mlsanityData to 14 Oct 2026

Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection

arXiv 2605.20502 ↗First posted 19 May 2026cs.LG cs.AI cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture differences, and covariate corruptions -- through a multi-encoder fusion of per-encoder representation-space diffusion models (RDMs). We statistically identify each encoder's sensitivity to specific shift types from ID data alone and introduce EncMin2L -- an encoder-agnostic two-level min(·)-gate that combines and calibrates per-encoder diffusion-based likelihood detectors without OOD labels, outperforming monolithic multi-encoder baselines at 2.3× lower parameter cost. Two ID-data diagnostics: η2 (class-conditional F-test) and Deltaμ (log-likelihood shift under synthetic corruptions) -- quantify encoder specialization, while a Tippett minimum p-value combination aggregates per-encoder scores into a single, calibration-stable OOD signal. EncMin2L achieves ≥ 0.94 AUROC across all four shift types simultaneously, outperforming the state-of-the-art representation-space diffusion OOD detectors across overlapping benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 25 of its 29 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

25 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Probability Density from Latent Diffusion Models for Out-of-Distribution Detection21 Aug
  2. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Model20 May
  3. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpainting20 Feb
  4. 2022Denoising diffusion models for out-of-distribution detection14 Nov

Other references · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2013Describing Textures in the Wildcited by 2,125
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,299
9 more
  1. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  3. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  4. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  5. 2023On Diffusion Modeling for Anomaly Detectioncited by 72
  6. 2018Out-of-Distribution Detection using Multiple Semantic Label Representationscited by 22
  7. 2024A Geometric Explanation of the Likelihood OOD Detection Paradoxcited by 22
  8. 2023Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Modelscited by 9
  9. 2025Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representationscited by 6

Built on by

Not cited yet.

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. 2024Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
  3. 2025OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection
  4. 2024Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model
  5. 2025GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
  6. 2026Sparse Autoencoders for Interpretable Out-of-Distribution Detection
  7. 2024NODI: Out-Of-Distribution Detection with Noise from Diffusion
  8. 2026Geometry over Density: Few-Shot Cross-Domain OOD Detection