A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices
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_ | 1866908694526033920 |
|---|---|
| author | Li, Yunzhe Zhu, Hongzi Deng, Zhuohong Cheng, Yunlong Zheng, Zimu Zhang, Liang Chang, Shan Guo, Minyi |
| author_facet | Li, Yunzhe Zhu, Hongzi Deng, Zhuohong Cheng, Yunlong Zheng, Zimu Zhang, Liang Chang, Shan Guo, Minyi |
| contents | Emerging Artificial Intelligence of Things (AIoT) applications desire online prediction using deep neural network (DNN) models on mobile devices. However, due to the movement of devices, unfamiliar test samples constantly appear, significantly affecting the prediction accuracy of a pre-trained DNN. In addition, unstable network connection calls for local model inference. In this paper, we propose a light-weight scheme, called Anole, to cope with the local DNN model inference on mobile devices. The core idea of Anole is to first establish an army of compact DNN models, and then adaptively select the model fitting the current test sample best for online inference. The key is to automatically identify model-friendly scenes for training scene-specific DNN models. To this end, we design a weakly-supervised scene representation learning algorithm by combining both human heuristics and feature similarity in separating scenes. Moreover, we further train a model classifier to predict the best-fit scene-specific DNN model for each test sample. We implement Anole on different types of mobile devices and conduct extensive trace-driven and real-world experiments based on unmanned aerial vehicles (UAVs). The results demonstrate that Anole outwits the method of using a versatile large DNN in terms of prediction accuracy (4.5% higher), response time (33.1% faster) and power consumption (45.1% lower). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices Li, Yunzhe Zhu, Hongzi Deng, Zhuohong Cheng, Yunlong Zheng, Zimu Zhang, Liang Chang, Shan Guo, Minyi Computer Vision and Pattern Recognition Artificial Intelligence Distributed, Parallel, and Cluster Computing Emerging Artificial Intelligence of Things (AIoT) applications desire online prediction using deep neural network (DNN) models on mobile devices. However, due to the movement of devices, unfamiliar test samples constantly appear, significantly affecting the prediction accuracy of a pre-trained DNN. In addition, unstable network connection calls for local model inference. In this paper, we propose a light-weight scheme, called Anole, to cope with the local DNN model inference on mobile devices. The core idea of Anole is to first establish an army of compact DNN models, and then adaptively select the model fitting the current test sample best for online inference. The key is to automatically identify model-friendly scenes for training scene-specific DNN models. To this end, we design a weakly-supervised scene representation learning algorithm by combining both human heuristics and feature similarity in separating scenes. Moreover, we further train a model classifier to predict the best-fit scene-specific DNN model for each test sample. We implement Anole on different types of mobile devices and conduct extensive trace-driven and real-world experiments based on unmanned aerial vehicles (UAVs). The results demonstrate that Anole outwits the method of using a versatile large DNN in terms of prediction accuracy (4.5% higher), response time (33.1% faster) and power consumption (45.1% lower). |
| title | A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2407.03331 |