SAGE: Spatial-visual Adaptive Graph Exploration For Efficient Visual Place Recognition

Abstract

Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the dynamic interplay between spatial context and visual similarity during training. We present SAGE (Spatial-visual Adaptive Graph Exploration), a unified training pipeline that enhances granular spatial-visual discrimination by jointly improving local feature aggregation, organize samples during training, and hard sample mining. We introduce a lightweight Soft Probing module that learns residual weights from training data for patch descriptors before bilinear aggregation, boosting distinctive local cues. During training we reconstruct an online geo-visual graph that fuses geographic proximity and current visual similarity so that candidate neighborhoods reflect the evolving embedding landscape. To concentrate learning on the most informative place neighborho

Stats

• citations0
• S2 citations—
• github stars11
• HF likes0
• heat score2.16
• arxiv keychen2025sage

Related papers

• Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32
• Optimal Transport Aggregation For Visual Place Recognition (2023)20.51
• Close, But Not There: Boosting Geographic Distance Sensitivity In Visual Place Recognition (2024)10.40
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
• Graph-based Non-linear Least Squares Optimization For Visual Place Recognition In Changing Environments (2020)7.16
• Towards Test-time Efficient Visual Place Recognition Via Asymmetric Query Processing (2025)0.00
• Text2graph VPR: A Text-to-graph Expert System For Explainable Place Recognition In Changing Environments (2025)0.00
• Structured Pruning For Efficient Visual Place Recognition (2024)2.26