Local Convolutional Features With Unsupervised Training for Image Retrieval

Mattis Paulin, Matthijs Douze, Zaid Harchaoui, Julien Mairal, Florent Perronin, Cordelia Schmid; The IEEE International Conference on Computer Vision (ICCV), 2015, pp. 91-99

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Paulin_2015_ICCV,
author = {Paulin, Mattis and Douze, Matthijs and Harchaoui, Zaid and Mairal, Julien and Perronin, Florent and Schmid, Cordelia},
title = {Local Convolutional Features With Unsupervised Training for Image Retrieval},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}