Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression

Bui, Tu, Ribeiro, Leonardo, Ponti, Moacir and Collomosse, John (2018) Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression Computers & Graphics, 71. pp. 77-87.

Preview

Text Sketch-based Image Retrieval using Convolutional NeuralNetworks with Multi-stage Regression.pdf - Accepted version Manuscript Download (2MB) | Preview

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 :	Name Email ORCID Bui, Tu t.v.bui@surrey.ac.uk Ribeiro, Leonardo Ponti, Moacir Collomosse, John J.Collomosse@surrey.ac.uk
Date :	4 January 2018
Funders :	Engineering and Physical Sciences Research Council (EPSRC)
DOI :	10.1016/j.cag.2017.12.006
Copyright Disclaimer :	© 2018. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
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 :	05 Jan 2019 02:08
URI:	http://epubs.surrey.ac.uk/id/eprint/845575

Actions (login required)

View Item

Downloads