{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:24:42Z","timestamp":1743153882166,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031779145"},{"type":"electronic","value":"9783031779152"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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\/978-3-031-77915-2_9","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T11:53:58Z","timestamp":1732794838000},"page":"116-129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TRAPL: Transformer-Based Patch Learning for Enhancing Semantic Representations Using Aggregated Features to\u00a0Estimate Patch-Class Distribution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2798-9991","authenticated-orcid":false,"given":"Sander Riis\u00f8en","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\/0009-0008-8702-7770","authenticated-orcid":false,"given":"Ivar","family":"Oveland","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"}]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"9_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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8219\u20138228 (2021)","DOI":"10.1109\/ICCV48922.2021.00811"},{"key":"9_CR2","doi-asserted-by":"publisher","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, pp. 3213\u20133223 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"9_CR3","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arxiv.2010.11929","DOI":"10.48550\/arxiv.2010.11929"},{"key":"9_CR4","unstructured":"Duman\u00a0Keles, F., Mahesakya\u00a0Wijewardena, P., Hegde, C., Agrawal, S., Orabona, F.: On the computational complexity of self-attention. In: Proceedings of Machine Learning Research, vol.\u00a0201, pp. 597\u2013619 (2023)"},{"key":"9_CR5","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 (CVPR), pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"9_CR6","doi-asserted-by":"publisher","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 - Proceedings, pp. 3518\u20133522 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746248","DOI":"10.1109\/ICASSP43922.2022.9746248"},{"key":"9_CR7","unstructured":"International Society for Photogrammetry and Remote Sensing: 2D Semantic Labeling Contest - Potsdam"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: OneFormer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2989\u20132998 (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"issue":"3","key":"9_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5617\/NMI.9849","volume":"2","author":"S Jyhne","year":"2022","unstructured":"Jyhne, S., et al.: MapAI: precision in building segmentation. Nordic Mach. Intell. 2(3), 1\u20133 (2022). https:\/\/doi.org\/10.5617\/NMI.9849","journal-title":"Nordic Mach. Intell."},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Jyhne, S., Jacobsen, J.R., Goodwin, M., Andersen, P.A.: DeNISE: deep networks for improved segmentation edges. In: Artificial Intelligence Applications and Innovations, pp. 81\u201389 (2023). https:\/\/doi.org\/10.1007\/978-3-031-34111-3_8","DOI":"10.1007\/978-3-031-34111-3_8"},{"key":"9_CR11","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-031-47994-6_8","volume-title":"Artificial Intelligence XL","author":"SR Jyhne","year":"2023","unstructured":"Jyhne, S.R., Andersen, P.A., Goodwin, M., Oveland, I.: A contrastive learning scheme with transformer innate patches. In: Bramer, M., Stahl, F. (eds.) SGAI 2023. LNCS, vol. 14381, pp. 103\u2013114. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-47994-6_8"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, T., Roy, S., Zhou, H., Lu, H., Lathuili\u00e8re, S.: Contrast, stylize and adapt: unsupervised contrastive learning framework for domain adaptive semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 4869\u20134879 (2023)","DOI":"10.1109\/CVPRW59228.2023.00515"},{"key":"9_CR13","unstructured":"Liu, B., Ravikumar, P., Risteski, A.: Contrastive learning of strong-mixing continuous-time stochastic processes. In: International Conference on Artificial Intelligence and Statistics (2021)"},{"key":"9_CR14","doi-asserted-by":"publisher","unstructured":"Liu, S., Zhi, S., Johns, E., Davison, A.J.: Bootstrapping semantic segmentation with regional contrast. In: International Conference on Learning Representations (2022). https:\/\/doi.org\/10.48550\/arxiv.2104.04465","DOI":"10.48550\/arxiv.2104.04465"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., Yuan, Y.: EfficientViT: memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14420\u201314430 (2023)","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer V2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"9_CR17","unstructured":"Ryali, C., et al.: Hiera: a hierarchical vision transformer without the bells-and-whistles. In: ICML (2023)"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Teichmann, M., Weber, M., Z\u00f6llner, M., Cipolla, R., Urtasun, R.: MultiNet: real-time joint semantic reasoning for autonomous driving. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1013\u20131020 (2018). https:\/\/doi.org\/10.1109\/IVS.2018.8500504","DOI":"10.1109\/IVS.2018.8500504"},{"key":"9_CR19","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/LGRS.2022.3143368","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., Van\u00a0Gool, L.: Exploring cross-image pixel contrast for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7303\u20137313 (2021)","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Wei, Y., et al.: Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation. arXiv (2022). https:\/\/doi.org\/10.48550\/arxiv.2205.14141","DOI":"10.48550\/arxiv.2205.14141"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"9_CR23","doi-asserted-by":"publisher","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. Lecture Notes in Computer Science, vol. 11209, pp. 432\u2013448 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"9_CR24","first-page":"3285","volume":"34","author":"F Zhang","year":"2021","unstructured":"Zhang, F., Torr, P., Ranftl, R., Richter, S.R.: Looking beyond single images for contrastive semantic segmentation learning. Adv. Neural. Inf. Process. Syst. 34, 3285\u20133297 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, X., et al.: Contrastive Learning for Label Efficient Semantic Segmentation (2021)","DOI":"10.1109\/ICCV48922.2021.01045"},{"key":"9_CR26","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 (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XLI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77915-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T12:10:54Z","timestamp":1732795854000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77915-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031779145","9783031779152"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77915-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}