Structured Regression Gradient Boosting

Ferran Diego, Fred A. Hamprecht; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1459-1467

Abstract

We propose a new way to train a structured output prediction model. More specifically, we train nonlinear data terms in a Gaussian Conditional Random Field (GCRF) by a generalized version of gradient boosting. The approach is evaluated on three challenging regression benchmarks: vessel detection, single image depth estimation and image inpainting. These experiments suggest that the proposed boosting framework matches or exceeds the state-of-the-art.

Related Material

[pdf]
[bibtex]
@InProceedings{Diego_2016_CVPR,
author = {Diego, Ferran and Hamprecht, Fred A.},
title = {Structured Regression Gradient Boosting},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}