AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915716003790848 |
|---|---|
| author | Hu, Yunqing Yang, Zheming Zhao, Chang Guo, Qi Gao, Meng Li, Pengcheng Ji, Wen |
| author_facet | Hu, Yunqing Yang, Zheming Zhao, Chang Guo, Qi Gao, Meng Li, Pengcheng Ji, Wen |
| contents | Multimodal large language models (MLLMs) demonstrate exceptional capabilities in semantic understanding and visual reasoning, yet they still face challenges in precise object localization and resource-constrained edge-cloud deployment. To address this, this paper proposes the AIVD framework, which achieves unified precise localization and high-quality semantic generation through the collaboration between lightweight edge detectors and cloud-based MLLMs. To enhance the cloud MLLM's robustness against edge cropped-box noise and scenario variations, we design an efficient fine-tuning strategy with visual-semantic collaborative augmentation, significantly improving classification accuracy and semantic consistency. Furthermore, to maintain high throughput and low latency across heterogeneous edge devices and dynamic network conditions, we propose a heterogeneous resource-aware dynamic scheduling algorithm. Experimental results demonstrate that AIVD substantially reduces resource consumption while improving MLLM classification performance and semantic generation quality. The proposed scheduling strategy also achieves higher throughput and lower latency across diverse scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04734 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection Hu, Yunqing Yang, Zheming Zhao, Chang Guo, Qi Gao, Meng Li, Pengcheng Ji, Wen Computer Vision and Pattern Recognition Multimodal large language models (MLLMs) demonstrate exceptional capabilities in semantic understanding and visual reasoning, yet they still face challenges in precise object localization and resource-constrained edge-cloud deployment. To address this, this paper proposes the AIVD framework, which achieves unified precise localization and high-quality semantic generation through the collaboration between lightweight edge detectors and cloud-based MLLMs. To enhance the cloud MLLM's robustness against edge cropped-box noise and scenario variations, we design an efficient fine-tuning strategy with visual-semantic collaborative augmentation, significantly improving classification accuracy and semantic consistency. Furthermore, to maintain high throughput and low latency across heterogeneous edge devices and dynamic network conditions, we propose a heterogeneous resource-aware dynamic scheduling algorithm. Experimental results demonstrate that AIVD substantially reduces resource consumption while improving MLLM classification performance and semantic generation quality. The proposed scheduling strategy also achieves higher throughput and lower latency across diverse scenarios. |
| title | AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.04734 |