mlsanityData to 7 Oct 2026

Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance

arXiv 1812.02765 ↗First posted 6 Dec 2018cs.LG stat.MLcited by 74

Not on the map. Why?

Abstract (arXiv)

There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems. A number of recent papers have proposed methods for detecting anomalous image data that appear different from known inlier data samples, including reconstruction-based autoencoders. Autoencoders optimize the compression of input data to a latent space of a dimensionality smaller than the original input and attempt to accurately reconstruct the input using that compressed representation. Since the latent vector is optimized to capture the salient features from the inlier class only, it is commonly assumed that images of objects from outside of the training class cannot effectively be compressed and reconstructed. Some thus consider reconstruction error as a kind of novelty measure. Here we suggest that reconstruction-based approaches fail to capture particular anomalies that lie far from known inlier samples in latent space but near the latent dimension manifold defined by the parameters of the model. We propose incorporating the Mahalanobis distance in latent space to better capture these out-of-distribution samples and our results show that this method often improves performance over the baseline approach.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 8; 2022: 7; 2023: 18; 2024: 14; 2025: 20; 2026: 6.

74 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  3. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  4. 2022Denoising diffusion models for out-of-distribution detectioncited by 102
  5. 2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
  6. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
  7. 2023Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learningcited by 40
  8. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 30
  9. 2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 25
  10. 2023Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objectscited by 23
  11. 2022Out-of-Distribution Detection with Semantic Mismatch under Maskingcited by 22
  12. 2023Unsupervised 3D out-of-distribution detection with latent diffusion modelscited by 22
38 more
  1. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Modelcited by 22
  2. 2021Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systemscited by 19
  3. 2024Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoningcited by 18
  4. 2021Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?cited by 16
  5. 2021Benchmarking Safety Monitors for Image Classifiers with Machine Learningcited by 14
  6. 2024Detecting Out-Of-Distribution Earth Observation Images with Diffusion Modelscited by 14
  7. 2021Resisting Out-of-Distribution Data Problem in Perturbation of XAIcited by 12
  8. 2021Out-of-distribution Detection with Boundary Aware Learningcited by 11
  9. 2023Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Modelscited by 10
  10. 2021WOOD: Wasserstein-based Out-of-Distribution Detectioncited by 9
  11. 2023MCROOD: Multi-Class Radar Out-Of-Distribution Detectioncited by 9
  12. 2025Autoencoders for Anomaly Detection are Unreliablecited by 9
  13. 2025Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoringcited by 9
  14. 2020Dynamic Horizon Value Estimation for Model-based Reinforcement Learningcited by 8
  15. 2023Out-of-distribution detection algorithms for robust insect classificationcited by 7
  16. 2022What do we learn? Debunking the Myth of Unsupervised Outlier Detectioncited by 6
  17. 2022READ: Aggregating Reconstruction Error into Out-of-distribution Detectioncited by 6
  18. 2023Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radarcited by 6
  19. 2023Unsupervised Recognition of Unknown Objects for Open-World Object Detectioncited by 6
  20. 2025Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimationcited by 6
  21. 2025Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomizationcited by 6
  22. 2021A Uniform Framework for Anomaly Detection in Deep Neural Networkscited by 4
  23. 2023Rethinking Polyp Segmentation from an Out-of-Distribution Perspectivecited by 4
  24. 2023HOOD: Real-Time Human Presence and Out-of-Distribution Detection Using FMCW Radarcited by 4
  25. 2024Can Your Generative Model Detect Out-of-Distribution Covariate Shift?cited by 4
  26. 2025EigenScore: OOD Detection using Covariance in Diffusion Modelscited by 4
  27. 2023Expecting The Unexpected: Towards Broad Out-Of-Distribution Detectioncited by 3
  28. 2024Safety Monitoring of Machine Learning Perception Functions: a Surveycited by 3
  29. 2025DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectoriescited by 3
  30. 2025Digital Twin-based Out-of-Distribution Detection in Autonomous Vesselscited by 3
  31. 2023Non-Invasive Fairness in Learning through the Lens of Data Driftcited by 2
  32. 2024UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detectioncited by 2
  33. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  34. 2022Geometric instability of out of distribution data across autoencoder architecturecited by 1
  35. 2023Out-of-distribution Object Detection through Bayesian Uncertainty Estimationcited by 1
  36. 2024Detecting Out-of-Distribution Objects through Class-Conditioned Inpaintingcited by 1
  37. 2024Differentiable Score-Based Likelihoods: Learning CT Motion Compensation From Clean Imagescited by 1
  38. 2024Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networkscited by 1

50 most cited of 74 All 74 (JSON)