Local Convolutional Features With Unsupervised Training for Image Retrieval
Mattis Paulin, Matthijs Douze, Zaid Harchaoui, Julien Mairal, Florent Perronin, Cordelia Schmid
Abstract
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, as an alternative to the popular SIFT descriptor for image retrieval. The proposed family of descriptors, called Patch-CKN, adapt the recently introduced Convolutional Kernel Network (CKN), an unsupervised framework to learn convolutional architectures. We present a comparison framework to benchmark current deep convolutional approaches along with Patch-CKN for both patch and image retrieval, including our novel ``RomePatches'' dataset. Patch-CKN descriptors yield competitive results compared to supervised CNN alternatives on patch and image retrieval.
BibTeX
@inproceedings{iccv2015_localconvolution,
title = {Local Convolutional Features With Unsupervised Training for Image Retrieval},
author = {Mattis Paulin and Matthijs Douze and Zaid Harchaoui and Julien Mairal and Florent Perronin and Cordelia Schmid},
booktitle = {ICCV 2015},
year = {2015}
}