Image Retrieval using Multi-scale CNN Features Pooling

2020/04/21 by Vaccaro, Federico, Bertini, Marco, Uricchio, Tiberio +1
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2004.09695

Abstract

In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.

Related

• Deep Convolutional Features for Image Based Retrieval and Scene Categorization
• Particular object retrieval with integral max-pooling of CNN activations
• Multi-scale Orderless Pooling of Deep Convolutional Activation Features
• Exploiting Local Features from Deep Networks for Image Retrieval
• A Triplet-loss Dilated Residual Network for High-Resolution Representation Learning in Image Retrieval