A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs With a Costly Max-Oracle

Neel Shah, Vladimir Kolmogorov, Christoph H. Lampert; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2737-2745

Abstract


Structural support vector machines (SSVMs) are amongst the best performing methods for structured computer vision tasks, such as semantic image segmentation or human pose estimation. Training SSVMs, however, is computationally costly, because it requires repeated calls to a structured prediction subroutine (called \emph{max-oracle}), which has to solve an optimization problem itself, e.g. a graph cut. In this work, we introduce a new algorithm for SSVM training that is more efficient than earlier techniques when the max-oracle is computationally expensive, as it is frequently the case in computer vision tasks. The main idea is to (i) combine the recent stochastic Block-Coordinate Frank-Wolfe algorithm with efficient hyperplane caching, and (ii) use an automatic selection rule for deciding whether to call the exact max-oracle or to rely on an approximate one based on the cached hyperplanes. We show experimentally that this strategy leads to faster convergence towards the optimum with respect to the number of required oracle calls, and that this also translates into faster convergence with respect to the total runtime when the max-oracle is slow compared to the other steps of the algorithm. A C++ implementation is provided at http://www.ist.ac.at/~vnk

Related Material


[pdf]
[bibtex]
@InProceedings{Shah_2015_CVPR,
author = {Shah, Neel and Kolmogorov, Vladimir and Lampert, Christoph H.},
title = {A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs With a Costly Max-Oracle},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}