Deep Image Retrieval

Deep Image Retrieval: Learning global representations for image search


Albert Gordo , Jon Almazan , Jerome Revaud , Diane Larlus      
ECCV 2016 - The 14th European Conference on Computer Vision ; Amsterdam, The Netherlands; 11th -14th October, 2016

Qualitative Results for Deep Image Retrieval



We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained deep networks as a black box to produce features, our method leverages a deep architecture trained for the specific task of image retrieval. Our contribution is twofold: (i) we leverage a ranking framework to learn convolution and projection weights that are used to build the region features; and (ii) we employ a region proposal network to learn which regions should be pooled to form the  final global descriptor. We show that using clean training data is key to the success of our approach. To that aim, we use a large scale but noisy landmark dataset and develop an automatic cleaning approach.

The proposed architecture produces a global image representation in a single forward pass. Our approach significantly outperforms previous approaches based on global descriptors on standard datasets. It even surpasses most prior works based on costly local descriptor indexing and spatial verification.  



Deep Image Retrieval model


Summary of the results:

deep image retrieval_summary of results


Models coming soon




How to cite:

author = {Albert Gordo and Jon Almaz{\'{a}}n and J{\'{e}}rome Revaud and Diane Larlus},
title = {Deep Image Retrieval: Learning global representations for image search},

Read more in this category