Abstract
Diffusion models have shown superior performance on unsupervised anomaly detection tasks. Since trained with normal data only, diffusion models tend to reconstruct normal counterparts of test images with certain noises added. However, these methods treat all potential anomalies equally, which may cause two main problems. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. For example, adding back a missing element is harder than dealing with a scratch, thus requiring a larger number of denoising steps. Therefore, instead of utilizing the same setting for all samples, we propose to predict a particular denoising step for each sample by evaluating the difference between image contents and the priors extracted from diffusion models. From the local perspective, reconstructing abnormal regions differs from normal areas even in the same image. Theoretically, the diffusion model predicts a noise for each step, typically following a standard Gaussian distribution. However, due to the difference between the anomaly and its potential normal counterpart, the predicted noise in abnormal regions will inevitably deviate from the standard Gaussian distribution. To this end, we propose introducing synthetic abnormal samples in training to encourage the diffusion models to break through the limitation of standard Gaussian distribution, and a spatial-adaptive feature fusion scheme is utilized during inference. With the above modifications, we propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection, which introduces appealing flexibility and achieves anomaly-free reconstruction while retaining as much normal information as possible. Extensive experiments are conducted on three commonly used anomaly detection datasets (MVTec-AD, MPDD, and VisA) and a printed circuit board dataset (PCB-Bank) we integrated, showing the effectiveness of the proposed method. The source code and pre-trained models are publicly available at https://github.com/hyao1/GLAD.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
In the setting of diffusion models, the randomness is equivalent to the weight of the random noise, which is determined by the denoising step. In other words, a larger denoising step means higher noise weight and stronger randomness.
- 2.
PCB-Bank is a printed circuit board dataset we integrated from existing datasets, please refer to https://github.com/SSRheart/industrial-anomaly-detection-dataset for more details.
References
Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD–a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592–9600 (2019)
Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Uninformed students: student-teacher anomaly detection with discriminative latent embeddings. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4183–4192 (2020)
Bergmann, P., Löwe, S., Fauser, M., Sattlegger, D., Steger, C.: Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv:1807.02011 (2018)
Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9650–9660 (2021)
Chen, X., Han, Y., Zhang, J.: A zero-/few-shot anomaly classification and segmentation method for CVPR 2023 vand workshop challenge tracks 1 &2: 1st place on zero-shot ad and 4th place on few-shot ad. arXiv preprint arXiv:2305.17382 (2023)
Defard, T., Setkov, A., Loesch, A., Audigier, R.: PaDiM: a patch distribution modeling framework for anomaly detection and localization. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12664, pp. 475–489. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68799-1_35
Deng, H., Li, X.: Anomaly detection via reverse distillation from one-class embedding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9737–9746 (2022)
Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)
He, H., et al.: Diad: a diffusion-based framework for multi-class anomaly detection. arXiv preprint arXiv:2312.06607 (2023)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advance in Neural Information Processing System, vol. 33, pp. 6840–6851 (2020)
Jezek, S., Jonak, M., Burget, R., Dvorak, P., Skotak, M.: Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In: 2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), pp. 66–71. IEEE (2021)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Liang, Y., Zhang, J., Zhao, S., Wu, R., Liu, Y., Pan, S.: Omni-frequency channel-selection representations for unsupervised anomaly detection. IEEE Trans. Image Process. (2023)
Liu, W., et al.: Towards visually explaining variational autoencoders. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8642–8651 (2020)
Liu, X., et al.: Smartcontrol: enhancing controlnet for handling rough visual conditions. arXiv preprint arXiv:2404.06451 (2024)
Liu, Z., Zhou, Y., Xu, Y., Wang, Z.: Simplenet: a simple network for image anomaly detection and localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20402–20411 (2023)
Lu, F., Yao, X., Fu, C.W., Jia, J.: Removing anomalies as noises for industrial defect localization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 16166–16175 (2023)
Mousakhan, A., Brox, T., Tayyub, J.: Anomaly detection with conditioned denoising diffusion models. arXiv preprint arXiv:2305.15956 (2023)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684–10695 (2022)
Roth, K., Pemula, L., Zepeda, J., Schölkopf, B., Brox, T., Gehler, P.: Towards total recall in industrial anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14318–14328 (2022)
Rudolph, M., Wehrbein, T., Rosenhahn, B., Wandt, B.: Asymmetric student-teacher networks for industrial anomaly detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2592–2602 (2023)
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500–22510 (2023)
Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256–2265. PMLR (2015)
Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)
Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15943–15953 (2023)
Yang, M., Wu, P., Feng, H.: MemSeg: a semi-supervised method for image surface defect detection using differences and commonalities. Eng. Appl. Artif. Intell. 119, 105835 (2023)
Yin, H., Jiao, G., Wu, Q., Karlsson, B.F., Huang, B., Lin, C.Y.: Lafite: latent diffusion model with feature editing for unsupervised multi-class anomaly detection. arXiv preprint arXiv:2307.08059 (2023)
Zavrtanik, V., Kristan, M., Skočaj, D.: Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8330–8339 (2021)
Zhang, X., Li, N., Li, J., Dai, T., Jiang, Y., Xia, S.T.: Unsupervised surface anomaly detection with diffusion probabilistic model. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6782–6791 (2023)
Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: training-free controllable text-to-video generation. In: The Twelfth International Conference on Learning Representations (2023)
Zhang, Y., et al.: Videoelevator: elevating video generation quality with versatile text-to-image diffusion models. arXiv preprint arXiv:2403.05438 (2024)
Zhao, Y., Deng, B., Shen, C., Liu, Y., Lu, H., Hua, X.S.: Spatio-temporal autoencoder for video anomaly detection. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1933–1941 (2017)
Zou, Y., Jeong, J., Pemula, L., Zhang, D., Dabeer, O.: Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 392–408. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20056-4_23
Acknowledgement
This work was supported in part by the National Key Research and Development Program of China under Grant No. 2023YFA1008500.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yao, H., Liu, M., Yin, Z., Yan, Z., Hong, X., Zuo, W. (2025). GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15129. Springer, Cham. https://doi.org/10.1007/978-3-031-73209-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-73209-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-73208-9
Online ISBN: 978-3-031-73209-6
eBook Packages: Computer ScienceComputer Science (R0)