# Episode-Based Active Learning with Bayesian Neural Networks

arXiv: https://arxiv.org/abs/1703.07473 · HTML: https://mlsanity.com/paper/1703.07473/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2017.

## Built on by (most cited first, 4 of 4)

- [ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2402.03235/) (2024)
- [Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Loss](https://mlsanity.com/paper/2309.05517/) (2023)
- [The Speed-up Factor: A Quantitative Multi-Iteration Active Learning Performance Metric](https://mlsanity.com/paper/2602.13359/) (2026)
- [Automated Coral Spawn Monitoring for Reef Restoration: The Coral Spawn and Larvae Imaging Camera System (CSLICS)](https://mlsanity.com/paper/2509.17299/) (2025)

## Abstract (arXiv)

We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation of different strategies for acquisition, updating, and final training on the CIFAR-10 dataset shows that incremental network updates with final training on the accumulated acquisition set are essential for best performance, while limiting the amount of required human labeling labor.