Asymmetric Sparse Kernel Approximations for Large-scale Visual Search

Damek Davis, Jonathan Balzer, Stefano Soatto; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 2107-2114

Abstract


We introduce an asymmetric sparse approximate embedding optimized for fast kernel comparison operations arising in large-scale visual search. In contrast to other methods that perform an explicit approximate embedding using kernel PCA followed by a distance compression technique in R^d, which loses information at both steps, our method utilizes the implicit kernel representation directly. In addition, we empirically demonstrate that our method needs no explicit training step and can operate with a dictionary of random exemplars from the dataset. We evaluate our method on three benchmark image retrieval datasets: SIFT1M, ImageNet, and 80M-TinyImages.

Related Material


[pdf]
[bibtex]
@InProceedings{Davis_2014_CVPR,
author = {Davis, Damek and Balzer, Jonathan and Soatto, Stefano},
title = {Asymmetric Sparse Kernel Approximations for Large-scale Visual Search},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}
}