2021/06/21 by Yuya Senzaki, Senzaki, Yuya, Christian Hamelain +1 · 2 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification #Networking and Internet Architecture (cs.NI)
paper · pdf · doi:10.48550/arxiv.2106.10836
openalex publication_date 2021/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
When dealing with deep neural network (DNN) applications on edge devices, continuously updating the model is important. Although updating a model with real incoming data is ideal, using all of them is not always feasible due to limits, such as labeling and communication costs. Thus, it is necessary to filter and select the data to use for training (i.e., active learning) on the device. In this paper, we formalize a practical active learning problem for DNNs on edge devices and propose a general task-agnostic framework to tackle this problem, which reduces it to a stream submodular maximization. This framework is light enough to be run with low computational resources, yet provides solutions whose quality is theoretically guaranteed thanks to the submodular property. Through this framework, we can configure data selection criteria flexibly, including using methods proposed in previous active learning studies. We evaluate our approach on both classification and object detection tasks in a practical setting to simulate a real-life scenario. The results of our study show that the proposed framework outperforms all other methods in both tasks, while running at a practical speed on real devices.