Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild
Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative...
Published in: | IEEE Access |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1109/ACCESS.2022.3156598 https://doaj.org/article/17c229bfaa2247d0a49ad3ebba9abd7d |
id |
ftdoajarticles:oai:doaj.org/article:17c229bfaa2247d0a49ad3ebba9abd7d |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:17c229bfaa2247d0a49ad3ebba9abd7d 2023-05-15T16:02:06+02:00 Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild Ali Pourramezan Fard Mohammad H. Mahoor 2022-01-01T00:00:00Z https://doi.org/10.1109/ACCESS.2022.3156598 https://doaj.org/article/17c229bfaa2247d0a49ad3ebba9abd7d EN eng IEEE https://ieeexplore.ieee.org/document/9727163/ https://doaj.org/toc/2169-3536 2169-3536 doi:10.1109/ACCESS.2022.3156598 https://doaj.org/article/17c229bfaa2247d0a49ad3ebba9abd7d IEEE Access, Vol 10, Pp 26756-26768 (2022) Facial expression recognition facial emotion recognition Ad-Corre loss loss function convolutional neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 article 2022 ftdoajarticles https://doi.org/10.1109/ACCESS.2022.3156598 2022-12-31T01:53:54Z Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative power of the learned embedded features. This paper proposes an Adaptive Correlation (Ad-Corre) Loss to guide the network towards generating embedded feature vectors with high correlation for within-class samples and less correlation for between-class samples. Ad-Corre consists of 3 components called Feature Discriminator, Mean Discriminator, and Embedding Discriminator. We design the Feature Discriminator component to guide the network to create the embedded feature vectors to be highly correlated if they belong to a similar class, and less correlated if they belong to different classes. In addition, the Mean Discriminator component leads the network to make the mean embedded feature vectors of different classes to be less similar to each other. We use Xception network as the backbone of our model, and contrary to previous work, we propose an embedding feature space that contains $k$ feature vectors. Then, the Embedding Discriminator component penalizes the network to generate the embedded feature vectors, which are dissimilar. We trained our model using the combination of our proposed loss functions called Ad-Corre Loss jointly with the cross-entropy loss. We achieved a very promising recognition accuracy on AffectNet, RAF-DB, and FER-2013. Our extensive experiments and ablation study indicate the power of our method to cope well with challenging FER tasks in the wild. The code is available on Github. Article in Journal/Newspaper DML Directory of Open Access Journals: DOAJ Articles IEEE Access 10 26756 26768 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Facial expression recognition facial emotion recognition Ad-Corre loss loss function convolutional neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
spellingShingle |
Facial expression recognition facial emotion recognition Ad-Corre loss loss function convolutional neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ali Pourramezan Fard Mohammad H. Mahoor Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild |
topic_facet |
Facial expression recognition facial emotion recognition Ad-Corre loss loss function convolutional neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
description |
Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative power of the learned embedded features. This paper proposes an Adaptive Correlation (Ad-Corre) Loss to guide the network towards generating embedded feature vectors with high correlation for within-class samples and less correlation for between-class samples. Ad-Corre consists of 3 components called Feature Discriminator, Mean Discriminator, and Embedding Discriminator. We design the Feature Discriminator component to guide the network to create the embedded feature vectors to be highly correlated if they belong to a similar class, and less correlated if they belong to different classes. In addition, the Mean Discriminator component leads the network to make the mean embedded feature vectors of different classes to be less similar to each other. We use Xception network as the backbone of our model, and contrary to previous work, we propose an embedding feature space that contains $k$ feature vectors. Then, the Embedding Discriminator component penalizes the network to generate the embedded feature vectors, which are dissimilar. We trained our model using the combination of our proposed loss functions called Ad-Corre Loss jointly with the cross-entropy loss. We achieved a very promising recognition accuracy on AffectNet, RAF-DB, and FER-2013. Our extensive experiments and ablation study indicate the power of our method to cope well with challenging FER tasks in the wild. The code is available on Github. |
format |
Article in Journal/Newspaper |
author |
Ali Pourramezan Fard Mohammad H. Mahoor |
author_facet |
Ali Pourramezan Fard Mohammad H. Mahoor |
author_sort |
Ali Pourramezan Fard |
title |
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild |
title_short |
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild |
title_full |
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild |
title_fullStr |
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild |
title_full_unstemmed |
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild |
title_sort |
ad-corre: adaptive correlation-based loss for facial expression recognition in the wild |
publisher |
IEEE |
publishDate |
2022 |
url |
https://doi.org/10.1109/ACCESS.2022.3156598 https://doaj.org/article/17c229bfaa2247d0a49ad3ebba9abd7d |
genre |
DML |
genre_facet |
DML |
op_source |
IEEE Access, Vol 10, Pp 26756-26768 (2022) |
op_relation |
https://ieeexplore.ieee.org/document/9727163/ https://doaj.org/toc/2169-3536 2169-3536 doi:10.1109/ACCESS.2022.3156598 https://doaj.org/article/17c229bfaa2247d0a49ad3ebba9abd7d |
op_doi |
https://doi.org/10.1109/ACCESS.2022.3156598 |
container_title |
IEEE Access |
container_volume |
10 |
container_start_page |
26756 |
op_container_end_page |
26768 |
_version_ |
1766397710588444672 |