AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 8526-8534
DOI: 10.1609/aaai.v38i8.28696 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Teng Hu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 164-mal zitiert (Crossref).
Abstract (Originalsprache)
Anomaly inspection plays an important role in industrial manufacture. Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data. Although anomaly generation methods have been proposed to augment the anomaly data, they either suffer from poor generation authenticity or inaccurate alignment between the generated anomalies and masks. To address the above problems, we propose AnomalyDiffusion, a novel diffusion-based few-shot anomaly generation model, which utilizes the strong prior information of latent diffusion model learned from large-scale dataset to enhance the generation authenticity under few-shot training data. Firstly, we propose Spatial Anomaly Embedding, which consists of a learnable anomaly embedding and a spatial embedding encoded from an anomaly mask, disentangling the anomaly information into anomaly appearance and location information. Moreover, to improve the alignment between the generated anomalies and the anomaly masks, we introduce a novel Adaptive Attention Re-weighting Mechanism. Based on the disparities between the generated anomaly image and normal sample, it dynamically guides the model to focus more on the areas with less noticeable generated anomalies, enabling generation of accurately-matched anomalous image-mask pairs. Extensive experiments demonstrate that our model significantly outperforms the state-of-the-art methods in generation authenticity and diversity, and effectively improves the performance of downstream anomaly inspection tasks. The code and data are available in https://github.com/sjtuplayer/anomalydiffusion.
Zitieren
APA
Hu, T., Zhang, J., Yi, R., Du, Y., Chen, X., Liu, L., Wang, Y., & Wang, C. (2024). AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8526-8534. https://doi.org/10.1609/aaai.v38i8.28696
Vancouver
Hu T, Zhang J, Yi R, Du Y, Chen X, Liu L, et al. AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):8526-8534. doi:10.1609/aaai.v38i8.28696
BibTeX
@article{Hu2024,
author = {Hu, Teng and Zhang, Jiangning and Yi, Ran and Du, Yuzhen and Chen, Xu and Liu, Liang and Wang, Yabiao and Wang, Chengjie},
title = {AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {8},
pages = {8526--8534},
doi = {10.1609/aaai.v38i8.28696}
}
EUVIMED