Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similarity
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916202655252480 |
|---|---|
| author | Vance, Nathan Flynn, Patrick |
| author_facet | Vance, Nathan Flynn, Patrick |
| contents | Domain shift differences between training data for deep learning models and the deployment context can result in severe performance issues for models which fail to generalize. We study the domain shift problem under the context of remote photoplethysmography (rPPG), a technique for video-based heart rate inference. We propose metrics based on model similarity which may be used as a measure of domain shift, and we demonstrate high correlation between these metrics and empirical performance. One of the proposed metrics with viable correlations, DS-diff, does not assume access to the ground truth of the target domain, i.e. it may be applied to in-the-wild data. To that end, we investigate a model selection problem in which ground truth results for the evaluation domain is not known, demonstrating a 13.9% performance improvement over the average case baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08184 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similarity Vance, Nathan Flynn, Patrick Computer Vision and Pattern Recognition Domain shift differences between training data for deep learning models and the deployment context can result in severe performance issues for models which fail to generalize. We study the domain shift problem under the context of remote photoplethysmography (rPPG), a technique for video-based heart rate inference. We propose metrics based on model similarity which may be used as a measure of domain shift, and we demonstrate high correlation between these metrics and empirical performance. One of the proposed metrics with viable correlations, DS-diff, does not assume access to the ground truth of the target domain, i.e. it may be applied to in-the-wild data. To that end, we investigate a model selection problem in which ground truth results for the evaluation domain is not known, demonstrating a 13.9% performance improvement over the average case baseline. |
| title | Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similarity |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.08184 |