Towards Latent Attribute Discovery from Triplet Similarities

October 2019

Towards Latent Attribute Discovery from Triplet Similarities

Authors:

I. Nigam, P. Tokmakov, and D. Ramanan
Conference Paper
Proceedings of (ICCV) International Conference on Computer Vision

Abstract:

This paper addresses the task of learning latent attributes from triplet similarity comparisons. Consider, for instance, the three shoes in Fig. 1(a). They can be compared according to color, comfort, size, or shape resulting in different rankings. Most approaches for embedding learning either make a simplifying assumption - that all inputs are comparable under a single criterion, or require expensive attribute supervision. We introduce Latent Similarity Networks (LSNs): a simple and effective technique to discover the underlying latent notions of similarity in data without any explicit attribute supervision. LSNs can be trained with standard triplet supervision and learn several latent embeddings that can be used to compare images under multiple notions of similarity. LSNs achieve state-of-the-art performance on UT-Zappos-50k Shoes and Celeb-A Faces datasets and also demonstrate the ability to uncover meaningful latent attributes.
@conference{Nigam-2019-121135,
author = {I. Nigam And P. Tokmakov And D. Ramanan},
title = {Towards Latent Attribute Discovery from Triplet Similarities},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2019},
month = {October},
pages = {402 - 410},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.