{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T07:21:13Z","timestamp":1773645673366,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T00:00:00Z","timestamp":1738800000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X019918\/1"],"award-info":[{"award-number":["EP\/X019918\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X019918\/1"],"award-info":[{"award-number":["EP\/X019918\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/X019918\/1"],"award-info":[{"award-number":["EP\/X019918\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002462","name":"Chungnam National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002462","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Learning meaningful representations of images in scientific domains that are robust to variations in centroids and orientations remains an important challenge. Here we introduce centroid- and orientation-aware disentangling autoencoder (CODAE), an encoder\u2013decoder-based neural network that learns meaningful content of objects in a latent space. Specifically, a combination of a translation- and rotation-equivariant encoder, Euler encoding and an image moment loss enables CODAE to extract features invariant to positions and orientations of objects of interest from randomly translated and rotated images. We evaluate this approach on several publicly available scientific datasets, including protein images from life sciences, four-dimensional scanning transmission electron microscopy data from material science and galaxy images from astronomy. The evaluation shows that CODAE learns centroids, orientations and their invariant features and outputs, as well as aligned reconstructions and the exact view reconstructions of the input images with high quality.<\/jats:p>","DOI":"10.1038\/s42256-024-00978-5","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T10:03:07Z","timestamp":1738836187000},"page":"307-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Discovering fully semantic representations via centroid- and orientation-aware feature learning"],"prefix":"10.1038","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2498-4214","authenticated-orcid":false,"given":"Jaehoon","family":"Cha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhae","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Pinilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle L.","family":"Morris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher S.","family":"Allen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2753-7890","authenticated-orcid":false,"given":"Mark I.","family":"Wilkinson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2167-1343","authenticated-orcid":false,"given":"Jeyan","family":"Thiyagalingam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"key":"978_CR1","unstructured":"Bepler, T., Zhong, E., Kelley, K., Brignole, E. & Berger, B. Explicitly disentangling image content from translation and rotation with spatial-VAE. In Advances in Neural Information Processing Systems (eds Wallach, H. et al.) 15435\u201315445 (Curran Associates, Inc., 2019)."},{"key":"978_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-021-00527-3","volume":"7","author":"MP Oxley","year":"2021","unstructured":"Oxley, M. P. et al. Probing atomic-scale symmetry breaking by rotationally invariant machine learning of multidimensional electron scattering. npj Comput. Mater. 7, 65 (2021).","journal-title":"npj Comput. Mater."},{"key":"978_CR3","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1093\/mnras\/stv632","volume":"450","author":"S Dieleman","year":"2015","unstructured":"Dieleman, S., Willett, K. W. & Dambre, J. Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon. Not. R. Astron. Soc. 450, 1441\u20131459 (2015).","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"978_CR4","first-page":"1","volume":"20","author":"A Bietti","year":"2019","unstructured":"Bietti, A. & Mairal, J. Group invariance, stability to deformations, and complexity of deep convolutional representations. J. Mach. Learn. Res. 20, 1\u201349 (2019).","journal-title":"J. Mach. Learn. Res."},{"key":"978_CR5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data 6, 60 (2019).","journal-title":"J. Big Data"},{"key":"978_CR6","unstructured":"Higgins, I. et al. beta-vae: learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations (ICLR, 2017)."