Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916541517266944 |
|---|---|
| author | Wu, Jiaqi Zhang, Shihao Chen, Simin Wang, Lixu Wang, Zehua Chen, Wei He, Fangyuan Tian, Zijian Yu, F. Richard Leung, Victor C. M. |
| author_facet | Wu, Jiaqi Zhang, Shihao Chen, Simin Wang, Lixu Wang, Zehua Chen, Wei He, Fangyuan Tian, Zijian Yu, F. Richard Leung, Victor C. M. |
| contents | Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios. However, existing edge detection methods face challenges: 1) difficulty balancing detection precision with lightweight models, 2) limited adaptability of generalized deployment designs, and 3) insufficient real-world validation. To address these issues, we propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments. Specifically, we introduce a lightweight Reparameterized Dynamic Convolutional Network (Rep-DConvNet) featuring weighted multi-shape convolutional branches to enhance detection performance. Additionally, we design a Sparse Cross-Attention (SC-A) network with a localized-mapping-assisted self-attention mechanism, enabling a well-crafted joint module for adaptive feature transfer. For real-world applications, we incorporate an Efficient Head into the YOLO framework to accelerate edge model optimization. To demonstrate practical impact, we identify a gap in helmet detection -- overlooking band fastening, a critical safety factor -- and create the Helmet Band Detection Dataset (HBDD). Using ED-TOOLBOX-optimized models, we address this real-world task. Extensive experiments validate the effectiveness of ED-TOOLBOX, with edge detection models outperforming six state-of-the-art methods in visual surveillance simulations, achieving real-time and accurate performance. These results highlight ED-TOOLBOX as a superior solution for edge object detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18230 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment Wu, Jiaqi Zhang, Shihao Chen, Simin Wang, Lixu Wang, Zehua Chen, Wei He, Fangyuan Tian, Zijian Yu, F. Richard Leung, Victor C. M. Computer Vision and Pattern Recognition Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios. However, existing edge detection methods face challenges: 1) difficulty balancing detection precision with lightweight models, 2) limited adaptability of generalized deployment designs, and 3) insufficient real-world validation. To address these issues, we propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments. Specifically, we introduce a lightweight Reparameterized Dynamic Convolutional Network (Rep-DConvNet) featuring weighted multi-shape convolutional branches to enhance detection performance. Additionally, we design a Sparse Cross-Attention (SC-A) network with a localized-mapping-assisted self-attention mechanism, enabling a well-crafted joint module for adaptive feature transfer. For real-world applications, we incorporate an Efficient Head into the YOLO framework to accelerate edge model optimization. To demonstrate practical impact, we identify a gap in helmet detection -- overlooking band fastening, a critical safety factor -- and create the Helmet Band Detection Dataset (HBDD). Using ED-TOOLBOX-optimized models, we address this real-world task. Extensive experiments validate the effectiveness of ED-TOOLBOX, with edge detection models outperforming six state-of-the-art methods in visual surveillance simulations, achieving real-time and accurate performance. These results highlight ED-TOOLBOX as a superior solution for edge object detection. |
| title | Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.18230 |