Object-Level Explanations for Image Geolocation Models: a GeoGuessr use-case

• URL: http://arxiv.org/abs/2605.00912v1
• Date: Wed, 29 Apr 2026 09:44:02 GMT
• Title: Object-Level Explanations for Image Geolocation Models: a GeoGuessr use-case
• Abstract summary: We propose an object-centric analysis pipeline to investigate the visual evidence used by geolocation models.<n>Experiments on a three-country benchmark show that attribution-guided crops consistently retain more information for the model's prediction than random crops.
• Score: 9.175493548143768
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: When humans play geolocation games such as GeoGuessr, they rely on concrete visual cues, such as road markings, vegetation, or architectural details, to infer where an image was captured. Whether image geolocation models rely on similar object-level evidence remains difficult to determine, as attribution methods like Grad-CAM typically highlight diffuse regions rather than coherent visual entities, making it difficult to link model predictions to specific objects or perceptible patterns. In this work, we propose an object-centric analysis pipeline to investigate the visual evidence used by geolocation models. Starting from attribution maps, we extract salient regions and segment them into object-like elements. We evaluate their predictive relevance through deletion and insertion tests, comparing attributionguided crops to randomly selected regions with similar coverage. Experiments on a three-country benchmark show that attribution-guided crops consistently retain more information for the model's prediction than random crops. These results suggest that attribution maps can be decomposed into interpretable, perceptible elements, providing a step toward object-level analysis of geolocation models.

Related papers

• GeoSEAN: Explainable Country-Level Image Geolocation for ASEAN Regions [0.0]
  This study presents an explainable country level image geolocation pipeline for 11 ASEAN countries.<n>We collected 4,850 images from GeoGuessr style sources, Google Images, and additional street level imagery.<n>For explainability, predictions were analyzed using CLIP attention rollout, YOLO26 object detection on original images, and Energy Based Pointing Game (EBPG) overlap.
  arXiv  Detail & Related papers  (2026-07-14T02:38:09Z)
• Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning [72.13218601075958]
  We introduce textbfWanderBench, the first open access global geolocation benchmark for actionable geolocation reasoning in embodied scenarios.<n>We propose textbfGeoAoT (Action of Thought), a underlineGeolocation framework with underlineAction of underlineThough, which couples reasoning with embodied actions.<n>Experiments on 19 large multimodal models show that GeoAoT achieves superior fine-grained localization and stronger generalization in dynamic environments.
  arXiv  Detail & Related papers  (2026-03-11T06:24:10Z)
• GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics [91.17301794848025]
  This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions.<n>Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies.
  arXiv  Detail & Related papers  (2026-02-13T04:48:05Z)
• Aggregating Local Saliency Maps for Semi-Global Explainable Image Classification [0.0]
  Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge.<n>Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the influence of specific pixels on a model's prediction.<n>We propose Segment Attribution Tables (SATs), a method for summarising local saliency explanations into (semi-)global insights.
  arXiv  Detail & Related papers  (2025-06-29T14:11:02Z)
• Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework [59.42946541163632]
  We introduce a comprehensive geolocation framework with three key components.<n>GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric.<n>We demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.
  arXiv  Detail & Related papers  (2025-02-19T14:21:25Z)
• Detecting Contextual Anomalies by Discovering Consistent Spatial Regions [5.160649627495959]
  We describe a method for modeling spatial context to enable video anomaly detection.<n>The main idea is to discover regions that share similar object-level activities by clustering joint object attributes.<n>We demonstrate this approach, using orders of magnitude fewer parameters than competing models, in the challenging spatial-context-dependent Street Scene dataset.
  arXiv  Detail & Related papers  (2025-01-14T22:33:07Z)
• Classification Drives Geographic Bias in Street Scene Segmentation [20.14340857253721]
  We investigated geo-biases in real-world driving datasets on a more complex task: instance segmentation.<n>We found that geo-biases came from classification errors rather than localization errors.<n>Our findings show that in region-specific models, geo-biases can be significantly mitigated by using coarser classes.
  arXiv  Detail & Related papers  (2024-12-15T05:33:10Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark [56.08664336835741]
  We propose a GeoGraphic Language Understanding Evaluation benchmark, named GeoGLUE. We collect data from open-released geographic resources and introduce six natural language understanding tasks. We pro vide evaluation experiments and analysis of general baselines, indicating the effectiveness and significance of the GeoGLUE benchmark.
  arXiv  Detail & Related papers  (2023-05-11T03:21:56Z)
• Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence [11.823147814005411]
  Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. Recent works achieve outstanding progress on cross-view geo-localization benchmarks. However, existing methods still suffer from poor performance on the cross-area benchmarks.
  arXiv  Detail & Related papers  (2022-12-08T04:54:01Z)
• G^3: Geolocation via Guidebook Grounding [92.46774241823562]
  We study explicit knowledge from human-written guidebooks that describe the salient and class-discriminative visual features humans use for geolocation. We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations. Our approach substantially outperforms a state-of-the-art image-only geolocation method, with an improvement of over 5% in Top-1 accuracy.
  arXiv  Detail & Related papers  (2022-11-28T16:34:40Z)
• Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching [102.39635336450262]
  We address the problem of ground-to-satellite image geo-localization by matching a query image captured at the ground level against a large-scale database with geotagged satellite images. Our new method is able to achieve the fine-grained location of a query image, up to pixel size precision of the satellite image.
  arXiv  Detail & Related papers  (2022-03-26T20:10:38Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.