Visual Instance Retrieval with Deep Convolutional Networks
Computer Vision and Pattern Recognition
2016-05-10 v4
Abstract
This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.
Cite
@article{arxiv.1412.6574,
title = {Visual Instance Retrieval with Deep Convolutional Networks},
author = {Ali Sharif Razavian and Josephine Sullivan and Stefan Carlsson and Atsuto Maki},
journal= {arXiv preprint arXiv:1412.6574},
year = {2016}
}