Toggle Main Menu Toggle Search

Open Access padlockePrints

Towards affordable semantic searching: Zero-shot retrieval via dominant attributes

Lookup NU author(s): Dr Yang Long

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


Abstract

Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Instance-level retrieval has become an essential paradigm to index and retrieves images from large-scale databases. Conventional instance search requires at least an example of the query image to retrieve images that contain the same object instance. Existing semantic retrieval can only search semantically-related images, such as those sharing the same category or a set of tags, not the exact instances. Meanwhile, the unrealistic assumption is that all categories or tags are known beforehand. Training models for these semantic concepts highly rely on instance-level attributes or human captions which are expensive to acquire. Given the above challenges, this paper studies the Zero-shot Retrieval problem that aims for instance-level image search using only a few dominant attributes. The contributions are: 1) we utilise automatic word embedding to infer class-level attributes to circumvent expensive human labelling; 2) the inferred class-attributes can be extended into discriminative instance attributes through our proposed Latent Instance Attributes Discovery (LIAD) algorithm; 3) our method is not restricted to complete attribute signatures, query of dominant attributes can also be dealt with. On two benchmarks, CUB and SUN, extensive experiments demonstrate that our method can achieve promising performance for the problem. Moreover, our approach can also benefit conventional ZSL tasks.


Publication metadata

Author(s): Long Y, Liu L, Shen Y, Shao L

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)

Year of Conference: 2018

Pages: 7210-7217

Online publication date: 01/04/2018

Acceptance date: 02/04/2016

Publisher: AAAI press

URL: https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16626

Library holdings: Search Newcastle University Library for this item

ISBN: 9781577358008


Share