},{"key":"978_CR7","unstructured":"Cha, J. & Thiyagalingam, J. Orthogonality-enforced latent space in autoencoders: an approach to learning disentangled representations. In International Conference on Machine Learning (eds Krause, A. et al.) 3913\u20133948 (PMLR, 2023)."},{"key":"978_CR8","unstructured":"Higgins, I. et al. Towards a definition of disentangled representations. Preprint at https:\/\/arxiv.org\/abs\/1812.02230 (2018)."},{"key":"978_CR9","unstructured":"Tonnaer, L., Perez Rey, L.A., Menkovski, V., Holenderski, M., & Portegies, J. Quantifying and learning linear symmetry-based disentanglement. In International Conference on Machine Learning (eds Chaudhuri, K. et al.) 21584\u201321608 (PMLR, 2022)."},{"key":"978_CR10","first-page":"15255","volume":"35","author":"A Nasiri","year":"2022","unstructured":"Nasiri, A. & Bepler, T. Unsupervised object representation learning using translation and rotation group equivariant vae. Adv. Neur. Inf. Process. Syst. 35, 15255\u201315267 (2022).","journal-title":"Adv. Neur. Inf. Process. Syst."},{"key":"978_CR11","unstructured":"Kwon, S., Choi, J. Y. & Ryu, E. K. Rotation and translation invariant representation learning with implicit neural representations. In International Conference on Machine Learning (eds Krause, A. et al.) 18037\u201318056 (PMLR, 2023)."},{"key":"978_CR12","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1109\/TIT.1962.1057692","volume":"8","author":"M-K Visual","year":"1962","unstructured":"Visual, M.-K. Visual pattern recognition by moment invariants. IRE Trans. Inf. Theory 8, 179\u2013187 (1962).","journal-title":"IRE Trans. Inf. Theory"},{"key":"978_CR13","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/1049-9652(92)90027-U","volume":"54","author":"RJ Prokop","year":"1992","unstructured":"Prokop, R. J. & Reeves, A. P. A survey of moment-based techniques for unoccluded object representation and recognition. CVGIP Graph. Models Image Process. 54, 438\u2013460 (1992).","journal-title":"CVGIP Graph. Models Image Process."},{"key":"978_CR14","unstructured":"Flusser, J. Moment invariants in image analysis. Proceedings of World Academy of Science, Engineering and Technology 11, 196\u2013201 (2006)"},{"key":"978_CR15","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/MSP.2019.2957822","volume":"37","author":"T Bendory","year":"2020","unstructured":"Bendory, T., Bartesaghi, A. & Singer, A. Single-particle cryo-electron microscopy: mathematical theory, computational challenges, and opportunities. IEEE Signal Process. Mag. 37, 58\u201376 (2020).","journal-title":"IEEE Signal Process. Mag."},{"key":"978_CR16","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.ultramic.2018.03.004","volume":"188","author":"W Xu","year":"2018","unstructured":"Xu, W. & LeBeau, J. M. A deep convolutional neural network to analyze position averaged convergent beam electron diffraction patterns. Ultramicroscopy 188, 59\u201369 (2018).","journal-title":"Ultramicroscopy"},{"key":"978_CR17","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1111\/j.1365-2966.2008.13689.x","volume":"389","author":"CJ Lintott","year":"2008","unstructured":"Lintott, C. J. et al. Galaxy Zoo: morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey. Mon. Not. R. Astron. Soc. 389, 1179\u20131189 (2008).","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"978_CR18","doi-asserted-by":"publisher","first-page":"3966","DOI":"10.1093\/mnras\/stab2093","volume":"509","author":"M Walmsley","year":"2022","unstructured":"Walmsley, M. et al. Galaxy Zoo DECaLS: detailed visual morphology measurements from volunteers and deep learning for 314 000 galaxies. Mon. Not. R. Astron. Soc. 509, 3966\u20133988 (2022).","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"978_CR19","unstructured":"Matthey, L., Higgins, I., Hassabis, D. & Lerchner, A. dsprites: disentanglement testing sprites dataset. GitHub https:\/\/github.com\/deepmind\/dsprites-dataset\/ (2017)."},{"key":"978_CR20","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1017\/S1431927619000497","volume":"25","author":"C Ophus","year":"2019","unstructured":"Ophus, C. Four-dimensional scanning transmission electron microscopy (4D-STEM): from scanning nanodiffraction to ptychography and beyond. Microsc. Microanal. 