Year: 2016
Type: article
Abstract: 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. The 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.
Authors: Yanyun Qu, Li Lin, Fumin Shen, Chang Lu, Yang Wu, Yuan Xie, Dacheng Tao
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Multiview Complete Space Learning for Sparse Camera Network Research, Nonlinear Transfer Distance Metric Learning for Gleaning Knowledge from the Crowd, G537489493, Fast, effective and robust person re-identification for large-scale real applications, G6600659455, FlashLite: A High Performance Machine for Data Intensive Science, G8206217862
OpenAlex ID: W2528206015