mlsanityData to 7 Oct 2026

AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion

arXiv 2404.19444 ↗First posted 30 Apr 2024cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Anomaly synthesis is one of the effective methods to augment abnormal samples for training. However, current anomaly synthesis methods predominantly rely on texture information as input, which limits the fidelity of synthesized abnormal samples. Because texture information is insufficient to correctly depict the pattern of anomalies, especially for logical anomalies. To surmount this obstacle, we present the AnomalyXFusion framework, designed to harness multi-modality information to enhance the quality of synthesized abnormal samples. The AnomalyXFusion framework comprises two distinct yet synergistic modules: the Multi-modal In-Fusion (MIF) module and the Dynamic Dif-Fusion (DDF) module. The MIF module refines modality alignment by aggregating and integrating various modality features into a unified embedding space, termed X-embedding, which includes image, text, and mask features. Concurrently, the DDF module facilitates controlled generation through an adaptive adjustment of X-embedding conditioned on the diffusion steps. In addition, to reveal the multi-modality representational power of AnomalyXFusion, we propose a new dataset, called MVTec Caption. More precisely, MVTec Caption extends 2.2k accurate image-mask-text annotations for the MVTec AD and LOCO datasets. Comprehensive evaluations demonstrate the effectiveness of AnomalyXFusion, especially regarding the fidelity and diversity for logical anomalies. Project page: http:github.com/hujiecpp/MVTec-Caption

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

29 of 43 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  9. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  10. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  11. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  12. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
17 more
  1. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  4. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  5. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  6. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  7. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 79
  8. 2020StyleGAN2 Distillation for Feed-forward Image Manipulationcited by 78
  9. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  10. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  11. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  12. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 66
  13. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  14. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 59
  15. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  16. 2021ISTR: End-to-End Instance Segmentation with Transformerscited by 52
  17. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 6.

21 papers.

Sort:

By area:

  1. 2024Unseen Visual Anomaly Generationcited by 23
  2. 2025One-for-More: Continual Diffusion Model for Anomaly Detectioncited by 19
  3. 2025A Survey on Diffusion Models for Anomaly Detectioncited by 13
  4. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  5. 2024AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesiscited by 7
  6. 2025A Survey on Industrial Anomaly Synthesiscited by 7
  7. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  8. 2025AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesiscited by 5
  9. 2025"Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injectioncited by 3
  10. 20253D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noisecited by 2
  11. 2025Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspectioncited by 2
  12. 2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2
9 more
  1. 2025Anomaly Detection by Effectively Leveraging Synthetic Imagescited by 1
  2. 2026One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Controlcited by 1
  3. 2025Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Modelcited by 0
  4. 2025FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesiscited by 0
  5. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  6. 2026SteelDefectX: A Multi-Form Vision-Language Dataset and Benchmark for Steel Surface Defect Analysiscited by 0
  7. 2026Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentationcited by 0
  8. 2026OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generationcited by 0
  9. 2026Multi-Modal Anomaly Detection: A Surveycited by 0