Decoupled Prompt-Adapter Tuning for Continual Activity Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913439219187712 |
|---|---|
| author | Fu, Di Vo, Thanh Vinh Ma, Haozhe Leong, Tze-Yun |
| author_facet | Fu, Di Vo, Thanh Vinh Ma, Haozhe Leong, Tze-Yun |
| contents | Action recognition technology plays a vital role in enhancing security through surveillance systems, enabling better patient monitoring in healthcare, providing in-depth performance analysis in sports, and facilitating seamless human-AI collaboration in domains such as manufacturing and assistive technologies. The dynamic nature of data in these areas underscores the need for models that can continuously adapt to new video data without losing previously acquired knowledge, highlighting the critical role of advanced continual action recognition. To address these challenges, we propose Decoupled Prompt-Adapter Tuning (DPAT), a novel framework that integrates adapters for capturing spatial-temporal information and learnable prompts for mitigating catastrophic forgetting through a decoupled training strategy. DPAT uniquely balances the generalization benefits of prompt tuning with the plasticity provided by adapters in pretrained vision models, effectively addressing the challenge of maintaining model performance amidst continuous data evolution without necessitating extensive finetuning. DPAT consistently achieves state-of-the-art performance across several challenging action recognition benchmarks, thus demonstrating the effectiveness of our model in the domain of continual action recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14811 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Decoupled Prompt-Adapter Tuning for Continual Activity Recognition Fu, Di Vo, Thanh Vinh Ma, Haozhe Leong, Tze-Yun Computer Vision and Pattern Recognition Artificial Intelligence Action recognition technology plays a vital role in enhancing security through surveillance systems, enabling better patient monitoring in healthcare, providing in-depth performance analysis in sports, and facilitating seamless human-AI collaboration in domains such as manufacturing and assistive technologies. The dynamic nature of data in these areas underscores the need for models that can continuously adapt to new video data without losing previously acquired knowledge, highlighting the critical role of advanced continual action recognition. To address these challenges, we propose Decoupled Prompt-Adapter Tuning (DPAT), a novel framework that integrates adapters for capturing spatial-temporal information and learnable prompts for mitigating catastrophic forgetting through a decoupled training strategy. DPAT uniquely balances the generalization benefits of prompt tuning with the plasticity provided by adapters in pretrained vision models, effectively addressing the challenge of maintaining model performance amidst continuous data evolution without necessitating extensive finetuning. DPAT consistently achieves state-of-the-art performance across several challenging action recognition benchmarks, thus demonstrating the effectiveness of our model in the domain of continual action recognition. |
| title | Decoupled Prompt-Adapter Tuning for Continual Activity Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.14811 |