Adversarial Learning of Hard Positives for Place Recognition

Wenxuan Fang, Kai Zhang, Yoli Shavit, Wensen Feng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Image retrieval methods for place recognition learn global image descriptors that are used for fetching geo-tagged images at inference time. Recent works have suggested employing weak and self-supervision for mining hard positives and hard negatives in order to improve localization accuracy and robustness to visibility changes (e.g. in illumination or view point). However, generating hard positives, which is essential for obtaining robustness, is still limited to hard-coded or global augmentations. In this work we propose an adversarial method to guide the creation of hard positives for training image retrieval networks. Our method learns local and global augmentation policies which will increase the training loss, while the image retrieval network is forced to learn more powerful features for discriminating increasingly difficult examples. This approach allows the image retrieval network to generalize beyond the hard examples presented in the data and learn features that are robust to a wide range of variations. Our method achieves state-of-the-art recalls on the Pitts250 and Tokyo 24/7 benchmarks and outperforms recent image retrieval methods on the rOxford and rParis datasets by a noticeable margin.

Original languageEnglish
Title of host publication2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728186719
DOIs
StatePublished - 2022
Event2022 International Joint Conference on Neural Networks, IJCNN 2022 - Padua, Italy
Duration: 18 Jul 202223 Jul 2022

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2022-July

Conference

Conference2022 International Joint Conference on Neural Networks, IJCNN 2022
Country/TerritoryItaly
CityPadua
Period18/07/2223/07/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

This work was supported by the Key-Area Research and Development Program of Guangdong Province (2020B0909050003), and Science and Technology Innovation Committee of Shenzhen (CJGJZD20200617102801005).

FundersFunder number
Science and Technology Innovation Committee of ShenzhenCJGJZD20200617102801005
Special Project for Research and Development in Key areas of Guangdong Province2020B0909050003

    Keywords

    • adversarial augmentation
    • constrastive learning
    • image retrieval
    • place recognition

    Fingerprint

    Dive into the research topics of 'Adversarial Learning of Hard Positives for Place Recognition'. Together they form a unique fingerprint.

    Cite this