An improved XGBoost based on weighted column subsampling for object classification

摘要

Object classification is one of main problems in computer vision and lots of state-of-the-art machine learning methods have been proposed recently. Traditional classifier may have the drawback of low effectiveness for image representations. In this paper, an improved eXtreme Gradient Boosting (XGBoost) based on weighted column (feature) subsampling is proposed to classify image representations for object classification. The contributions of the paper are as follows. First, Convolutional Neural Networks (CNN) pre-trained on large-scale image database ILSVRC and fine-tuned on PASCAL VOC 2012 dataset is used to extract features from object images. Besides, we concatenate multiple layers of learned features to obtain more information of image contents for determining their categories. Second, due to the high dimensional of extracted features, feature redundancy will unavoidably be incurred, so a weighted column subsampling method is proposed to applied to XGBoost algorithm, in order to draw the features by the importance during growing each tree. Furthermore, our proposed method is general, which can be easily extended to other methods which need column subsampling, when the feature of data is high dimensional and redundant. Finally, we validate performance of proposed method on the PASCAL VOC 2007 dataset. Compared with four typical methods, the proposed method has superior average precision (AP) on 5 out of 20 classes, e.g. the AP of person class we obtained is 92.1, 1% higher than that of best method mentioned above.