall: 98.63

논문 코드

CMU-MPIE

A-LINK

16x16 Accuracy: 92.424x24 Accuracy: 92.632x32 Accuracy: 92.848x48 Accuracy: 92.9

논문 코드

데이터셋

3개

Disguised Faces in the Wild Disguised Faces in the Wild 2019 CMU-MPIE

논문

A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain Knowledge

2020-06-01 이 페이지의 평가 3건

GAR @0.1% FAR Impersonation: 69.27GAR @0.1% FAR Obfuscation: 93.08GAR @0.1% FAR Overall: 93.01GAR @1% FAR Impersonation: 99.01

A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge

2019-09-23 이 페이지의 평가 2건

GAR @0.1% FAR Impersonation: 75.38GAR @0.1% FAR Obfuscation: 72.13GAR @0.1% FAR Overall: 72.72GAR @1% FAR Impersonation: 95.73

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/iamgroot42/A-LINK 2 논문