FAemb: A Function Approximation-Based Embedding Method for Image Retrieval
Abstract
The objective of this paper is to design an embedding method mapping local features describing image (e.g. SIFT) to a higher dimensional representation used for image retrieval problem. By investigating the relationship between the linear approximation of a nonlinear function in high dimensional space and state-of-the-art feature representation used in image retrieval, i.e., VLAD, we first introduce a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework. The evaluation shows that our embedding method gives a performance boost over the state of the art in image retrieval, as demonstrated by our experiments on the standard public image retrieval benchmarks.
Cite
Text
Do et al. "FAemb: A Function Approximation-Based Embedding Method for Image Retrieval." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298978Markdown
[Do et al. "FAemb: A Function Approximation-Based Embedding Method for Image Retrieval." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/do2015cvpr-faemb/) doi:10.1109/CVPR.2015.7298978BibTeX
@inproceedings{do2015cvpr-faemb,
title = {{FAemb: A Function Approximation-Based Embedding Method for Image Retrieval}},
author = {Do, Thanh-Toan and Tran, Quang D. and Cheung, Ngai-Man},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7298978},
url = {https://mlanthology.org/cvpr/2015/do2015cvpr-faemb/}
}