Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering
While deep neural networks demonstrate robust performance in visual tasks, the long-tail distribution of real-world data leads to significant recognition accuracy degradation in critical scenarios such as medical human–robot affective interaction, particularly the misidentification of low-frequency...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/5/296 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327508326973440 |
|---|---|
| author | Qingdu Li Keting Fu Jian Liu Yishan Li Qinze Ren Kang Xu Junxiu Fu Na Liu Ye Yuan |
| author_facet | Qingdu Li Keting Fu Jian Liu Yishan Li Qinze Ren Kang Xu Junxiu Fu Na Liu Ye Yuan |
| author_sort | Qingdu Li |
| collection | DOAJ |
| description | While deep neural networks demonstrate robust performance in visual tasks, the long-tail distribution of real-world data leads to significant recognition accuracy degradation in critical scenarios such as medical human–robot affective interaction, particularly the misidentification of low-frequency negative emotions (e.g., fear and disgust) that may trigger psychological resistance in patients. Here, we propose a method based on dynamic intra-class clustering (DICC) to optimize the class imbalance problem in facial expression recognition tasks. The DICC method dynamically adjusts the distribution of majority classes by clustering them into subclasses and generating pseudo-labels, which helps the model learn more discriminative features and improve classification accuracy. By comparing with existing methods, we demonstrate that the DICC method can help the model achieve superior performance across various facial expression datasets. In this study, we conducted an in-depth evaluation of the DICC method against baseline methods using the FER2013, MMAFEDB, and Emotion-Domestic datasets, achieving improvements in classification accuracy of 1.73%, 1.97%, and 5.48%, respectively. This indicates that the DICC method can effectively enhance classification precision, especially in the recognition of minority class samples. This approach provides a novel perspective for addressing the class imbalance challenge in facial expression recognition and offers a reference for future research and applications in related fields. |
| format | Article |
| id | doaj-art-acf09dc29ca54d8f858cb4aead6999df |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-acf09dc29ca54d8f858cb4aead6999df2025-08-20T03:47:52ZengMDPI AGBiomimetics2313-76732025-05-0110529610.3390/biomimetics10050296Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class ClusteringQingdu Li0Keting Fu1Jian Liu2Yishan Li3Qinze Ren4Kang Xu5Junxiu Fu6Na Liu7Ye Yuan8Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaInstitute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, ChinaWhile deep neural networks demonstrate robust performance in visual tasks, the long-tail distribution of real-world data leads to significant recognition accuracy degradation in critical scenarios such as medical human–robot affective interaction, particularly the misidentification of low-frequency negative emotions (e.g., fear and disgust) that may trigger psychological resistance in patients. Here, we propose a method based on dynamic intra-class clustering (DICC) to optimize the class imbalance problem in facial expression recognition tasks. The DICC method dynamically adjusts the distribution of majority classes by clustering them into subclasses and generating pseudo-labels, which helps the model learn more discriminative features and improve classification accuracy. By comparing with existing methods, we demonstrate that the DICC method can help the model achieve superior performance across various facial expression datasets. In this study, we conducted an in-depth evaluation of the DICC method against baseline methods using the FER2013, MMAFEDB, and Emotion-Domestic datasets, achieving improvements in classification accuracy of 1.73%, 1.97%, and 5.48%, respectively. This indicates that the DICC method can effectively enhance classification precision, especially in the recognition of minority class samples. This approach provides a novel perspective for addressing the class imbalance challenge in facial expression recognition and offers a reference for future research and applications in related fields.https://www.mdpi.com/2313-7673/10/5/296facial expression recognitionclass imbalancedynamic intra-class clustering algorithmdeep learning |
| spellingShingle | Qingdu Li Keting Fu Jian Liu Yishan Li Qinze Ren Kang Xu Junxiu Fu Na Liu Ye Yuan Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering Biomimetics facial expression recognition class imbalance dynamic intra-class clustering algorithm deep learning |
| title | Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering |
| title_full | Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering |
| title_fullStr | Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering |
| title_full_unstemmed | Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering |
| title_short | Optimizing Class Imbalance in Facial Expression Recognition Using Dynamic Intra-Class Clustering |
| title_sort | optimizing class imbalance in facial expression recognition using dynamic intra class clustering |
| topic | facial expression recognition class imbalance dynamic intra-class clustering algorithm deep learning |
| url | https://www.mdpi.com/2313-7673/10/5/296 |
| work_keys_str_mv | AT qingduli optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT ketingfu optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT jianliu optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT yishanli optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT qinzeren optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT kangxu optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT junxiufu optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT naliu optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering AT yeyuan optimizingclassimbalanceinfacialexpressionrecognitionusingdynamicintraclassclustering |