In this paper, we study the cross-view geo-localization problem to match images from different viewpoints. The key motivation underpinning this task is to learn a discriminative viewpoint-invariant visual representation. Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network. Specifically, we introduce a Unit Subtraction Attention Module (USAM) that can automatically discover representative keypoints from feature maps and draw attention to the salient regions. USAM contains very few learning parameters but yields significant performance improvement and can be easily plugged into different networks. We demonstrate through extensive experiments that (1) by incorporating USAM, RK-Net facilitates end-to-end joint learning without the prerequisite of extra annotations. Representation learning and keypoint detection are two highly-related tasks. Representation learning aids keypoint detection. Keypoint detection, in turn, enriches the model capability against large appearance changes caused by viewpoint variants. (2) USAM is easy to implement and can be integrated with existing methods, further improving the state-of-the-art performance. We achieve competitive geo-localization accuracy on three challenging datasets, i. e., University-1652, CVUSA and CVACT. Our code is available at https://github.com/AggMan96/RK-Net.

Joint Representation Learning and Keypoint Detection for Cross-View Geo-Localization / Lin, J.; Zheng, Z.; Zhong, Z.; Luo, Z.; Li, S.; Yang, Y.; Sebe, N.. - In: IEEE TRANSACTIONS ON IMAGE PROCESSING. - ISSN 1057-7149. - 31:(2022), pp. 3780-3792. [10.1109/TIP.2022.3175601]

Joint Representation Learning and Keypoint Detection for Cross-View Geo-Localization

Zhong Z.;Sebe N.
2022-01-01

Abstract

In this paper, we study the cross-view geo-localization problem to match images from different viewpoints. The key motivation underpinning this task is to learn a discriminative viewpoint-invariant visual representation. Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network. Specifically, we introduce a Unit Subtraction Attention Module (USAM) that can automatically discover representative keypoints from feature maps and draw attention to the salient regions. USAM contains very few learning parameters but yields significant performance improvement and can be easily plugged into different networks. We demonstrate through extensive experiments that (1) by incorporating USAM, RK-Net facilitates end-to-end joint learning without the prerequisite of extra annotations. Representation learning and keypoint detection are two highly-related tasks. Representation learning aids keypoint detection. Keypoint detection, in turn, enriches the model capability against large appearance changes caused by viewpoint variants. (2) USAM is easy to implement and can be integrated with existing methods, further improving the state-of-the-art performance. We achieve competitive geo-localization accuracy on three challenging datasets, i. e., University-1652, CVUSA and CVACT. Our code is available at https://github.com/AggMan96/RK-Net.
2022
Lin, J.; Zheng, Z.; Zhong, Z.; Luo, Z.; Li, S.; Yang, Y.; Sebe, N.
Joint Representation Learning and Keypoint Detection for Cross-View Geo-Localization / Lin, J.; Zheng, Z.; Zhong, Z.; Luo, Z.; Li, S.; Yang, Y.; Sebe, N.. - In: IEEE TRANSACTIONS ON IMAGE PROCESSING. - ISSN 1057-7149. - 31:(2022), pp. 3780-3792. [10.1109/TIP.2022.3175601]
File in questo prodotto:
File Dimensione Formato  
JointRepresentation2-TIP22.pdf

Solo gestori archivio

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Altra licenza (Other type of license)
Dimensione 10.24 MB
Formato Adobe PDF
10.24 MB Adobe PDF   Visualizza/Apri
Joint_Representation_Learning_and_Keypoint_Detection_for_Cross-View_Geo-Localization.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 6.56 MB
Formato Adobe PDF
6.56 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/361028
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 53
  • ???jsp.display-item.citation.isi??? 44
social impact