Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914387247235072 |
|---|---|
| author | Sharafi, Masoumeh Belharbi, Soufiane Zeeshan, Muhammad Osama Salem, Houssem Ben Etemad, Ali Koerich, Alessandro Lameiras Pedersoli, Marco Bacon, Simon Granger, Eric |
| author_facet | Sharafi, Masoumeh Belharbi, Soufiane Zeeshan, Muhammad Osama Salem, Houssem Ben Etemad, Ali Koerich, Alessandro Lameiras Pedersoli, Marco Bacon, Simon Granger, Eric |
| contents | Facial expression recognition (FER) models are widely used in video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting performance in real-world settings. Source-free domain adaptation (SFDA) has been proposed to personalize a pretrained source model using only unlabeled target data, avoiding privacy, storage, and transmission constraints. We address a particularly challenging setting where source data is unavailable and the target data contains only neutral expressions. Existing SFDA methods are not designed for adaptation from a single target class, while generating non-neutral facial images is often unstable and expensive. To address this, we propose Source-Free Domain Adaptation with Personalized Feature Translation (SFDA-PFT), a lightweight latent-space approach. A translator is first pretrained on source data to map subject-specific style features between subjects while preserving expression information through expression-consistency and style-aware objectives. It is then adapted to neutral target data without source data or image synthesis. By operating in the latent space, SFDA-PFT avoids noisy facial image generation, reduces computation, and learns discriminative embeddings for classification. Experiments on BioVid, StressID, BAH, and Aff-Wild2 show that SFDA-PFT consistently outperforms state-of-the-art SFDA methods in privacy-sensitive FER scenarios. Our code is publicly available at: \href{https://github.com/MasoumehSharafi/SFDA-PFT}{GitHub}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09202 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method Sharafi, Masoumeh Belharbi, Soufiane Zeeshan, Muhammad Osama Salem, Houssem Ben Etemad, Ali Koerich, Alessandro Lameiras Pedersoli, Marco Bacon, Simon Granger, Eric Computer Vision and Pattern Recognition Artificial Intelligence Facial expression recognition (FER) models are widely used in video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting performance in real-world settings. Source-free domain adaptation (SFDA) has been proposed to personalize a pretrained source model using only unlabeled target data, avoiding privacy, storage, and transmission constraints. We address a particularly challenging setting where source data is unavailable and the target data contains only neutral expressions. Existing SFDA methods are not designed for adaptation from a single target class, while generating non-neutral facial images is often unstable and expensive. To address this, we propose Source-Free Domain Adaptation with Personalized Feature Translation (SFDA-PFT), a lightweight latent-space approach. A translator is first pretrained on source data to map subject-specific style features between subjects while preserving expression information through expression-consistency and style-aware objectives. It is then adapted to neutral target data without source data or image synthesis. By operating in the latent space, SFDA-PFT avoids noisy facial image generation, reduces computation, and learns discriminative embeddings for classification. Experiments on BioVid, StressID, BAH, and Aff-Wild2 show that SFDA-PFT consistently outperforms state-of-the-art SFDA methods in privacy-sensitive FER scenarios. Our code is publicly available at: \href{https://github.com/MasoumehSharafi/SFDA-PFT}{GitHub}. |
| title | Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09202 |