mlsanityData to 14 Oct 2026

UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection

arXiv 2307.12540 ↗First posted 24 Jul 2023cs.CV cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Visual anomaly detection aims to learn normality from normal images, but existing approaches are fragmented across various tasks: defect detection, semantic anomaly detection, multi-class anomaly detection, and anomaly clustering. This one-task-one-model approach is resource-intensive and incurs high maintenance costs as the number of tasks increases. We present UniFormaly, a universal and powerful anomaly detection framework. We emphasize the necessity of our off-the-shelf approach by pointing out a suboptimal issue in online encoder-based methods. We introduce Back Patch Masking (BPM) and top k-ratio feature matching to achieve unified anomaly detection. BPM eliminates irrelevant background regions using a self-attention map from self-supervised ViTs. This operates in a task-agnostic manner and alleviates memory storage consumption, scaling to tasks with large-scale datasets. Top k-ratio feature matching unifies anomaly levels and tasks by casting anomaly scoring into multiple instance learning. Finally, UniFormaly achieves outstanding results on various tasks and datasets. Codes are available at https://github.com/YoojLee/Uniformaly.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 24 Jul 2023.

Builds on

31 of 45 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  6. 2017Billion-scale similarity search with GPUscited by 2,497
  7. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  9. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  10. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  11. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  12. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
19 more
  1. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  2. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  3. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  4. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  5. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 421
  6. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  7. 2020SCAN: Learning to Classify Images without Labelscited by 352
  8. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  9. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  10. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  11. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  12. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  13. 2020Explainable Deep One-Class Classificationcited by 127
  14. 2020Deep Nearest Neighbor Anomaly Detectioncited by 104
  15. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  16. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  17. 2020GATCluster: Self-Supervised Gaussian-Attention Network for Image Clusteringcited by 32
  18. 2021Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Typescited by 13
  19. 2021PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 2.

11 papers.

  1. 2024AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarioscited by 9
  2. 2025LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questionscited by 9
  3. 2024VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantizationcited by 5
  4. 2025TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detectioncited by 5
  5. 2025A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Featurescited by 5
  6. 2025Multi-class Image Anomaly Detection for Practical Applications: Requirements and Robust Solutionscited by 1
  7. 2025Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student Networkscited by 0
  8. 2025Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learningcited by 0
  9. 2025ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarioscited by 0
  10. 2026StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detectioncited by 0
  11. 2026Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classificationcited by 0