Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5673-5681
DOI: 10.1609/aaai.v40i7.37487 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jaeyoon Kim und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Visual Place Recognition (VPR) has advanced significantly with high-capacity foundation models like DINOv2, achieving remarkable performance. Nonetheless, their substantial computational cost makes deployment on resource-constrained devices impractical. In this paper, we introduce an efficient asymmetric VPR framework that incorporates a high-capacity gallery model for offline feature extraction with a lightweight query network for online processing. A key challenge in this setting is ensuring compatibility between these heterogeneous networks, which conventional approaches address through computationally expensive k-NN-based compatible training. To overcome this, we propose a geographical memory bank that structures gallery features using geolocation metadata inherent in VPR databases, eliminating the need for exhaustive k-NN computations. Additionally, we introduce an implicit embedding augmentation technique that enhances the query network to model feature variations despite its limited capacity. Extensive experiments demonstrate that our method not only significantly reduces computational costs but also outperforms existing asymmetric retrieval techniques, establishing a new aspect for VPR in resource-limited environments.
Zitieren
APA
Kim, J., Cho, Y., & Yoon, S. (2026). Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5673-5681. https://doi.org/10.1609/aaai.v40i7.37487
Vancouver
Kim J, Cho Y, Yoon S. Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5673-5681. doi:10.1609/aaai.v40i7.37487
BibTeX
@article{Kim2026,
author = {Kim, Jaeyoon and Cho, Yoonki and Yoon, Sung-Eui},
title = {Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {7},
pages = {5673--5681},
doi = {10.1609/aaai.v40i7.37487}
}
EUVIMED