Efficient match kernel in fine-grained image categorization

In this paper, we study the problem of fine-grained image categorization, which is much more useful in real applications than basic image classification. Based on the most challenge dataset, CUB-200, we combine Efficient match kernel (EMK) with the weighted spatial pyramid to achieve state-of-art performance. Comparison with BoW, which can also be viewed as kernel matching approach, EMK digs the relations among vocabulary bases and finds a new mapping in kernel framework. By it, local features are mapped to a low dimensional feature space and average the resulting vectors to form a set level feature in EMK. It is proved that it is helpful to improve the system performance.