Visual Instance Retrieval with Deep Convolutional Networks

12/20/2014
by   Ali Sharif Razavian, et al.
0

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.

READ FULL TEXT

page 1

page 6

research
04/20/2015

Exploiting Local Features from Deep Networks for Image Retrieval

Deep convolutional neural networks have been successfully applied to ima...
research
03/01/2016

Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach

Convolutional neural networks (CNNs) have recently received a lot of att...
research
07/09/2017

Class-Weighted Convolutional Features for Visual Instance Search

Image retrieval in realistic scenarios targets large dynamic datasets of...
research
02/07/2018

From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval

Convolutional Neural Network (CNN) is a very powerful approach to extrac...
research
06/03/2014

Image retrieval with hierarchical matching pursuit

A novel representation of images for image retrieval is introduced in th...
research
07/03/2017

Appearance invariance in convolutional networks with neighborhood similarity

We present a neighborhood similarity layer (NSL) which induces appearanc...
research
11/16/2016

On the Exploration of Convolutional Fusion Networks for Visual Recognition

Despite recent advances in multi-scale deep representations, their limit...

Please sign up or login with your details

Forgot password? Click here to reset