# Active Learning for Deep Neural Networks on Edge Devices

arXiv: https://arxiv.org/abs/2106.10836 · HTML: https://mlsanity.com/paper/2106.10836/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 21 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision](https://mlsanity.com/paper/1901.01151/) (2019)
- [Localization-Aware Active Learning for Object Detection](https://mlsanity.com/paper/1801.05124/) (2018)
- [Scalable Log Determinants for Gaussian Process Kernel Learning](https://mlsanity.com/paper/1711.03481/) (2017)
- [Neural Active Learning with Performance Guarantees](https://mlsanity.com/paper/2106.03243/) (2021)
- [Submodular Streaming in All its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity](https://mlsanity.com/paper/1905.00948/) (2019)
- [Identifying Wrongly Predicted Samples: A Method for Active Learning](https://mlsanity.com/paper/2010.06890/) (2020)
- [Very Fast Streaming Submodular Function Maximization](https://mlsanity.com/paper/2010.10059/) (2020)

## Built on by (most cited first, 6 of 6)

- [Streaming Active Learning with Deep Neural Networks](https://mlsanity.com/paper/2303.02535/) (2023)
- [Accelerating Batch Active Learning Using Continual Learning Techniques](https://mlsanity.com/paper/2305.06408/) (2023)
- [Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Loss](https://mlsanity.com/paper/2309.05517/) (2023)
- [Deep Active Learning in the Presence of Label Noise: A Survey](https://mlsanity.com/paper/2302.11075/) (2023)
- [TActiLE: Tiny Active LEarning for wearable devices](https://mlsanity.com/paper/2505.01160/) (2025)
- [Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration](https://mlsanity.com/paper/2606.12913/) (2026)

## Abstract (arXiv)

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.