# Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation

arXiv: https://arxiv.org/abs/2108.01634 · HTML: https://mlsanity.com/paper/2108.01634/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 69 references that are in the map.
- First posted on arXiv 3 Aug 2021.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [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)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)

## Built on by (most cited first, 30 of 40)

- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [RbA: Segmenting Unknown Regions Rejected by All](https://mlsanity.com/paper/2211.14293/) (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)
- [MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks](https://mlsanity.com/paper/2203.01437/) (2022)
- [Open-World Semantic Segmentation Including Class Similarity](https://mlsanity.com/paper/2403.07532/) (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)
- [Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models](https://mlsanity.com/paper/2409.13174/) (2024)
- [Latent Discriminant deterministic Uncertainty](https://mlsanity.com/paper/2207.10130/) (2022)
- [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)
- [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)
- [RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection](https://mlsanity.com/paper/2204.02553/) (2022)
- [Placing Objects in Context via Inpainting for Out-of-distribution Segmentation](https://mlsanity.com/paper/2402.16392/) (2024)
- [Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation](https://mlsanity.com/paper/2303.06920/) (2023)
- [Hybrid Open-set Segmentation with Synthetic Negative Data](https://mlsanity.com/paper/2301.08555/) (2023)
- [Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow](https://mlsanity.com/paper/2305.09610/) (2023)
- [ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models](https://mlsanity.com/paper/2307.00398/) (2023)
- [Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression](https://mlsanity.com/paper/2308.09065/) (2023)
- [Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification](https://mlsanity.com/paper/2205.10906/) (2022)
- [The BRAVO Semantic Segmentation Challenge Results in UNCV2024](https://mlsanity.com/paper/2409.15107/) (2024)
- [Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation](https://mlsanity.com/paper/2308.09965/) (2023)
- [The Robust Semantic Segmentation UNCV2023 Challenge Results](https://mlsanity.com/paper/2309.15478/) (2023)
- [Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systems](https://mlsanity.com/paper/2303.01300/) (2023)
- [VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection](https://mlsanity.com/paper/2409.17330/) (2024)
- [Probing Contextual Diversity for Dense Out-of-Distribution Detection](https://mlsanity.com/paper/2208.14195/) (2022)
- [Likelihood Annealing: Fast Calibrated Uncertainty for Regression](https://mlsanity.com/paper/2302.11012/) (2023)

## Abstract (arXiv)

In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. By analyzing the literature, we found that current methods are either accurate or fast but not both which limits their usability in real world applications. To get the best of both aspects, we propose to mitigate the common shortcomings by following four design principles: decoupling the OOD detection from the segmentation task, observing the entire segmentation network instead of just its output, generating training data for the OOD detector by leveraging blind spots in the segmentation network and focusing the generated data on localized regions in the image to simulate OOD objects. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA). We validate the soundness of our approach across numerous ablation studies. We also show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.