Unsupervised data labeling on graphs by self-assignment flows
This paper extends the recently introduced assignment flow approach for supervised image labeling to unsupervised scenarios where no labels are given. The resulting self-assignment flow takes a pairwise data affinity matrix as input data and maximizes the correlation with a low-rank matrix that is p...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
2021
|
| In: |
Proceedings in applied mathematics and mechanics
Year: 2021, Jahrgang: 20, Heft: 1, Pages: 1-2 |
| ISSN: | 1617-7061 |
| DOI: | 10.1002/pamm.202000156 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1002/pamm.202000156 Verlag, kostenfrei, Volltext: https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.202000156 |
| Verfasserangaben: | Matthias Zisler, Artjom Zern, Bastian Boll, Stefania Petra, and Christoph Schnörr |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1770926712 | ||
| 003 | DE-627 | ||
| 005 | 20220208214309.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210918s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/pamm.202000156 |2 doi | |
| 035 | |a (DE-627)1770926712 | ||
| 035 | |a (DE-599)KXP1770926712 | ||
| 035 | |a (OCoLC)1295678908 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 27 |2 sdnb | ||
| 100 | 1 | |a Zisler, Matthias |d 1986- |e VerfasserIn |0 (DE-588)1154408760 |0 (DE-627)1015699901 |0 (DE-576)500933790 |4 aut | |
| 245 | 1 | 0 | |a Unsupervised data labeling on graphs by self-assignment flows |c Matthias Zisler, Artjom Zern, Bastian Boll, Stefania Petra, and Christoph Schnörr |
| 264 | 1 | |c 2021 | |
| 300 | |a 2 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a First published: 25 January 2021 | ||
| 500 | |a Gesehen am 18.09.2021 | ||
| 520 | |a This paper extends the recently introduced assignment flow approach for supervised image labeling to unsupervised scenarios where no labels are given. The resulting self-assignment flow takes a pairwise data affinity matrix as input data and maximizes the correlation with a low-rank matrix that is parametrized by the variables of the assignment flow, which entails an assignment of the data to themselves through the formation of latent labels (feature prototypes). A single user parameter, the neighborhood size for the geometric regularization of assignments, drives the entire process. By smooth geodesic interpolation between different normalizations of self-assignment matrices on the positive definite matrix manifold, a one-parameter family of self-assignment flows is defined. Accordingly, our approach can be characterized from different viewpoints, e.g. as performing spatially regularized, rank-constrained discrete optimal transport, or as computing spatially regularized normalized spectral cuts. Regarding combinatorial optimization, our approach successfully determines completely positive factorizations of self-assignments in large-scale scenarios, subject to spatial regularization. Various experiments including the unsupervised learning of patch dictionaries using a locally invariant distance function, illustrate the properties of the approach. | ||
| 700 | 1 | |a Zern, Artjom |d 1987- |e VerfasserIn |0 (DE-588)1216462747 |0 (DE-627)1727696050 |4 aut | |
| 700 | 1 | |a Boll, Bastian |d 1996- |e VerfasserIn |0 (DE-588)1241416443 |0 (DE-627)1770926682 |4 aut | |
| 700 | 1 | |a Petra, Stefania |e VerfasserIn |0 (DE-588)1065905580 |0 (DE-627)816924961 |0 (DE-576)425560155 |4 aut | |
| 700 | 1 | |a Schnörr, Christoph |e VerfasserIn |0 (DE-588)1023033348 |0 (DE-627)717351017 |0 (DE-576)168404540 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Proceedings in applied mathematics and mechanics |d Weinheim : Wiley-VCH, 2002 |g 20(2021), 1, Artikel-ID e202000156, Seite 1-2 |h Online-Ressource |w (DE-627)347754171 |w (DE-600)2078931-2 |w (DE-576)098842102 |x 1617-7061 |7 nnas |a Unsupervised data labeling on graphs by self-assignment flows |
