# Large-Scale Visual Active Learning with Deep Probabilistic Ensembles

arXiv: https://arxiv.org/abs/1811.03575 · HTML: https://mlsanity.com/paper/1811.03575/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2018.

## Built on by (most cited first, 13 of 13)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation](https://mlsanity.com/paper/2101.02323/) (2021)
- [ELFNet: Evidential Local-global Fusion for Stereo Matching](https://mlsanity.com/paper/2308.00728/) (2023)
- [Warm Start Active Learning with Proxy Labels & Selection via Semi-Supervised Fine-Tuning](https://mlsanity.com/paper/2209.06285/) (2022)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation](https://mlsanity.com/paper/2411.15763/) (2024)
- [When Deep Learners Change Their Mind: Learning Dynamics for Active Learning](https://mlsanity.com/paper/2107.14707/) (2021)
- [Looking at the posterior: accuracy and uncertainty of neural-network predictions](https://mlsanity.com/paper/2211.14605/) (2022)
- [Gaussian Mixture based Evidential Learning for Stereo Matching](https://mlsanity.com/paper/2408.02796/) (2024)
- [Practical Deep Heteroskedastic Regression](https://mlsanity.com/paper/2603.01750/) (2026)

## Abstract (arXiv)

Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, where both performance and uncertainty estimation are crucial. In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep BNN. We conduct a series of large-scale visual active learning experiments to evaluate DPEs on classification with the CIFAR-10, CIFAR-100 and ImageNet datasets, and semantic segmentation with the BDD100k dataset. Our models require significantly less training data to achieve competitive performances, and steadily improve upon strong active learning baselines as the annotation budget is increased.