Large-Scale Universal Defect Generation: Foundation Models and Datasets

• URL: http://arxiv.org/abs/2604.08915v1
• Date: Fri, 10 Apr 2026 03:21:17 GMT
• Title: Large-Scale Universal Defect Generation: Foundation Models and Datasets
• Abstract summary: We introduce UDG, a large-scale dataset of 300K normal-abnormal-mask-caption quadruplets spanning diverse domains.<n>We present UniDG, a universal defect generation foundation model that supports both reference-based defect generation and text instruction-based defect editing without per-category fine-tuning.<n>Experiments on MVTec-AD and VisA show that UniDG outperforms prior few-shot anomaly generation and image insertion/editing baselines in synthesis quality and downstream single- and multi-class anomaly detection/localization.
• Score: 51.150071370083026
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing defect/anomaly generation methods often rely on few-shot learning, which overfits to specific defect categories due to the lack of large-scale paired defect editing data. This issue is aggravated by substantial variations in defect scale and morphology, resulting in limited generalization, degraded realism, and category consistency. We address these challenges by introducing UDG, a large-scale dataset of 300K normal-abnormal-mask-caption quadruplets spanning diverse domains, and by presenting UniDG, a universal defect generation foundation model that supports both reference-based defect generation and text instruction-based defect editing without per-category fine-tuning. UniDG performs Defect-Context Editing via adaptive defect cropping and structured diptych input format, and fuses reference and target conditions through MM-DiT multimodal attention. A two-stage training strategy, Diversity-SFT followed by Consistency-RFT, further improves diversity while enhancing realism and reference consistency. Extensive experiments on MVTec-AD and VisA show that UniDG outperforms prior few-shot anomaly generation and image insertion/editing baselines in synthesis quality and downstream single- and multi-class anomaly detection/localization. Code will be available at https://github.com/RetoFan233/UniDG.

Related papers

• Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation [12.030059666003972]
  We introduce DAPO, a novel approach for Defect-aware Prompt Optimization based on progressive tuning for the zero-shot multi-type and binary anomaly detection and segmentation under distribution shifts.<n>Our approach aligns anomaly-relevant image features with their corresponding text semantics by learning hybrid defect-aware prompts with both fixed textual anchors and learnable token embeddings.
  arXiv  Detail & Related papers  (2025-12-10T09:19:17Z)
• Unified Unsupervised Anomaly Detection via Matching Cost Filtering [113.43366521994396]
  Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data.<n>We present Unified Cost Filtering (UCF), a generic post-hoc refinement framework for refining anomaly cost volume of any UAD model.
  arXiv  Detail & Related papers  (2025-10-03T03:28:18Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• UniFault: A Fault Diagnosis Foundation Model from Bearing Data [23.797786758616223]
  Existing machine fault diagnosis models are operation-specific with limited generalization across diverse datasets.<n>We introduce UniFault, a foundation model for fault diagnosis that systematically addresses these issues.<n>UniFault is pretrained on over 6.9 million samples spanning diverse FD datasets, enabling superior few-shot performance.
  arXiv  Detail & Related papers  (2025-04-02T05:34:27Z)
• Bi-Grid Reconstruction for Image Anomaly Detection [0.0]
  This paper introduces textbfGRAD: Bi-textbfGrid textbfReconstruction for Image textbfAnomaly textbfDetection.<n>It employs two continuous grids to enhance anomaly detection from both normal and abnormal perspectives.<n>It excels in overall accuracy and in discerning subtle differences, demonstrating its superiority over existing methods.
  arXiv  Detail & Related papers  (2025-04-01T10:06:38Z)
• CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection [34.675120608542265]
  We propose a novel approach that leverages class-agnostic learnable prompts to guide the decoded features towards a normal textual representation.<n>Our method achieves competitive performance on the MVTec AD and VisA datasets, demonstrating its effectiveness.
  arXiv  Detail & Related papers  (2024-12-31T08:43:44Z)
• Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection [109.72772150095646]
  FAPrompt is a novel framework designed to learn Fine-grained Abnormality Prompts for accurate ZSAD.<n>Experiments on 19 real-world datasets, covering both industrial defects and medical anomalies, demonstrate that FAPrompt substantially outperforms state-of-the-art methods in both image- and pixel-level ZSAD tasks.
  arXiv  Detail & Related papers  (2024-10-14T08:41:31Z)
• DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series [83.76994646443498]
  In time series anomaly detection, the scarcity of labeled data poses a challenge to the development of accurate models.<n>We propose a novel Domain Contrastive learning model for Anomaly Detection in time series (DACAD)<n>Our model employs supervised contrastive loss for the source domain and self-supervised contrastive triplet loss for the target domain.
  arXiv  Detail & Related papers  (2024-04-17T11:20:14Z)
• Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts [25.629973843455495]
  Generalist Anomaly Detection (GAD) aims to train one single detection model that can generalize to detect anomalies in diverse datasets from different application domains without further training on the target data. We introduce a novel approach that learns an in-context residual learning model for GAD, termed InCTRL. InCTRL is the best performer and significantly outperforms state-of-the-art competing methods.
  arXiv  Detail & Related papers  (2024-03-11T08:07:46Z)
• Diversity-Measurable Anomaly Detection [106.07413438216416]
  We propose Diversity-Measurable Anomaly Detection (DMAD) framework to enhance reconstruction diversity. PDM essentially decouples deformation from embedding and makes the final anomaly score more reliable.
  arXiv  Detail & Related papers  (2023-03-09T05:52:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.