{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:23:39Z","timestamp":1783095819545,"version":"3.54.6"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731150","type":"print"},{"value":"9783031731167","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73116-7_21","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:15:38Z","timestamp":1730301338000},"page":"360-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Few-Shot Defect Image Generation Based on\u00a0Consistency Modeling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8480-9314","authenticated-orcid":false,"given":"Qingfeng","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7697-8070","authenticated-orcid":false,"given":"Jing","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9263-4489","authenticated-orcid":false,"given":"Fei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1659-7879","authenticated-orcid":false,"given":"Zhengtao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, C.M., Gauthama Raman, M.R., Mathur, A.P.: Challenges in machine learning based approaches for real-time anomaly detection in industrial control systems. In: Proceedings of the 6th ACM on Cyber-Physical System Security Workshop, October 2020. https:\/\/doi.org\/10.1145\/3384941.3409588","DOI":"10.1145\/3384941.3409588"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models, January 2023","DOI":"10.1145\/3592116"},{"key":"21_CR3","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/978-3-031-19836-6_6","volume-title":"ECCV 2022","author":"K Crowson","year":"2022","unstructured":"Crowson, K., et al.: VQGAN-CLIP: open domain image generation and editing with natural language guidance. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 88\u2013105. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_6"},{"key":"21_CR4","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Duan, Y., Hong, Y., Niu, L., Zhang, L.: Few-shot defect image generation via defect-aware feature manipulation, March 2023","DOI":"10.1609\/aaai.v37i1.25132"},{"key":"21_CR6","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)"},{"key":"21_CR7","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"21_CR8","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS 2014, pp. 2672\u20132680. MIT Press, Cambridge, MA, USA (2014)"},{"key":"21_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Neural Information Processing Systems, January 2020"},{"key":"21_CR10","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"21_CR11","unstructured":"Hu, T., et al.: AnomalyDiffusion: few-shot anomaly image generation with diffusion model, December 2023"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Jeong, J., Zou, Y., Kim, T., Zhang, D., Ravichandran, A., Dabeer, O.: WinCLIP: zero-\/few-shot anomaly classification and segmentation, March 2023","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"21_CR13","doi-asserted-by":"publisher","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8107\u20138116 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00813","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"21_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-58621-8_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Kowalski","year":"2020","unstructured":"Kowalski, M., Garbin, S.J., Estellers, V., Baltru\u0161aitis, T., Johnson, M., Shotton, J.: CONFIG: controllable neural face image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 299\u2013315. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_18"},{"key":"21_CR16","unstructured":"Kulikov, V., Yadin, S., Kleiner, M., Michaeli, T.: SinDDM: a single image denoising diffusion model. In: International Conference on Machine Learning, pp. 17920\u201317930. PMLR (2023)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"21_CR18","doi-asserted-by":"publisher","unstructured":"Liu, R., et al.: Anomaly-GAN: a data augmentation method for train surface anomaly detection. Exp. Syst. Appl., 120284 (2023). https:\/\/doi.org\/10.1016\/j.eswa.2023.120284","DOI":"10.1016\/j.eswa.2023.120284"},{"key":"21_CR19","doi-asserted-by":"publisher","unstructured":"Niu, S., Li, B., Wang, X., Lin, H.: Defect image sample generation with GAN for improving defect recognition. IEEE Trans. Autom. Sci. Eng., 1\u201312 (2020). https:\/\/doi.org\/10.1109\/tase.2020.2967415","DOI":"10.1109\/tase.2020.2967415"},{"key":"21_CR20","doi-asserted-by":"publisher","unstructured":"Niu, S., Li, B., Wang, X., Peng, Y.: Region- and strength-controllable GAN for defect generation and segmentation in industrial images. IEEE Trans. Ind. Inf., 4531\u20134541 (2022). https:\/\/doi.org\/10.1109\/tii.2021.3127188","DOI":"10.1109\/tii.2021.3127188"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Niu, S., Peng, Y., Li, B., Wang, X.: