{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:43:35Z","timestamp":1777657415937,"version":"3.51.4"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T00:00:00Z","timestamp":1719878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T00:00:00Z","timestamp":1719878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005306","name":"Alfried Krupp von Bohlen und Halbach-Stiftung","doi-asserted-by":"crossref","award":["http:\/\/dx.doi.org\/10.13039\/501100005306"],"award-info":[{"award-number":["http:\/\/dx.doi.org\/10.13039\/501100005306"]}],"id":[{"id":"10.13039\/501100005306","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Appl. and Comput. Topology"],"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The magnitude of a finite metric space has recently emerged as a novel invariant quantity, allowing to measure the <jats:italic>effective size<\/jats:italic> of a metric space. Despite encouraging first results demonstrating the descriptive abilities of the magnitude, such as being able to detect the boundary of a metric space, the potential use cases of magnitude remain under-explored. In this work, we investigate the properties of the magnitude on images, an important data modality in many machine learning applications. By endowing each individual image with its own metric space, we are able to define the concept of magnitude on images and analyse the individual contribution of each pixel with the magnitude vector. In particular, we theoretically show that the previously known properties of boundary detection translate to edge detection abilities in images. Furthermore, we demonstrate practical use cases of magnitude for machine learning applications and propose a novel magnitude <jats:italic>model<\/jats:italic> that consists of a computationally efficient magnitude computation and a learnable metric. By doing so, we address one computational hurdle that used to make magnitude impractical for many applications and open the way for the adoption of magnitude in machine learning research.\n<\/jats:p>","DOI":"10.1007\/s41468-024-00182-9","type":"journal-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T15:21:21Z","timestamp":1719933681000},"page":"447-473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The magnitude vector of images"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-7167","authenticated-orcid":false,"given":"Michael F.","family":"Adamer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"De Brouwer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leslie","family":"O\u2019Bray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Rieck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,2]]},"reference":[{"key":"182_CR1","doi-asserted-by":"publisher","unstructured":"Alman, J., Williams, V.V.: A refined laser method and faster matrix multiplication (2021). https:\/\/doi.org\/10.1137\/1.9781611976465.32","DOI":"10.1137\/1.9781611976465.32"},{"key":"182_CR2","unstructured":"Bunch, E., Kline, J., Dickinson, D., Bhat, S., Fung, G.: Weighting vectors for machine learning: numerical harmonic analysis applied to boundary detection. arXiv preprint arXiv:2106.00827 (2021)"},{"key":"182_CR3","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"6","author":"J Canny","year":"1986","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679\u2013698 (1986)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"182_CR4","doi-asserted-by":"crossref","unstructured":"Ge, W.: Deep metric learning with hierarchical triplet loss. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 269\u2013285 (2018)","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"182_CR5","doi-asserted-by":"crossref","unstructured":"Hoffer, Elad, Ailon, Nir: Deep metric learning using triplet network. In: International Workshop on Similarity-based Pattern Recognition, pp. 84\u201392. Springer (2015)","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"182_CR6","unstructured":"Hu, X., Li, F., Samaras, D., Chen, C.: Topology-preserving deep image segmentation. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"182_CR7","doi-asserted-by":"crossref","unstructured":"Huan, L., Xue, N., Zheng, X., He, W., Gong, J., Xia, G.S.: Unmixing convolutional features for crisp edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6602\u20136609 (2022)","DOI":"10.1109\/TPAMI.2021.3084197"},{"issue":"9","key":"182_CR8","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.3390\/sym11091066","volume":"11","author":"M Kaya","year":"2019","unstructured":"Kaya, M., Bilge, H.