期刊
NEURAL NETWORKS
卷 164, 期 -, 页码 245-263出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2023.04.009
关键词
Content-based image retrieval; Co-attention; Clustering
Content-based image retrieval (CBIR) aims to provide similar images to a given query. Feature extraction is crucial in CBIR for retrieval performance. This paper introduces a query-sensitive co-attention mechanism for large-scale CBIR tasks, which employs clustering of selected local features to reduce computation cost. Experimental results show that the proposed co-attention maps achieve the best retrieval results in challenging situations. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
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 it 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-attention1 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.(c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据