{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:13:01Z","timestamp":1775578381461,"version":"3.50.1"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-72992-8_4","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"54-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["On Pretraining Data Diversity for\u00a0Self-Supervised Learning"],"prefix":"10.1007","author":[{"given":"Hasan Abed","family":"Al Kader Hammoud","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuhin","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Pizzati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip H. S.","family":"Torr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adel","family":"Bibi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"4_CR1","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: NeurIPS (2019)"},{"key":"4_CR2","unstructured":"Balestriero, R., et\u00a0al.: A cookbook of self-supervised learning. arXiv preprint arXiv:2304.12210 (2023)"},{"key":"4_CR3","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEit: BERT pre-training of image transformers. In: ICML (2022)"},{"key":"4_CR4","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. In: ICLR (2022)"},{"key":"4_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Mairal, J., Joulin, A.: Unsupervised pre-training of image features on non-curated data. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00305"},{"key":"4_CR8","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"4_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"4_CR11","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.: Big self-supervised models are strong semi-supervised learners. In: NeurIPS (2020)"},{"key":"4_CR12","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Cole, E., Yang, X., Wilber, K., Aodha, O.M., Belongie, S.: When does contrastive visual representation learning work? In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01434"},{"key":"4_CR16","unstructured":"Costa, V.G.T.D., Fini, E., Nabi, M., Sebe, N., Ricci, E.: solo-learn: a library of self-supervised methods for visual representation learning. In: JMLR (2022)"},{"key":"4_CR17","unstructured":"Dehghani, M., et\u00a0al.: Scaling vision transformers to 22 billion parameters. In: ICML (2023)"},{"key":"4_CR18","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: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Doersch, C., Zisserman, A.: Multi-task self-supervised visual learning. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.226"},{"key":"4_CR21","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"4_CR22","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., Grave, E.: Are large-scale datasets necessary for self-supervised pre-training? arXiv (2021)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Ericsson, L., Gouk, H., Hospedales, T.M.: How well do self-supervised models transfer? In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"4_CR24","unstructured":"Fini, E., Astolfi, P., Romero-Soriano, A., Verbeek, J., Drozdzal, M.: Improved baselines for vision-language pre-training. TMLR (2023)"},{"key":"4_CR25","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)"},{"key":"4_CR26","unstructured":"Goyal, P., et\u00a0al.: Self-supervised pretraining of visual features in the wild. arXiv preprint arXiv:2103.01988 (2021)"},{"key":"4_CR27","unstructured":"Goyal, P., et al.: Vision models are more robust and fair when pretrained on uncurated images without supervision. arXiv preprint arXiv:2202.08360 (2022)"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Goyal, P., Mahajan, D., Gupta, A., Misra, I.: Scaling and benchmarking self-supervised visual representation learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00649"},{"key":"4_CR29","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS, vol.\u00a033 (2020)"},{"key":"4_CR30","unstructured":"Hammoud, H.A.A.K., Itani, H., Pizzati, F., Torr, P., Bibi, A., Ghanem, B.: SynthCLIP: are we ready for a fully synthetic clip training? arXiv (2024)"},{"key":"4_CR31","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR34","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS, vol. 30 (2017)"},{"key":"4_CR35","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: ICLR (2018)"},{"key":"4_CR36","unstructured":"H\u00e9naff, O.J., et al.: Data-efficient image recognition with contrastive predictive coding. In: ICML (2019)"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Kotar, K., Ilharco, G., Schmidt, L., Ehsani, K., Mottaghi, R.: Contrasting contrastive self-supervised representation learning pipelines. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00980"},{"key":"4_CR38","unstructured":"Krause, J., Deng, J., Stark, M., Fei-Fei, L.: Collecting a large-scale dataset of fine-grained cars. In: FGVC (2013)"},{"key":"4_CR39","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"4_CR40","unstructured":"Le, Y., Yang, X.: Tiny ImageNet visual recognition challenge. CS 231N (2015)"},{"key":"4_CR41","unstructured":"Li, A.C., Brown, E.L., Efros, A.A., Pathak, D.: Internet explorer: targeted representation learning on the open web. In: ICML (2023)"},{"key":"4_CR42","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.C.H.: Prototypical contrastive learning of unsupervised representations. In: ICLR (2021)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Misra, I., Maaten, L.V.D.: Self-supervised learning of pretext-invariant representations. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"4_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"4_CR46","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"4_CR47","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Ramtoula, B., Gadd, M., Newman, P., De\u00a0Martini, D.: Visual DNA: representing and comparing images using distributions of neuron activations. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01069"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4_CR52","unstructured":"Shi, Y., Daunhawer, I., Vogt, J.E., Torr, P., Sanyal, A.: How robust is unsupervised representation learning to distribution shift? In: ICLR (2022)"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM (2016)","DOI":"10.1145\/2812802"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Tian, Y., Henaff, O.J., Van Den\u00a0Oord, A.: Divide and contrast: self-supervised learning from uncurated data. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00991"},{"key":"4_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"4_CR58","unstructured":"Tong, S., Chen, Y., Ma, Y., Lecun, Y.: EMP-SSL: towards self-supervised learning in one training epoch. arXiv preprint arXiv:2304.03977 (2023)"},{"key":"4_CR59","doi-asserted-by":"crossref","unstructured":"Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"4_CR60","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Georgoulis, S., Gool, L.V.: Revisiting contrastive methods for unsupervised learning of visual representations. In: NeurIPS (2021)"},{"key":"4_CR61","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac\u00a0Aodha, O.: Benchmarking representation learning for natural world image collections. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01269"},{"key":"4_CR62","unstructured":"Wei, J., et\u00a0al.: Emergent abilities of large language models. TMLR (2022)"},{"key":"4_CR63","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"4_CR64","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"4_CR65","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: On data scaling in masked image modeling. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00999"},{"key":"4_CR66","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: ICML (2021)"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"4_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"4_CR69","unstructured":"Zhao, N., Wu, Z., Lau, R.W.H., Lin, S.: What makes instance discrimination good for transfer learning? In: ICML (2021)"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. T-PAMI (2017)","DOI":"10.1167\/17.10.296"},{"key":"4_CR71","unstructured":"Zhou, P., Zhou, Y., Si, C., Yu, W., Ng, T.K., Yan, S.: Mugs: a multi-granular self-supervised learning framework. arXiv preprint arXiv:2203.14415 (2022)"},{"key":"4_CR72","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Zhai, A.L., Yamins, D.: Local aggregation for unsupervised learning of visual embeddings. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00610"}],"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\/978-3-031-72992-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:42:31Z","timestamp":1730191351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 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"}}]}}