\u015e: Deep metric learning: a survey. Symmetry 11(9), 1066 (2019)","journal-title":"Symmetry"},{"key":"182_CR9","doi-asserted-by":"crossref","unstructured":"Leinster, T., Meckes, M.W.: The magnitude of a metric space: from category theory to geometric measure theory. In: Gigli, N. (ed.) Measure Theory in Non-Smooth Spaces, pp. 156\u2013193. De Gruyter Open Poland (2017)","DOI":"10.1515\/9783110550832-005"},{"key":"182_CR10","doi-asserted-by":"publisher","first-page":"857","DOI":"10.4171\/DM\/415","volume":"18","author":"T Leinster","year":"2013","unstructured":"Leinster, T.: The magnitude of metric spaces. Doc. Math. 18, 857\u2013905 (2013). https:\/\/doi.org\/10.4171\/DM\/415","journal-title":"Doc. Math."},{"key":"182_CR11","doi-asserted-by":"crossref","unstructured":"Malik, J., Perona, P.: Finding boundaries in images. In: Neural Networks for Perception, pp. 315\u2013344. Elsevier (1992)","DOI":"10.1016\/B978-0-12-741251-1.50023-0"},{"key":"182_CR12","unstructured":"Poma, X.S., Riba, E., Sappa, A.: Dense extreme inception network: towards a robust CNN model for edge detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1923\u20131932 (2020)"},{"key":"182_CR13","doi-asserted-by":"publisher","unstructured":"Rieck, B., Sadlo, F., Leitte, H.: Topological machine learning with persistence indicator functions. In: Carr, H., Fujishiro, I., Sadlo, F., Takahashi, S. (eds.) Topological Methods in Data Analysis and Visualization\u00a0V, pp. 87\u2013101. Springer, Cham (2020). ISBN 978-3-030-43036-8. https:\/\/doi.org\/10.1007\/978-3-030-43036-8_6","DOI":"10.1007\/978-3-030-43036-8_6"},{"key":"182_CR14","first-page":"6900","volume":"33","author":"B Rieck","year":"2020","unstructured":"Rieck, B., Yates, T., Bock, C., Borgwardt, K., Wolf, G., Turk-Browne, N., Krishnaswamy, S.: Uncovering the topology of time-varying fMRI data using cubical persistence. Adv. Neural Inf. Process. Syst. 33, 6900\u20136912 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"182_CR15","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/ICCEA.2010.192","volume":"2","author":"C Saravanan","year":"2010","unstructured":"Saravanan, C.: Color image to grayscale image conversion. Sec. Int. Confer. Comput. Eng. Appl. 2, 196\u2013199 (2010). https:\/\/doi.org\/10.1109\/ICCEA.2010.192","journal-title":"Sec. Int. Confer. Comput. Eng. Appl."},{"key":"182_CR16","doi-asserted-by":"publisher","unstructured":"Sobel, I., Feldman, G.: An Isotropic 3x3 Image Gradient Operator (2015). https:\/\/doi.org\/10.13140\/RG.2.1.1912.4965","DOI":"10.13140\/RG.2.1.1912.4965"},{"issue":"2","key":"182_CR17","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/BF02426650","volume":"1","author":"AR Solow","year":"1994","unstructured":"Solow, A.R., Polasky, S.: Measuring biological diversity. Environ. Ecol. Stat. 1(2), 95\u2013103 (1994). https:\/\/doi.org\/10.1007\/BF02426650","journal-title":"Environ. Ecol. Stat."},{"issue":"1","key":"182_CR18","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s10711-013-9831-8","volume":"168","author":"S Willerton","year":"2014","unstructured":"Willerton, S.: On the magnitude of spheres, surfaces and other homogeneous spaces. Geom. Dedic. 168(1), 291\u2013310 (2014)","journal-title":"Geom. Dedic."}],"container-title":["Journal of Applied and Computational Topology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41468-024-00182-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41468-024-00182-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41468-024-00182-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T15:10:12Z","timestamp":1726845012000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41468-024-00182-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,2]]},"references-count":18,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["182"],"URL":"https:\/\/doi.org\/10.1007\/s41468-024-00182-9","relation":{},"ISSN":["2367-1726","2367-1734"],"issn-type":[{"value":"2367-1726","type":"print"},{"value":"2367-1734","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,2]]},"assertion":[{"value":"30 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}