Revisiting IM2GPS In The Deep Learning Era

Abstract

Image geolocalization, inferring the geographic location of an image, is a challenging computer vision problem with many potential applications. The recent state-of-the-art approach to this problem is a deep image classification approach in which the world is spatially divided into cells and a deep network is trained to predict the correct cell for a given image. We propose to combine this approach with the original Im2GPS approach in which a query image is matched against a database of geotagged images and the location is inferred from the retrieved set. We estimate the geographic location of a query image by applying kernel density estimation to the locations of its nearest neighbors in the reference database. Interestingly, we find that the best features for our retrieval task are derived from networks trained with classification loss even though we do not use a classification approach at test time. Training with classification loss outperforms several deep feature learning methods

Stats

• citations88
• S2 citations—
• github stars0
• HF likes0
• heat score14.62
• arxiv keyvo2017revisiting

Related papers

• Img2loc: Revisiting Image Geolocalization Using Multi-modality Foundation Models And Image-based Retrieval-augmented Generation (2024)9.23
• Leveraging Efficientnet And Contrastive Learning For Accurate Global-scale Location Estimation (2021)9.03
• Improved Visual Localization Via Graph Smoothing (2019)0.00
• Cross-view Image Matching For Geo-localization In Urban Environments (2017)17.16
• Why-so-deep: Towards Boosting Previously Trained Models For Visual Place Recognition (2022)7.81
• Multiview Image-based Localization (2025)0.00
• G3: An Effective And Adaptive Framework For Worldwide Geolocalization Using Large Multi-modality Models (2024)3.58
• Deep Metric Learning For Ground Images (2021)0.00