Asking friendly strangers: Non-semantic attribute transfer

1Citations
Citations of this article
14Readers
Mendeley users who have this article in their library.

Abstract

Attributes can be used to recognize unseen objects from a textual description. Their learning is oftentimes accomplished with a large amount of annotations, e.g. around 160k-180k, but what happens if for a given attribute, we do not have many annotations? The standard approach would be to perform transfer learning, where we use source models trained on other attributes, to learn a separate target attribute. However existing approaches only consider transfer from attributes in the same domain i.e. they perform semantic transfer between attributes that have related meaning. Instead, we propose to perform non-semantic transfer from attributes that may be in different domains, hence they have no semantic relation to the target attributes. We develop an attention-guided transfer architecture that learns how to weigh the available source attribute classifiers, and applies them to image features for the attribute name of interest, to make predictions for that attribute. We validate our approach on 272 attributes from five domains: animals, objects, scenes, shoes and textures. We show that semantically unrelated attributes provide knowledge that helps improve the accuracy of the target attribute of interest, more so than only allowing transfer from semantically related attributes.

Cite

CITATION STYLE

APA

Murrugarra-Llerena, N., & Kovashka, A. (2018). Asking friendly strangers: Non-semantic attribute transfer. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 7268–7275). AAAI press. https://doi.org/10.1609/aaai.v32i1.12243

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free