# Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach

arXiv: https://arxiv.org/abs/2502.19691 · HTML: https://mlsanity.com/paper/2502.19691/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 58 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Deep Deterministic Uncertainty: A Simple Baseline](https://mlsanity.com/paper/2102.11582/) (2021)
- [Understanding Measures of Uncertainty for Adversarial Example Detection](https://mlsanity.com/paper/1803.08533/) (2018)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Learning Open Set Network with Discriminative Reciprocal Points](https://mlsanity.com/paper/2011.00178/) (2020)
- [Hybrid Models for Open Set Recognition](https://mlsanity.com/paper/2003.12506/) (2020)
- [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020)
- [Can multi-label classification networks know what they don't know?](https://mlsanity.com/paper/2109.14162/) (2021)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network](https://mlsanity.com/paper/1806.05473/) (2018)
- [Generative Adversarial Active Learning](https://mlsanity.com/paper/1702.07956/) (2017)
- [Adversarial Sampling for Active Learning](https://mlsanity.com/paper/1808.06671/) (2018)
- [Sparse Representation-based Open Set Recognition](https://mlsanity.com/paper/1705.02431/) (2017)
- [Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm](https://mlsanity.com/paper/2303.14382/) (2023)
- [Active Learning for Open-set Annotation](https://mlsanity.com/paper/2201.06758/) (2022)
- [Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning](https://mlsanity.com/paper/2210.07805/) (2022)
- [Entropic Open-set Active Learning](https://mlsanity.com/paper/2312.14126/) (2023)
- [Dirichlet-Based Prediction Calibration for Learning with Noisy Labels](https://mlsanity.com/paper/2401.07062/) (2024)
- [Bidirectional Uncertainty-Based Active Learning for Open Set Annotation](https://mlsanity.com/paper/2402.15198/) (2024)

## Built on by (most cited first, 5 of 5)

- [Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learning](https://mlsanity.com/paper/2603.07898/) (2026)
- [Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models](https://mlsanity.com/paper/2604.10963/) (2026)
- [Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification](https://mlsanity.com/paper/2509.24181/) (2025)
- [Softmax is not Enough (for Adaptive Conformal Classification)](https://mlsanity.com/paper/2602.19498/) (2026)
- [Federated Active Learning Under Extreme Non-IID and Global Class Imbalance](https://mlsanity.com/paper/2603.10341/) (2026)

## Abstract (arXiv)

Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the presence of open-set classes. Existing methods either prioritize query examples likely to belong to known classes, indicating low epistemic uncertainty (EU), or focus on querying those with highly uncertain predictions, reflecting high aleatoric uncertainty (AU). However, they both yield suboptimal performance, as low EU corresponds to limited useful information, and closed-set AU metrics for unknown class examples are less meaningful. In this paper, we propose an Energy-based Active Open-set Annotation (EAOA) framework, which effectively integrates EU and AU to achieve superior performance. EAOA features a (C+1)-class detector and a target classifier, incorporating an energy-based EU measure and a margin-based energy loss designed for the detector, alongside an energy-based AU measure for the target classifier. Another crucial component is the target-driven adaptive sampling strategy. It first forms a smaller candidate set with low EU scores to ensure closed-set properties, making AU metrics meaningful. Subsequently, examples with high AU scores are queried to form the final query set, with the candidate set size adjusted adaptively. Extensive experiments show that EAOA achieves state-of-the-art performance while maintaining high query precision and low training overhead. The code is available at https://github.com/chenchenzong/EAOA.