PAtt-Lite: Lightweight Patch and Attention MobileNet for Challenging Facial Expression Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ngwe, Jia Le, Lim, Kian Ming, Lee, Chin Poo, Ong, Thian Song
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909285383929856
author Ngwe, Jia Le
Lim, Kian Ming
Lee, Chin Poo
Ong, Thian Song
author_facet Ngwe, Jia Le
Lim, Kian Ming
Lee, Chin Poo
Ong, Thian Song
contents Facial Expression Recognition (FER) is a machine learning problem that deals with recognizing human facial expressions. While existing work has achieved performance improvements in recent years, FER in the wild and under challenging conditions remains a challenge. In this paper, a lightweight patch and attention network based on MobileNetV1, referred to as PAtt-Lite, is proposed to improve FER performance under challenging conditions. A truncated ImageNet-pre-trained MobileNetV1 is utilized as the backbone feature extractor of the proposed method. In place of the truncated layers is a patch extraction block that is proposed for extracting significant local facial features to enhance the representation from MobileNetV1, especially under challenging conditions. An attention classifier is also proposed to improve the learning of these patched feature maps from the extremely lightweight feature extractor. The experimental results on public benchmark databases proved the effectiveness of the proposed method. PAtt-Lite achieved state-of-the-art results on CK+, RAF-DB, FER2013, FERPlus, and the challenging conditions subsets for RAF-DB and FERPlus.
format Preprint
id arxiv_https___arxiv_org_abs_2306_09626
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PAtt-Lite: Lightweight Patch and Attention MobileNet for Challenging Facial Expression Recognition
Ngwe, Jia Le
Lim, Kian Ming
Lee, Chin Poo
Ong, Thian Song
Computer Vision and Pattern Recognition
Facial Expression Recognition (FER) is a machine learning problem that deals with recognizing human facial expressions. While existing work has achieved performance improvements in recent years, FER in the wild and under challenging conditions remains a challenge. In this paper, a lightweight patch and attention network based on MobileNetV1, referred to as PAtt-Lite, is proposed to improve FER performance under challenging conditions. A truncated ImageNet-pre-trained MobileNetV1 is utilized as the backbone feature extractor of the proposed method. In place of the truncated layers is a patch extraction block that is proposed for extracting significant local facial features to enhance the representation from MobileNetV1, especially under challenging conditions. An attention classifier is also proposed to improve the learning of these patched feature maps from the extremely lightweight feature extractor. The experimental results on public benchmark databases proved the effectiveness of the proposed method. PAtt-Lite achieved state-of-the-art results on CK+, RAF-DB, FER2013, FERPlus, and the challenging conditions subsets for RAF-DB and FERPlus.
title PAtt-Lite: Lightweight Patch and Attention MobileNet for Challenging Facial Expression Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.09626