# Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data

arXiv: https://arxiv.org/abs/2112.12833 · HTML: https://mlsanity.com/paper/2112.12833/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 102 references that are in the map.
- First posted on arXiv 23 Dec 2021.

## Builds on (most cited first, 30 of 63)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation](https://mlsanity.com/paper/2104.14812/) (2021)
- [Detecting the Unexpected via Image Resynthesis](https://mlsanity.com/paper/1904.07595/) (2019)
- [OpenGAN: Open-Set Recognition via Open Data Generation](https://mlsanity.com/paper/2104.02939/) (2021)
- [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://mlsanity.com/paper/1812.01593/) (2018)
- [Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation](https://mlsanity.com/paper/2012.06575/) (2020)

## Built on by (most cited first, 10 of 10)

- [Outlier detection by ensembling uncertainty with negative objectness](https://mlsanity.com/paper/2402.15374/) (2024)
- [PixOOD: Pixel-Level Out-of-Distribution Detection](https://mlsanity.com/paper/2405.19882/) (2024)
- [AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving](https://mlsanity.com/paper/2405.07865/) (2024)
- [A Likelihood Ratio-Based Approach to Segmenting Unknown Objects](https://mlsanity.com/paper/2409.06424/) (2024)
- [Hybrid Open-set Segmentation with Synthetic Negative Data](https://mlsanity.com/paper/2301.08555/) (2023)
- [AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains](https://mlsanity.com/paper/2212.14397/) (2022)
- [Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios](https://mlsanity.com/paper/2412.05707/) (2024)
- [Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection](https://mlsanity.com/paper/2508.00587/) (2025)
- [Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation](https://mlsanity.com/paper/2505.22805/) (2025)
- [Real-World On-Vehicle Evaluation of Embedding-Based Anomaly Detection](https://mlsanity.com/paper/2605.19744/) (2026)

## Abstract (arXiv)

Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction since input images may be only partially anomalous. Previous work has addressed dense out-of-distribution detection by discriminative training with respect to off-the-shelf negative datasets. However, real negative data are unlikely to cover all modes of the entire visual world. To this end, we extend this approach by generating synthetic negative patches along the border of the inlier manifold. We leverage a jointly trained normalizing flow due to coverage-oriented learning objective and the capability to generate samples at different resolutions. We detect anomalies according to a principled information-theoretic criterion which can be consistently applied through training and inference. The resulting models set the new state of the art on benchmarks for out-of-distribution detection in road-driving scenes and remote sensing imagery, in spite of minimal computational overhead.