Query-based Adaptive Aggregation For Multi-dataset Joint Training Toward Universal Visual Place Recognition

Abstract

Deep learning methods for Visual Place Recognition (VPR) have advanced significantly, largely driven by large-scale datasets. However, most existing approaches are trained on a single dataset, which can introduce dataset-specific inductive biases and limit model generalization. While multi-dataset joint training offers a promising solution for developing universal VPR models, divergences among training datasets can saturate the limited information capacity in feature aggregation layers, leading to suboptimal performance. To address these challenges, we propose Query-based Adaptive Aggregation (QAA), a novel feature aggregation technique that leverages learned queries as reference codebooks to effectively enhance information capacity without significant computational or parameter complexity. We show that computing the Cross-query Similarity (CS) between query-level image features and reference codebooks provides a simple yet effective way to generate robust descriptors. Our results demo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxiao2025query

Related papers

• Towards Test-time Efficient Visual Place Recognition Via Asymmetric Query Processing (2025)0.00
• Vlad-buff: Burst-aware Fast Feature Aggregation For Visual Place Recognition (2024)10.46
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• Attention-aware Age-agnostic Visual Place Recognition (2019)8.82
• Optimal Transport Aggregation For Visual Place Recognition (2023)20.51
• SAGE: Spatial-visual Adaptive Graph Exploration For Efficient Visual Place Recognition (2025)2.16
• Unipr-3d: Towards Universal Visual Place Recognition With Visual Geometry Grounded Transformer (2025)2.95
• Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32