25, 563\u2013582 (2019).","journal-title":"Microsc. Microanal."},{"key":"978_CR21","doi-asserted-by":"crossref","unstructured":"Abell, P. A. et al. LSST Science Book, Version 2.0 (2009).","DOI":"10.2172\/1156415"},{"key":"978_CR22","doi-asserted-by":"publisher","first-page":"D1503","DOI":"10.1093\/nar\/gkac1062","volume":"51","author":"A Iudin","year":"2023","unstructured":"Iudin, A. et al. EMPIAR: the electron microscopy public image archive. Nucleic Acids Res. 51, D1503\u2013D1511 (2023).","journal-title":"Nucleic Acids Res."},{"key":"978_CR23","unstructured":"Cesa, G., Lang, L. & Weiler, M. A program to build E (N)-equivariant steerable CNNs. In International Conference on Learning Representations (ICLR, 2022)."},{"key":"978_CR24","doi-asserted-by":"crossref","unstructured":"Carbonneau, M.-A, Zaidi, J., Boilard, J. & Gagnon, G. Measuring disentanglement: a review of metrics. In IEEE Transactions on Neural Networks and Learning Systems. 35, 8747\u20138761 (2022).","DOI":"10.1109\/TNNLS.2022.3218982"},{"key":"978_CR25","unstructured":"Kim, H. & Mnih, A. Disentangling by factorising. In International Conference on Machine Learning (eds Dy, J. & Krause, A.) 2649\u20132658 (PMLR, 2018)."},{"key":"978_CR26","unstructured":"Suter, R., Miladinovic, D., Sch\u00f6lkopf, B. & Bauer, S. Robustly disentangled causal mechanisms: validating deep representations for interventional robustness. In International Conference on Machine Learning (eds Chaudhuri, K. & Salakhutdinov, R.) 6056\u20136065 (PMLR, 2019)."},{"key":"978_CR27","unstructured":"Eastwood, C. & Williams, C. K. I. A framework for the quantitative evaluation of disentangled representations. In International Conference on Learning Representations (ICLR, 2018)."},{"key":"978_CR28","unstructured":"Kumar, A., Sattigeri, P. & Balakrishnan, A. Variational inference of disentangled latent concepts from unlabeled observations. In International Conference on Learning Representations (ICLR, 2018)."},{"key":"978_CR29","unstructured":"Chen, R. T. Q., Li, X., Grosse, R. B. & Duvenaud, D. K. Isolating sources of disentanglement in variational autoencoders. In Advances in Neural Information Processing Systems (eds Bengio, S. et al.) 2610\u20132620 (Curran Associates, Inc., 2018)."},{"key":"978_CR30","unstructured":"Do, K. & Tran, T. Theory and evaluation metrics for learning disentangled representations. In International Conference on Learning Representations (ICLR, 2020)."},{"key":"978_CR31","unstructured":"Sepliarskaia, A., Kiseleva, J. & de Rijke, M. Evaluating disentangled representations. Preprint at https:\/\/arxiv.org\/abs\/1910.05587v1 (2019)."},{"key":"978_CR32","doi-asserted-by":"publisher","unstructured":"Cha, J. Discovering fully semantic representations via centroid- and orientation-aware feature learning. Code Ocean https:\/\/doi.org\/10.24433\/CO.2120714.v1 (2024).","DOI":"10.24433\/CO.2120714.v1"},{"key":"978_CR33","unstructured":"Cohen, T. & Welling, M. Group equivariant convolutional networks. In International Conference on Machine Learning (eds Balcan, M. F. & Weinberger, K. Q.) 2990\u20132999 (PMLR, 2016)."},{"key":"978_CR34","unstructured":"Burgess, C. P. et al. Understanding disentangling in \u03b2-VAE. Preprint at https:\/\/arxiv.org\/abs\/1804.03599 (2018)."}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00978-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00978-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00978-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T09:43:01Z","timestamp":1747302181000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00978-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["978"],"URL":"https:\/\/doi.org\/10.1038\/s42256-024-00978-5","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,6]]},"assertion":[{"value":"11 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Since the version of the article initially published, in the Acknowledgements section, the text \"STFC Facilities Fund\" has been amended to \"the STFC Facilities Fund through the Ada Lovelace Centre\" in the HTML and PDF versions of the article.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}