mlsanityData to 14 Oct 2026

Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning

arXiv 2311.06481 ↗First posted 11 Nov 2023cs.RO cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required. A powerful approach for OOD detection is based on density estimation with Normalizing Flows (NFs). However, we find that prior work with NFs attempts to match the complex target distribution topologically with naive base distributions leading to adverse implications. In this work, we circumvent this topological mismatch using an expressive class-conditional base distribution trained with an information-theoretic objective to match the required topology. The proposed method enjoys the merits of wide compatibility with existing learned models without any performance degradation and minimum computation overhead while enhancing OOD detection capabilities. We demonstrate superior results in density estimation and 2D object detection benchmarks in comparison with extensive baselines. Moreover, we showcase the applicability of the method with a real-robot deployment.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 49 of its 65 references that are in the map. First posted on arXiv 11 Nov 2023.

Builds on

49 of 65 references.

References · 49

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2016Density estimation using Real NVPcited by 2,042
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  8. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  10. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  11. 2019Neural Spline Flowscited by 596
  12. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
37 more
  1. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  2. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  3. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  4. 2019Residual Flows for Invertible Generative Modelingcited by 257
  5. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  6. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  7. 2018Neural Autoregressive Flowscited by 208
  8. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  9. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  10. 2020Stochastic Normalizing Flowscited by 157
  11. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  12. 2020Hybrid Models for Open Set Recognitioncited by 109
  13. 2020Understanding and Mitigating Exploding Inverses in Invertible Neural Networkscited by 71
  14. 2020SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flowscited by 71
  15. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  16. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  17. 2018Resampled Priors for Variational Autoencoderscited by 57
  18. 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
  19. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  20. 2019Hybrid Models with Deep and Invertible Featurescited by 41
  21. 2020Out-of-Distribution Detection for Automotive Perceptioncited by 37
  22. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  23. 2020Estimating Model Uncertainty of Neural Networks in Sparse Information Formcited by 31
  24. 2020Stabilizing Invertible Neural Networks Using Mixture Modelscited by 30
  25. 2019Understanding the Limitations of Conditional Generative Modelscited by 28
  26. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  27. 2022Safe Output Feedback Motion Planning from Images via Learned Perception Modules and Contraction Theorycited by 19
  28. 2019A RAD approach to deep mixture modelscited by 18
  29. 2021Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstructioncited by 16
  30. 2023Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detectioncited by 16
  31. 2021Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributionscited by 13
  32. 2021Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processescited by 12
  33. 2021Bayesian Active Learning for Sim-to-Real Robotic Perceptioncited by 8
  34. 2023Training, Architecture, and Prior for Deterministic Uncertainty Methodscited by 7
  35. 2021Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networkscited by 5
  36. 2023Out-of-Distribution Detection for Adaptive Computer Visioncited by 2
  37. 2023Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assemblycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 2.

7 papers.

  1. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulationcited by 104
  2. 2024Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Plannerscited by 15
  3. 2025Mobi-π: Mobilizing Your Robot Learning Policycited by 10
  4. 2024FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inferencecited by 3
  5. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  6. 2026SPIRIT: Perceptive Shared Autonomy for Robust Robotic Manipulation under Deep Learning Uncertaintycited by 1
  7. 2026ConFlow: Constraints-Guided Learning with Flow Matching for Motion Generationcited by 0