{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T12:33:32Z","timestamp":1784810012645,"version":"3.55.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031928048","type":"print"},{"value":"9783031928055","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92805-5_20","type":"book-chapter","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T12:59:53Z","timestamp":1747918793000},"page":"310-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-supervised Models are Strong Industrial Few-Shot Defect Classification Learners"],"prefix":"10.1007","author":[{"given":"Teng","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengcheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"20_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"20_CR2","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":"20_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2022.107294","volume":"161","author":"Y Cao","year":"2023","unstructured":"Cao, Y., Zhu, W., Yang, J., Fu, G., Lin, D., Cao, Y.: An effective industrial defect classification method under the few-shot setting via two-stream training. Opt. Lasers Eng. 161, 107294 (2023)","journal-title":"Opt. Lasers Eng."},{"key":"20_CR5","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"20_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"20_CR8","first-page":"22243","volume":"33","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. Adv. Neural. Inf. Process. Syst. 33, 22243\u201322255 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Context autoencoder for self-supervised representation learning. Int. J. Comput. Vis., 1\u201316 (2023)","DOI":"10.1007\/s11263-023-01852-4"},{"key":"20_CR10","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Chen*, X., Xie*, S., He, K.: An empirical study of training self-supervised vision transformers. arXiv preprint arXiv:2104.02057 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"20_CR13","unstructured":"Contributors, M.: OpenMMLab\u2019s pre-training toolbox and benchmark (2023). https:\/\/github.com\/open-mmlab\/mmpretrain"},{"issue":"5","key":"20_CR14","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.3390\/s20051459","volume":"20","author":"T Czimmermann","year":"2020","unstructured":"Czimmermann, T., et al.: Visual-based defect detection and classification approaches for industrial applications-a survey. Sensors 20(5), 1459 (2020)","journal-title":"Sensors"},{"key":"20_CR15","unstructured":"Dehghani, M., Djolonga, J., et\u00a0al.: Scaling vision transformers to 22 billion parameters. In: International Conference on Machine Learning, pp. 7480\u20137512. PMLR (2023)"},{"key":"20_CR16","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: PECO: perceptual codebook for BERT pre-training of vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 552\u2013560 (2023)","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: EVA: exploring the limits of masked visual representation learning at scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19358\u201319369 (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"20_CR22","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":"20_CR23","unstructured":"Hou, Z., Sun, F., Chen, Y.K., Xie, Y., Kung, S.Y.: MILAN: masked image pretraining on language assisted representation. arXiv preprint arXiv:2208.06049 (2022)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Contrastive masked autoencoders are stronger vision learners. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"20_CR25","unstructured":"Jiang, Z., et al.: Layer grafted pre-training: bridging contrastive learning and masked image modeling for label-efficient representations. arXiv preprint arXiv:2302.14138 (2023)"},{"key":"20_CR26","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"20_CR27","unstructured":"Li, S., et\u00a0al.: Architecture-agnostic masked image modeling\u2013from VIT back to CNN. arXiv preprint arXiv:2205.13943 (2022)"},{"issue":"8","key":"20_CR28","doi-asserted-by":"publisher","first-page":"3507","DOI":"10.1007\/s10845-022-02022-y","volume":"34","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Song, Y., Tang, R., Duan, G., Tan, J.: Few-shot defect recognition of metal surfaces via attention-embedding and self-supervised learning. J. Intell. Manuf. 34(8), 3507\u20133521 (2023)","journal-title":"J. Intell. Manuf."},{"key":"20_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"20_CR30","unstructured":"Mishra, S., et al.: A simple, efficient and scalable contrastive masked autoencoder for learning visual representations. arXiv preprint arXiv:2210.16870 (2022)"},{"key":"20_CR31","unstructured":"Peng, Z., Dong, L., Bao, H., Ye, Q., Wei, F.: BEIT V2: masked image modeling with vector-quantized visual tokenizers. arXiv preprint arXiv:2208.06366 (2022)"},{"key":"20_CR32","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":"20_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2023.103901","volume":"148","author":"X Shi","year":"2023","unstructured":"Shi, X., Zhang, S., Cheng, M., He, L., Tang, X., Cui, Z.: Few-shot semantic segmentation for industrial defect recognition. Comput. Ind. 148, 103901 (2023)","journal-title":"Comput. Ind."},{"key":"20_CR34","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","volume":"285","author":"K Song","year":"2013","unstructured":"Song, K., Yan, Y.: A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Appl. Surf. Sci. 285, 858\u2013864 (2013)","journal-title":"Appl. Surf. Sci."},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Tao, C., et al.: Siamese image modeling for self-supervised vision representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2132\u20132141 (2023)","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"20_CR37","unstructured":"Tian, K., Jiang, Y., Diao, Q., Lin, C., Wang, L., Yuan, Z.: Designing BERT for convolutional networks: sparse and hierarchical masked modeling. arXiv preprint arXiv:2301.03580 (2023)"},{"key":"20_CR38","unstructured":"Tomasev, N., et al.: Pushing the limits of self-supervised resnets: can we outperform supervised learning without labels on imagenet? arXiv preprint arXiv:2201.05119 (2022)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"20_CR40","unstructured":"Xie, J., Li, W., Zhan, X., Liu, Z., Ong, Y.S., Loy, C.C.: Masked frequency modeling for self-supervised visual pre-training. arXiv preprint arXiv:2206.07706 (2022)"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"20_CR42","unstructured":"Yi, K., et al.: Masked image modeling with denoising contrast. arXiv preprint arXiv:2205.09616 (2022)"},{"key":"20_CR43","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888 (2017)"},{"key":"20_CR44","unstructured":"Zhang, S., Zhu, F., Zhao, R., Yan, J.: Contextual image masking modeling via synergized contrasting without view augmentation for faster and better visual pretraining. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"20_CR45","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Yu, C., Luo, H., Wang, Z., Li, H.: MimCo: masked image modeling pre-training with contrastive teacher. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4487\u20134495 (2022)","DOI":"10.1145\/3503161.3548173"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92805-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T13:00:19Z","timestamp":1747918819000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92805-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031928048","9783031928055"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92805-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}