Hu, Zechao and Bors, Adrian Gheorghe orcid.org/0000-0001-7838-0021 (2023) Co-attention enabled content-based image retrieval. Neural Networks. pp. 245-263. ISSN 0893-6080
Abstract
Content-based image retrieval (CBIR) aims to provide the most similar images to a given query. Feature extraction plays an essential role in retrieval performance within a CBIR pipeline. Current CBIR studies would either uniformly extract feature information from the input image and use them directly or employ some trainable spatial weighting module which is then used for similarity comparison between pairs of query and candidate matching images. These spatial weighting modules are normally query non-sensitive and only based on the knowledge learned during the training stage. They may focus towards incorrect regions, especially when the target image is not salient or is surrounded by distractors. This paper proposes an efficient query sensitive co-attention\footnote{``Co-attention'' in this paper refers to spatial attention conditioned on the query content.} mechanism for large-scale CBIR tasks. In order to reduce the extra computation cost required by the query sensitivity to the co-attention mechanism, the proposed method employs clustering of the selected local features. Experimental results indicate that the co-attention maps can provide the best retrieval results on benchmark datasets under challenging situations, such as having completely different image acquisition conditions between the query and its match image.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Author(s). |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Funding Information: | Funder Grant number EPSRC EP/V009591/1 |
Depositing User: | Pure (York) |
Date Deposited: | 23 Jun 2023 08:20 |
Last Modified: | 05 Dec 2024 00:27 |
Published Version: | https://doi.org/10.1016/j.neunet.2023.04.009 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1016/j.neunet.2023.04.009 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:200830 |
Download
Filename: 1_s2.0_S0893608023001867_main.pdf
Description: Co-attention enabled content-based image retrieval
Licence: CC-BY 2.5