期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 19, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2021.3131592
关键词
Feature extraction; Semantics; Image retrieval; Fuses; Correlation; Buildings; Representation learning; Correlation learning; cross-modal retrieval; multimodal fusion; text-remote sensing (RS) image matching
类别
资金
- National Natural Science Foundation of China [61790550, 61790554, 91538201]
In this study, a fusion-based correlation learning model is proposed to address the heterogeneity gap in remote sensing image-text retrieval. By designing a cross-modal fusion network and utilizing knowledge distillation, this model improves the discriminative ability of feature representation and enhances the intermodality semantic consistency.
With the increasing of cross-modal data, cross-modal retrieval has attracted more attention in remote sensing (RS), since it provides a more flexible and convenient way to obtain interesting information than traditional retrieval. However, existing methods cannot fully exploit the semantic information, which only focuses on the semantic consistency, and ignore the information complementarity between different modalities. In this letter, to bridge the modality gap, we propose a novel fusion-based correlation learning model (FCLM) for image-text retrieval in RS. Specifically, a cross-modal-fusion network is designed to capture the intermodality complementary information and fused feature. The fused knowledge is furtherly transferred to supervise the learning of modality-specific network by knowledge distillation, which is helpful in improving the discriminative ability of feature representation and enhancing the intermodality semantic consistency to solve the heterogeneity gap problem. Finally, extensive experiments have been conducted on a public dataset and experimental results have shown that the FCLM method is effective in performing cross-modal retrieval and outperforms several baseline methods.
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