mlsanityData to 7 Oct 2026

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

arXiv 2303.10449 ↗First posted 18 Mar 2023cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set. The coexistence of in-distribution and out-of-distribution samples will exacerbate the model overfitting when no distinction is made. To address this problem, we propose a novel uncertainty-aware optimal transport scheme. Our scheme consists of an energy-based transport (ET) mechanism that estimates the fluctuating cost of uncertainty to promote the assignment of semantic-agnostic representation, and an inter-cluster extension strategy that enhances the discrimination of semantic property among different clusters by widening the corresponding margin distance. Furthermore, a T-energy score is presented to mitigate the magnitude gap between the parallel transport and classifier branches. Extensive experiments on two standard SCOOD benchmarks demonstrate the above-par OOD detection performance, outperforming the state-of-the-art methods by a margin of 27.69% and 34.4% on FPR@95, respectively.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 18 Mar 2023.

Builds on

27 of 36 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  5. 2013Describing Textures in the Wildcited by 2,110
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  10. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  11. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  12. 2021Domain Generalization: A Surveycited by 760
15 more
  1. 2017Wasserstein GANcited by 635
  2. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  3. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  4. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  5. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  6. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  7. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  8. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  9. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  10. 2022Training OOD Detectors in their Natural Habitatscited by 86
  11. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  12. 2020Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transportcited by 28
  13. 2018Building robust classifiers through generation of confident out of distribution examplescited by 20
  14. 2022Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transportcited by 14
  15. 2020Mutual Learning Network for Multi-Source Domain Adaptationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 9; 2026: 2.

19 papers.

Sort:

By area:

  1. 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Priorcited by 28
  2. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  3. 2024Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detectioncited by 8
  4. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  5. 2024Rethinking Out-of-Distribution Detection on Imbalanced Data Distributioncited by 6
  6. 2023Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detectioncited by 5
  7. 2025Digital Twin-based Out-of-Distribution Detection in Autonomous Vesselscited by 3
  8. 2024Out-of-Distribution Detection using Neural Activation Priorcited by 2
  9. 2024FlowCon: Out-of-Distribution Detection using Flow-Based Contrastive Learningcited by 2
  10. 2024Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generationcited by 2
  11. 2024Prototype-based Optimal Transport for Out-of-Distribution Detectioncited by 1
  12. 2025OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detectioncited by 1
7 more
  1. 2025Network Inversion for Uncertainty-Aware Out-of-Distribution Detectioncited by 1
  2. 2026Semi-Supervised Hierarchical Open-Set Classificationcited by 1
  3. 2025Energy-Based Pseudo-Label Refining for Source-free Domain Adaptationcited by 0
  4. 2025Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learningcited by 0
  5. 2025TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detectioncited by 0
  6. 2025Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detectioncited by 0
  7. 2026SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identificationcited by 0