Preserving Semantic Relations for Zero-Shot Learning

Annadani, Yashas and Biswas, Soma (2018) Preserving Semantic Relations for Zero-Shot Learning. In: 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), JUN 18-23, 2018, Salt Lake City, UT, pp. 7603-7612.

PDF Iee_Cvf_Con_Vis_Pat_Rec_CVPR_7603_2018.pdf - Published Version Restricted to Registered users only Download (653kB) | Request a copy

Abstract

Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data. This is usually achieved by associating categories with their semantic information like attributes. However, we believe that the potential offered by this paradigm is not yet fully exploited. In this work, we propose to utilize the structure of the space spanned by the attributes using a set of relations. We devise objective functions to preserve these relations in the embedding space, thereby inducing semanticity to the embedding space. Through extensive experimental evaluation on five benchmark datasets, we demonstrate that inducing semanticity to the embedding space is beneficial for zero-shot learning. The proposed approach outperforms the state-of-the-art on the standard zero-shot setting as well as the more realistic generalized zero-shot setting. We also demonstrate how the proposed approach can be useful for making approximate semantic inferences about an image belonging to a category for which attribute information is not available.

Item Type:	Conference Paper
Series.:	IEEE Conference on Computer Vision and Pattern Recognition
Publisher:	IEEE
Additional Information:	31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, JUN 18-23, 2018
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	27 Feb 2019 09:29
Last Modified:	27 Feb 2019 09:29
URI:	http://eprints.iisc.ac.in/id/eprint/61852

Actions (login required)

View Item