{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:49:37Z","timestamp":1767340177136,"version":"3.40.3"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012151"},{"type":"electronic","value":"9783030012168"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01216-8_6","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"86-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":99,"title":["Effective Use of Synthetic Data for Urban Scene Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3695-9876","authenticated-orcid":false,"given":"Fatemeh Sadat","family":"Saleh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3948-6418","authenticated-orcid":false,"given":"Mohammad Sadegh","family":"Aliakbarian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8347-8637","authenticated-orcid":false,"given":"Mathieu","family":"Salzmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0103-1904","authenticated-orcid":false,"given":"Lars","family":"Petersson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7535-6322","authenticated-orcid":false,"given":"Jose M.","family":"Alvarez","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"6_CR1","unstructured":"Badrinarayanan, V., Handa, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293 (2015)"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46478-7_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Bearman","year":"2016","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What\u2019s the point: semantic segmentation with point supervision. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_34"},{"issue":"2","key":"6_CR3","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. Pattern Recognit. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recognit. Lett."},{"key":"6_CR4","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. arXiv preprint arXiv:1606.00915 (2016)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., Chen, W.Y., Chen, Y.T., Tsai, B.C., Wang, Y.C.F., Sun, M.: No more discrimination: cross city adaptation of road scene segmenters. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2011\u20132020. IEEE (2017)","DOI":"10.1109\/ICCV.2017.220"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., Van Gool, L.: ROAD: reality oriented adaptation for semantic segmentation of urban scenes. arXiv preprint arXiv:1711.11556 (2017)","DOI":"10.1109\/CVPR.2018.00823"},{"key":"6_CR7","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, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.191"},{"key":"6_CR9","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A., Koltun, V.: CARLA: an open urban driving simulator. arXiv preprint arXiv:1711.03938 (2017)"},{"key":"6_CR10","unstructured":"Epic-Games: Unreal Engine 4 (2018)"},{"issue":"8","key":"6_CR11","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915\u20131929 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR12","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180\u20131189 (2015)"},{"key":"6_CR13","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096\u20132030 (2016)"},{"key":"6_CR14","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"issue":"3","key":"6_CR15","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11263-008-0140-x","volume":"80","author":"S Gould","year":"2008","unstructured":"Gould, S., Rodgers, J., Cohen, D., Elidan, G., Koller, D.: Multi-class segmentation with relative location prior. Int. J. Comput. Vis. 80(3), 300\u2013316 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"6_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/978-3-540-88682-2_4","volume-title":"Computer Vision \u2013 ECCV 2008","author":"G Heitz","year":"2008","unstructured":"Heitz, G., Koller, D.: Learning spatial context: using stuff to find things. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 30\u201343. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_4"},{"key":"6_CR18","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"6_CR19","unstructured":"Hoffman, J., et al.: CYCADA: cycle-consistent adversarial domain adaptation. arXiv preprint arXiv:1711.03213 (2017)"},{"key":"6_CR20","unstructured":"Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNs in the wild: pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649 (2016)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Weakly supervised semantic labelling and instance segmentation. arXiv preprint arXiv:1603.07485 (2016)","DOI":"10.1109\/CVPR.2017.181"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. arXiv preprint arXiv:1801.00868 (2018)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"6_CR23","unstructured":"Kolesnikov, A., Lampert, C.H.: Seed, expand and constrain: three principles for weakly-supervised image segmentation. CoRR abs\/1603.06098 (2016). http:\/\/arxiv.org\/abs\/1603.06098"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Liu, B., He, X.: Multiclass semantic video segmentation with object-level active inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4286\u20134294 (2015)","DOI":"10.1109\/CVPR.2015.7299057"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. arXiv preprint arXiv:1712.00479 (2017)","DOI":"10.1109\/CVPR.2018.00473"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Oh, S.J., Benenson, R., Khoreva, A., Akata, Z., Fritz, M., Schiele, B.: Exploiting saliency for object segmentation from image level labels. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.535"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L.C., Murphy, K.P., Yuille, A.L.: Weakly- and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.203"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.209"},{"key":"6_CR32","unstructured":"Pathak, D., Shelhamer, E., Long, J., Darrell, T.: Fully convolutional multi-class multiple instance learning. In: ICLR Workshop (2015)"},{"key":"6_CR33","unstructured":"Pinheiro, P., Collobert, R.: Recurrent convolutional neural networks for scene labeling. In: International Conference on Machine Learning, pp. 82\u201390 (2014)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Pinheiro, P.O., Collobert, R.: From image-level to pixel-level labeling with convolutional networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Richter, S.R., Hayder, Z., Koltun, V.: Playing for benchmarks. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.243"},{"key":"6_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: The IEEE International Conference on Computer Vision (ICCV), vol. 2, p. 6 (2017)","DOI":"10.1109\/CVPR.2016.352"},{"issue":"3","key":"6_CR38","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Sadat Saleh, F., Sadegh Aliakbarian, M., Salzmann, M., Petersson, L., Alvarez, J.M.: Bringing background into the foreground: making all classes equal in weakly-supervised video semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2106\u20132116 (2017)","DOI":"10.1109\/ICCV.2017.232"},{"key":"6_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-319-46484-8_25","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Saleh","year":"2016","unstructured":"Saleh, F., Ali Akbarian, M.S., Salzmann, M., Petersson, L., Gould, S., Alvarez, J.M.: Built-in foreground\/background prior for weakly-supervised semantic segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 413\u2013432. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_25"},{"issue":"6","key":"6_CR41","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1109\/TPAMI.2017.2713785","volume":"40","author":"F Saleh","year":"2017","unstructured":"Saleh, F., Aliakbarian, M.S., Salzmann, M., Petersson, L., Alvarez, J.M., Gould, S.: Incorporating network built-in priors in weakly-supervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1382\u20131396 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Sharma, A., Tuzel, O., Jacobs, D.W.: Deep hierarchical parsing for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 530\u2013538. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298651"},{"key":"6_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11744023_1","volume-title":"Computer Vision \u2013 ECCV 2006","author":"J Shotton","year":"2006","unstructured":"Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1\u201315. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_1"},{"key":"6_CR44","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Sun, B., Saenko, K.: From virtual to reality: Fast adaptation of virtual object detectors to real domains. In: BMVC, vol. 1, p. 3 (2014)","DOI":"10.5244\/C.28.82"},{"key":"6_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/978-3-642-15555-0_26","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J Tighe","year":"2010","unstructured":"Tighe, J., Lazebnik, S.: SuperParsing: scalable nonparametric image parsing with superpixels. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 352\u2013365. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_26"},{"key":"6_CR47","unstructured":"Unity3D: Unity Technologies. Unity Development Platform (2018)"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.687"},{"issue":"11","key":"6_CR49","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/TPAMI.2016.2636150","volume":"39","author":"Y Wei","year":"2016","unstructured":"Wei, Y., et al.: STC: a simple to complex framework for weakly-supervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2314\u20132320 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR50","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: The IEEE International Conference on Computer Vision (ICCV), vol. 2, p. 6 (2017)","DOI":"10.1109\/ICCV.2017.223"},{"key":"6_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"6_CR53","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529\u20131537 (2015)","DOI":"10.1109\/ICCV.2015.179"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01216-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:18:43Z","timestamp":1665188323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}