Related papers: Zero-shot Vision-Language Reranking for Cross-View Geolocalization

Zero-shot Vision-Language Reranking for Cross-View Geolocalization

URL: http://arxiv.org/abs/2603.27251v1
Date: Sat, 28 Mar 2026 11:57:41 GMT
Title: Zero-shot Vision-Language Reranking for Cross-View Geolocalization
Abstract summary: Cross-view geolocalization systems often fail to identify the single best match (low Top-1 accuracy)<n>This work investigates the use of zero-shot Vision-Language Models (VLMs) as rerankers to address this gap.
Score: 3.7515646463759698
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Cross-view geolocalization (CVGL) systems, while effective at retrieving a list of relevant candidates (high Recall@k), often fail to identify the single best match (low Top-1 accuracy). This work investigates the use of zero-shot Vision-Language Models (VLMs) as rerankers to address this gap. We propose a two-stage framework: state-of-the-art (SOTA) retrieval followed by VLM reranking. We systematically compare two strategies: (1) Pointwise (scoring candidates individually) and (2) Pairwise (comparing candidates relatively). Experiments on the VIGOR dataset show a clear divergence: all pointwise methods cause a catastrophic drop in performance or no change at all. In contrast, a pairwise comparison strategy using LLaVA improves Top-1 accuracy over the strong retrieval baseline. Our analysis concludes that, these VLMs are poorly calibrated for absolute relevance scoring but are effective at fine-grained relative visual judgment, making pairwise reranking a promising direction for enhancing CVGL precision.

Related papers

VFM-Loc: Zero-Shot Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchies [5.868908918033978]
Cross-View Geo-Localization (CVGL) in remote sensing aims to locate a drone-view query by matching it to geo-tagged satellite images.<n>We present VFM-Loc, a training-free framework for zero-shot CVGL that leverages the generalizable visual representations from vision foundational models (VFMs)<n>Experiments demonstrate that VFM-Loc exhibits strong zero-shot accuracy on standard benchmarks and surpasses supervised methods by over 20% in Recall@1 on the challenging LO-UCV dataset with large oblique angles.
arXiv Detail & Related papers (2026-03-14T09:23:59Z)
GLEAM: Learning to Match and Explain in Cross-View Geo-Localization [66.11208984986813]
Cross-View Geo-Localization (CVGL) focuses on identifying correspondences between images captured from distinct perspectives of the same geographical location.<n>We present GLEAM-C, a foundational CVGL model that unifies multiple views and modalities-including UAV imagery, street maps, panoramic views, and ground photographs-by aligning them exclusively with satellite imagery.<n>To address the lack of interpretability in traditional CVGL methods, we propose GLEAM-X, which combines cross-view correspondence prediction with explainable reasoning.
arXiv Detail & Related papers (2025-09-09T07:14:31Z)
SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
arXiv Detail & Related papers (2025-02-24T07:15:05Z)
AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition [48.043749855085025]
Visual place recognition (VPR) is one of the research hotspots in robotics, which uses visual information to locate robots. We present a unified network capable of extracting global features for retrieving candidates via an aggregation module. We also propose a Semi-hard Positive Sample Mining (ShPSM) strategy to select appropriate hard positive images for training more robust VPR networks.
arXiv Detail & Related papers (2023-10-08T14:46:11Z)
AffineGlue: Joint Matching and Robust Estimation [74.04609046690913]
We propose AffineGlue, a method for joint two-view feature matching and robust estimation. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches.
arXiv Detail & Related papers (2023-07-28T08:05:36Z)
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance [53.49803579981569]
We consider a global objective for contrastive learning, which contrasts each positive pair with all negative pairs for an anchor point. Existing methods such as SimCLR requires a large batch size in order to achieve a satisfactory result. We propose a memory-efficient optimization algorithm for solving the Global Contrastive Learning of Representations, named SogCLR.
arXiv Detail & Related papers (2022-02-24T22:16:53Z)
Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
Local features provide region-to-region rather than point-to-point correspondences. We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline. Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
arXiv Detail & Related papers (2020-07-20T12:07:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.