FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing
We propose original semantic labels for detailed face parsing to improve the accuracy of face recognition by focusing on parts in a face. The part labels used in conventional face parsing are defined based on biological features, and thus, one label is given to a large region, such as skin. Our sema...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | IET Biometrics |
| Online Access: | http://dx.doi.org/10.1049/2024/6663315 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524297821061120 |
|---|---|
| author | Hiroya Kawai Koichi Ito Hwann-Tzong Chen Takafumi Aoki |
| author_facet | Hiroya Kawai Koichi Ito Hwann-Tzong Chen Takafumi Aoki |
| author_sort | Hiroya Kawai |
| collection | DOAJ |
| description | We propose original semantic labels for detailed face parsing to improve the accuracy of face recognition by focusing on parts in a face. The part labels used in conventional face parsing are defined based on biological features, and thus, one label is given to a large region, such as skin. Our semantic labels are defined by separating parts with large areas based on the structure of the face and considering the left and right sides for all parts to consider head pose changes, occlusion, and other factors. By utilizing the capability of assigning detailed part labels to face images, we propose a novel data augmentation method based on detailed face parsing called Face Semantic Erasing (FSErasing) to improve the performance of face recognition. FSErasing is to randomly mask a part of the face image based on the detailed part labels, and therefore, we can apply erasing-type data augmentation to the face image that considers the characteristics of the face. Through experiments using public face image datasets, we demonstrate that FSErasing is effective for improving the performance of face recognition and face attribute estimation. In face recognition, adding FSErasing in training ResNet-34 with Softmax using CelebA improves the average accuracy by 0.354 points and the average equal error rate (EER) by 0.312 points, and with ArcFace, the average accuracy and EER improve by 0.752 and 0.802 points, respectively. ResNet-50 with Softmax using CASIA-WebFace improves the average accuracy by 0.442 points and the average EER by 0.452 points, and with ArcFace, the average accuracy and EER improve by 0.228 points and 0.500 points, respectively. In face attribute estimation, adding FSErasing as a data augmentation method in training with CelebA improves the estimation accuracy by 0.54 points. We also apply our detailed face parsing model to visualize face recognition models and demonstrate its higher explainability than general visualization methods. |
| format | Article |
| id | doaj-art-b91bafe5c4d644a1a05c896330249b72 |
| institution | Kabale University |
| issn | 2047-4946 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-b91bafe5c4d644a1a05c896330249b722025-02-03T07:23:25ZengWileyIET Biometrics2047-49462024-01-01202410.1049/2024/6663315FSErasing: Improving Face Recognition with Data Augmentation Using Face ParsingHiroya Kawai0Koichi Ito1Hwann-Tzong Chen2Takafumi Aoki3Graduate School of Information SciencesGraduate School of Information SciencesDepartment of Computer ScienceGraduate School of Information SciencesWe propose original semantic labels for detailed face parsing to improve the accuracy of face recognition by focusing on parts in a face. The part labels used in conventional face parsing are defined based on biological features, and thus, one label is given to a large region, such as skin. Our semantic labels are defined by separating parts with large areas based on the structure of the face and considering the left and right sides for all parts to consider head pose changes, occlusion, and other factors. By utilizing the capability of assigning detailed part labels to face images, we propose a novel data augmentation method based on detailed face parsing called Face Semantic Erasing (FSErasing) to improve the performance of face recognition. FSErasing is to randomly mask a part of the face image based on the detailed part labels, and therefore, we can apply erasing-type data augmentation to the face image that considers the characteristics of the face. Through experiments using public face image datasets, we demonstrate that FSErasing is effective for improving the performance of face recognition and face attribute estimation. In face recognition, adding FSErasing in training ResNet-34 with Softmax using CelebA improves the average accuracy by 0.354 points and the average equal error rate (EER) by 0.312 points, and with ArcFace, the average accuracy and EER improve by 0.752 and 0.802 points, respectively. ResNet-50 with Softmax using CASIA-WebFace improves the average accuracy by 0.442 points and the average EER by 0.452 points, and with ArcFace, the average accuracy and EER improve by 0.228 points and 0.500 points, respectively. In face attribute estimation, adding FSErasing as a data augmentation method in training with CelebA improves the estimation accuracy by 0.54 points. We also apply our detailed face parsing model to visualize face recognition models and demonstrate its higher explainability than general visualization methods.http://dx.doi.org/10.1049/2024/6663315 |
| spellingShingle | Hiroya Kawai Koichi Ito Hwann-Tzong Chen Takafumi Aoki FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing IET Biometrics |
| title | FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing |
| title_full | FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing |
| title_fullStr | FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing |
| title_full_unstemmed | FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing |
| title_short | FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing |
| title_sort | fserasing improving face recognition with data augmentation using face parsing |
| url | http://dx.doi.org/10.1049/2024/6663315 |
| work_keys_str_mv | AT hiroyakawai fserasingimprovingfacerecognitionwithdataaugmentationusingfaceparsing AT koichiito fserasingimprovingfacerecognitionwithdataaugmentationusingfaceparsing AT hwanntzongchen fserasingimprovingfacerecognitionwithdataaugmentationusingfaceparsing AT takafumiaoki fserasingimprovingfacerecognitionwithdataaugmentationusingfaceparsing |