mlsanityData to 7 Oct 2026

Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection

arXiv 2203.02194 ↗First posted 4 Mar 2022cs.CV cs.LGcited by 59

Not on the map. Why?

Abstract (arXiv)

In some scenarios, classifier requires detecting out-of-distribution samples far from its training data. With desirable characteristics, reconstruction autoencoder-based methods deal with this problem by using input reconstruction error as a metric of novelty vs. normality. We formulate the essence of such approach as a quadruplet domain translation with an intrinsic bias to only query for a proxy of conditional data uncertainty. Accordingly, an improvement direction is formalized as maximumly compressing the autoencoder's latent space while ensuring its reconstructive power for acting as a described domain translator. From it, strategies are introduced including semantic reconstruction, data certainty decomposition and normalized L2 distance to substantially improve original methods, which together establish state-of-the-art performance on various benchmarks, e.g., the FPR@95%TPR of CIFAR-100 vs. TinyImagenet-crop on Wide-ResNet is 0.2%. Importantly, our method works without any additional data, hard-to-implement structure, time-consuming pipeline, and even harming the classification accuracy of known classes.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

24 of 33 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2016Wide Residual Networkscited by 3,057
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2016End-to-end Optimized Image Compressioncited by 673
  9. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  10. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  11. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  12. 2015Inverting Visual Representations with Convolutional Networkscited by 168
12 more
  1. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  2. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  3. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  4. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  5. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  6. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  7. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  8. 2021An Effective Baseline for Robustness to Distributional Shiftcited by 25
  9. 2017Robust, Deep and Inductive Anomaly Detectioncited by 24
  10. 2018Out-of-Distribution Detection using Multiple Semantic Label Representationscited by 22
  11. 2014Web-Scale Training for Face Identificationcited by 20
  12. 2020Roundtrip: A Deep Generative Neural Density Estimatorcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 10; 2024: 18; 2025: 20; 2026: 8.

59 papers.

Sort:

By area:

  1. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  2. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  3. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  4. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 30
  5. 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalitiescited by 28
  6. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  7. 2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
  8. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  9. 2024MirrorCheck: Efficient Adversarial Defense for Vision-Language Modelscited by 19
  10. 2022ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inferencecited by 15
  11. 2024Detecting Out-Of-Distribution Earth Observation Images with Diffusion Modelscited by 14
  12. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
38 more
  1. 2023Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videoscited by 12
  2. 2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
  3. 2024Enabling Uncertainty Estimation in Iterative Neural Networkscited by 11
  4. 2023A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognitioncited by 10
  5. 2025Autoencoders for Anomaly Detection are Unreliablecited by 9
  6. 2025Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoringcited by 9
  7. 2024Pedestrian Attribute Recognition as Label-balanced Multi-label Learningcited by 8
  8. 2024Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detectioncited by 8
  9. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  10. 2023Out-of-Distribution Detection for Monocular Depth Estimationcited by 7
  11. 2022What do we learn? Debunking the Myth of Unsupervised Outlier Detectioncited by 6
  12. 2023Unsupervised Recognition of Unknown Objects for Open-World Object Detectioncited by 6
  13. 2025Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomizationcited by 6
  14. 2023Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detectioncited by 5
  15. 2024Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detectioncited by 5
  16. 2025Digital Twin-based Out-of-Distribution Detection in Autonomous Vesselscited by 3
  17. 2025FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detectioncited by 3
  18. 2023Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenescited by 2
  19. 2023A Hybrid Architecture for Out of Domain Intent Detection and Intent Discoverycited by 2
  20. 2024Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detectioncited by 2
  21. 2025Zero-Shot Image Anomaly Detection Using Generative Foundation Modelscited by 2
  22. 2025Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detectioncited by 2
  23. 2025STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignmentcited by 2
  24. 2026Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthinesscited by 2
  25. 2023Cluster-aware Contrastive Learning for Unsupervised Out-of-distribution Detectioncited by 1
  26. 2023Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Methodcited by 1
  27. 2024Beyond the Known: Adversarial Autoencoders in Novelty Detectioncited by 1
  28. 2024Differentiable Score-Based Likelihoods: Learning CT Motion Compensation From Clean Imagescited by 1
  29. 2024Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activationscited by 1
  30. 2025Hypercone Assisted Contour Generation for Out-of-Distribution Detectioncited by 1
  31. 2025Advancing Out-of-Distribution Detection via Local Neuroplasticitycited by 1
  32. 2025Multi-label out-of-distribution detection via evidential learningcited by 1
  33. 2025EquiReg: Equivariance Regularized Diffusion for Inverse Problemscited by 1
  34. 2025An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivitycited by 1
  35. 2025Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognitioncited by 1
  36. 2026Adaptive Confidence Regularization for Multimodal Failure Detectioncited by 1
  37. 2026Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detectioncited by 1
  38. 2025Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detectioncited by 0

50 most cited of 59 All 59 (JSON)