Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Miguel A. Gonzalez-Ballester

Efficient Column Generation for Cell Detection and Segmentation

Sep 21, 2017
Chong Zhang, Shaofei Wang, Miguel A. Gonzalez-Ballester, Julian Yarkony

Figure 1 for Efficient Column Generation for Cell Detection and Segmentation

Figure 2 for Efficient Column Generation for Cell Detection and Segmentation

Figure 3 for Efficient Column Generation for Cell Detection and Segmentation

Figure 4 for Efficient Column Generation for Cell Detection and Segmentation

We study the problem of instance segmentation in biological images with crowded and compact cells. We formulate this task as an integer program where variables correspond to cells and constraints enforce that cells do not overlap. To solve this integer program, we propose a column generation formulation where the pricing program is solved via exact optimization of very small scale integer programs. Column generation is tightened using odd set inequalities which fit elegantly into pricing problem optimization. Our column generation approach achieves fast stable anytime inference for our instance segmentation problems. We demonstrate on three distinct light microscopy datasets, with several hundred cells each, that our proposed algorithm rapidly achieves or exceeds state of the art accuracy.

Via

Access Paper or Ask Questions

Multi-Person Pose Estimation via Column Generation

Sep 18, 2017
Shaofei Wang, Chong Zhang, Miguel A. Gonzalez-Ballester, Alexander Ihler, Julian Yarkony

Figure 1 for Multi-Person Pose Estimation via Column Generation

Figure 2 for Multi-Person Pose Estimation via Column Generation

Figure 3 for Multi-Person Pose Estimation via Column Generation

Figure 4 for Multi-Person Pose Estimation via Column Generation

We study the problem of multi-person pose estimation in natural images. A pose estimate describes the spatial position and identity (head, foot, knee, etc.) of every non-occluded body part of a person. Pose estimation is difficult due to issues such as deformation and variation in body configurations and occlusion of parts, while multi-person settings add complications such as an unknown number of people, with unknown appearance and possible interactions in their poses and part locations. We give a novel integer program formulation of the multi-person pose estimation problem, in which variables correspond to assignments of parts in the image to poses in a two-tier, hierarchical way. This enables us to develop an efficient custom optimization procedure based on column generation, where columns are produced by exact optimization of very small scale integer programs. We demonstrate improved accuracy and speed for our method on the MPII multi-person pose estimation benchmark.

Via

Access Paper or Ask Questions

Efficient Pose and Cell Segmentation using Column Generation

Dec 01, 2016
Shaofei Wang, Chong Zhang, Miguel A. Gonzalez-Ballester, Julian Yarkony

Figure 1 for Efficient Pose and Cell Segmentation using Column Generation

Figure 2 for Efficient Pose and Cell Segmentation using Column Generation

Figure 3 for Efficient Pose and Cell Segmentation using Column Generation

Figure 4 for Efficient Pose and Cell Segmentation using Column Generation

We study the problems of multi-person pose segmentation in natural images and instance segmentation in biological images with crowded cells. We formulate these distinct tasks as integer programs where variables correspond to poses/cells. To optimize, we propose a generic relaxation scheme for solving these combinatorial problems using a column generation formulation where the program for generating a column is solved via exact optimization of very small scale integer programs. This results in efficient exploration of the spaces of poses and cells.

Via

Access Paper or Ask Questions