Face Attributes as Cues for Deep Face Recognition Understanding

05/14/2021
by   Matheus Alves Diniz, et al.
11

Deeply learned representations are the state-of-the-art descriptors for face recognition methods. These representations encode latent features that are difficult to explain, compromising the confidence and interpretability of their predictions. Most attempts to explain deep features are visualization techniques that are often open to interpretation. Instead of relying only on visualizations, we use the outputs of hidden layers to predict face attributes. The obtained performance is an indicator of how well the attribute is implicitly learned in that layer of the network. Using a variable selection technique, we also analyze how these semantic concepts are distributed inside each layer, establishing the precise location of relevant neurons for each attribute. According to our experiments, gender, eyeglasses and hat usage can be predicted with over 96 used to predict each attribute. These performances are less than 3 percentage points lower than the ones achieved by deep supervised face attribute networks. In summary, our experiments show that, inside DCNNs optimized for face identification, there exists latent neurons encoding face attributes almost as accurately as DCNNs optimized for these attributes.

READ FULL TEXT

page 1

page 4

page 5

page 6

research
09/07/2022

Can GAN-induced Attribute Manipulations Impact Face Recognition?

Impact due to demographic factors such as age, sex, race, etc., has been...
research
02/12/2016

Face Attribute Prediction Using Off-the-Shelf CNN Features

Predicting attributes from face images in the wild is a challenging comp...
research
08/09/2021

PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition

Face recognition networks encode information about sensitive attributes ...
research
12/03/2014

Deeply learned face representations are sparse, selective, and robust

This paper designs a high-performance deep convolutional network (DeepID...
research
09/21/2020

Beyond Identity: What Information Is Stored in Biometric Face Templates?

Deeply-learned face representations enable the success of current face r...
research
12/19/2018

Physical Attribute Prediction Using Deep Residual Neural Networks

Images taken from the Internet have been used alongside Deep Learning fo...
research
02/14/2020

Single Unit Status in Deep Convolutional Neural Network Codes for Face Identification: Sparseness Redefined

Deep convolutional neural networks (DCNNs) trained for face identificati...

Please sign up or login with your details

Forgot password? Click here to reset