mlsanityData to 7 Oct 2026

Out-of-Distribution Detection with Semantic Mismatch under Masking

arXiv 2208.00446 ↗First posted 31 Jul 2022cs.CV cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

This paper proposes a novel out-of-distribution (OOD) detection framework named MoodCat for image classifiers. MoodCat masks a random portion of the input image and uses a generative model to synthesize the masked image to a new image conditioned on the classification result. It then calculates the semantic difference between the original image and the synthesized one for OOD detection. Compared to existing solutions, MoodCat naturally learns the semantic information of the in-distribution data with the proposed mask and conditional synthesis strategy, which is critical to identifying OODs. Experimental results demonstrate that MoodCat outperforms state-of-the-art OOD detection solutions by a large margin.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 31 Jul 2022.

Builds on

43 of 54 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2016Wide Residual Networkscited by 3,057
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2016Concrete Problems in AI Safetycited by 1,582
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
31 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  2. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  6. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  10. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  11. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  12. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  13. 2018cGANs with Projection Discriminatorcited by 253
  14. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  15. 2017Modulating early visual processing by languagecited by 167
  16. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  17. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  18. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  19. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  20. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  21. 2021Can multi-label classification networks know what they don't know?cited by 100
  22. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  23. 2020Convolutional Networks with Dense Connectivitycited by 98
  24. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  25. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  26. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  27. 2020Feature Space Singularity for Out-of-Distribution Detectioncited by 49
  28. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  29. 2018Building robust classifiers through generation of confident out of distribution examplescited by 20
  30. 2021Conditional Variational Capsule Network for Open Set Recognitioncited by 17
  31. 2022What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradictioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 7; 2025: 4; 2026: 3.

22 papers.

Sort:

By area:

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  2. 2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 25
  3. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  4. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  5. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
  6. 2024Open World Object Detection: A Surveycited by 13
  7. 2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
  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. 2026Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Languagecited by 6
  12. 2023Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detectioncited by 5
10 more
  1. 2023Expecting The Unexpected: Towards Broad Out-Of-Distribution Detectioncited by 3
  2. 2023Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenescited by 2
  3. 2023A Hybrid Architecture for Out of Domain Intent Detection and Intent Discoverycited by 2
  4. 2023Non-Cross Diffusion for Semantic Consistencycited by 2
  5. 2026Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthinesscited by 2
  6. 2024Collaborative Knowledge Distillation via a Learning-by-Education Node Communitycited by 1
  7. 2025Hypercone Assisted Contour Generation for Out-of-Distribution Detectioncited by 1
  8. 2025Multi-label out-of-distribution detection via evidential learningcited by 1
  9. 2025An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivitycited by 1
  10. 2026Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detectioncited by 0