Multi-way classification for large scale visual object dataset

ImageNet dataset [1] with more than 14M images and 21K classes makes the problem of visual classification more difficult to deal with. One of the most difficult tasks is to train a fast and accurate classifier. In this paper, we address this challenge by extending the state-of-the-art large scale classifier Power Mean SVM (PmSVM) proposed by Jianxin Wu [2] in three ways: (1) An incremental learning for PmSVM, (2) A balanced bagging algorithm for training binary classifiers, (3) Parallelize the training process of classifiers with several multicore computers. Our approach is evaluated on 1K classes of ImageNet (ILSVRC 1000 [3]). The evaluation shows that our approach can save up to 82.01% memory usage and the training process is 255 times faster than the original implementation and 1276 times faster than the state-of-the-art linear classifier (LIBLINEAR [4]).