DeepAI AI Chat
Log In Sign Up

Attention-based Partial Face Recognition

06/11/2021
by   Stefan Hörmann, et al.
0

Photos of faces captured in unconstrained environments, such as large crowds, still constitute challenges for current face recognition approaches as often faces are occluded by objects or people in the foreground. However, few studies have addressed the task of recognizing partial faces. In this paper, we propose a novel approach to partial face recognition capable of recognizing faces with different occluded areas. We achieve this by combining attentional pooling of a ResNet's intermediate feature maps with a separate aggregation module. We further adapt common losses to partial faces in order to ensure that the attention maps are diverse and handle occluded parts. Our thorough analysis demonstrates that we outperform all baselines under multiple benchmark protocols, including naturally and synthetically occluded partial faces. This suggests that our method successfully focuses on the relevant parts of the occluded face.

READ FULL TEXT

page 1

page 3

08/26/2021

State of the Art: Face Recognition

Working with Child Sexual Exploitation Material (CSEM) in forensic appli...
09/08/2021

On Recognizing Occluded Faces in the Wild

Facial appearance variations due to occlusion has been one of the main c...
11/28/2014

Effective Face Frontalization in Unconstrained Images

"Frontalization" is the process of synthesizing frontal facing views of ...
12/11/2017

FHEDN: A based on context modeling Feature Hierarchy Encoder-Decoder Network for face detection

Because of affected by weather conditions, camera pose and range, etc. O...
08/04/2022

OCFR 2022: Competition on Occluded Face Recognition From Synthetically Generated Structure-Aware Occlusions

This work summarizes the IJCB Occluded Face Recognition Competition 2022...
10/25/2021

Facial Recognition in Collaborative Learning Videos

Face recognition in collaborative learning videos presents many challeng...
09/01/2016

Grid Loss: Detecting Occluded Faces

Detection of partially occluded objects is a challenging computer vision...

Code Repositories

PartialLFW

Official repository for Attention-based Partial Face Recognition


view repo