University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Sketch-based Image Retrieval using Convolutional NeuralNetworks with Multi-stage Regression

Bui, Tu, Ribeiro, Leonardo, Ponti, Moacir and Collomosse, John (2018) Sketch-based Image Retrieval using Convolutional NeuralNetworks with Multi-stage Regression Computers & Graphics.

[img] Text
Sketch-based Image Retrieval using Convolutional NeuralNetworks with Multi-stage Regression.pdf - Accepted version Manuscript
Restricted to Repository staff only until 28 December 2018.

Download (2MB)

Abstract

We propose and evaluate several deep network architectures for measuring the similarity between sketches and photographs, within the context of the sketch based image retrieval (SBIR) task. We study the ability of our networks to generalize across diverse object categories from limited training data, and explore in detail strategies for weight sharing, pre-processing, data augmentation and dimensionality reduction. In addition to a detailed comparative study of network configurations, we contribute by describing a hybrid multi-stage training network that exploits both contrastive and triplet networks to exceed state of the art performance on several SBIR benchmarks by a significant margin.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Bui, Tut.v.bui@surrey.ac.uk
Ribeiro, Leonardo
Ponti, Moacir
Collomosse, JohnJ.Collomosse@surrey.ac.uk
Date : 2018
Funders : Engineering and Physical Sciences Research Council (EPSRC)
Copyright Disclaimer : © 2018 Elsevier B.V. All rights reserved.
Uncontrolled Keywords : Sketch based image retrieval (SBIR); Deep learning; Cross-domain modelling; Compact feature representations; Multi-stage regression; Contrastive and triplet losses
Depositing User : Clive Harris
Date Deposited : 10 Jan 2018 08:34
Last Modified : 14 Mar 2018 15:52
URI: http://epubs.surrey.ac.uk/id/eprint/845575

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800