Summary
Researchers propose HoloGeo, an evidence-driven reasoning framework that mitigates landmark bias in Vision-Language Model (VLM) based image geo-localization. The team first introduces two quantitative metrics—Bias Intensity (BI) and Bias Harmfulness (BH)—to characterize how landmarks distort model reasoning, and builds the LandmarkBias-3K benchmark. To reduce this bias, HoloGeo is trained on BF-30k, a high-quality dataset annotated with structured, bias-free multi-evidence reasoning chains. Multi-dimensional rewards explicitly encourage balanced attention across diverse visual cues, enabling evidence-driven joint reasoning. Experiments show HoloGeo maintains strong performance on IM2GPS3K and YFCC4k while significantly outperforming existing open-source VLMs on LandmarkBias-3K, demonstrating robust geospatial reasoning. Paper: arXiv 2607.15255.
Paper Overview
Field: cs.CV
Authors: Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Bobo Li, Shengqiong Wu, Mong-Li Lee, Wynne Hsu
Published: 2026-07-16
arXiv:
2607.15255Abstract
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 of landmarks on model reasoning, and establish a comprehensive benchmark, LandmarkBias-3K. To mitigate landmark bias, they further 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.
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178446934