Growing Regression Forests by Classification: Applications to Object Pose Estimation
This work addresses the challenge of efficient regression in computer vision for tasks like object pose estimation, offering a novel approach that improves accuracy over existing methods.
The authors tackled the problem of improving regression forests by proposing a novel node splitting method that clusters training data to minimize loss and then determines splitting rules via classification, resulting in more efficient tree structures. They applied this method to head pose and car direction estimation, achieving significant error reductions of 38.5% and 22.5% compared to state-of-the-art methods.
In this work, we propose a novel node splitting method for regression trees and incorporate it into the regression forest framework. Unlike traditional binary splitting, where the splitting rule is selected from a predefined set of binary splitting rules via trial-and-error, the proposed node splitting method first finds clusters of the training data which at least locally minimize the empirical loss without considering the input space. Then splitting rules which preserve the found clusters as much as possible are determined by casting the problem into a classification problem. Consequently, our new node splitting method enjoys more freedom in choosing the splitting rules, resulting in more efficient tree structures. In addition to the Euclidean target space, we present a variant which can naturally deal with a circular target space by the proper use of circular statistics. We apply the regression forest employing our node splitting to head pose estimation (Euclidean target space) and car direction estimation (circular target space) and demonstrate that the proposed method significantly outperforms state-of-the-art methods (38.5% and 22.5% error reduction respectively).