# Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?

arXiv: https://arxiv.org/abs/1908.09625 · HTML: https://mlsanity.com/paper/1908.09625/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2019.

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

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [OpenTAL: Towards Open Set Temporal Action Localization](https://mlsanity.com/paper/2203.05114/) (2022)
- [UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs](https://mlsanity.com/paper/2201.13279/) (2022)
- [Hard Negative Sampling Strategies for Contrastive Representation Learning](https://mlsanity.com/paper/2206.01197/) (2022)
- [Managing the unknown: a survey on Open Set Recognition and tangential areas](https://mlsanity.com/paper/2312.08785/) (2023)
- [Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projection](https://mlsanity.com/paper/2210.06512/) (2022)
- [Likelihood Annealing: Fast Calibrated Uncertainty for Regression](https://mlsanity.com/paper/2302.11012/) (2023)
- [Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition](https://mlsanity.com/paper/2212.06023/) (2022)
- [Latent Space Energy-based Model for Fine-grained Open Set Recognition](https://mlsanity.com/paper/2309.10711/) (2023)
- [Analysis and Applications of Deep Learning with Finite Samples in Full Life-Cycle Intelligence of Nuclear Power Generation](https://mlsanity.com/paper/2311.04247/) (2023)
- [BOWL: A Deceptively Simple Open World Learner](https://mlsanity.com/paper/2402.04814/) (2024)
- [Learning Model Successors](https://mlsanity.com/paper/2502.00197/) (2025)
- [Open-Set Living Need Prediction with Large Language Models](https://mlsanity.com/paper/2506.02713/) (2025)

## Abstract (arXiv)

We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition. While the former alone does not seem to be enough to overcome this challenge, we demonstrate that uncertainty goes hand in hand with the latter method. This seems to be particularly reflected in a generative model approach, where we show that posterior based open set recognition outperforms discriminative models and predictive uncertainty based outlier rejection, raising the question of whether classifiers need to be generative in order to know what they have not seen.