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


Filip Radenović, Giorgos Tolias, Ondřej Chum; ECCV 2016
CNNImageRetrieval

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.

Paper

Downloads