GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms
This addresses training speed for object detection practitioners, but is an incremental improvement over existing Adaboost methods.
The paper tackles the lengthy training process of Viola-Jones object detection by proposing GAdaBoost, which uses a genetic algorithm to accelerate feature selection. The method achieves up to 3.7 times faster training with only a 3-4% decrease in detection accuracy on benchmark datasets.
Boosted cascade of simple features, by Viola and Jones, is one of the most famous object detection frameworks. However, it suffers from a lengthy training process. This is due to the vast features space and the exhaustive search nature of Adaboost. In this paper we propose GAdaboost: a Genetic Algorithm to accelerate the training procedure through natural feature selection. Specifically, we propose to limit Adaboost search within a subset of the huge feature space, while evolving this subset following a Genetic Algorithm. Experiments demonstrate that our proposed GAdaboost is up to 3.7 times faster than Adaboost. We also demonstrate that the price of this speedup is a mere decrease (3%, 4%) in detection accuracy when tested on FDDB benchmark face detection set, and Caltech Web Faces respectively.