PAM: Pose Attention Module for Pose-Invariant Face Recognition

11/23/2021
by   En-Jung Tsai, et al.
0

Pose variation is one of the key challenges in face recognition. Conventional techniques mainly focus on face frontalization or face augmentation in image space. However, transforming face images in image space is not guaranteed to preserve the lossless identity features of the original image. Moreover, these methods suffer from more computational costs and memory requirements due to the additional models. We argue that it is more desirable to perform feature transformation in hierarchical feature space rather than image space, which can take advantage of different feature levels and benefit from joint learning with representation learning. To this end, we propose a lightweight and easy-to-implement attention block, named Pose Attention Module (PAM), for pose-invariant face recognition. Specifically, PAM performs frontal-profile feature transformation in hierarchical feature space by learning residuals between pose variations with a soft gate mechanism. We validated the effectiveness of PAM block design through extensive ablation studies and verified the performance on several popular benchmarks, including LFW, CFP-FP, AgeDB-30, CPLFW, and CALFW. Experimental results show that our method not only outperforms state-of-the-art methods but also effectively reduces memory requirements by more than 75 times. It is noteworthy that our method is not limited to face recognition with large pose variations. By adjusting the soft gate mechanism of PAM to a specific coefficient, such semantic attention block can easily extend to address other intra-class imbalance problems in face recognition, including large variations in age, illumination, expression, etc.

READ FULL TEXT

page 3

page 5

research
06/27/2021

Attention-guided Progressive Mapping for Profile Face Recognition

The past few years have witnessed great progress in the domain of face r...
research
07/25/2021

PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition

Despite the great success achieved by deep learning methods in face reco...
research
11/26/2020

ClusterFace: Joint Clustering and Classification for Set-Based Face Recognition

Deep learning technology has enabled successful modeling of complex faci...
research
09/15/2022

Pose Attention-Guided Profile-to-Frontal Face Recognition

In recent years, face recognition systems have achieved exceptional succ...
research
02/10/2017

Reconstruction-Based Disentanglement for Pose-invariant Face Recognition

Deep neural networks (DNNs) trained on large-scale datasets have recentl...
research
10/25/2019

Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network

There is an urgent need to apply face alignment in a memory-efficient an...
research
03/15/2021

LARNet: Lie Algebra Residual Network for Profile Face Recognition

Due to large variations between profile and frontal faces, profile-based...

Please sign up or login with your details

Forgot password? Click here to reset