Dynamic match kernel with deep convolutional features for image retrieval

Yang, Jufeng, Liang, Jie, Shen, Hui, Wang, Kai, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884 and Yang, Ming-Hsuan 2018. Dynamic match kernel with deep convolutional features for image retrieval. IEEE Transactions on Image Processing 27 (11) , pp. 5288-5302. 10.1109/TIP.2018.2845136

Preview

PDF - Accepted Post-Print Version Download (6MB) | Preview

Abstract

For image retrieval methods based on bag of visual words, much attention has been paid to enhancing the discriminative powers of the local features. Although retrieved images are usually similar to a query in minutiae, they may be significantly different from a semantic perspective, which can be effectively distinguished by convolutional neural networks (CNN). Such images should not be considered as relevant pairs. To tackle this problem, we propose to construct a dynamic match kernel by adaptively calculating the matching thresholds between query and candidate images based on the pairwise distance among deep CNN features. In contrast to the typical static match kernel which is independent to the global appearance of retrieved images, the dynamic one leverages the semantical similarity as a constraint for determining the matches. Accordingly, we propose a semantic-constrained retrieval framework by incorporating the dynamic match kernel, which focuses on matched patches between relevant images and filters out the ones for irrelevant pairs. Furthermore, we demonstrate that the proposed kernel complements recent methods, such as hamming embedding, multiple assignment, local descriptors aggregation, and graph-based re-ranking, while it outperforms the static one under various settings on off-the-shelf evaluation metrics. We also propose to evaluate the matched patches both quantitatively and qualitatively. Extensive experiments on five benchmark data sets and large-scale distractors validate the merits of the proposed method against the state-of-the-art methods for image retrieval.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	IEEE
ISSN:	1057-7149
Date of First Compliant Deposit:	21 June 2018
Date of Acceptance:	26 May 2018
Last Modified:	25 Nov 2024 16:15
URI:	https://orca.cardiff.ac.uk/id/eprint/112677

Citation Data

Cited 28 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item