ScaleFace: Uncertainty-aware Deep Metric Learning

09/05/2022
by   Roman Kail, et al.
0

The performance of modern deep learning-based systems dramatically depends on the quality of input objects. For example, face recognition quality would be lower for blurry or corrupted inputs. However, it is hard to predict the influence of input quality on the resulting accuracy in more complex scenarios. We propose an approach for deep metric learning that allows direct estimation of the uncertainty with almost no additional computational cost. The developed ScaleFace algorithm uses trainable scale values that modify similarities in the space of embeddings. These input-dependent scale values represent a measure of confidence in the recognition result, thus allowing uncertainty estimation. We provide comprehensive experiments on face recognition tasks that show the superior performance of ScaleFace compared to other uncertainty-aware face recognition approaches. We also extend the results to the task of text-to-image retrieval showing that the proposed approach beats the competitors with significant margin.

READ FULL TEXT

page 5

page 13

research
06/24/2015

Targeting Ultimate Accuracy: Face Recognition via Deep Embedding

Face Recognition has been studied for many decades. As opposed to tradit...
research
04/08/2019

On Learning Density Aware Embeddings

Deep metric learning algorithms have been utilized to learn discriminati...
research
03/20/2020

SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness

Face image quality is an important factor to enable high performance fac...
research
11/26/2021

QMagFace: Simple and Accurate Quality-Aware Face Recognition

Face recognition systems have to deal with large variabilities (such as ...
research
10/19/2022

Stating Comparison Score Uncertainty and Verification Decision Confidence Towards Transparent Face Recognition

Face Recognition (FR) is increasingly used in critical verification deci...
research
04/21/2019

Probabilistic Face Embeddings

Embedding methods have achieved success in face recognition by comparing...
research
03/25/2020

Data Uncertainty Learning in Face Recognition

Modeling data uncertainty is important for noisy images, but seldom expl...

Please sign up or login with your details

Forgot password? Click here to reset