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

04/08/2016
by   Filip Radenovic, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset