Hu, Zechao and Bors, Adrian Gheorghe orcid.org/0000-0001-7838-0021 (2023) Enabling Large-Scale Image Search with Co-Attention Mechanism. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 04-10 Jun 2023 IEEE , GRC
Abstract
Content-based image retrieval (CBIR) consists of searching the most similar images to a given query. Most existing attention mechanisms for CBIR are query non-sensitive and are only based on single candidate image's feature regardless of the actual query content. This can result in incorrect regions especially when the target object is not salient or surrounded by distractors. This paper proposes an efficient and effective query sensitive co-attention mechanism for large scale CBIR tasks. Local feature selection and clustering are employed to reduce the computation cost caused by the query sensitivity. Experimental results indicate that the proposed co-attention method can generate good co-attention maps even under challenging situations leading to a new state of the art performance on several benchmark datasets.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © IEEE, 2023. This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy. |
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 07:50 |
Last Modified: | 15 Mar 2025 00:15 |
Published Version: | https://doi.org/10.1109/ICASSP49357.2023.10095901 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/ICASSP49357.2023.10095901 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:200827 |