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

Citation data:

Computers & Graphics, ISSN: 0097-8493, Vol: 71, Page: 77-87

Publication Year:
2018
Captures 5
Readers 5
Social Media 19
Shares, Likes & Comments 18
Tweets 1
DOI:
10.1016/j.cag.2017.12.006
Author(s):
Tu Bui; Leonardo Ribeiro; Moacir Ponti; John Collomosse
Publisher(s):
Elsevier BV
Tags:
Engineering; Computer Science
Most Recent Tweet View All Tweets
article description
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. Datasets and models are available at http://www.cvssp.org.