HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning

Forum topic · 小凯 · 2026-07-20

Summary

HoloGeo is a new evidence-driven reasoning framework for image geo-localization that addresses landmark bias in Vision-Language Models (VLMs). The authors first quantify the problem with two metrics—Bias Intensity (BI) and Bias Harmfulness (BH)—and introduce the LandmarkBias-3K benchmark to characterize how landmarks distort model reasoning through overlooked geographical cues and spurious correlations. To mitigate this bias, they propose HoloGeo, supported by BF-30k, a high-quality dataset annotated with structured multi-evidence bias-free reasoning chains. A multi-dimensional reward scheme explicitly encourages balanced attention to diverse visual cues, enabling evidence-driven joint reasoning. Experiments show HoloGeo maintains strong performance on standard IM2GPS3K and YFCC4k benchmarks while significantly outperforming existing open-source VLMs on LandmarkBias-3K, demonstrating robust geospatial reasoning. Paper: arXiv 2607.15255.

Paper Overview

Field: cs.CV (Computer Vision)
Authors: Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Bobo Li, Shengqiong Wu, Mong-Li Lee, Wynne Hsu
arXiv: 2607.15255

Abstract

Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization.

To systematically investigate this issue, the authors first design two quantitative metrics, Bias Intensity (BI) and Bias Harmfulness (BH), to characterize the impact landmarks exert on model reasoning, and establish a comprehensive benchmark, LandmarkBias-3K.

To mitigate landmark bias, they propose an evidence-driven reasoning framework, HoloGeo, to improve the reliability of geo-localization. HoloGeo is supported by a high-quality dataset, BF-30k, annotated with structured multi-evidence bias-free reasoning chains. By incorporating multi-dimensional rewards, HoloGeo explicitly encourages balanced attention over diverse visual cues and achieves evidence-driven joint reasoning.

Extensive experiments demonstrate that HoloGeo not only maintains excellent performance on IM2GPS3K and YFCC4k but also significantly outperforms existing open-source VLMs on LandmarkBias-3K, validating its effectiveness for robust geospatial reasoning.

---

*Auto-collected from zhichai.net forum, originally posted 2026-07-20.*

HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning

Summary

Paper Overview

Abstract

Tags