{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T19:36:03Z","timestamp":1771788963950,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726668","type":"print"},{"value":"9783031726675","type":"electronic"}],"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_2","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:11:48Z","timestamp":1727554308000},"page":"20-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SINDER: Repairing the\u00a0Singular Defects of\u00a0DINOv2"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5760-4097","authenticated-orcid":false,"given":"Haoqi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5818-4285","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8347-8637","authenticated-orcid":false,"given":"Mathieu","family":"Salzmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"2_CR2","first-page":"26671","volume":"35","author":"R Balestriero","year":"2022","unstructured":"Balestriero, R., LeCun, Y.: Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods. Adv. Neural. Inf. Process. Syst. 35, 26671\u201326685 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR3","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":"2_CR4","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":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: CVF International Conference on Computer Vision (ICCV), pp. 9620\u20139629 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"2_CR7","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers (2024)"},{"key":"2_CR8","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":"2_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"2_CR10","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html"},{"key":"2_CR11","unstructured":"Geshkovski, B., Letrouit, C., Polyanskiy, Y., Rigollet, P.: The emergence of clusters in self-attention dynamics (2023). arXiv preprint arXiv:2305.05465"},{"key":"2_CR12","unstructured":"Geshkovski, B., Letrouit, C., Polyanskiy, Y., Rigollet, P.: A mathematical perspective on transformers (2023). arXiv preprint arXiv:2312.10794"},{"key":"2_CR13","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent: A new approach to self-supervised learning (2020). arXiv preprint arXiv:2006.07733"},{"key":"2_CR14","unstructured":"Hamilton, M., Zhang, Z., Hariharan, B., Snavely, N., Freeman, W.T.: Unsupervised semantic segmentation by distilling feature correspondences (2022). arXiv preprint arXiv:2203.08414"},{"key":"2_CR15","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":"2_CR16","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9865\u20139874 (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, B.K., Ro, Y.M.: Causal unsupervised semantic segmentation (2023). arXiv preprint arXiv:2310.07379","DOI":"10.2139\/ssrn.4967689"},{"key":"2_CR18","unstructured":"Oquab, M., et\u00a0al.: Dinov2: Learning robust visual features without supervision. Trans. Mach. Learn. Res. (2023)"},{"key":"2_CR19","unstructured":"Qiu, C., Zhang, T., Wu, Y., Ke, W., Salzmann, M., S\u00fcsstrunk, S.: Mind your augmentation: the key to decoupling dense self-supervised learning. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision - ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from rgbd images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) Computer Vision - ECCV 2012, pp. 746\u2013760. Springer, Berlin Heidelberg, Berlin, Heidelberg (2012)"},{"key":"2_CR21","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? (2020). arXiv preprint arXiv:2005.10243"},{"key":"2_CR22","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning, pp. 9929\u20139939. PMLR (2020)"},{"key":"2_CR23","unstructured":"Wang, Y., Zhang, Q., Wang, Y., Yang, J., Lin, Z.: Chaos is a ladder: A new theoretical understanding of contrastive learning via augmentation overlap (2022). arXiv preprint arXiv:2203.13457"},{"key":"2_CR24","unstructured":"Wikipedia: Power iteration \u2014 Wikipedia, the free encyclopedia. http:\/\/en.wikipedia.org\/w\/index.php?title=Power%20iteration&oldid=1188380344 (2024). [Online Accessed 06 Mar 2024]"},{"key":"2_CR25","unstructured":"Xiao, T., Wang, X., Efros, A.A., Darrell, T.: What should not be contrastive in contrastive learning (2020). arXiv preprint arXiv:2008.05659"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, T., Qiu, C., Ke, W., S\u00fcsstrunk, S., Salzmann, M.: Leverage your local and global representations: a new self-supervised learning strategy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16580\u201316589 (2022)","DOI":"10.1109\/CVPR52688.2022.01608"},{"key":"2_CR27","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, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"2_CR28","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., Kong, T.: ibot: Image bert pre-training with online tokenizer (2021). arXiv preprint arXiv:2111.07832"}],"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_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:12:31Z","timestamp":1727554351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72667-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031726668","9783031726675"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72667-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}