{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:40:16Z","timestamp":1732830016478,"version":"3.30.0"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726668"},{"type":"electronic","value":"9783031726675"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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\/978-3-031-72667-5_11","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:11:48Z","timestamp":1727554308000},"page":"187-203","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Defect Spectrum: A Granular Look of\u00a0Large-Scale Defect Datasets with\u00a0Rich Semantics"],"prefix":"10.1007","author":[{"given":"Shuai","family":"Yang","sequence":"first","affiliation":[]},{"given":"Zhifei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Pengguang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xi","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Yixun","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Shu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yingcong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"11_CR1","unstructured":"Bai, H., et al.: Vision datasets: a benchmark for vision-based industrial inspection. arXiv preprint arXiv:2306.07890 (2023)"},{"issue":"4","key":"11_CR2","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1007\/s11263-020-01400-4","volume":"129","author":"P Bergmann","year":"2021","unstructured":"Bergmann, P., Batzner, K., Fauser, M., Sattlegger, D., Steger, C.: The MVTec anomaly detection dataset: a comprehensive real-world dataset for unsupervised anomaly detection. Int. J. Comput. Vision 129(4), 1038\u20131059 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD\u2013a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592\u20139600 (2019)","DOI":"10.1109\/CVPR.2019.00982"},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1007\/978-3-031-15928-2_133","volume-title":"JCM 2022","author":"P Carvalho","year":"2022","unstructured":"Carvalho, P., Durupt, A., Grandvalet, Y.: A review of benchmarks for visual defect detection in the manufacturing industry. In: Gerbino, S., Lanzotti, A., Martorelli, M., Mir\u00e1lbes Buil, R., Rizzi, C., Roucoules, L. (eds.) JCM 2022, pp. 1527\u20131538. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15928-2_133"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhao, Z., Yu, F., Zhang, Y., Duan, M.: Conditional diffusion for interactive segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00725"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhao, Z., Zhang, Y., Duan, M., Qi, D., Zhao, H.: Focalclick: towards practical interactive image segmentation (2022)","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., Yoon, S.: Perception prioritized training of diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., Audigier, R.: Padim: a patch distribution modeling framework for anomaly detection and localization (2020)","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255. IEEE (2009). https:\/\/ieeexplore.ieee.org\/abstract\/document\/5206848\/","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR12","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":"11_CR13","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2021)"},{"key":"11_CR14","first-page":"1","volume":"72","author":"Z Du","year":"2022","unstructured":"Du, Z., Gao, L., Li, X.: A new contrastive GAN with data augmentation for surface defect recognition under limited data. IEEE Trans. Instrum. Meas. 72, 1\u201313 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Faghih-Roohi, S., Hajizadeh, S., N\u00fa\u00f1ez, A., Babuska, R., De\u00a0Schutter, B.: Deep convolutional neural networks for detection of rail surface defects. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 2584\u20132589 (2016)","DOI":"10.1109\/IJCNN.2016.7727522"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Guo, J., Wang, Q., Li, Y.: Semi-supervised learning based on convolutional neural network and uncertainty filter for fa\u00e7ade defects classification. In: Computer-Aided Civil and Infrastructure Engineering, pp. 302\u2013317 (2021)","DOI":"10.1111\/mice.12632"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR18","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"11_CR19","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/TSMCA.2008.2009941","volume":"39","author":"Q Huang","year":"2009","unstructured":"Huang, Q., Wu, Y., Baruch, J., Jiang, P., Peng, Y.: A template model for defect simulation for evaluating nondestructive testing in X-radiography. IEEE Trans. Syst. Man Cybern. Part A Syst. Hum. 39, 466\u2013475 (2009)","journal-title":"IEEE Trans. Syst. Man Cybern. Part A Syst. Hum."},{"key":"11_CR20","unstructured":"Cotton Incorporated: Standard fabric defect glossary (2023). https:\/\/www.cottoninc.com\/quality-products\/textile-resources\/fabric-defect-glossary"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"11_CR22","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"11_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"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\u201316175 (2023)","DOI":"10.1109\/ICCV51070.2023.01481"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Mery, D., Hahn, D., Hitschfeld, N.: Simulation of defects in aluminium castings using cad models of flaws and real X-ray images. Insight: Non-Destr. Test. Cond. Monit. 618\u2013624 (2005)","DOI":"10.1784\/insi.2005.47.10.618"},{"issue":"6","key":"11_CR26","doi-asserted-by":"publisher","first-page":"890","DOI":"10.1109\/TRA.2002.805646","volume":"18","author":"D Mery","year":"2002","unstructured":"Mery, D., Filbert, D.: Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence. IEEE Trans. Robot. Autom. 