Asymmetric Totally-corrective Boosting for Real-time Object Detection

TL;DR

This paper introduces new totally corrective boosting algorithms tailored for real-time object detection, explicitly optimizing asymmetric loss functions and outperforming existing methods in face detection tasks.

Contribution

The paper develops novel totally corrective boosting algorithms that explicitly optimize asymmetric loss functions for improved real-time object detection.

Findings

Outperform state-of-the-art asymmetric boosting methods in face detection

Explicitly optimize asymmetric loss objectives in a totally corrective manner

Enhance detection performance with updated weak classifier coefficients

Abstract

Real-time object detection is one of the core problems in computer vision. The cascade boosting framework proposed by Viola and Jones has become the standard for this problem. In this framework, the learning goal for each node is asymmetric, which is required to achieve a high detection rate and a moderate false positive rate. We develop new boosting algorithms to address this asymmetric learning problem. We show that our methods explicitly optimize asymmetric loss objectives in a totally corrective fashion. The methods are totally corrective in the sense that the coefficients of all selected weak classifiers are updated at each iteration. In contract, conventional boosting like AdaBoost is stage-wise in that only the current weak classifier's coefficient is updated. At the heart of the totally corrective boosting is the column generation technique. Experiments on face detection show that our methods outperform the state-of-the-art asymmetric boosting methods.