English

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

Computer Vision and Pattern Recognition 2016-09-08 v3

Abstract

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.

Keywords

Cite

@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}
}

Comments

ECCV 2016

R2 v1 2026-06-22T13:28:18.061Z