EUVIMEDEUVIMED entdecken
Crossref

Unsupervised Hashing with Semantic Concept Mining

Rong-Cheng Tu, Xian-Ling Mao, Kevin Qinghong Lin, Chengfei Cai, Weize Qin, Wei Wei, Hongfa Wang, Heyan Huang

Proceedings of the ACM on Management of Data · 26.05.2023 · 1 (1) · 1-19

DOI: 10.1145/3588683 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 30.05.2023. Verfasst von Rong-Cheng Tu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R\&D Plan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, to improve the unsupervised image retrieval performance, plenty of unsupervised hashing methods have been proposed by designing a semantic similarity matrix, which is based on the similarities between image features extracted by a pre-trained CNN model. However, most of these methods tend to ignore high-level abstract semantic concepts contained in images. Intuitively, concepts play an important role in calculating the similarity among images. In real-world scenarios, each image is associated with some concepts, and the similarity between two images will be larger if they share more identical concepts. Inspired by the above intuition, in this work, we propose a novel Unsupervised Hashing with Semantic Concept Mining, called UHSCM, which leverages a VLP model to construct a high-quality similarity matrix. Specifically, a set of randomly chosen concepts is first collected. Then, by employing a vision-language pretraining (VLP) model with the prompt engineering which has shown strong power in visual representation learning, the set of concepts is denoised according to the training images. Next, the proposed method UHSCM applies the VLP model with prompting again to mine the concept distribution of each image and construct a high-quality semantic similarity matrix based on the mined concept distributions. Finally, with the semantic similarity matrix as guiding information, a novel hashing loss with a modified contrastive loss based regularization item is proposed to optimize the hashing network. Extensive experiments on three benchmark datasets show that the proposed method outperforms the state-of-the-art baselines in the image retrieval task.

Förderung

  • National Natural Science Foundation of China
  • National Key R\&D Plan

Zitieren

APA

Tu, R., Mao, X., Lin, K. Q., Cai, C., Qin, W., Wei, W., Wang, H., & Huang, H. (2023). Unsupervised Hashing with Semantic Concept Mining. Proceedings of the ACM on Management of Data, 1(1), 1-19. https://doi.org/10.1145/3588683

Vancouver

Tu R, Mao X, Lin KQ, Cai C, Qin W, Wei W, et al. Unsupervised Hashing with Semantic Concept Mining. Proceedings of the ACM on Management of Data. 2023;1(1):1-19. doi:10.1145/3588683

BibTeX
@article{Tu2023,
  author = {Tu, Rong-Cheng and Mao, Xian-Ling and Lin, Kevin Qinghong and Cai, Chengfei and Qin, Weize and Wei, Wei and Wang, Hongfa and Huang, Heyan},
  title = {Unsupervised Hashing with Semantic Concept Mining},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2023},
  volume = {1},
  number = {1},
  pages = {1--19},
  doi = {10.1145/3588683}
}
Kostenlos starten →