Data-specific Adaptive Threshold for Face Recognition and Authentication

Many face recognition systems boost the performance using deep learning models, but only a few researches go into the mechanisms for dealing with online registration. Although we can obtain discriminative facial features through the state-of-the-art deep model training, how to decide the best threshold for practical use remains a challenge... (read more)

PDF Abstract

Results from the Paper


 Ranked #1 on Face Recognition on LFW (Online Open Set) (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Face Recognition Adience (Online Open Set) FaceNet+Fixed Threshold (0.2487) Average Accuracy (10 times) 80.6 # 2
Face Recognition Adience (Online Open Set) FaceNet+Adaptive Threshold Average Accuracy (10 times) 84.3 # 1
Face Recognition Color FERET (Online Open Set) FaceNet+Fixed Threshold (0.3968) Average Accuracy (10 times) 80.72 # 2
Face Recognition Color FERET (Online Open Set) FaceNet+Adaptive Threshold Average Accuracy (10 times) 83.79 # 1
Face Recognition LFW (Online Open Set) FaceNet+Fixed Threshold (0.3779) Average Accuracy (10 times) 53.97 # 2
Face Recognition LFW (Online Open Set) FaceNet+Adaptive Threshold Average Accuracy (10 times) 76.46 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet