Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2412.20290 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915084003966976 |
|---|---|
| author | Wang, Junyao Faruque, Mohammad Abdullah Al |
| author_facet | Wang, Junyao Faruque, Mohammad Abdullah Al |
| contents | Deep learning has been widely adopted for human activity recognition (HAR) while generalizing a trained model across diverse users and scenarios remains challenging due to distribution shifts. The inherent low-resource challenge in HAR, i.e., collecting and labeling adequate human-involved data can be prohibitively costly, further raising the difficulty of tackling DS. We propose TACO, a novel transformer-based contrastive meta-learning approach for generalizable HAR. TACO addresses DS by synthesizing virtual target domains in training with explicit consideration of model generalizability. Additionally, we extract expressive feature with the attention mechanism of Transformer and incorporate the supervised contrastive loss function within our meta-optimization to enhance representation learning. Our evaluation demonstrates that TACO achieves notably better performance across various low-resource DS scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20290 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition Wang, Junyao Faruque, Mohammad Abdullah Al Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Deep learning has been widely adopted for human activity recognition (HAR) while generalizing a trained model across diverse users and scenarios remains challenging due to distribution shifts. The inherent low-resource challenge in HAR, i.e., collecting and labeling adequate human-involved data can be prohibitively costly, further raising the difficulty of tackling DS. We propose TACO, a novel transformer-based contrastive meta-learning approach for generalizable HAR. TACO addresses DS by synthesizing virtual target domains in training with explicit consideration of model generalizability. Additionally, we extract expressive feature with the attention mechanism of Transformer and incorporate the supervised contrastive loss function within our meta-optimization to enhance representation learning. Our evaluation demonstrates that TACO achieves notably better performance across various low-resource DS scenarios. |
| title | Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.20290 |