18(6), 890\u2013901 (2002)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Mishra, P., Verk, R., Fornasier, D., Piciarelli, C., Foresti, G.L.: VT-ADL: a vision transformer network for image anomaly detection and localization. In: 30th IEEE\/IES International Symposium on Industrial Electronics (ISIE) (2021)","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Mundt, M., Majumder, S., Murali, S., Panetsos, P., Ramesh, V.: Meta-learning convolutional neural architectures for multi-target concrete defect classification with the concrete defect bridge image dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11196\u201311205 (2019)","DOI":"10.1109\/CVPR.2019.01145"},{"key":"11_CR29","unstructured":"Ni, C., Yang, K., Xia, X., Lo, D., Chen, X., Yang, X.: Defect identification, categorization, and repair: better together (2022)"},{"key":"11_CR30","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"issue":"3","key":"11_CR31","first-page":"1611","volume":"17","author":"S Niu","year":"2020","unstructured":"Niu, S., Li, B., Wang, X., Lin, H.: Defect image sample generation with GAN for improving defect recognition. IEEE Trans. Autom. Sci. Eng. 17(3), 1611\u20131622 (2020)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J., Sch\u00f6lkopf, B., Brox, T., Gehler, P.: Towards total recall in industrial anomaly detection (2022)","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Rott\u00a0Shaham, T., Dekel, T., Michaeli, T.: Singan: learning a generative model from a single natural image. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00467"},{"key":"11_CR36","doi-asserted-by":"publisher","unstructured":"Silvestre-Blanes, J., Albero-Albero, T., Miralles, I., P\u00e9rez-Llorens, R., Moreno, J.: A public fabric database for defect detection methods and results. Autex Res. J. 19(4), 363\u2013374 (2019). https:\/\/doi.org\/10.2478\/aut-2019-0035","DOI":"10.2478\/aut-2019-0035"},{"key":"11_CR37","doi-asserted-by":"publisher","unstructured":"Song, W., Chen, T., Gu, Z., Gai, W., Huang, W., Wang, B.: Wood materials defects detection using image block percentile color histogram and eigenvector texture feature. In: Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy. Atlantis Press (2015). https:\/\/doi.org\/10.2991\/icismme-15.2015.163","DOI":"10.2991\/icismme-15.2015.163"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"issue":"3","key":"11_CR39","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1007\/s10845-019-01476-x","volume":"31","author":"D Tabernik","year":"2020","unstructured":"Tabernik, D., \u0160ela, S., Skvar\u010d, J., Sko\u010daj, D.: Segmentation-based deep-learning approach for surface-defect detection. J. Intell. Manuf. 31(3), 759\u2013776 (2020)","journal-title":"J. Intell. Manuf."},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: An incremental unified framework for small defect inspection. In: 18th European Conference on Computer Vision (ECCV) (2024). https:\/\/github.com\/jqtangust\/IUF","DOI":"10.1007\/978-3-031-72751-1_18"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities. In: Measures of Complexity: Festschrift for Alexey Chervonenkis (2015)","DOI":"10.1007\/978-3-319-21852-6_3"},{"key":"11_CR42","unstructured":"Wagner, S.: A literature survey of the quality economics of defect-detection techniques. CoRR abs\/1612.04590 (2016). http:\/\/arxiv.org\/abs\/1612.04590"},{"issue":"10","key":"11_CR43","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR44","unstructured":"Wang, W., et al.: Sindiffusion: learning a diffusion model from a single natural image. arXiv preprint arXiv:2211.12445 (2022)"},{"issue":"12","key":"11_CR45","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.3390\/machines10121239","volume":"10","author":"J Wei","year":"2022","unstructured":"Wei, J., Zhang, Z., Shen, F., Lv, C.: Mask-guided generation method for industrial defect images with non-uniform structures. Machines 10(12), 1239 (2022)","journal-title":"Machines"},{"key":"11_CR46","unstructured":"Wieler, M., Hahn, T.: Weakly supervised learning for industrial optical inspection. In: DAGM Symposium, vol.\u00a06 (2007)"},{"key":"11_CR47","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers (2021)"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Yao, X., Li, R., Zhang, J., Sun, J., Zhang, C.: Explicit boundary guided semi-push-pull contrastive learning for supervised anomaly detection (2023). https:\/\/arxiv.org\/abs\/2207.01463","DOI":"10.1109\/CVPR52729.2023.02346"},{"key":"11_CR49","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vision 129, 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, G., Cui, K., Hung, T.Y., Lu, S.: Defect-GAN: high-fidelity defect synthesis for automated defect inspection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2524\u20132534 (2021)","DOI":"10.1109\/WACV48630.2021.00257"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhao, Z., Zhang, X., Sun, C., Chen, X.: Industrial anomaly detection with domain shift: a real-world dataset and masked multi-scale reconstruction. arXiv preprint arXiv:2304.02216 (2023)","DOI":"10.1016\/j.compind.2023.103990"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.544"},{"issue":"3","key":"11_CR54","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"11_CR56","doi-asserted-by":"crossref","unstructured":"Zou, Y., Jeong, J., Pemula, L., Zhang, D., Dabeer, O.: Spot-the-difference self-supervised pre-training for anomaly detection and segmentation (2022)","DOI":"10.1007\/978-3-031-20056-4_23"}],"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\/978-3-031-72667-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:08:01Z","timestamp":1732828081000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72667-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031726668","9783031726675"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72667-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 September 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"}}]}}