| Residential College | false |
| Status | 即將出版Forthcoming |
| Learning Cross-View Geo-Localization Embeddings via Dynamic Weighted Decorrelation Regularization | |
Wang, Tingyu2; Zheng, Zhedong1 ; Zhu, Zunjie2,3; Sun, Yaoqi2,3; Yan, Chenggang2; Yang, Yi4
| |
| 2024 | |
| Source Publication | IEEE Transactions on Geoscience and Remote Sensing
 |
| ISSN | 0196-2892 |
| Volume | 62 |
| Abstract | In the domain of cross-view geo-localization, the challenge lies in accurately matching images captured from distinct perspectives, such as aerial drone imagery and satellite imagery of the same geographical location. Existing methods predominantly concentrate on minimizing distances between feature embeddings in the representational space, inadvertently overlooking the significance of reducing embedding redundancy. This oversight potentially hampers the extraction of diverse and distinctive visual patterns critical for precise localization. This work argues that minimizing embedding redundancy is a pivotal factor in enhancing a model's ability to discriminate diverse scene characteristics. To support this claim, we introduce a straightforward yet effective regularization technique, termed dynamic weighted decorrelation regularization (DWDR). DWDR serves to actively promote the learning of orthogonal feature channels within neural networks. By dynamically adjusting weights, DWDR targets the minimization of interchannel correlations, guiding the correlation matrix toward diagonality, indicative of independence among channels. The dynamic weighting mechanism adaptively prioritizes the decorrelation of channels that remain highly correlated throughout training. Additionally, we devise a symmetrical sampling strategy for cross-view scenarios to ensure that the training examples are balanced across different imaging platforms in a batch. Despite its simplicity, the integration of DWDR and the proposed sampling scheme yields remarkable performance across four extensive benchmark datasets: University-1652, CVUSA, CVACT, and VIGOR. Notably, in stringent conditions, such as when constrained to exceedingly compact feature dimensions of 64, our methodology significantly outperforms conventional baselines, thereby affirming its efficacy and robustness under challenging constraints. |
| Keyword | Decorrelation deep learning geo-localization image retrieval the cross-correlation coefficient matrix |
| DOI | 10.1109/TGRS.2024.3491757 |
| URL | View the original |
| Language | 英語English |
| Scopus ID | 2-s2.0-85208658977 |
| Fulltext Access | |
| Citation statistics | |
| Document Type | Journal article |
| Collection | DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE |
| Affiliation | 1.University of Macau, Faculty of Science and Technology, Institute of Collaborative Innovation, Macao 2.Hangzhou Dianzi University, School of Communication Engineering, Hangzhou, 310018, China 3.Lishui Institute of Hangzhou Dianzi University, Lishui, 323000, China 4.Zhejiang University, School of Computer Science, Hangzhou, 310027, China |
| Recommended Citation GB/T 7714 | Wang, Tingyu,Zheng, Zhedong,Zhu, Zunjie,et al. Learning Cross-View Geo-Localization Embeddings via Dynamic Weighted Decorrelation Regularization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62. |
| APA | Wang, Tingyu., Zheng, Zhedong., Zhu, Zunjie., Sun, Yaoqi., Yan, Chenggang., & Yang, Yi (2024). Learning Cross-View Geo-Localization Embeddings via Dynamic Weighted Decorrelation Regularization. IEEE Transactions on Geoscience and Remote Sensing, 62. |
| MLA | Wang, Tingyu,et al."Learning Cross-View Geo-Localization Embeddings via Dynamic Weighted Decorrelation Regularization".IEEE Transactions on Geoscience and Remote Sensing 62(2024). |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment