Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes.
@article{arxiv.1604.02426,
title = {CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples},
author = {Filip Radenović and Giorgos Tolias and Ondřej Chum},
journal= {arXiv preprint arXiv:1604.02426},
year = {2016}
}