{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:21:58Z","timestamp":1743103318900,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031479939"},{"type":"electronic","value":"9783031479946"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-47994-6_8","type":"book-chapter","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T08:02:28Z","timestamp":1699344148000},"page":"103-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Contrastive Learning Scheme with\u00a0Transformer Innate Patches"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2798-9991","authenticated-orcid":false,"given":"Sander R.","family":"Jyhne","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7742-4907","authenticated-orcid":false,"given":"Per-Arne","family":"Andersen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6331-702X","authenticated-orcid":false,"given":"Morten","family":"Goodwin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8702-7770","authenticated-orcid":false,"given":"Ivar","family":"Oveland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,8]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Alonso, I., Sabater, A., Ferstl, D., Montesano, L., Murillo, A.C.: Semi-supervised semantic segmentation with pixel-level contrastive learning from a class-wise memory bank (2021)","DOI":"10.1109\/ICCV48922.2021.00811"},{"key":"8_CR2","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.isprsjprs.2017.11.011","volume":"140","author":"N Audebert","year":"2018","unstructured":"Audebert, N., Le Saux, B., Lef\u00e8vre, S.: Beyond RGB: very high resolution urban remote sensing with multimodal deep networks. ISPRS J. Photogramm. Remote. Sens. 140, 20\u201332 (2018)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"8_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. ArXiv (2020)"},{"key":"8_CR4","unstructured":"Dao, S.D., Zhao, E., Phung, D., Cai, J.: Multi-label image classification with contrastive learning. ArXiv (2021)"},{"key":"8_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the 9th International Conference on Learning Representations (ICLR), pp. 1\u201321 (2021)"},{"key":"8_CR6","unstructured":"Duman Keles, F., Mahesakya Wijewardena, P., Hegde, C., Agrawal, S., Orabona, F.: On the computational complexity of self-attention (2023)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Huang, L., et al.: A two-stage contrastive learning framework for imbalanced aerial scene recognition. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing May 2022, pp. 3518\u20133522 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746248"},{"key":"8_CR9","unstructured":"isprs.org. ISPRS Potsdam Dataset"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Khoshboresh-Masouleh, M., Alidoost, F., Arefi, H.: Multiscale building segmentation based on deep learning for remote sensing RGB images from different sensors. J. Appl. Remote Sens. 14(03), 1 (2020)","DOI":"10.1117\/1.JRS.14.034503"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: UniFormer: unifying convolution and self-attention for visual recognition (2022)","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Li, Q., et al.: Instance segmentation of buildings using keypoints. In: IGARSS 2020\u20132020 IEEE International Geoscience and Remote Sensing Symposium, pp. 1452\u20131455 (2020)","DOI":"10.1109\/IGARSS39084.2020.9324457"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, W., Zhong, H., He, C., Lin, D.: Joint semantic-geometric learning for polygonal building segmentation. In: 35th AAAI Conference on Artificial Intelligence, AAAI 2021, vol. 3A, pp. 1958\u20131965 (2021)","DOI":"10.1609\/aaai.v35i3.16291"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Q., Kampffmeyer, M., Jenssen, R., Salberg, A.B.: Dense dilated convolutions merging network for land cover classification. IEEE Trans. Geosci. Remote Sens. 58(9), 6309\u20136320 (2020)","DOI":"10.1109\/TGRS.2020.2976658"},{"key":"8_CR15","unstructured":"Liu, S., Zhi, S., Johns, E., Davison, A.J.: Bootstrapping semantic segmentation with regional contrast (2021)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, B., Wang, L., Bai, J., Xiang, S., Pan, C.: Semantic labeling in very high resolution images via a self-cascaded convolutional neural network. ISPRS J. Photogramm. Remote Sens. 145, 78\u201395 (2018)","DOI":"10.1016\/j.isprsjprs.2017.12.007"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Matei, B.C., Sawhney, H.S., Samarasekera, S., Kim, J., Kumar, R.: Building segmentation for densely built urban regions using aerial LIDAR data. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition (2008)","DOI":"10.1109\/CVPR.2008.4587458"},{"key":"8_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"8_CR20","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.isprsjprs.2019.11.004","volume":"159","author":"Y Shi","year":"2019","unstructured":"Shi, Y., Li, Q., Zhu, X.X.: Building segmentation through a gated graph convolutional neural network with deep structured feature embedding. ISPRS J. Photogramm. Remote. Sens. 159, 184\u2013197 (2019)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Tang, M., Georgiou, K., Qi, H., Champion, C., Bosch, M.: Semantic segmentation in aerial imagery using multi-level contrastive learning with local consistency. In: Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023, pp. 3787\u20133796 (2023)","DOI":"10.1109\/WACV56688.2023.00379"},{"key":"8_CR22","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: DeepMind representation learning with contrastive predictive coding (2018)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, R., Duan, C., Zhang, C., Meng, X., Fang, S.: A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 19 (2022)","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","volume":"190","author":"L Wang","year":"2022","unstructured":"Wang, L., Li, R., Zhang, C., Fang, S., Duan, C., Meng, X., Atkinson, P.M.: UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS J. Photogramm. Remote. Sens. 190, 196\u2013214 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., Van Gool, L.: Exploring cross-image pixel contrast for semantic segmentation (2021)","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: MetaFormer is actually what you need for vision (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"8_CR28","unstructured":"Zhang, F., Torr, P., Ranftl, R., Richter, S.R.: Looking beyond single images for contrastive semantic segmentation learning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 3285\u20133297 (2021)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: Contrastive learning for label efficient semantic segmentation (2021)","DOI":"10.1109\/ICCV48922.2021.01045"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XL"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47994-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T08:03:52Z","timestamp":1699344232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47994-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031479939","9783031479946"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47994-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SGAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovative Techniques and Applications of Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConferenceExpert","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"27","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":"20","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":"40% - 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":"2 or 3","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":"2","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)"}},{"value":"A total of 76 reviewers plus two \u2018executive program committees\u2019 (one for each stream)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}