Graphical model parameter learning by inverse linear programming
We introduce two novel methods for learning parameters of graphical models for image labelling. The following two tasks underline both methods: (i) perturb model parameters based on given features and ground truth labelings, so as to exactly reproduce these labelings as optima of the local polytope...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
18 May 2017
|
| In: |
Scale Space and Variational Methods in Computer Vision
Year: 2017, Pages: 323-334 |
| DOI: | 10.1007/978-3-319-58771-4_26 |
| Subjects: | |
| Online Access: | Verlag, Volltext: http://dx.doi.org/10.1007/978-3-319-58771-4_26 Verlag, Volltext: https://link.springer.com/chapter/10.1007/978-3-319-58771-4_26 |
| Author Notes: | Vera Trajkovska, Paul Swoboda, Freddie Åström, Stefania Petra |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1571088431 | ||
| 003 | DE-627 | ||
| 005 | 20220814093235.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 180315s2017 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/978-3-319-58771-4_26 |2 doi | |
| 035 | |a (DE-627)1571088431 | ||
| 035 | |a (DE-576)501088431 | ||
| 035 | |a (DE-599)BSZ501088431 | ||
| 035 | |a (OCoLC)1340994316 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 27 |2 sdnb | ||
| 100 | 1 | |a Trajkovska, Vera |e VerfasserIn |0 (DE-588)115115086X |0 (DE-627)1011385104 |0 (DE-576)497515741 |4 aut | |
| 245 | 1 | 0 | |a Graphical model parameter learning by inverse linear programming |c Vera Trajkovska, Paul Swoboda, Freddie Åström, Stefania Petra |
| 264 | 1 | |c 18 May 2017 | |
| 300 | |a 12 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 15.03.2018 | ||
| 520 | |a We introduce two novel methods for learning parameters of graphical models for image labelling. The following two tasks underline both methods: (i) perturb model parameters based on given features and ground truth labelings, so as to exactly reproduce these labelings as optima of the local polytope relaxation of the labelling problem; (ii) train a predictor for the perturbed model parameters so that improved model parameters can be applied to the labelling of novel data. Our first method implements task (i) by inverse linear programming and task (ii) using a regressor e.g. a Gaussian process. Our second approach simultaneously solves tasks (i) and (ii) in a joint manner, while being restricted to linearly parameterised predictors. Experiments demonstrate the merits of both approaches. | ||
| 655 | 7 | |a Konferenzschrift |0 (DE-588)1071861417 |0 (DE-627)826484824 |0 (DE-576)433375485 |2 gnd-content | |
| 700 | 1 | |a Swoboda, Paul |e VerfasserIn |0 (DE-588)1066353379 |0 (DE-627)817351434 |0 (DE-576)425790231 |4 aut | |
| 700 | 1 | |a Åström, Freddie |e VerfasserIn |0 (DE-588)1153903539 |0 (DE-627)1015504132 |0 (DE-576)500624267 |4 aut | |
| 700 | 1 | |a Petra, Stefania |e VerfasserIn |0 (DE-588)1065905580 |0 (DE-627)816924961 |0 (DE-576)425560155 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Scale Space and Variational Methods in Computer Vision |d Cham : Springer, 2017 |g (2017), Seite 323-334 |h Online-Ressource (XV, 708 p. 244 illus, online resource) |w (DE-627)165910999X |w (DE-576)489629679 |z 9783319587714 |7 nnam |a Graphical model parameter learning by inverse linear programming |
| 773 | 1 | 8 | |g year:2017 |g pages:323-334 |g extent:12 |a Graphical model parameter learning by inverse linear programming |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1007/978-3-319-58771-4_26 |x Verlag |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u https://link.springer.com/chapter/10.1007/978-3-319-58771-4_26 |x Verlag |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20180315 | ||
| 993 | |a ConferencePaper | ||
| 994 | |a 2017 | ||
