Spatially Coherent Random Forests

TL;DR

Spatially Coherent Random Forests (SCRF) enhance traditional random forests by incorporating spatial regularization, leading to improved image contour detection and segmentation performance.

Contribution

SCRF introduces a spatial coherency term into the split function evaluation, promoting spatially consistent labeling in random forests.

Findings

Improves segmentation accuracy by about 10% on Berkeley datasets.

Effectively detects image contours with hierarchical boundary maps.

Enhances random forest performance through spatial regularization.

Abstract

Spatially Coherent Random Forest (SCRF) extends Random Forest to create spatially coherent labeling. Each split function in SCRF is evaluated based on a traditional information gain measure that is regularized by a spatial coherency term. This way, SCRF is encouraged to choose split functions that cluster pixels both in appearance space and in image space. In particular, we use SCRF to detect contours in images, where contours are taken to be the boundaries between different regions. Each tree in the forest produces a segmentation of the image plane and the boundaries of the segmentations of all trees are aggregated to produce a final hierarchical contour map. We show that this modification improves the performance of regular Random Forest by about 10% on the standard Berkeley Segmentation Datasets. We believe that SCRF can be used in other settings as well.