Channel Selective Relation Network for Efficient Few-shot Facial Expression Recognition

Few-shot learning-based facial expression recognition (FER) aims to achieve maximum efficiency from a few numbers of data. Therefore, it is significant to utilize the given training dataset efficiently. However, the existing few-shot FERs are too dependent on the datasets they trained, so it is chal...

Full description

Saved in:
Bibliographic Details
Main Authors: Kim, Chae-Lin, Lee, Ga-Eun, Choi, Young-Ju, Kang, Jiwoo, Kim, Byung-Gyu
Format: Conference Proceeding
Language:English
Subjects:
channel selective relation network
Data mining
Face recognition
facial expression recognition
Feature extraction
Few-shot learning
Image reconstruction
Lips
Spatial databases
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Few-shot learning-based facial expression recognition (FER) aims to achieve maximum efficiency from a few numbers of data. Therefore, it is significant to utilize the given training dataset efficiently. However, the existing few-shot FERs are too dependent on the datasets they trained, so it is challenging to generalize the FER performance. To address the problem, we propose a Channel Selective Relation Network with channel selection module and spatial data construction to train optimal features. Our method helps the network to prevent irrelevant information and focus on essential information by comparing the original sample features with the averaged feature. Furthermore, our network efficiently learns dominant facial expression features in local patches, such as the eyes and lips. Compared to the current state-of-the-art method, the average performances on RAFDB, FER2013, SFEW, and AFEW datasets are improved by 3.5%, 4.44%, 5.58%, and 2.31% in accuracy, respectively.
ISSN:2158-4001
DOI:10.1109/ICCE59016.2024.10444505