Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data
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_ | 1866915313446027264 |
|---|---|
| author | Sharafi, Masoumeh Ollivier, Emma Zeeshan, Muhammad Osama Belharbi, Soufiane Pedersoli, Marco Koerich, Alessandro Lameiras Bacon, Simon Granger, Eric |
| author_facet | Sharafi, Masoumeh Ollivier, Emma Zeeshan, Muhammad Osama Belharbi, Soufiane Pedersoli, Marco Koerich, Alessandro Lameiras Bacon, Simon Granger, Eric |
| contents | Facial Expression Recognition (FER) from videos is a crucial task in various application areas, such as human-computer interaction and health diagnosis and monitoring (e.g., assessing pain and depression). Beyond the challenges of recognizing subtle emotional or health states, the effectiveness of deep FER models is often hindered by the considerable inter-subject variability in expressions. Source-free (unsupervised) domain adaptation (SFDA) methods may be employed to adapt a pre-trained source model using only unlabeled target domain data, thereby avoiding data privacy, storage, and transmission issues. Typically, SFDA methods adapt to a target domain dataset corresponding to an entire population and assume it includes data from all recognition classes. However, collecting such comprehensive target data can be difficult or even impossible for FER in healthcare applications. In many real-world scenarios, it may be feasible to collect a short neutral control video (which displays only neutral expressions) from target subjects before deployment. These videos can be used to adapt a model to better handle the variability of expressions among subjects. This paper introduces the Disentangled SFDA (DSFDA) method to address the challenge posed by adapting models with missing target expression data. DSFDA leverages data from a neutral target control video for end-to-end generation and adaptation of target data with missing non-neutral data. Our method learns to disentangle features related to expressions and identity while generating the missing non-neutral expression data for the target subject, thereby enhancing model accuracy. Additionally, our self-supervision strategy improves model adaptation by reconstructing target images that maintain the same identity and source expression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20771 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data Sharafi, Masoumeh Ollivier, Emma Zeeshan, Muhammad Osama Belharbi, Soufiane Pedersoli, Marco Koerich, Alessandro Lameiras Bacon, Simon Granger, Eric Computer Vision and Pattern Recognition Facial Expression Recognition (FER) from videos is a crucial task in various application areas, such as human-computer interaction and health diagnosis and monitoring (e.g., assessing pain and depression). Beyond the challenges of recognizing subtle emotional or health states, the effectiveness of deep FER models is often hindered by the considerable inter-subject variability in expressions. Source-free (unsupervised) domain adaptation (SFDA) methods may be employed to adapt a pre-trained source model using only unlabeled target domain data, thereby avoiding data privacy, storage, and transmission issues. Typically, SFDA methods adapt to a target domain dataset corresponding to an entire population and assume it includes data from all recognition classes. However, collecting such comprehensive target data can be difficult or even impossible for FER in healthcare applications. In many real-world scenarios, it may be feasible to collect a short neutral control video (which displays only neutral expressions) from target subjects before deployment. These videos can be used to adapt a model to better handle the variability of expressions among subjects. This paper introduces the Disentangled SFDA (DSFDA) method to address the challenge posed by adapting models with missing target expression data. DSFDA leverages data from a neutral target control video for end-to-end generation and adaptation of target data with missing non-neutral data. Our method learns to disentangle features related to expressions and identity while generating the missing non-neutral expression data for the target subject, thereby enhancing model accuracy. Additionally, our self-supervision strategy improves model adaptation by reconstructing target images that maintain the same identity and source expression. |
| title | Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.20771 |