Explainable Face Recognition

by   Jonathan R. Williford, et al.

Explainable face recognition is the problem of explaining why a facial matcher matches faces. In this paper, we provide the first comprehensive benchmark and baseline evaluation for explainable face recognition. We define a new evaluation protocol called the “inpainting game”, which is a curated set of 3648 triplets (probe, mate, nonmate) of 95 subjects, which differ by synthetically inpainting a chosen facial characteristic like the nose, eyebrows or mouth creating an inpainted nonmate. An explainable face matcher is tasked with generating a network attention map which best explains which regions in a probe image match with a mated image, and not with an inpainted nonmate for each triplet. This provides ground truth for quantifying what image regions contribute to face matching. Furthermore, we provide a comprehensive benchmark on this dataset comparing five state of the art methods for network attention in face recognition on three facial matchers. This benchmark includes two new algorithms for network attention called subtree EBP and Density-based Input Sampling for Explanation (DISE) which outperform the state of the art by a wide margin. Finally, we show qualitative visualization of these network attention techniques on novel images, and explore how these explainable face recognition models can improve transparency and trust for facial matchers.


page 21

page 22

page 24

page 26

page 33

page 36

page 37

page 38


Activation Template Matching Loss for Explainable Face Recognition

Can we construct an explainable face recognition network able to learn a...

Discriminative Deep Feature Visualization for Explainable Face Recognition

Despite the huge success of deep convolutional neural networks in face r...

Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation

Explainable Face Recognition is gaining growing attention as the use of ...

Four Principles of Explainable AI as Applied to Biometrics and Facial Forensic Algorithms

Traditionally, researchers in automatic face recognition and biometric t...

Explanation of Face Recognition via Saliency Maps

Despite the significant progress in face recognition in the past years, ...

Facial Keypoints Detection

Detect facial keypoints is a critical element in face recognition. Howev...

Evaluation of Dense 3D Reconstruction from 2D Face Images in the Wild

This paper investigates the evaluation of dense 3D face reconstruction f...

Please sign up or login with your details

Forgot password? Click here to reset