Alleviating Catastrophic Forgetting in Facial Expression Recognition with Emotion-Centered Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913320995389440 |
|---|---|
| author | Laurensi, Israel A. Britto Jr., Alceu de Souza Barddal, Jean Paul Koerich, Alessandro Lameiras |
| author_facet | Laurensi, Israel A. Britto Jr., Alceu de Souza Barddal, Jean Paul Koerich, Alessandro Lameiras |
| contents | Facial expression recognition is a pivotal component in machine learning, facilitating various applications. However, convolutional neural networks (CNNs) are often plagued by catastrophic forgetting, impeding their adaptability. The proposed method, emotion-centered generative replay (ECgr), tackles this challenge by integrating synthetic images from generative adversarial networks. Moreover, ECgr incorporates a quality assurance algorithm to ensure the fidelity of generated images. This dual approach enables CNNs to retain past knowledge while learning new tasks, enhancing their performance in emotion recognition. The experimental results on four diverse facial expression datasets demonstrate that incorporating images generated by our pseudo-rehearsal method enhances training on the targeted dataset and the source dataset while making the CNN retain previously learned knowledge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12260 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Alleviating Catastrophic Forgetting in Facial Expression Recognition with Emotion-Centered Models Laurensi, Israel A. Britto Jr., Alceu de Souza Barddal, Jean Paul Koerich, Alessandro Lameiras Computer Vision and Pattern Recognition Machine Learning Facial expression recognition is a pivotal component in machine learning, facilitating various applications. However, convolutional neural networks (CNNs) are often plagued by catastrophic forgetting, impeding their adaptability. The proposed method, emotion-centered generative replay (ECgr), tackles this challenge by integrating synthetic images from generative adversarial networks. Moreover, ECgr incorporates a quality assurance algorithm to ensure the fidelity of generated images. This dual approach enables CNNs to retain past knowledge while learning new tasks, enhancing their performance in emotion recognition. The experimental results on four diverse facial expression datasets demonstrate that incorporating images generated by our pseudo-rehearsal method enhances training on the targeted dataset and the source dataset while making the CNN retain previously learned knowledge. |
| title | Alleviating Catastrophic Forgetting in Facial Expression Recognition with Emotion-Centered Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.12260 |