# Discriminative out-of-distribution detection for semantic segmentation

arXiv: https://arxiv.org/abs/1808.07703 · HTML: https://mlsanity.com/paper/1808.07703/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2018.

## Built on by (most cited first, 30 of 47)

- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space](https://mlsanity.com/paper/2105.01879/) (2021)
- [DICE: Leveraging Sparsification for Out-of-Distribution Detection](https://mlsanity.com/paper/2111.09805/) (2021)
- [Non-Parametric Outlier Synthesis](https://mlsanity.com/paper/2303.02966/) (2023)
- [Pixel-wise Anomaly Detection in Complex Driving Scenes](https://mlsanity.com/paper/2103.05445/) (2021)
- [Training OOD Detectors in their Natural Habitats](https://mlsanity.com/paper/2202.03299/) (2022)
- [Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes](https://mlsanity.com/paper/2111.12264/) (2021)
- [Provable Guarantees for Understanding Out-of-distribution Detection](https://mlsanity.com/paper/2112.00787/) (2021)
- [Dream the Impossible: Outlier Imagination with Diffusion Models](https://mlsanity.com/paper/2309.13415/) (2023)
- [Energy-based Out-of-Distribution Detection for Graph Neural Networks](https://mlsanity.com/paper/2302.02914/) (2023)
- [RbA: Segmenting Unknown Regions Rejected by All](https://mlsanity.com/paper/2211.14293/) (2022)
- [Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2306.09158/) (2023)
- [How Does Unlabeled Data Provably Help Out-of-Distribution Detection?](https://mlsanity.com/paper/2402.03502/) (2024)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Dense outlier detection and open-set recognition based on training with noisy negative images](https://mlsanity.com/paper/2101.09193/) (2021)
- [Out-of-Distribution Detection for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2209.14435/) (2022)
- [Balanced Energy Regularization Loss for Out-of-distribution Detection](https://mlsanity.com/paper/2306.10485/) (2023)
- [CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen](https://mlsanity.com/paper/2312.05538/) (2023)
- [How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?](https://mlsanity.com/paper/2312.14452/) (2023)
- [Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data](https://mlsanity.com/paper/2112.12833/) (2021)
- [Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning](https://mlsanity.com/paper/2103.00869/) (2021)
- [Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs](https://mlsanity.com/paper/2502.17912/) (2025)
- [Out-of-distribution detection algorithms for robust insect classification](https://mlsanity.com/paper/2305.01823/) (2023)
- [Taming False Positives in Out-of-Distribution Detection with Human Feedback](https://mlsanity.com/paper/2404.16954/) (2024)
- [Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment](https://mlsanity.com/paper/2308.08696/) (2023)
- [When and How Does In-Distribution Label Help Out-of-Distribution Detection?](https://mlsanity.com/paper/2405.18635/) (2024)
- [Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs](https://mlsanity.com/paper/2504.13429/) (2025)
- [Your Classifier Can Be Secretly a Likelihood-Based OOD Detector](https://mlsanity.com/paper/2408.04851/) (2024)
- [Diffusion based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection](https://mlsanity.com/paper/2408.14841/) (2024)

## Abstract (arXiv)

Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However, such assumption implies unavoidable and often unnoticeable failures in presence of out-of-distribution (OOD) input. These failures are bound to happen in most real-life applications since current visual ontologies are far from being comprehensive. We propose to address this issue by discriminative detection of OOD pixels in input data. Different from recent approaches, we avoid to bring any decisions by only observing the training dataset of the primary model trained to solve the desired computer vision task. Instead, we train a dedicated OOD model which discriminates the primary training set from a much larger "background" dataset which approximates the variety of the visual world. We perform our experiments on high resolution natural images in a dense prediction setup. We use several road driving datasets as our training distribution, while we approximate the background distribution with the ILSVRC dataset. We evaluate our approach on WildDash test, which is currently the only public test dataset that includes out-of-distribution images. The obtained results show that the proposed approach succeeds to identify out-of-distribution pixels while outperforming previous work by a wide margin.