mlsanityData to 14 Oct 2026

SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection

arXiv 2208.13930 ↗First posted 29 Aug 2022cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

We address the problem of out-of-distribution (OOD) detection for the task of object detection. We show that residual convolutional layers with batch normalisation produce Sensitivity-Aware FEatures (SAFE) that are consistently powerful for distinguishing in-distribution from out-of-distribution detections. We extract SAFE vectors for every detected object, and train a multilayer perceptron on the surrogate task of distinguishing adversarially perturbed from clean in-distribution examples. This circumvents the need for realistic OOD training data, computationally expensive generative models, or retraining of the base object detector. SAFE outperforms the state-of-the-art OOD object detectors on multiple benchmarks by large margins, e.g. reducing the FPR95 by an absolute 30.6% from 48.3% to 17.7% on the OpenImages dataset.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 59 of its 78 references that are in the map. First posted on arXiv 29 Aug 2022.

Builds on

59 of 78 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2017Mask R-CNNcited by 7,277
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2017On Calibration of Modern Neural Networkscited by 4,960
  10. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  12. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
38 more
  1. 2016Concrete Problems in AI Safetycited by 1,642
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  4. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  6. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  7. 2020Designing Network Design Spacescited by 960
  8. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  10. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  11. 2015Towards Open Set Deep Networkscited by 538
  12. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  13. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  14. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  15. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  16. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  17. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  18. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  19. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  20. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  21. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  22. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  23. 2021Towards Open World Object Detectioncited by 297
  24. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  25. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  26. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 153
  27. 2021OW-DETR: Open-world Detection Transformercited by 129
  28. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  29. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  30. 2018The Limits and Potentials of Deep Learning for Roboticscited by 104
  31. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  32. 2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
  33. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  34. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  35. 2020Feature Space Singularity for Out-of-Distribution Detectioncited by 49
  36. 2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
  37. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  38. 2020Multiscale Score Matching for Out-of-Distribution Detectioncited by 36

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 16; 2025: 8; 2026: 6.

33 papers.

Sort:

By area:

  1. 2023BatchNorm-based Weakly Supervised Video Anomaly Detectioncited by 22
  2. 2024Interpreting Object-level Foundation Models via Visual Precision Searchcited by 20
  3. 2024Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detectioncited by 11
  4. 2024DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detectioncited by 11
  5. 2024Can OOD Object Detectors Learn from Foundation Models?cited by 10
  6. 2024OoDIS: Anomaly Instance Segmentation and Detection Benchmarkcited by 8
  7. 2024On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenescited by 5
  8. 2024Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesiscited by 4
  9. 2024Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similaritycited by 4
  10. 2023Neuron Sensitivity Guided Test Case Selection for Deep Learning Testingcited by 3
  11. 2024Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detectioncited by 2
  12. 2024Large-Scale Evaluation of Open-Set Image Classification Techniquescited by 2
21 more
  1. 2024Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectorscited by 2
  2. 2024Edge Case Detection in Automated Driving: Methods, Challenges, and Future Directionscited by 2
  3. 2024Uncertainty Quantification in Detection Transformers: Object-Level Calibration and Image-Level Reliabilitycited by 2
  4. 2025Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Drivingcited by 2
  5. 2025Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigmcited by 2
  6. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  7. 2023Advancing Perception in Artificial Intelligence through Principles of Cognitive Sciencecited by 1
  8. 2024Detecting Out-of-Distribution Objects through Class-Conditioned Inpaintingcited by 1
  9. 2025Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?cited by 1
  10. 2026PhaseWin: An Efficient Search Algorithm for Faithful Visual Attributioncited by 1
  11. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  12. 2024On the Inherent Robustness of One-Stage Object Detection against Out-of-Distribution Datacited by 0
  13. 2025VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detectioncited by 0
  14. 2025FindMeIfYouCan: Bringing Open Set metrics to textitnear , textitfar and textitfarther Out-of-Distribution Object Detectioncited by 0
  15. 2025Detecting What Matters: A Novel Approach for Out-of-Distribution 3D Object Detection in Autonomous Vehiclescited by 0
  16. 2025Three-Way Open-Set Detection for Robust Autonomous Navigationcited by 0
  17. 2026ALOOD: Exploiting Language Representations for LiDAR-based Out-of-Distribution Object Detectioncited by 0
  18. 2026Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learningcited by 0
  19. 2026Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landingcited by 0
  20. 2026NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Modelscited by 0
  21. 2026SAM3-O2D2: Zero-Shot Object Out-of-Distribution Detection by Object Class Prompting of the SAM3-Image Modelcited by 0