Vlad-buff: Burst-aware Fast Feature Aggregation For Visual Place Recognition
2024 · Ahmad Khaliq, Ming Xu, Stephen Hausler, et al.
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-similar
Authors
(none)
Tags
Stats
Related papers
- Optimal Transport Aggregation For Visual Place Recognition (2023)20.51
- Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
- Towards Implicit Aggregation: Robust Image Representation For Place Recognition In The Transformer Era (2025)3.09
- Mixvpr: Feature Mixing For Visual Place Recognition (2023)22.68
- Query-based Adaptive Aggregation For Multi-dataset Joint Training Toward Universal Visual Place Recognition (2025)0.00
- Structvpr++: Distill Structural And Semantic Knowledge With Weighting Samples For Visual Place Recognition (2025)3.58
- Embodiedplace: Learning Mixture-of-features With Embodied Constraints For Visual Place Recognition (2025)0.00
- Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70