mlsanityData to 7 Oct 2026

Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data

arXiv 2310.10461 ↗First posted 16 Oct 2023cs.LG cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Anomaly detection is the task of identifying abnormal samples in large unlabeled datasets. While the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the absence of labeled validation data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors without labeled validation data. Instead of collecting labeled validation data, we generate synthetic anomalies without any training or fine-tuning, using only a small support set of normal images. Our synthetic anomalies are used to create detection tasks that compose a validation framework for model selection. In an empirical study, we evaluate SWSA with three types of synthetic anomalies and on two selection tasks: model selection of image-based anomaly detectors and prompt selection for CLIP-based anomaly detection. SWSA often selects models and prompts that match selections made with a ground-truth validation set, outperforming baseline selection strategies.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 51 of its 90 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

51 of 90 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  11. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
38 more
  1. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  2. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  3. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  4. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  5. 2018Assessing Generative Models via Precision and Recallcited by 401
  6. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  7. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  8. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  9. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  10. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  11. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  12. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  13. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  14. 2020Classification-Based Anomaly Detection for General Datacited by 210
  15. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  16. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  17. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  18. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  19. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  20. 2018Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detectioncited by 121
  21. 2020Deep Nearest Neighbor Anomaly Detectioncited by 103
  22. 2022How to Backdoor Diffusion Models?cited by 102
  23. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  24. 2023TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targetscited by 88
  25. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  26. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  27. 2014Toward Supervised Anomaly Detectioncited by 73
  28. 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Modelscited by 68
  29. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  30. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  31. 2023Training-free Content Injection using h-space in Diffusion Modelscited by 36
  32. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  33. 2022Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solutioncited by 24
  34. 2023Zero-shot Model Diagnosiscited by 23
  35. 2022Toward Unsupervised Outlier Model Selectioncited by 18
  36. 2022Detecting Anomalies within Time Series using Local Neural Transformationscited by 12
  37. 2023Deep Anomaly Detection under Labeling Budget Constraintscited by 9
  38. 2021Synthetic Data for Model Selectioncited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 5.

8 papers.

  1. 2024Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posteriorcited by 2
  2. 2025Contextual Learning for Anomaly Detection in Tabular Datacited by 1
  3. 2025ASBench: Image Anomalies Synthesis Benchmark for Anomaly Detectioncited by 1
  4. 2026Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?cited by 1
  5. 2026AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detectioncited by 0
  6. 2026Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detectioncited by 0
  7. 2026Anomaly-Free Self-Optimization via AUC Boundscited by 0
  8. 2026Visual Anomaly Synthesis for Model Selection in Data Scarcitycited by 0