FaceNet: A Unified Embedding for Face Recognition and Clustering

CVPR 2015 Florian SchroffDmitry KalenichenkoJames Philbin

Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity... (read more)

PDF Abstract

Code


Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Face Verification IJB-C FaceNet TAR @ FAR=0.01 66.50% # 3
Face Verification Labeled Faces in the Wild FaceNet Accuracy 99.63% # 3
Face Verification MegaFace FaceNet Accuracy 86.47% # 4
Face Identification MegaFace FaceNet Accuracy 70.49% # 6
Face Verification YouTube Faces DB FaceNet Accuracy 95.12% # 7