Feature Combination with Multi-Kernel Learning for Fine-Grained Visual Classification

This paper addresses the problem of fine-grained recog-nition in which local, mid-level features are used for clas-sification. We propose to use the Multi-Kernel Learning framework to learn the relative importance of the features and to select optimal features with regards to the clas-sification performance, in a principled way. Our results show improved classification results on common bench-marks for fine-grained classification, as compared to the best prior state-of-the-art methods. The proposed learning-based combination method also improves the concatenation combination approach which has been the standard prac-tice in combining features so far. 1