{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:07:47Z","timestamp":1778080067960,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609710","type":"print"},{"value":"9789819609727","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"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\/978-981-96-0972-7_21","type":"book-chapter","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T08:06:42Z","timestamp":1733731602000},"page":"359-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Graph Cut-Guided Maximal Coding Rate Reduction for\u00a0Learning Image Embedding and\u00a0Clustering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2222-8818","authenticated-orcid":false,"given":"Wei","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4047-3328","authenticated-orcid":false,"given":"Zhiyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4042-917X","authenticated-orcid":false,"given":"Xianghan","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8493-1966","authenticated-orcid":false,"given":"Xianbiao","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2207-5698","authenticated-orcid":false,"given":"Rong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5716-268X","authenticated-orcid":false,"given":"Chun-Guang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"21_CR1","unstructured":"Adaloglou, N., Michels, F., Kalisch, H., Kollmann, M.: Exploring the limits of deep image clustering using pretrained models. In: British Machine Vision Conference. pp. 297\u2013299. BMVA Press (2023)"},{"key":"21_CR2","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: Vicreg: Variance-invariance-covariance regularization for self-supervised learning. In: International Conference on Learning Representations (2022)"},{"issue":"8","key":"21_CR3","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2012.230","volume":"35","author":"J Bruna","year":"2013","unstructured":"Bruna, J., Mallat, S.: Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872\u20131886 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: IEEE\/CVF International Conference on Computer Vision. pp. 9630\u20139640. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"21_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning. vol.\u00a0119, pp. 1597\u20131607. PMLR (2020)"},{"key":"21_CR6","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, C.G., You, C.: Stochastic sparse subspace clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4155\u20134164 (2020)","DOI":"10.1109\/CVPR42600.2020.00421"},{"key":"21_CR8","unstructured":"Chu, T., Tong, S., Ding, T., Dai, X., Haeffele, B.D., Vidal, R., Ma, Y.: Image clustering via the principle of rate reduction in the age of pretrained models. In: International Conference on Learning Representations (2024)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition. pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21_CR10","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Ding, T., Tong, S., Chan, K.H.R., Dai, X., Ma, Y., Haeffele, B.D.: Unsupervised manifold linearizing and clustering. In: IEEE\/CVF International Conference on Computer Vision. pp. 5427\u20135438 (2023)","DOI":"10.1109\/ICCV51070.2023.00502"},{"key":"21_CR12","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (2021)"},{"key":"21_CR13","unstructured":"Grill, J., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.\u00c1., Guo, Z., Azar, M.G., Piot, B., Kavukcuoglu, K., Munos, R., Valko, M.: Bootstrap your own latent - A new approach to self-supervised learning. In: Advances in Neural Information Processing Systems (2020)"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15979\u201315988 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"21_CR16","unstructured":"He, W., Zhang, S., Li, C.G., Qi, X., Xiao, R., Guo, J.: Neural normalized cut: A differential and generalizable approach for spectral clustering. Submitted to Pattern Recognition (2024)"},{"issue":"6","key":"21_CR17","doi-asserted-by":"publisher","first-page":"7509","DOI":"10.1109\/TPAMI.2022.3216454","volume":"45","author":"Z Huang","year":"2022","unstructured":"Huang, Z., Chen, J., Zhang, J., Shan, H.: Learning representation for clustering via prototype scattering and positive sampling. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7509\u20137524 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"21_CR18","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. 31(3), 264\u2013323 (1999)","journal-title":"ACM Comput. Surv."},{"key":"21_CR19","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: 5th International Conference on Learning Representations (2017)"},{"key":"21_CR20","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Fei-Fei, L.: Novel dataset for fine-grained image categorization. In: IEEE Conference on Computer Vision and Pattern Recognition (2011)"},{"key":"21_CR21","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. In: Int. Conf. Learn. Represent. (2014)"},{"key":"21_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (2014)"},{"key":"21_CR23","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images. Technical Report TR-2009, University of Toronto, Toronto (2009)"},{"issue":"1\u20132","key":"21_CR24","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 research logistics quarterly 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval research logistics quarterly"},{"issue":"11","key":"21_CR25","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Hu, P., Liu, Z., Peng, D., Zhou, J.T., Peng, X.: