Joint Hierarchical Category Structure Learning and Large-Scale Image Classification
This addresses the problem of efficient and accurate large-scale image classification for computer vision applications, but it is incremental as it builds on existing visual tree-based methods.
The paper tackles scalable image classification with many categories by learning hierarchical inter-class structures, resulting in significantly better category hierarchies and more accurate classification on ILSVRC2010 and Caltech 256 datasets.
We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a novel image classification method based on learning hierarchical inter-class structures. Specifically, we first design a fast algorithm to compute the similarity metric between categories, based on which a visual tree is constructed by hierarchical spectral clustering. Using the learned visual tree, a test sample label is efficiently predicted by searching for the best path over the entire tree. The proposed method is extensively evaluated on the ILSVRC2010 and Caltech 256 benchmark datasets. Experimental results show that our method obtains significantly better category hierarchies than other state-of-the-art visual tree-based methods and, therefore, much more accurate classification.