mlsanityData to 7 Oct 2026

Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning

arXiv 2103.00869 ↗First posted 1 Mar 2021cs.CV cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

In this work, we train a network to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD dataset with a novel contrastive objective and data augmentation scheme. By combining data including unknown classes in the training data, a more robust feature representation can be learned with known classes represented distinctly from those unknown. When presented with unknown classes or conditions, many current approaches for segmentation frequently exhibit high confidence in their inaccurate segmentations and cannot be trusted in many operational environments. We validate our system on a real-world dataset of unusual driving scenes, and show that by selectively segmenting scenes based on what is predicted as OoD, we can increase the segmentation accuracy by an IoU of 0.2 with respect to alternative techniques.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 1 Mar 2021.

Builds on

35 of 43 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2020Supervised Contrastive Learningcited by 2,803
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  12. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
23 more
  1. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  3. 2019When Does Label Smoothing Help?cited by 985
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  5. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  6. 2015Weight Uncertainty in Neural Networkscited by 554
  7. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  10. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  11. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  12. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  13. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  14. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  15. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  16. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  17. 2019Ensemble Distribution Distillationcited by 158
  18. 2018Efficient GAN-Based Anomaly Detectioncited by 122
  19. 2018The Limits and Potentials of Deep Learning for Roboticscited by 104
  20. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  21. 2018Discriminative out-of-distribution detection for semantic segmentationcited by 47
  22. 2018Dropout Distillation for Efficiently Estimating Model Confidencecited by 9
  23. 2020Sense-Assess-eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarioscited by 9

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 3; 2025: 3.

9 papers.

  1. 2022Out-of-Distribution Detection for LiDAR-based 3D Object Detectioncited by 17
  2. 2024Towards certifiable AI in aviation: landscape, challenges, and opportunitiescited by 2
  3. 2025Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMscited by 2
  4. 2025Relative Energy Learning for LiDAR Out-of-Distribution Detectioncited by 2
  5. 2024Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modelingcited by 1
  6. 2024Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Datacited by 1
  7. 2021DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructionscited by 0
  8. 2021Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Datacited by 0
  9. 2025Elements of Active Continuous Learning and Uncertainty Self-Awareness: a Narrow Implementation for Face and Facial Expression Recognitioncited by 0