{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:52:13Z","timestamp":1775325133932,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585709","type":"print"},{"value":"9783030585716","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58571-6_9","type":"book-chapter","created":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T16:02:34Z","timestamp":1604851354000},"page":"142-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Autoregressive Unsupervised Image Segmentation"],"prefix":"10.1007","author":[{"given":"Yassine","family":"Ouali","sequence":"first","affiliation":[]},{"given":"C\u00e9line","family":"Hudelot","sequence":"additional","affiliation":[]},{"given":"Myriam","family":"Tami","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,9]]},"reference":[{"key":"9_CR1","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: Advances in Neural Information Processing Systems, pp. 15509\u201315519 (2019)"},{"issue":"6356","key":"9_CR2","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1038\/355161a0","volume":"355","author":"S Becker","year":"1992","unstructured":"Becker, S., Hinton, G.E.: Self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355(6356), 161\u2013163 (1992)","journal-title":"Nature"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3286\u20133295 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"9_CR4","unstructured":"Bielski, A., Favaro, P.: Emergence of object segmentation in perturbed generative models. In: Advances in Neural Information Processing Systems, pp. 7256\u20137266 (2019)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"9_CR6","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":"9_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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2959\u20132968 (2019)","DOI":"10.1109\/ICCV.2019.00305"},{"key":"9_CR8","unstructured":"Chen, M., Arti\u00e8res, T., Denoyer, L.: Unsupervised object segmentation by redrawing. In: Advances in Neural Information Processing Systems, pp. 12705\u201312716 (2019)"},{"key":"9_CR9","unstructured":"Chen, X., Mishra, N., Rohaninejad, M., Abbeel, P.: PixelSNAIL: an improved autoregressive generative model. In: International Conference on Machine Learning, pp. 864\u2013872 (2018)"},{"key":"9_CR10","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"9_CR12","unstructured":"Fard, M.M., Thonet, T., Gaussier, E.: Deep $$k$$-means: Jointly clustering with $$k$$-means and learning representations. arXiv preprint arXiv:1806.10069 (2018)"},{"key":"9_CR13","unstructured":"Federici, M., Dutta, A., Forr\u00e9, P., Kushman, N., Akata, Z.: Learning robust representations via multi-view information bottleneck. arXiv preprint arXiv:2002.07017 (2020)"},{"key":"9_CR14","unstructured":"Gerke, M.: Use of the stair vision library within the ISPRS 2D semantic labeling benchmark (Vaihingen) (2014)"},{"key":"9_CR15","unstructured":"Germain, M., Gregor, K., Murray, I., Larochelle, H.: MADE: masked autoencoder for distribution estimation. In: International Conference on Machine Learning, pp. 881\u2013889 (2015)"},{"key":"9_CR16","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"9_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-12939-2_2","volume-title":"Pattern Recognition","author":"P Haeusser","year":"2019","unstructured":"Haeusser, P., Plapp, J., Golkov, V., Aljalbout, E., Cremers, D.: Associative deep clustering: training a classification network with no labels. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 18\u201332. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-12939-2_2"},{"issue":"337","key":"9_CR19","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1080\/01621459.1972.10481214","volume":"67","author":"JA Hartigan","year":"1972","unstructured":"Hartigan, J.A.: Direct clustering of a data matrix. J. Am. Stat. Assoc. 67(337), 123\u2013129 (1972)","journal-title":"J. Am. Stat. Assoc."},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"9_CR21","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/j.inffus.2006.05.006","volume":"9","author":"Z He","year":"2008","unstructured":"He, Z., Xu, X., Deng, S.: k-ANMI: a mutual information based clustering algorithm for categorical data. Inf. Fusion 9(2), 223\u2013233 (2008)","journal-title":"Inf. Fusion"},{"key":"9_CR22","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"9_CR23","unstructured":"Hu, W., Miyato, T., Tokui, S., Matsumoto, E., Sugiyama, M.: Learning discrete representations via information maximizing self-augmented training. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1558\u20131567. JMLR.org (2017)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Hwang, J.J., et al.: SegSort: segmentation by discriminative sorting of segments. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7334\u20137344 (2019)","DOI":"10.1109\/ICCV.2019.00743"},{"key":"9_CR25","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"9_CR26","unstructured":"Isola, P., Zoran, D., Krishnan, D., Adelson, E.H.: Learning visual groups from co-occurrences in space and time. arXiv preprint arXiv:1511.06811 (2015)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9865\u20139874 (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"9_CR28","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734 (2017)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Kanezaki, A.: Unsupervised image segmentation by backpropagation. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1543\u20131547. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462533"},{"issue":"1\u20132","key":"9_CR30","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"9_CR31","unstructured":"Larochelle, H., Murray, I.: The neural autoregressive distribution estimator. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, pp. 29\u201337 (2011)"},{"issue":"2","key":"9_CR32","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"issue":"11","key":"9_CR33","doi-asserted-by":"publisher","first-page":"5847","DOI":"10.1109\/TIT.2010.2068870","volume":"56","author":"X Nguyen","year":"2010","unstructured":"Nguyen, X., Wainwright, M.J., Jordan, M.I.: Estimating divergence functionals and the likelihood ratio by convex risk minimization. IEEE Trans. Inf. Theor. 56(11), 5847\u20135861 (2010)","journal-title":"IEEE Trans. Inf. Theor."},{"key":"9_CR34","unstructured":"Van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et al.: Conditional image generation with PixelCNN decoders. In: Advances in Neural Information Processing Systems, pp. 4790\u20134798 (2016)"},{"key":"9_CR35","unstructured":"van den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. arXiv preprint arXiv:1601.06759 (2016)"},{"key":"9_CR36","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"9_CR37","unstructured":"Parmar, N., et al.: Image transformer. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, PMLR, Stockholmsm\u00e4ssan, Stockholm Sweden, 10\u201315 July 2018, vol. 80, pp. 4055\u20134064 (2018)"},{"key":"9_CR38","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"9_CR39","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR40","unstructured":"Salimans, T., Karpathy, A., Chen, X., Kingma, D.P.: PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications. arXiv preprint arXiv:1701.05517 (2017)"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. arXiv preprint arXiv:1906.05849 (2019)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"9_CR42","unstructured":"Tschannen, M., Djolonga, J., Rubenstein, P.K., Gelly, S., Lucic, M.: On mutual information maximization for representation learning. arXiv preprint arXiv:1907.13625 (2019)"},{"key":"9_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Ssystems, pp. 5998\u20136008 (2017)"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"9_CR45","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58571-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:03:48Z","timestamp":1731024228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58571-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585709","9783030585716"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58571-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 November 2020","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":"Glasgow","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}