A transformed-feature-space data augmentation method for defect segmentation (2023)","DOI":"10.1016\/j.compind.2023.103860"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"21_CR23","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR24","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents (2022)"},{"key":"21_CR25","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022. https:\/\/doi.org\/10.1109\/cvpr52688.2022.01042","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation, August 2022","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"21_CR27","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-031-19821-2_27","volume-title":"ECCV 2022","author":"HM Schl\u00fcter","year":"2022","unstructured":"Schl\u00fcter, H.M., Tan, J., Hou, B., Kainz, B.: Natural synthetic anomalies for self-supervised anomaly detection and localization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 474\u2013489. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_27"},{"key":"21_CR28","doi-asserted-by":"publisher","unstructured":"Singh, S.A., Desai, K.A.: Automated surface defect detection framework using machine vision and convolutional neural networks. J. Intell. Manuf., 1995\u20132011 (2023). https:\/\/doi.org\/10.1007\/s10845-021-01878-w","DOI":"10.1007\/s10845-021-01878-w"},{"key":"21_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-030-58595-2_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tang","year":"2020","unstructured":"Tang, H., Bai, S., Zhang, L., Torr, P.H.S., Sebe, N.: XingGAN for person image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 717\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_43"},{"key":"21_CR30","doi-asserted-by":"publisher","unstructured":"Wei, J., Zhang, Z., Shen, F., Lv, C.: Mask-guided generation method for industrial defect images with non-uniform structures. Machines 10(12) (2022). https:\/\/doi.org\/10.3390\/machines10121239. https:\/\/www.mdpi.com\/2075-1702\/10\/12\/1239","DOI":"10.3390\/machines10121239"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M., Zhou, H., Shen, C.: DiffuMask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models, March 2023","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Yang, S., Chen, Z., Chen, P., Fang, X., Liu, S., Chen, Y.: Defect spectrum: a granular look of large-scale defect datasets with rich semantics. arXiv preprint arXiv:2310.17316 (2023)","DOI":"10.1007\/978-3-031-72667-5_11"},{"key":"21_CR33","unstructured":"Yoshihashi, R., Otsuka, Y., Doi, K., Tanaka, T.: Attention as annotation: generating images and pseudo-masks for weakly supervised semantic segmentation with diffusion, September 2023"},{"key":"21_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/978-3-031-19821-2_31","volume-title":"ECCV 2022","author":"V Zavrtanik","year":"2022","unstructured":"Zavrtanik, V., Kristan, M., Sko\u010daj, D.: DSR-a dual subspace re-projection network for surface anomaly detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 539\u2013554. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_31"},{"key":"21_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, G., Cui, K., Hung, T.Y., Lu, S.: Defect-GAN: high-fidelity defect synthesis for automated defect inspection. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2524\u20132534, January 2021. https:\/\/doi.org\/10.1109\/wacv48630.2021.00257","DOI":"10.1109\/wacv48630.2021.00257"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"21_CR37","unstructured":"Zhao, S., et al.: Uni-ControlNet: all-in-one control to text-to-image diffusion models. In: Advances in Neural Information Processing Systems (2023)"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., Li, X.: LayoutDiffusion: controllable diffusion model for layout-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22490\u201322499, June 2023","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"21_CR39","unstructured":"Zhou, Q., Pang, G., Tian, Y., He, S., Chen, J.: AnomalyCLIP: object-agnostic prompt learning for zero-shot anomaly detection, October 2023"},{"key":"21_CR40","unstructured":"Zhou, Y., Zhou, D., Zhu, Z.L., Wang, Y., Hou, Q., Feng, J.: MaskDiffusion: boosting text-to-image consistency with conditional mask. arXiv preprint arXiv:2309.04399 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73116-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:25:54Z","timestamp":1730301954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73116-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031731150","9783031731167"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73116-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}