Quadruplet-Wise Image Similarity Learning

Marc Law 1 Nicolas Thome 1 Matthieu Cord 1
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper introduces a novel similarity learning frame-work. Working with inequality constraints involving quadruplets of images, our approach aims at efficiently modeling similarity from rich or complex semantic label relationships. From these quadruplet-wise constraints, we propose a similarity learning framework relying on a con-vex optimization scheme. We then study how our metric learning scheme can exploit specific class relationships, such as class ranking (relative attributes), and class tax-onomy. We show that classification using the learned met-rics gets improved performance over state-of-the-art meth-ods on several datasets. We also evaluate our approach in a new application to learn similarities between webpage screenshots in a fully unsupervised way.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [30 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01094069
Contributor : Marc Law <>
Submitted on : Thursday, December 11, 2014 - 3:46:55 PM
Last modification on : Thursday, March 21, 2019 - 1:14:15 PM
Document(s) archivé(s) le : Thursday, March 12, 2015 - 10:56:22 AM

File

law_iccv_2013.pdf
Files produced by the author(s)

Identifiers

Citation

Marc Law, Nicolas Thome, Matthieu Cord. Quadruplet-Wise Image Similarity Learning. IEEE International Conference on Computer Vision (ICCV), Dec 2013, Sydney, Australia. pp.249 - 256, ⟨10.1109/ICCV.2013.38⟩. ⟨hal-01094069⟩

Share

Metrics

Record views

228

Files downloads

132