Sökning: onr:"swepub:oai:lup.lub.lu.se:632a92cc-920b-48d2-96d0-a523a8a2b1bc" > Volumetric bias in ...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 02832naa a2200325 4500 | |
001 | oai:lup.lub.lu.se:632a92cc-920b-48d2-96d0-a523a8a2b1bc | |
003 | SwePub | |
008 | 170213s2016 | |||||||||||000 ||eng| | |
024 | 7 | a https://lup.lub.lu.se/record/632a92cc-920b-48d2-96d0-a523a8a2b1bc2 URI |
024 | 7 | a https://doi.org/10.1109/ICCV.2015.2062 DOI |
040 | a (SwePub)lu | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a kon2 swepub-publicationtype |
072 | 7 | a ref2 swepub-contenttype |
100 | 1 | a Boykov, Yuriu University of Western Ontario4 aut |
245 | 1 0 | a Volumetric bias in segmentation and reconstruction : Secrets and solutions |
264 | 1 | c 2016 |
300 | a 9 s. | |
520 | a Many standard optimization methods for segmentation and reconstruction compute ML model estimates for ap- pearance or geometry of segments, e.g. Zhu-Yuille [23], Torr [20], Chan-Vese [6], GrabCut [18], Delong et al. [8]. We observe that the standard likelihood term in these formu- lations corresponds to a generalized probabilistic K-means energy. In learning it is well known that this energy has a strong bias to clusters of equal size [11], which we express as a penalty for KL divergence from a uniform distribution of cardinalities. However, this volumetric bias has been mostly ignored in computer vision. We demonstrate signif- icant artifacts in standard segmentation and reconstruction methods due to this bias. Moreover, we propose binary and multi-label optimization techniques that either (a) remove this bias or (b) replace it by a KL divergence term for any given target volume distribution. Our general ideas apply to continuous or discrete energy formulations in segmenta- tion, stereo, and other reconstruction problems. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Datorseende och robotik0 (SwePub)102072 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Computer Vision and Robotics0 (SwePub)102072 hsv//eng |
700 | 1 | a Isack, Hossamu University of Western Ontario4 aut |
700 | 1 | a Olsson, Carlu Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH4 aut0 (Swepub:lu)math-coo |
700 | 1 | a Ayed, Ismail Benu École de technologie supérieure ETS4 aut |
710 | 2 | a University of Western Ontariob Matematik LTH4 org |
773 | 0 | t Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015g 11-18-December-2015, s. 1769-1777q 11-18-December-2015<1769-1777z 9781467383912 |
856 | 4 | u http://dx.doi.org/10.1109/ICCV.2015.206y FULLTEXT |
856 | 4 8 | u https://lup.lub.lu.se/record/632a92cc-920b-48d2-96d0-a523a8a2b1bc |
856 | 4 8 | u https://doi.org/10.1109/ICCV.2015.206 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
Kopiera och spara länken för att återkomma till aktuell vy