Boosting part-sense multi-feature learners toward effective object detection
Lists
Only you see this
Abstract
AdaBoost has been applied to object detection to construct the detectors with high performance of discrimination and generalization by single-feature learner. However, the poor discriminative power of extremely weak single-feature learners limits its application for general object detection. In this paper, we propose a novel comprehensive learner design mechanism toward effective object detection in terms of both discrimination and generalization abilities. Firstly, the part-sense multi-feature learners are designed to linearly combine the multiple local features to improve the descriptive and discriminative capacity of the learner. Secondly, we formulate the feature selection in part-sense multi-feature learner as a weighted LASSO regression. Using Least Angle Regression (LARS) method, our approach can choose features adaptively, efficiently and as few as possible to guarantee generalization performance. Finally, a robust L1-regularized gradient boosting is proposed to integrate our part-sense sparse features learner into an object classifier. Extensive experiments and comparisons on the face dataset and the human dataset show the proposed approach outperforms the traditional single-feature learner and other multi-feature learners in discriminative and generalization abilities. Research highlights ► Part-sense multi-feature learners are designed to improve the ability of learners. ► We formulate the feature selection as a weighted LASSO regression. ► A robust L1-regularized gradient boosting is proposed.
BibTeX
@article{chen2011boosting,
author = {Shi Chen and Jinqiao Wang and Yi Ouyang and Bo Wang and Changsheng Xu and Hanqing Lu},
title = {{Boosting part-sense multi-feature learners toward effective object detection}},
journal = {Comput. Vis. Image Underst.},
year = {2011},
url = {https://openreview.net/forum?id=I69zfu4Wj-},
}Loading related content...