Cover Image

The assignment manifold: a smooth model for image labeling

We introduce a novel geometric approach to the image labeling problem. A general objective function is defined on a manifold of stochastic matrices, whose elements assign prior data that are given in any metric space, to observed image measurements. The corresponding Riemannian gradient flow entails...

Full description

Saved in:
Bibliographic Details
Main Authors: Åström, Freddie (Author) , Petra, Stefania (Author) , Schmitzer, Bernhard (Author) , Schnörr, Christoph (Author)
Format: Chapter/Article Conference Paper
Language:English
Published: 19 December 2016
In: 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops
Year: 2016, Pages: 963-971
DOI:10.1109/CVPRW.2016.124
Online Access:Resolving-System, Volltext: http://dx.doi.org/10.1109/CVPRW.2016.124
Verlag, Volltext: https://ieeexplore.ieee.org/document/7789614
Get full text
Author Notes:F. Åström, S. Petra, B. Schmitzer, C. Schnörr

MARC

LEADER 00000caa a2200000 c 4500
001 1585658308
003 DE-627
005 20220815082933.0
007 cr uuu---uuuuu
008 181218s2016 xx |||||o 00| ||eng c
024 7 |a 10.1109/CVPRW.2016.124  |2 doi 
035 |a (DE-627)1585658308 
035 |a (DE-576)515658308 
035 |a (DE-599)BSZ515658308 
035 |a (OCoLC)1341031014 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 28  |2 sdnb 
100 1 |a Åström, Freddie  |e VerfasserIn  |0 (DE-588)1153903539  |0 (DE-627)1015504132  |0 (DE-576)500624267  |4 aut 
245 1 4 |a The assignment manifold  |b a smooth model for image labeling  |c F. Åström, S. Petra, B. Schmitzer, C. Schnörr 
264 1 |c 19 December 2016 
300 |a 9 
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 18.12.2018 
520 |a We introduce a novel geometric approach to the image labeling problem. A general objective function is defined on a manifold of stochastic matrices, whose elements assign prior data that are given in any metric space, to observed image measurements. The corresponding Riemannian gradient flow entails a set of replicator equations, one for each data point, that are spatially coupled by geometric averaging on the manifold. Starting from uniform assignments at the barycenter as natural initialization, the flow terminates at some global maximum, each of which corresponds to an image labeling that uniquely assigns the prior data. No tuning parameters are involved, except for two parameters setting the spatial scale of geometric averaging and scaling globally the numerical range of features, respectively. Our geometric variational approach can be implemented with sparse interior-point numerics in terms of parallel multiplicative updates that converge efficiently. 
650 4 |a barycenter 
650 4 |a computational geometry 
650 4 |a Conferences 
650 4 |a general objective function 
650 4 |a geometric averaging spatial scale 
650 4 |a Geometry 
650 4 |a image labeling 
650 4 |a image measurements 
650 4 |a image texture 
650 4 |a Labeling 
650 4 |a Linear programming 
650 4 |a Manifolds 
650 4 |a matrix algebra 
650 4 |a Measurement 
650 4 |a numerical analysis 
650 4 |a numerical feature range 
650 4 |a Optimization 
650 4 |a replicator equations 
650 4 |a Riemannian gradientflow 
650 4 |a stochastic matrices 
700 1 |a Petra, Stefania  |e VerfasserIn  |0 (DE-588)1065905580  |0 (DE-627)816924961  |0 (DE-576)425560155  |4 aut 
700 1 |a Schmitzer, Bernhard  |e VerfasserIn  |0 (DE-588)1052204724  |0 (DE-627)787990426  |0 (DE-576)407956654  |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  |a IEEE Conference on Computer Vision and Pattern Recognition Workshops (29. : 2016 : Las Vegas, Nev.)  |t 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops  |d Piscataway, NJ : IEEE, 2016  |g (2016), Seite 963-971  |h 1 Online-Ressource (980 Seiten)  |w (DE-627)1658529588  |w (DE-576)515657344  |z 9781467388504  |7 nnam 
773 1 8 |g year:2016  |g pages:963-971  |g extent:9  |a The assignment manifold a smooth model for image labeling 
856 4 0 |u http://dx.doi.org/10.1109/CVPRW.2016.124  |x Resolving-System  |x Verlag  |3 Volltext 
856 4 0 |u https://ieeexplore.ieee.org/document/7789614  |x Verlag  |3 Volltext 
951 |a AR 
992 |a 20181218 
993 |a ConferencePaper 
994 |a 2016 
998 |g 1023033348  |a Schnörr, Christoph  |m 1023033348:Schnörr, Christoph  |d 110000  |d 110200  |d 110000  |d 110400  |d 700000  |d 708000  |e 110000PS1023033348  |e 110200PS1023033348  |e 110000PS1023033348  |e 110400PS1023033348  |e 700000PS1023033348  |e 708000PS1023033348  |k 0/110000/  |k 1/110000/110200/  |k 0/110000/  |k 1/110000/110400/  |k 0/700000/  |k 1/700000/708000/  |p 4  |y j 
998 |g 1052204724  |a Schmitzer, Bernhard  |m 1052204724:Schmitzer, Bernhard  |p 3 
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 2 
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 1  |x j 
999 |a KXP-PPN1585658308  |e 3038542695 
BIB |a Y 
JSO |a {"person":[{"role":"aut","given":"Freddie","family":"Åström","display":"Åström, Freddie"},{"family":"Petra","display":"Petra, Stefania","given":"Stefania","role":"aut"},{"given":"Bernhard","role":"aut","display":"Schmitzer, Bernhard","family":"Schmitzer"},{"role":"aut","given":"Christoph","display":"Schnörr, Christoph","family":"Schnörr"}],"language":["eng"],"note":["Gesehen am 18.12.2018"],"title":[{"title":"The assignment manifold","title_sort":"assignment manifold","subtitle":"a smooth model for image labeling"}],"origin":[{"dateIssuedKey":"2016","dateIssuedDisp":"19 December 2016"}],"type":{"media":"Online-Ressource","bibl":"chapter"},"recId":"1585658308","physDesc":[{"extent":"9 S."}],"name":{"displayForm":["F. Åström, S. Petra, B. Schmitzer, C. Schnörr"]},"id":{"doi":["10.1109/CVPRW.2016.124"],"eki":["1585658308"]},"relHost":[{"physDesc":[{"extent":"1 Online-Ressource (980 Seiten)"}],"recId":"1658529588","id":{"isbn":["9781467388504"],"eki":["1658529588"]},"corporate":[{"display":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (29., 2016, Las Vegas, Nev.)","role":"aut"},{"display":"Institute of Electrical and Electronics Engineers","role":"isb"}],"disp":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (29. : 2016 : Las Vegas, Nev.)29th IEEE Conference on Computer Vision and Pattern Recognition Workshops","title":[{"title":"29th IEEE Conference on Computer Vision and Pattern Recognition Workshops","subtitle":"proceedings : 26 June-1 July 2016, Las Vegas, Nevada","title_sort":"29th IEEE Conference on Computer Vision and Pattern Recognition Workshops"}],"origin":[{"dateIssuedDisp":"[2016]","publisherPlace":"Piscataway, NJ","publisher":"IEEE","dateIssuedKey":"2016"}],"titleAlt":[{"title":"CVPRW 2016"},{"title":"2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2016)"}],"type":{"bibl":"book","media":"Online-Ressource"},"part":{"text":"(2016), Seite 963-971","pages":"963-971","year":"2016","extent":"9"},"language":["eng"]}]} 
SRT |a ASTROEMFREASSIGNMENT1920 

Similar Items