{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:39:12Z","timestamp":1792543152925,"version":"4.5.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198175","type":"print"},{"value":"9783031198182","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19818-2_5","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T12:21:10Z","timestamp":1666354870000},"page":"73-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["TransFGU: A Top-Down Approach to\u00a0Fine-Grained Unsupervised Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Zhaoyuan","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianzhe","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanling","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Zhu, P., Mitra, N., Wonka, P.: Labels4Free: unsupervised segmentation using StyleGAN. arXiv preprint arXiv:2103.14968 (2021)","DOI":"10.1109\/ICCV48922.2021.01371"},{"key":"5_CR2","unstructured":"Bielski, A., Favaro, P.: Emergence of object segmentation in perturbed generative models. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp. 7256\u20137266 (2019)"},{"key":"5_CR3","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"5_CR6","unstructured":"Chen, M., Arti\u00e8res, T., Denoyer, L.: Unsupervised object segmentation by redrawing. In: Advances in Neural Information Processing Systems 32 (NIPS 2019), pp. 12705\u201312716. Curran Associates, Inc. (2019)"},{"key":"5_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"5_CR8","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"5_CR10","unstructured":"Cho, J.H., Mall, U., Bala, K., Hariharan, B.: PiCIE: unsupervised semantic segmentation using invariance and equivariance in clustering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16794\u201316804 (2021)"},{"key":"5_CR11","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":"5_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"2","key":"5_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Zhang, D., Shen, X., Lin, L.: Look into person: self-supervised structure-sensitive learning and a new benchmark for human parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 932\u2013940 (2017)","DOI":"10.1109\/CVPR.2017.715"},{"key":"5_CR15","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: Neural Information Processing Systems (2020)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Harb, R., Kn\u00f6belreiter, P.: InfoSeg: unsupervised semantic image segmentation with mutual information maximization (2021)","DOI":"10.1007\/978-3-030-92659-5_2"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Hwang, J.J., et al.: SegSort: segmentation by discriminative sorting of segments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7334\u20137344 (2019)","DOI":"10.1109\/ICCV.2019.00743"},{"key":"5_CR20","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\/CVF International Conference on Computer Vision, pp. 9865\u20139874 (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"5_CR21","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"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Kim, D., Hong, B.W.: Unsupervised segmentation incorporating shape prior via generative adversarial networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7324\u20137334 (2021)","DOI":"10.1109\/ICCV48922.2021.00723"},{"key":"5_CR23","doi-asserted-by":"publisher","first-page":"8055","DOI":"10.1109\/TIP.2020.3011269","volume":"29","author":"W Kim","year":"2020","unstructured":"Kim, W., Kanezaki, A., Tanaka, M.: Unsupervised learning of image segmentation based on differentiable feature clustering. IEEE Trans. Image Process. 29, 8055\u20138068 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"5_CR24","unstructured":"Li, C., et al.: Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785 (2021)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Dense semantic contrast for self-supervised visual representation learning. arXiv preprint arXiv:2109.07756 (2021)","DOI":"10.1145\/3474085.3475551"},{"key":"5_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"5_CR27","unstructured":"Liu, Y., Guo, H.: Peer loss functions: learning from noisy labels without knowing noise rates. In: International Conference on Machine Learning, pp. 6226\u20136236. PMLR (2020)"},{"issue":"4","key":"5_CR28","doi-asserted-by":"publisher","first-page":"6931","DOI":"10.1109\/LRA.2021.3095311","volume":"6","author":"SE Mirsadeghi","year":"2021","unstructured":"Mirsadeghi, S.E., Royat, A., Rezatofighi, H.: Unsupervised image segmentation by mutual information maximization and adversarial regularization. IEEE Robot. Autom. Lett. 6(4), 6931\u20136938 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"5_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-58571-6_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Ouali","year":"2020","unstructured":"Ouali, Y., Hudelot, C., Tami, M.: Autoregressive unsupervised image segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 142\u2013158. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_9"},{"key":"5_CR30","unstructured":"Pinheiro, P.O., Almahairi, A., Benmalek, R.Y., Golemo, F., Courville, A.C.: Unsupervised learning of dense visual representations. In: NeurIPS (2020)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Shi, X., Khademi, S., Li, Y., van Gemert, J.: Zoom-cam: generating fine-grained pixel annotations from image labels. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10289\u201310296. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412980"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Van Gool, L.: Unsupervised semantic segmentation by contrasting object mask proposals. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3024\u20133033 (2021)","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Exploring set similarity for dense self-supervised representation learning. arXiv preprint arXiv:2107.08712 (2021)","DOI":"10.1109\/CVPR52688.2022.01609"},{"key":"5_CR37","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16684\u201316693 (2021)","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Xu, J., Wang, X.: Rethinking self-supervised correspondence learning: a video frame-level similarity perspective. arXiv preprint arXiv:2103.17263 (2021)","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Yao, Z., Cao, Y., Lin, Y., Liu, Z., Zhang, Z., Hu, H.: Leveraging batch normalization for vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 413\u2013422 (2021)","DOI":"10.1109\/ICCVW54120.2021.00050"},{"key":"5_CR40","unstructured":"Zou, Y., et al.: PseudoSeg: designing pseudo labels for semantic segmentation. In: International Conference on Learning Representations (ICLR) (2021)"}],"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\/978-3-031-19818-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:10:46Z","timestamp":1792541446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-19818-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198175","9783031198182"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19818-2_5","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":"22 October 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}