SwePub - search: WFRF:(Boykov Yuri)

Enumeration	Reference	Cover	Find
1.	Boykov, Yuri, et al. (author) Volumetric bias in segmentation and reconstruction : Secrets and solutions 2016 In: Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. - 9781467383912 ; 11-18-December-2015, s. 1769-1777 Conference paper (peer-reviewed)abstract 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.

Boykov, Yuri, et al. (author)
Volumetric bias in segmentation and reconstruction : Secrets and solutions
2016
In: Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. - 9781467383912 ; 11-18-December-2015, s. 1769-1777
Conference paper (peer-reviewed)abstract
- 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.

Träfflista för sökning "WFRF:(Boykov Yuri) srt2:(2016)"