We present a CLIP-based, multi-modal, multi-label classifier for predicting geographical context tags from landscape photos in the Geograph dataset--a crowdsourced image archive spanning the British Isles, including remote regions lacking POIs and street-level imagery. Our approach addresses a Kaggle competition\footnote{this https URL} task based on a subset of Geograph's 8M images, with strict evaluation: exact match accuracy is required across 49 possible tags. We show that combining location and title embeddings with image features improves accuracy over using image embeddings alone. We release a lightweight pipeline\footnote{this https URL} that trains on a modest laptop, using pre-trained CLIP image and text embeddings and a simple classification head. Predicted tags can support downstream tasks such as building location embedders for GeoAI applications, enriching spatial understanding in data-sparse regions.
View on arXiv@article{ilyankou2025_2506.12214,
title={ CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images },
author={ Ilya Ilyankou and Natchapon Jongwiriyanurak and Tao Cheng and James Haworth },
journal={arXiv preprint arXiv:2506.12214},
year={ 2025 }
}