| 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 |y j | ||
| 998 | |g 1153903539 |a Åström, Freddie |m 1153903539:Åström, Freddie |d 700000 |d 708070 |e 700000PA1153903539 |e 708070PA1153903539 |k 0/700000/ |k 1/700000/708070/ |p 3 | ||
| 998 | |g 1066353379 |a Swoboda, Paul |m 1066353379:Swoboda, Paul |p 2 | ||
| 998 | |g 115115086X |a Trajkovska, Vera |m 115115086X:Trajkovska, Vera |d 700000 |d 708000 |e 700000PT115115086X |e 708000PT115115086X |k 0/700000/ |k 1/700000/708000/ |p 1 |x j | ||
| 999 | |a KXP-PPN1571088431 |e 3003441485 | ||
| BIB | |a Y | ||
| JSO | |a {"id":{"eki":["1571088431"],"doi":["10.1007/978-3-319-58771-4_26"]},"recId":"1571088431","name":{"displayForm":["Vera Trajkovska, Paul Swoboda, Freddie Åström, Stefania Petra"]},"type":{"bibl":"chapter","media":"Online-Ressource"},"person":[{"roleDisplay":"VerfasserIn","given":"Vera","display":"Trajkovska, Vera","family":"Trajkovska","role":"aut"},{"display":"Swoboda, Paul","roleDisplay":"VerfasserIn","given":"Paul","family":"Swoboda","role":"aut"},{"role":"aut","display":"Åström, Freddie","roleDisplay":"VerfasserIn","given":"Freddie","family":"Åström"},{"role":"aut","roleDisplay":"VerfasserIn","given":"Stefania","display":"Petra, Stefania","family":"Petra"}],"title":[{"title":"Graphical model parameter learning by inverse linear programming","title_sort":"Graphical model parameter learning by inverse linear programming"}],"origin":[{"dateIssuedDisp":"18 May 2017","dateIssuedKey":"2017"}],"relHost":[{"part":{"text":"(2017), Seite 323-334","extent":"12","pages":"323-334","year":"2017"},"person":[{"family":"Lauze","roleDisplay":"Hrsg.","given":"Francois","display":"Lauze, Francois","role":"edt"},{"given":"Yiqiu","roleDisplay":"Hrsg.","display":"Dong, Yiqiu","family":"Dong","role":"edt"},{"role":"edt","given":"Anders Bjorholm","roleDisplay":"Hrsg.","display":"Dahl, Anders Bjorholm","family":"Dahl"}],"type":{"media":"Online-Ressource","bibl":"edited-book"},"title":[{"title_sort":"Scale Space and Variational Methods in Computer Vision","subtitle":"6th International Conference, SSVM 2017, Kolding, Denmark, June 4-8, 2017, Proceedings","title":"Scale Space and Variational Methods in Computer Vision"}],"relMultPart":[{"pubHistory":["1.1973 -"],"id":{"issn":["1611-3349"],"eki":["316228877"],"zdb":["2018930-8"]},"recId":"316228877","title":[{"title_sort":"Lecture notes in computer science","title":"Lecture notes in computer science"}],"titleAlt":[{"title":"LNCS online"},{"title":"LNAI"},{"title":"Lecture notes in artificial intelligence"},{"title":"Lecture notes in bioinformatics"},{"title":"LNAI"},{"title":"LNBI"},{"title":"LNCS-LNAI"},{"title":"LNCS-LNBI"}],"type":{"media":"Online-Ressource","bibl":"serial"},"part":{"number_sort":["10302"],"number":["10302"]},"dispAlt":"Lecture notes in computer science","origin":[{"dateIssuedKey":"1973","dateIssuedDisp":"1973-","publisher":"Springer","publisherPlace":"Berlin ; Heidelberg"}],"disp":"Lecture Notes in Computer Science","language":["eng"],"note":["Gesehen am 28.02.20","Das Gesamtwerk gliedert sich in: Lecture notes in artificial intelligence; Lecture notes in bioinformatics"],"physDesc":[{"extent":"Online-Ressource"}]}],"recId":"165910999X","id":{"doi":["10.1007/978-3-319-58771-4"],"isbn":["9783319587714"],"eki":["165910999X"]},"name":{"displayForm":["edited by François Lauze, Yiqiu Dong, Anders Bjorholm Dahl"]},"physDesc":[{"extent":"Online-Ressource (XV, 708 p. 244 illus, online resource)"}],"language":["eng"],"disp":"Graphical model parameter learning by inverse linear programmingScale Space and Variational Methods in Computer Vision","origin":[{"dateIssuedDisp":"2017","publisher":"Springer","publisherPlace":"Cham","dateIssuedKey":"2017"}]}],"physDesc":[{"extent":"12 S."}],"note":["Gesehen am 15.03.2018"],"language":["eng"]} | ||
| SRT | |a TRAJKOVSKAGRAPHICALM1820 | ||