MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning

arXiv 2505.09265 ↗First posted 14 May 2025cs.CV cs.AIcited by 12

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

Zero- and few-shot visual anomaly segmentation relies on powerful vision-language models that detect unseen anomalies using manually designed textual prompts. However, visual representations are inherently independent of language. In this paper, we explore the potential of a pure visual foundation model as an alternative to widely used vision-language models for universal visual anomaly segmentation. We present a novel paradigm that unifies anomaly segmentation into change segmentation. This paradigm enables us to leverage large-scale synthetic image pairs, featuring object-level and local region changes, derived from existing image datasets, which are independent of target anomaly datasets. We propose a one-prompt Meta-learning framework for Universal Anomaly Segmentation (MetaUAS) that is trained on this synthetic dataset and then generalizes well to segment any novel or unseen visual anomalies in the real world. To handle geometrical variations between prompt and query images, we propose a soft feature alignment module that bridges paired-image change perception and single-image semantic segmentation. This is the first work to achieve universal anomaly segmentation using a pure vision model without relying on special anomaly detection datasets and pre-trained visual-language models. Our method effectively and efficiently segments any anomalies with only one normal image prompt and enjoys training-free without guidance from language. Our MetaUAS significantly outperforms previous zero-shot, few-shot, and even full-shot anomaly segmentation methods. The code and pre-trained models are available at https://github.com/gaobb/MetaUAS.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 48 of its 79 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

48 of 79 references.

References · 48

2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
2014Microsoft COCO: Common Objects in Contextcited by 17,498
2016Feature Pyramid Networks for Object Detectioncited by 5,021
2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
2018Real-world Anomaly Detection in Surveillance Videoscited by 570
2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529

36 more

2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
2022A Unified Model for Multi-class Anomaly Detectioncited by 267
2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 147
2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 145
2022Registration based Few-Shot Anomaly Detectioncited by 133
2023DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Modelscited by 122
2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 97
2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
2023Diversity-Measurable Anomaly Detectioncited by 41
2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
2022How to Reduce Change Detection to Semantic Segmentationcited by 28
2023PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentationcited by 21

Built on by

Cited by year (2026 to 7 Oct)

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

12 papers.

2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformercited by 10
2025DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookupcited by 9
2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detectioncited by 4
2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 3
2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2
2025TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detectioncited by 0
2026HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detectioncited by 0
2026Res2CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignmentcited by 0
2026C3-Bench: A Context-Aware Change Captioning Benchmarkcited by 0
2026VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detectioncited by 0

Similar, not cited

Close in wording, no citation either way