Boq: A Place Is Worth A Bag Of Learnable Queries

Abstract

In visual place recognition, accurately identifying and matching images of locations under varying environmental conditions and viewpoints remains a significant challenge. In this paper, we introduce a new technique, called Bag-of-Queries (BoQ), which learns a set of global queries designed to capture universal place-specific attributes. Unlike existing methods that employ self-attention and generate the queries directly from the input features, BoQ employs distinct learnable global queries, which probe the input features via cross-attention, ensuring consistent information aggregation. In addition, our technique provides an interpretable attention mechanism and integrates with both CNN and Vision Transformer backbones. The performance of BoQ is demonstrated through extensive experiments on 14 large-scale benchmarks. It consistently outperforms current state-of-the-art techniques including NetVLAD, MixVPR and EigenPlaces. Moreover, as a global retrieval technique (one-stage), BoQ surpa

Stats

• citations34
• S2 citations—
• github stars178
• HF likes0
• heat score16.09
• arxiv keyalibey2024boq

Related papers

• Why-so-deep: Towards Boosting Previously Trained Models For Visual Place Recognition (2022)7.81
• Eigenplaces: Training Viewpoint Robust Models For Visual Place Recognition (2023)15.46
• Are Local Features All You Need For Cross-domain Visual Place Recognition? (2023)13.80
• Uniloc: Towards Universal Place Recognition Using Any Single Modality (2024)0.00
• Query-based Adaptive Aggregation For Multi-dataset Joint Training Toward Universal Visual Place Recognition (2025)0.00
• Pointnetvlad: Deep Point Cloud Based Retrieval For Large-scale Place Recognition (2018)25.45
• Graph-based Non-linear Least Squares Optimization For Visual Place Recognition In Changing Environments (2020)7.16
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70