Contrastive clustering. In: Proceedings of the AAAI conference on artificial intelligence (2021)","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"21_CR27","unstructured":"Li, Y., Hu, P., Peng, D., Lv, J., Fan, J., Peng, X.: Image clustering with external guidance. In: Proceedings of the International Conference on Machine Learning (2024)"},{"key":"21_CR28","unstructured":"Li, Z., Chen, Y., LeCun, Y., Sommer, F.T.: Neural manifold clustering and embedding. arXiv preprint arXiv:2201.10000 (2022)"},{"key":"21_CR29","unstructured":"Lim, D., Vidal, R., Haeffele, B.D.: Doubly stochastic subspace clustering. arXiv preprint arXiv:2011.14859 (2020)"},{"key":"21_CR30","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: Int. Conf. Learn. Represent. (2017)"},{"issue":"4","key":"21_CR31","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","volume":"17","author":"U von Luxburg","year":"2007","unstructured":"von Luxburg, U.: A tutorial on spectral clustering. Stat. Comput. 17(4), 395\u2013416 (2007)","journal-title":"Stat. Comput."},{"key":"21_CR32","unstructured":"MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. pp. 281\u2013297 (1967)"},{"key":"21_CR33","unstructured":"Nene, S.A., Nayar, S.K., Murase, H.: Columbia object image library (coil-100). Tech. Rep. CUCS-006-96, Department of Computer Science, Columbia University (February 1996)"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Nilsback, M., Zisserman, A.: Automated flower classification over a large number of classes. In: Sixth Indian Conference on Computer Vision, Graphics & Image Processing. pp. 722\u2013729. IEEE Computer Society (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"21_CR35","doi-asserted-by":"publisher","first-page":"7264","DOI":"10.1109\/TIP.2022.3221290","volume":"31","author":"C Niu","year":"2022","unstructured":"Niu, C., Shan, H., Wang, G.: SPICE: semantic pseudo-labeling for image clustering. IEEE Trans. Image Process. 31, 7264\u20137278 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109042","volume":"250","author":"F Ntelemis","year":"2022","unstructured":"Ntelemis, F., Jin, Y., Thomas, S.A.: Information maximization clustering via multi-view self-labelling. Knowl.-Based Syst. 250, 109042 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"21_CR37","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et\u00a0al.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Park, S., Han, S., Kim, S., Kim, D., Park, S., Hong, S., Cha, M.: Improving unsupervised image clustering with robust learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12278\u201312287 (2021)","DOI":"10.1109\/CVPR46437.2021.01210"},{"key":"21_CR39","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J., et\u00a0al.: Learning internal representations by error propagation. Parallel Distributed Processing pp. 318\u2013362 (1986)","DOI":"10.21236\/ADA164453"},{"issue":"8","key":"21_CR41","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888\u2013905 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Souvenir, R., Pless, R.: Manifold clustering. In: IEEE\/CVF International Conference on Computer Vision. pp. 648\u2013653 (2005)","DOI":"10.1109\/ICCV.2005.149"},{"key":"21_CR43","unstructured":"Tsai, T.W., Li, C., Zhu, J.: Mice: Mixture of contrastive experts for unsupervised image clustering. In: Proceedings of the International Conference on Learning Representations (2021)"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Georgoulis, S., Proesmans, M., Van\u00a0Gool, L.: Scan: Learning to classify images without labels. In: European Conference on Computer Vision. pp. 268\u2013285 (2020)","DOI":"10.1007\/978-3-030-58607-2_16"},{"issue":"3","key":"21_CR45","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/MSP.2010.939739","volume":"28","author":"R Vidal","year":"2011","unstructured":"Vidal, R.: Subspace clustering. IEEE Signal Process. Mag. 28(3), 52\u201368 (2011)","journal-title":"IEEE Signal Process. Mag."},{"key":"21_CR46","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv: 1708.07747 (2019)"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"You, C., Li, C.G., Robinson, D.P., Vidal, R.: Oracle based active set algorithm for scalable elastic net subspace clustering. In: IEEE Conference on Computer Vision and Pattern Recognition. pp. 3928\u20133937 (2016)","DOI":"10.1109\/CVPR.2016.426"},{"key":"21_CR48","unstructured":"Yu, Y., Chan, K.H.R., You, C., Song, C., Ma, Y.: Learning diverse and discriminative representations via the principle of maximal coding rate reduction. In: Advances in Neural Information Processing Systems. pp. 9422\u20139434 (2020)"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Zhong, H., Wu, J., Chen, C., Huang, J., Deng, M., Nie, L., Lin, Z., Hua, X.S.: Graph contrastive clustering. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 9224\u20139233 (2021)","DOI":"10.1109\/ICCV48922.2021.00909"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0972-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T09:09:53Z","timestamp":1733735393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0972-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"ISBN":["9789819609710","9789819609727"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0972-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"10 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","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":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}