| 773 | 1 | 8 | |g volume:20 |g year:2021 |g number:1 |g elocationid:e202000156 |g pages:1-2 |g extent:2 |a Unsupervised data labeling on graphs by self-assignment flows |
| 856 | 4 | 0 | |u https://doi.org/10.1002/pamm.202000156 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.202000156 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20210918 | ||
| 993 | |a Article | ||
| 994 | |a 2021 | ||
| 998 | |g 1023033348 |a Schnörr, Christoph |m 1023033348:Schnörr, Christoph |d 110000 |d 110200 |d 110000 |d 110400 |e 110000PS1023033348 |e 110200PS1023033348 |e 110000PS1023033348 |e 110400PS1023033348 |k 0/110000/ |k 1/110000/110200/ |k 0/110000/ |k 1/110000/110400/ |p 5 |y j | ||
| 998 | |g 1065905580 |a Petra, Stefania |m 1065905580:Petra, Stefania |d 110000 |d 110200 |d 110000 |d 110400 |e 110000PP1065905580 |e 110200PP1065905580 |e 110000PP1065905580 |e 110400PP1065905580 |k 0/110000/ |k 1/110000/110200/ |k 0/110000/ |k 1/110000/110400/ |p 4 | ||
| 998 | |g 1241416443 |a Boll, Bastian |m 1241416443:Boll, Bastian |d 700000 |d 708070 |e 700000PB1241416443 |e 708070PB1241416443 |k 0/700000/ |k 1/700000/708070/ |p 3 | ||
| 998 | |g 1216462747 |a Zern, Artjom |m 1216462747:Zern, Artjom |d 110000 |d 110200 |d 110000 |d 110400 |e 110000PZ1216462747 |e 110200PZ1216462747 |e 110000PZ1216462747 |e 110400PZ1216462747 |k 0/110000/ |k 1/110000/110200/ |k 0/110000/ |k 1/110000/110400/ |p 2 | ||
| 998 | |g 1154408760 |a Zisler, Matthias |m 1154408760:Zisler, Matthias |d 110000 |d 110200 |d 110000 |d 110400 |e 110000PZ1154408760 |e 110200PZ1154408760 |e 110000PZ1154408760 |e 110400PZ1154408760 |k 0/110000/ |k 1/110000/110200/ |k 0/110000/ |k 1/110000/110400/ |p 1 |x j | ||
| 999 | |a KXP-PPN1770926712 |e 397923178X | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"id":{"eki":["1770926712"],"doi":["10.1002/pamm.202000156"]},"relHost":[{"language":["eng"],"part":{"volume":"20","extent":"2","pages":"1-2","text":"20(2021), 1, Artikel-ID e202000156, Seite 1-2","year":"2021","issue":"1"},"origin":[{"dateIssuedDisp":"2002-","publisherPlace":"Weinheim","dateIssuedKey":"2002","publisher":"Wiley-VCH"}],"note":["Gesehen am 18.10.2019"],"type":{"bibl":"periodical","media":"Online-Ressource"},"titleAlt":[{"title":"PAMM"}],"title":[{"title_sort":"Proceedings in applied mathematics and mechanics","subtitle":"PAMM","title":"Proceedings in applied mathematics and mechanics"}],"disp":"Unsupervised data labeling on graphs by self-assignment flowsProceedings in applied mathematics and mechanics","id":{"doi":["10.1002/(ISSN)1617-7061"],"issn":["1617-7061"],"eki":["347754171"],"zdb":["2078931-2"]},"recId":"347754171","pubHistory":["1.2002 -"],"physDesc":[{"extent":"Online-Ressource"}]}],"recId":"1770926712","physDesc":[{"extent":"2 S."}],"name":{"displayForm":["Matthias Zisler, Artjom Zern, Bastian Boll, Stefania Petra, and Christoph Schnörr"]},"language":["eng"],"note":["First published: 25 January 2021","Gesehen am 18.09.2021"],"title":[{"title_sort":"Unsupervised data labeling on graphs by self-assignment flows","title":"Unsupervised data labeling on graphs by self-assignment flows"}],"origin":[{"dateIssuedDisp":"2021","dateIssuedKey":"2021"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"person":[{"given":"Matthias","role":"aut","family":"Zisler","display":"Zisler, Matthias"},{"role":"aut","given":"Artjom","display":"Zern, Artjom","family":"Zern"},{"role":"aut","given":"Bastian","display":"Boll, Bastian","family":"Boll"},{"display":"Petra, Stefania","family":"Petra","role":"aut","given":"Stefania"},{"display":"Schnörr, Christoph","family":"Schnörr","given":"Christoph","role":"aut"}]} | ||
| SRT | |a ZISLERMATTUNSUPERVIS2021 | ||