DEMO: A Statistical Perspective for Efficient Image-Text Matching

Fan Zhang, Xian-Sheng Hua, Chong Chen, Xiao Luo


Abstract
Image-text matching has been a long-standing problem, which seeks to connect vision and language through semantic understanding. Due to the capability to manage large-scale raw data, unsupervised hashing-based approaches have gained prominence recently. They typically construct a semantic similarity structure using the natural distance, which subsequently guides the optimization of the hashing network. However, the similarity structure could be biased at the boundaries of semantic distributions, causing error accumulation during sequential optimization. To tackle this, we introduce a novel hashing approach termed Distribution-based Structure Mining with Consistency Learning (DEMO) for efficient image-text matching. From a statistical view, DEMO characterizes each image using multiple augmented views, which are considered as samples drawn from its intrinsic semantic distribution. Then, we employ a non-parametric distribution divergence to ensure a robust and precise similarity structure. In addition, we introduce collaborative consistency learning which not only preserves the similarity structure in the Hamming space but also encourages consistency between retrieval distribution from different directions in a self-supervised manner. Extensive experiments on several widely used datasets demonstrate that DEMO achieves superior performance compared with various state-of-the-art methods.
Anthology ID:
2024.naacl-long.21
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
355–369
Language:
URL:
https://aclanthology.org/2024.naacl-long.21
DOI:
10.18653/v1/2024.naacl-long.21
Bibkey:
Cite (ACL):
Fan Zhang, Xian-Sheng Hua, Chong Chen, and Xiao Luo. 2024. DEMO: A Statistical Perspective for Efficient Image-Text Matching. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 355–369, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
DEMO: A Statistical Perspective for Efficient Image-Text Matching (Zhang et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.naacl-long.21.pdf