Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition

04/03/2018
by   Rajeev Ranjan, et al.
0

In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for subject classification with softmax loss, using the penultimate layer output as the feature descriptor, and generating a cosine similarity score given a pair of face images or videos. The softmax loss function does not optimize the features to have higher similarity score for positive pairs and lower similarity score for negative pairs, which leads to a performance gap. In this paper, we propose a new loss function, called Crystal Loss, that restricts the features to lie on a hypersphere of a fixed radius. The loss can be easily implemented using existing deep learning frameworks. We show that integrating this simple step in the training pipeline significantly improves the performance of face verification and recognition systems. We achieve state-of-the-art performance for face verification and recognition on challenging LFW, IJB-A, IJB-B and IJB-C datasets over a large range of false alarm rates (10-1 to 10-7).

READ FULL TEXT

page 1

page 4

page 5

page 7

page 13

page 15

research
03/28/2017

L2-constrained Softmax Loss for Discriminative Face Verification

In recent years, the performance of face verification systems has signif...
research
05/01/2019

AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations

The cosine-based softmax losses and their variants achieve great success...
research
06/13/2017

von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification

A number of pattern recognition tasks, e.g., face verification, can be b...
research
07/25/2023

An Explainable Model-Agnostic Algorithm for CNN-based Biometrics Verification

This paper describes an adaptation of the Local Interpretable Model-Agno...
research
07/27/2020

Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality

The popular softmax loss and its recent extensions have achieved great s...
research
03/22/2022

Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition

The goal of face recognition (FR) can be viewed as a pair similarity opt...
research
11/15/2018

Face Verification and Forgery Detection for Ophthalmic Surgery Images

Although modern face verification systems are accessible and accurate, t...

Please sign up or login with your details

Forgot password? Click here to reset