狠狠撸shows by User: rezoolab / http://www.slideshare.net/images/logo.gif 狠狠撸shows by User: rezoolab / Fri, 30 Jan 2015 11:47:49 GMT 狠狠撸Share feed for 狠狠撸shows by User: rezoolab 颁补蹿蹿别のデータレイヤで梦が広がる话 /slideshow/caffe/44082851 caffe-150130114749-conversion-gate02
颁补蹿蹿别のデータレイヤに手を加えることで，いろいろと可能性が広がる话をします闭闭>
颁补蹿蹿别のデータレイヤに手を加えることで，いろいろと可能性が広がる话をします闭闭> Fri, 30 Jan 2015 11:47:49 GMT /slideshow/caffe/44082851 rezoolab@slideshare.net(rezoolab) 颁补蹿蹿别のデータレイヤで梦が広がる话 rezoolab 颁补蹿蹿别のデータレイヤに手を加えることで，いろいろと可能性が広がる话をします <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/caffe-150130114749-conversion-gate02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 颁补蹿蹿别のデータレイヤに手を加えることで，いろいろと可能性が広がる话をします
颁补蹿蹿别のデータレイヤで梦が広がる话 from Masaki Saito
]]> 17388 7 https://cdn.slidesharecdn.com/ss_thumbnails/caffe-150130114749-conversion-gate02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space /slideshow/cvpr2013-07/24747123 cvpr201307-130729203733-phpapp01
This paper is concerned with the inference of marginal densities based on MRF models. The optimization algorithms for continuous variables are only applicable to a limited number of problems, whereas those for discrete variables are versatile. Thus, it is quite common to convert the continuous variables into discrete ones for the problems that ideally should be solved in the continuous domain, such as stereo matching and optical flow estimation. In this paper, we show a novel formulation for this continuous-discrete conversion. The key idea is to estimate the marginal densities in the continuous domain by approximating them with mixtures of rectangular densities. Based on this formulation, we derive a mean field (MF) algorithm and a belief propagation (BP) algorithm. These algorithms can correctly handle the case where the variable space is discretized in a non-uniform manner. By intentionally using such a non-uniform discretization, a higher balance between computational efficiency and accuracy of marginal density estimates could be achieved. We present a method for actually doing this, which dynamically discretizes the variable space in a coarse-to-fine manner in the course of the computation. Experimental results show the effectiveness of our approach.]]>
This paper is concerned with the inference of marginal densities based on MRF models. The optimization algorithms for continuous variables are only applicable to a limited number of problems, whereas those for discrete variables are versatile. Thus, it is quite common to convert the continuous variables into discrete ones for the problems that ideally should be solved in the continuous domain, such as stereo matching and optical flow estimation. In this paper, we show a novel formulation for this continuous-discrete conversion. The key idea is to estimate the marginal densities in the continuous domain by approximating them with mixtures of rectangular densities. Based on this formulation, we derive a mean field (MF) algorithm and a belief propagation (BP) algorithm. These algorithms can correctly handle the case where the variable space is discretized in a non-uniform manner. By intentionally using such a non-uniform discretization, a higher balance between computational efficiency and accuracy of marginal density estimates could be achieved. We present a method for actually doing this, which dynamically discretizes the variable space in a coarse-to-fine manner in the course of the computation. Experimental results show the effectiveness of our approach.]]> Mon, 29 Jul 2013 20:37:33 GMT /slideshow/cvpr2013-07/24747123 rezoolab@slideshare.net(rezoolab) Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space rezoolab This paper is concerned with the inference of marginal densities based on MRF models. The optimization algorithms for continuous variables are only applicable to a limited number of problems, whereas those for discrete variables are versatile. Thus, it is quite common to convert the continuous variables into discrete ones for the problems that ideally should be solved in the continuous domain, such as stereo matching and optical flow estimation. In this paper, we show a novel formulation for this continuous-discrete conversion. The key idea is to estimate the marginal densities in the continuous domain by approximating them with mixtures of rectangular densities. Based on this formulation, we derive a mean field (MF) algorithm and a belief propagation (BP) algorithm. These algorithms can correctly handle the case where the variable space is discretized in a non-uniform manner. By intentionally using such a non-uniform discretization, a higher balance between computational efficiency and accuracy of marginal density estimates could be achieved. We present a method for actually doing this, which dynamically discretizes the variable space in a coarse-to-fine manner in the course of the computation. Experimental results show the effectiveness of our approach. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cvpr201307-130729203733-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This paper is concerned with the inference of marginal densities based on MRF models. The optimization algorithms for continuous variables are only applicable to a limited number of problems, whereas those for discrete variables are versatile. Thus, it is quite common to convert the continuous variables into discrete ones for the problems that ideally should be solved in the continuous domain, such as stereo matching and optical flow estimation. In this paper, we show a novel formulation for this continuous-discrete conversion. The key idea is to estimate the marginal densities in the continuous domain by approximating them with mixtures of rectangular densities. Based on this formulation, we derive a mean field (MF) algorithm and a belief propagation (BP) algorithm. These algorithms can correctly handle the case where the variable space is discretized in a non-uniform manner. By intentionally using such a non-uniform discretization, a higher balance between computational efficiency and accuracy of marginal density estimates could be achieved. We present a method for actually doing this, which dynamically discretizes the variable space in a coarse-to-fine manner in the course of the computation. Experimental results show the effectiveness of our approach.
Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space from Masaki Saito
]]> 1985 3 https://cdn.slidesharecdn.com/ss_thumbnails/cvpr201307-130729203733-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 条件付き确率场の推论と学习 /slideshow/seminar-19715143/19715143 seminar-130423031651-phpapp01
]]>
]]> Tue, 23 Apr 2013 03:16:51 GMT /slideshow/seminar-19715143/19715143 rezoolab@slideshare.net(rezoolab) 条件付き确率场の推论と学习 rezoolab <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/seminar-130423031651-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
条件付き确率场の推论と学习 from Masaki Saito
]]> 54906 11 https://cdn.slidesharecdn.com/ss_thumbnails/seminar-130423031651-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://public.slidesharecdn.com/v2/images/profile-picture.png mglab.blogspot.jp/ https://cdn.slidesharecdn.com/ss_thumbnails/caffe-150130114749-conversion-gate02-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/caffe/44082851 颁补蹿蹿别のデータレイヤで梦が広がる话 https://cdn.slidesharecdn.com/ss_thumbnails/cvpr201307-130729203733-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/cvpr2013-07/24747123 Discrete MRF Inference... https://cdn.slidesharecdn.com/ss_thumbnails/seminar-130423031651-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/seminar-19715143/19715143 条件付き确率场の推论と学习