TY - GEN
T1 - A Deep Cross-Modal Hashing Technique for Large-Scale SAR and VHR Image Retrieval
AU - Sun, Yuxi
AU - Feng, Shanshan
AU - Ye, Yunming
AU - Li, Xutao
AU - Kang, Jian
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/9/22
Y1 - 2021/9/22
N2 - Cross-modal hashing is an important technology for large-scale very high resolution (VHR) and synthetic-aperture radar (SAR) image retrieval. Current cross-modal hashing methods fail to effectively preserve the intra-class similarities and the inter-class discriminations between VHR and SAR images when learning common semantic representation of these cross-modal images. This is because these methods use derived signals to implicitly guide hashing learning, which leads to low discrimination of generated hash codes. To address the drawback, this paper proposes an explicit semantic preserving-based deep hashing method, which can fully learn the intra-class and inter-class semantic structure. Specifically, we design a novel objective function to explicitly preserve the intra-class and inter-class semantic structure directly with class labels. Extensive experiments on a VHR-SAR dataset demonstrate that our method outperforms various state-of-the-art cross-modal hashing methods.
AB - Cross-modal hashing is an important technology for large-scale very high resolution (VHR) and synthetic-aperture radar (SAR) image retrieval. Current cross-modal hashing methods fail to effectively preserve the intra-class similarities and the inter-class discriminations between VHR and SAR images when learning common semantic representation of these cross-modal images. This is because these methods use derived signals to implicitly guide hashing learning, which leads to low discrimination of generated hash codes. To address the drawback, this paper proposes an explicit semantic preserving-based deep hashing method, which can fully learn the intra-class and inter-class semantic structure. Specifically, we design a novel objective function to explicitly preserve the intra-class and inter-class semantic structure directly with class labels. Extensive experiments on a VHR-SAR dataset demonstrate that our method outperforms various state-of-the-art cross-modal hashing methods.
KW - Content-based remote sensing image retrieval
KW - cross-source image retrieval
KW - deep cross-modal hashing
KW - optical and synthetic aperture radar data
UR - https://www.scopus.com/pages/publications/85119084011
U2 - 10.1109/BIGSARDATA53212.2021.9574218
DO - 10.1109/BIGSARDATA53212.2021.9574218
M3 - 会议稿件
AN - SCOPUS:85119084011
T3 - 2021 SAR in Big Data Era, BIGSARDATA 2021 - Proceedings
BT - 2021 SAR in Big Data Era, BIGSARDATA 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 SAR in Big Data Era, BIGSARDATA 2021
Y2 - 22 September 2021 through 24 September 2021
ER -