Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
Not on the map. Why?
Abstract (arXiv)
Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications, where they frequently face data distributions unseen during training. Despite progress, existing methods are often vulnerable to spurious correlations that mislead models and compromise robustness. To address this, we propose SPROD, a novel prototype-based OOD detection approach that explicitly addresses the challenge posed by unknown spurious correlations. Our post-hoc method refines class prototypes to mitigate bias from spurious features without additional data or hyperparameter tuning, and is broadly applicable across diverse backbones and OOD detection settings. We conduct a comprehensive spurious correlation OOD detection benchmarking, comparing our method against existing approaches and demonstrating its superior performance across challenging OOD datasets, such as CelebA, Waterbirds, UrbanCars, Spurious Imagenet, and the newly introduced Animals MetaCoCo. On average, SPROD improves AUROC by 4.8% and FPR@95 by 9.4% over the second best.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 61 of its 81 references that are in the map. First posted on arXiv 30 Jun 2025.
Builds on
61 of 81 references.
References · 61
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2018YOLOv3: An Incremental Improvementcited by 2,659
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
38 more
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
- 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
- 2020Energy-based Out-of-distribution Detectioncited by 1,299
- 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
- 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
- 2018Deep Anomaly Detection with Outlier Exposurecited by 942
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
- 2018Recognition in Terra Incognitacited by 658
- 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
- 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
- 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
- 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
- 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
- 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 381
- 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
- 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
- 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
- 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
- 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
- 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
- 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
- 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
- 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
- 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
- 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
- 2020Estimating Example Difficulty Using Variance of Gradientscited by 97
- 2022A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Otherscited by 85
- 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
- 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
- 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
- 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
- 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 49
- 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
- 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
- 2022Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNetcited by 41
50 most cited of 61 All 61 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.