VLAD-BuFF: Burst-Aware Fast Feature Aggregation for Visual Place Recognition
Date
2025
Authors
Khaliq, A.
Xu, M.
Hausler, S.
Milford, M.
Garg, S.
Editors
Leonardis, A.
Ricci, E.
Roth, S.
Russakovsky, O.
Sattler, T.
Varol, G.
Ricci, E.
Roth, S.
Russakovsky, O.
Sattler, T.
Varol, G.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Lecture Notes in Artificial Intelligence, 2025 / Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (ed./s), vol.15102, pp.447-466
Statement of Responsibility
Ahmad Khaliq, Ming Xu, Stephen Hausler, Michael Milford, Sourav Garg
Conference Name
18th European Conference on Computer Vision (ECCV) (29 Sep 2024 - 4 Oct 2024 : Milan)
Abstract
Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The current state-of-the-art VPR methods rely on VLAD aggregation, which can be trained to learn a weighted contribution of features through their soft assignment to cluster centers. However, this process has two key limitations. Firstly, the feature-to-cluster weighting does not account for over-represented repetitive structures within a cluster, e.g., shadows or window panes; this phenomenon is also referred to as the ‘burstiness’ problem, classically solved by discounting repetitive features before aggregation. Secondly, feature to cluster comparisons are compute-intensive for state-of-the-art image encoders with high-dimensional local features. This paper addresses these limitations by introducing VLAD-BuFF with two novel contributions: i) a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training, and ii) Fast Feature aggregation by reducing local feature dimensions specifically through PCA-initialized learnable pre-projection. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall. Through additional qualitative studies, we show how our proposed weighting method effectively downweights the non-distinctive features. Source code: https://github.com/Ahmedest61/VLAD-BuFF/.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG