Structure-aware Feature Disentanglement with Knowledge Transfer for Appearance-changing Place Recognition

Cao Qin, Yunzhou Zhang, Yingda Liu, Delong Zhu, Sonya Coleman, Dermot Kerr

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
178 Downloads (Pure)


Long-term visual place recognition (VPR) is challenging as the environment is subject to drastic appearance changes across different temporal resolutions, such as time of the day, month, and season. A wide variety of existing methods address the problem by means of feature disentangling or image style transfer but ignore the structural information that often remains stable even under environmental condition changes. To overcome this limitation, this article presents a novel structure-aware feature disentanglement network (SFDNet) based on knowledge transfer and adversarial learning. Explicitly, probabilistic knowledge transfer (PKT) is employed to transfer knowledge obtained from the Canny edge detector to the structure encoder. An appearance teacher module is then designed to ensure that the learning of appearance encoder does not only rely on metric learning. The generated content features with structural information are used to measure the similarity of images. We finally evaluate the proposed approach and compare it to state-of-the-art place recognition methods using six datasets with extreme environmental changes. Experimental results demonstrate the effectiveness and improvements achieved using the proposed framework. Source code and some trained models will be available at

Original languageEnglish
Pages (from-to)1278-1290
Number of pages13
JournalIEEE Transactions on Neural Networks and Learning Systems
Issue number3
Early online date30 Aug 2021
Publication statusPublished (in print/issue) - 1 Mar 2023

Bibliographical note

Publisher Copyright:
© 2012 IEEE.


  • Disentanglement
  • Representation
  • Changing environment
  • Knowledge transfer
  • Visual place recognition
  • visual place recognition (VPR)
  • knowledge transfer
  • representation disentanglement


Dive into the research topics of 'Structure-aware Feature Disentanglement with Knowledge Transfer for Appearance-changing Place Recognition'. Together they form a unique fingerprint.

Cite this