mlsanityData to 14 Oct 2026

DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories

arXiv 2502.16725 ↗First posted 23 Feb 2025cs.LG cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions. While recent research demonstrates the applicability of diffusion models to OOD detection, existing approaches are limited to Euclidean or latent image spaces. Our work extends OOD detection to trajectories in the Special Euclidean Group in 3D (mathbbSE(3)), addressing a critical need in computer vision, robotics, and engineering applications that process object pose sequences in mathbbSE(3). We present Diffusion-based Out-of-distribution detection on mathbbSE(3) (DOSE3), a novel OOD framework that extends diffusion to a unified sample space of mathbbSE(3) pose sequences. Through extensive validation on multiple benchmark datasets, we demonstrate DOSE3's superior performance compared to state-of-the-art OOD detection frameworks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 23 Feb 2025.

Builds on

26 of 37 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  8. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  11. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  12. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
14 more
  1. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  2. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  3. 2022Riemannian Diffusion Modelscited by 122
  4. 2022Denoising diffusion models for out-of-distribution detectioncited by 104
  5. 2020se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 90
  6. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  7. 2018WAIC, but Why? Generative Ensembles for Robust Anomaly Detectioncited by 25
  8. 2024DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Darkcited by 25
  9. 2020Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimationcited by 24
  10. 2023Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directionscited by 23
  11. 2021Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?cited by 16
  12. 2021Parallelised Diffeomorphic Sampling-based Motion Planningcited by 16
  13. 2023Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teachingcited by 14
  14. 2023Towards Efficient Trajectory Generation for Ground Robots beyond 2D Environmentcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Rewind-IL: Online Failure Detection and State Respawning for Imitation Learningcited by 9
  2. 2026AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policiescited by 2
  3. 2026ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
  2. 2026Geometry over Density: Few-Shot Cross-Domain OOD Detection
  3. 2025Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories
  4. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Model
  5. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpainting
  6. 2024NODI: Out-Of-Distribution Detection with Noise from Diffusion
  7. 2024Exploiting Diffusion Prior for Out-of-Distribution Detection
  8. 2024Non-Linear Outlier Synthesis for Out-of-Distribution Detection