# Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation

arXiv: https://arxiv.org/abs/2012.06575 · HTML: https://mlsanity.com/paper/2012.06575/

## Key facts

- Cited by 133 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 30 of 133)

- [SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation](https://mlsanity.com/paper/2104.14812/) (2021)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes](https://mlsanity.com/paper/2111.12264/) (2021)
- [Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation](https://mlsanity.com/paper/2107.11264/) (2021)
- [RbA: Segmenting Unknown Regions Rejected by All](https://mlsanity.com/paper/2211.14293/) (2022)
- [Nearest Neighbor Guidance for Out-of-Distribution Detection](https://mlsanity.com/paper/2309.14888/) (2023)
- [Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation](https://mlsanity.com/paper/2211.14512/) (2022)
- [Unmasking Anomalies in Road-Scene Segmentation](https://mlsanity.com/paper/2307.13316/) (2023)
- [DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition](https://mlsanity.com/paper/2207.02606/) (2022)
- [On Advantages of Mask-level Recognition for Outlier-aware Segmentation](https://mlsanity.com/paper/2301.03407/) (2023)
- [Maskomaly:Zero-Shot Mask Anomaly Segmentation](https://mlsanity.com/paper/2305.16972/) (2023)
- [Outlier detection by ensembling uncertainty with negative objectness](https://mlsanity.com/paper/2402.15374/) (2024)
- [An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving](https://mlsanity.com/paper/2103.03678/) (2021)
- [Open-World Semantic Segmentation Including Class Similarity](https://mlsanity.com/paper/2403.07532/) (2024)
- [Segment Every Out-of-Distribution Object](https://mlsanity.com/paper/2311.16516/) (2023)
- [Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty](https://mlsanity.com/paper/2405.05145/) (2024)
- [PixOOD: Pixel-Level Out-of-Distribution Detection](https://mlsanity.com/paper/2405.19882/) (2024)
- [Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects](https://mlsanity.com/paper/2210.02074/) (2022)
- [Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation](https://mlsanity.com/paper/2309.04573/) (2023)
- [Balanced Energy Regularization Loss for Out-of-distribution Detection](https://mlsanity.com/paper/2306.10485/) (2023)
- [MetaOOD: Automatic Selection of OOD Detection Models](https://mlsanity.com/paper/2410.03074/) (2024)
- [Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2211.06660/) (2022)
- [UGainS: Uncertainty Guided Anomaly Instance Segmentation](https://mlsanity.com/paper/2308.02046/) (2023)
- [CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen](https://mlsanity.com/paper/2312.05538/) (2023)
- [Learning to Prompt Knowledge Transfer for Open-World Continual Learning](https://mlsanity.com/paper/2312.14990/) (2023)
- [ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation](https://mlsanity.com/paper/2309.05994/) (2023)
- [Panoptic Out-of-Distribution Segmentation](https://mlsanity.com/paper/2310.11797/) (2023)
- [AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving](https://mlsanity.com/paper/2405.07865/) (2024)
- [Towards Unsupervised Open World Semantic Segmentation](https://mlsanity.com/paper/2201.01073/) (2022)
- [Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art](https://mlsanity.com/paper/2503.08695/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) for the semantic segmentation of images are usually trained to operate on a predefined closed set of object classes. This is in contrast to the "open world" setting where DNNs are envisioned to be deployed to. From a functional safety point of view, the ability to detect so-called "out-of-distribution" (OoD) samples, i.e., objects outside of a DNN's semantic space, is crucial for many applications such as automated driving. A natural baseline approach to OoD detection is to threshold on the pixel-wise softmax entropy. We present a two-step procedure that significantly improves that approach. Firstly, we utilize samples from the COCO dataset as OoD proxy and introduce a second training objective to maximize the softmax entropy on these samples. Starting from pretrained semantic segmentation networks we re-train a number of DNNs on different in-distribution datasets and consistently observe improved OoD detection performance when evaluating on completely disjoint OoD datasets. Secondly, we perform a transparent post-processing step to discard false positive OoD samples by so-called "meta classification". To this end, we apply linear models to a set of hand-crafted metrics derived from the DNN's softmax probabilities. In our experiments we consistently observe a clear additional gain in OoD detection performance, cutting down the number of detection errors by up to 52% when comparing the best baseline with our results. We achieve this improvement sacrificing only marginally in original segmentation performance. Therefore, our method contributes to safer DNNs with more reliable overall system performance.