mlsanityData to 7 Oct 2026

Towards Accurate Unified Anomaly Segmentation

arXiv 2501.12295 ↗First posted 21 Jan 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations to distinguish and precisely localize anomalies. Despite recent advancements in the efficient and unified one-for-all scheme, challenges persist in accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by the widely-used AUROC metric under imbalanced UAD settings. This motivates us to emphasize the significance of precise segmentation of anomaly pixels using pAP and DSC as metrics. To address the unsolved segmentation task, we introduce the Unified Anomaly Segmentation (UniAS). UniAS presents a multi-level hybrid pipeline that progressively enhances normal information from coarse to fine, incorporating a novel multi-granularity gated CNN (MGG-CNN) into Transformer layers to explicitly aggregate local details from different granularities. UniAS achieves state-of-the-art anomaly segmentation performance, attaining 65.12/59.33 and 40.06/32.50 in pAP/DSC on the MVTec-AD and VisA datasets, respectively, surpassing previous methods significantly. The codes are shared at https://github.com/Mwxinnn/UniAS.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 47 of its 54 references that are in the map. First posted on arXiv 21 Jan 2025.

Builds on

47 of 54 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  10. 2015Variational Inference with Normalizing Flowscited by 2,161
  11. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  12. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
35 more
  1. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  2. 2018Panoptic Segmentationcited by 796
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  8. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  9. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  10. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  11. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  12. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  13. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  14. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  15. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  16. 2022DaViT: Dual Attention Vision Transformerscited by 174
  17. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  18. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
  19. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  20. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  21. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  22. 2023Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detectioncited by 66
  23. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  24. 2023Label-Free Liver Tumor Segmentationcited by 56
  25. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  26. 2020Label-Free Segmentation of COVID-19 Lesions in Lung CTcited by 37
  27. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  28. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  29. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  30. 2022ADTR: Anomaly Detection Transformer with Feature Reconstructioncited by 31
  31. 2023Uncertainty-inspired Open Set Learning for Retinal Anomaly Identificationcited by 18
  32. 2023On Pixel-level Performance Assessment in Anomaly Detectioncited by 6
  33. 2023MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentationcited by 4
  34. 2024AUPIMO: Redefining Visual Anomaly Detection Benchmarks with High Speed and Low Tolerancecited by 4
  35. 2023Adversarial Medical Image with Hierarchical Feature Hidingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 1.

7 papers.

  1. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 72
  2. 2025Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Boostercited by 7
  3. 2025BeltCrack: the First Sequential-image Industrial Conveyor Belt Crack Detection Dataset and Its Baseline with Triple-domain Feature Learningcited by 2
  4. 2025ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rayscited by 1
  5. 2025MIAS-SAM: Medical Image Anomaly Segmentation without thresholdingcited by 0
  6. 2025Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precisioncited by 0
  7. 2026Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentationcited by 0