# Calibrating Retrieval Geometry: Reliability-Guided Training-Free Aggregation for Visual Place Recognition

arXiv: https://arxiv.org/abs/2609.25937 · HTML: https://mlsanity.com/paper/2609.25937/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation](https://mlsanity.com/paper/2303.11851/) (2023)
- [VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change](https://mlsanity.com/paper/2005.08135/) (2020)
- [Deep Learning Features at Scale for Visual Place Recognition](https://mlsanity.com/paper/1701.05105/) (2017)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite](https://mlsanity.com/paper/2204.10704/) (2022)
- [BoQ: A Place is Worth a Bag of Learnable Queries](https://mlsanity.com/paper/2405.07364/) (2024)
- [4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving](https://mlsanity.com/paper/2009.06364/) (2020)
- [Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments](https://mlsanity.com/paper/2201.09201/) (2022)
- [Adaptive-Attentive Geolocalization from few queries: a hybrid approach](https://mlsanity.com/paper/2010.06897/) (2020)
- [AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift](https://mlsanity.com/paper/2203.16291/) (2022)
- [A Cross-Season Correspondence Dataset for Robust Semantic Segmentation](https://mlsanity.com/paper/1903.06916/) (2019)
- [CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data](https://mlsanity.com/paper/2112.09081/) (2021)
- [UAV-VisLoc: A Large-scale Dataset for UAV Visual Localization](https://mlsanity.com/paper/2405.11936/) (2024)
- [Revisit Anything: Visual Place Recognition via Image Segment Retrieval](https://mlsanity.com/paper/2409.18049/) (2024)
- [Memorable Maps: A Framework for Re-defining Places in Visual Place Recognition](https://mlsanity.com/paper/1811.03529/) (2018)
- [VPAIR -- Aerial Visual Place Recognition and Localization in Large-scale Outdoor Environments](https://mlsanity.com/paper/2205.11567/) (2022)
- [SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition](https://mlsanity.com/paper/2502.16601/) (2025)
- [Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a Benchmark](https://mlsanity.com/paper/2503.10692/) (2025)
- [Beyond First-Order: Learning Riemannian Geometries for Invariant Visual Place Recognition](https://mlsanity.com/paper/2602.00841/) (2026)
- [RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs](https://mlsanity.com/paper/2607.20116/) (2026)

## Abstract (arXiv)

Frozen visual foundation models provide transferable features for visual place recognition, but fixed aggregation can suppress useful distinctions in new environments. We introduce TFA, a reliability-guided, training-free aggregation method requiring neither place labels nor task-specific weight updates. Our key observation is that reproducible retrieval need not be discriminative: independent codebooks can consistently retrieve a few database hubs. TFA combines cross-codebook agreement, retrieval coverage, and spectral statistics to control residual assignment, spectral shaping, and global-feature fusion. Its spectral kernel exactly recovers original descriptor similarity at zero intervention. Database-only TFA fixes its rules before accessing queries; TFA-C64 uses 64 disjoint unlabeled target images to calibrate retrieval for subsequent queries. Across 20 ground protocols with a fixed DINOv2-B backbone and matched resolution, database-only TFA improves Recall@1 over AnyLoc by 17.39 percentage points on MSLS-val and 9.55 on SPED. C64 mitigates failures of database-only calibration in driving environments. Across eight aerial/cross-view protocols, TFA achieves the highest Recall@1 among compared training-free heads in 14 of 16 DINOv2/DINOv3 backbone-protocol combinations. In a separate native-system comparison, DINOv2-G-based TFA-C64 reaches 91.46% Recall@1 on Pitts30k and 76.29% on VPAIR, outperforming the displayed training-free comparators on all five benchmarks. These results show that reliability-guided aggregation can recover additional retrieval capability from frozen representations, providing a practical baseline for new environments with scarce place supervision.