{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:11:41Z","timestamp":1783437101254,"version":"3.54.6"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200557","type":"print"},{"value":"9783031200564","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20056-4_29","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:31:54Z","timestamp":1667417514000},"page":"499-515","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["CP$$^2$$: Copy-Paste Contrastive Pretraining for\u00a0Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Feng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P., Pont-Tuset, J., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"29_CR2","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: NeurIPS (2019)"},{"key":"29_CR3","unstructured":"Belghazi, M., Oquab, M., Lopez-Paz, D.: Learning about an exponential amount of conditional distributions. In: NeurIPS (2019)"},{"key":"29_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Caron","year":"2018","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 139\u2013156. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_9"},{"key":"29_CR5","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":"29_CR6","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":"29_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE TPAMI 40, 834\u2013848 (2017)","journal-title":"IEEE TPAMI"},{"key":"29_CR8","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. In: CVPR (2017)"},{"key":"29_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"29_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"29_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":"29_CR12","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"29_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":"29_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":"29_CR15","unstructured":"Contributors, M.: MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"29_CR17","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":"29_CR18","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":"29_CR19","unstructured":"Donahue, J., Kr\u00e4henb\u00fchl, P., Darrell, T.: Adversarial feature learning. In: ICLR (2016)"},{"key":"29_CR20","unstructured":"Donahue, J., Simonyan, K.: Large scale adversarial representation learning. In: NeurIPS (2019)"},{"key":"29_CR21","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"29_CR22","unstructured":"Dumoulin, V., et al.: Adversarially learned inference. In: ICLR (2016)"},{"key":"29_CR23","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV 111, 98\u2013136 (2015)","journal-title":"IJCV"},{"key":"29_CR24","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167\u2013181 (2004)","journal-title":"IJCV"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"29_CR26","unstructured":"Grill, J.B., et al.: Bootstrap your own latent a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"29_CR28","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":"29_CR29","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":"29_CR30","doi-asserted-by":"crossref","unstructured":"H\u00e9naff, O.J., Koppula, S., Alayrac, J.B., Oord, A.V.D., Vinyals, O., Carreira, J.: Efficient visual pretraining with contrastive detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"29_CR31","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: AugMix: a simple data processing method to improve robustness and uncertainty. In: ICLR (2019)"},{"key":"29_CR32","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS (2020)"},{"key":"29_CR33","unstructured":"Komodakis, N., Gidaris, S.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"29_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"29_CR36","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":"29_CR37","unstructured":"O Pinheiro, P.O., Almahairi, A., Benmalek, R., Golemo, F., Courville, A.C.: Unsupervised learning of dense visual representations. In: NIPS (2020)"},{"key":"29_CR38","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-V4, inception-ResNet and the impact of residual connections on learning. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"29_CR41","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? In: NeurIPS (2020)"},{"key":"29_CR42","unstructured":"Wei, C., Wang, H., Shen, W., Yuille, A.: CO2: consistent contrast for unsupervised visual representation learning. In: ICLR (2021)"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: Iterative reorganization with weak spatial constraints: solving arbitrary jigsaw puzzles for unsupervised representation learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00201"},{"key":"29_CR44","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":"29_CR45","doi-asserted-by":"crossref","unstructured":"Xie, Z., Lin, Y., Zhang, Z., Cao, Y., Lin, S., Hu, H.: Propagate yourself: exploring pixel-level consistency for unsupervised visual representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Yang, C., Wu, Z., Zhou, B., Lin, S.: Instance localization for self-supervised detection pretraining. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Ye, M., Zhang, X., Yuen, P.C., Chang, S.F.: Unsupervised embedding learning via invariant and spreading instance feature. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00637"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2017)","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"29_CR50","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":"29_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.76"},{"key":"29_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: Contrastive learning for label efficient semantic segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01045"},{"key":"29_CR53","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. IJCV 127, 302\u2013321 (2019)","journal-title":"IJCV"},{"key":"29_CR54","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. In: ICLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20056-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T00:32:24Z","timestamp":1667608344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20056-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200557","9783031200564"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20056-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}