Learned Contextual Feature Reweighting for Image Geo-Localization

Hyo Jin Kim, Enrique Dunn, Jan-Michael Frahm; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2136-2145


We address the problem of large scale image geo-localization where the location of an image is estimated by identifying geo-tagged reference images depicting the same place. We propose a novel model for learning image representations that integrates context-aware feature reweighting in order to effectively focus on regions that positively contribute to geo-localization. In particular, we introduce a Contextual Reweighting Network (CRN) that predicts the importance of each region in the feature map based on the image context. Our model is learned end-to-end for the image geo-localization task, and requires no annotation other than image geo-tags for training. In experimental results, the proposed approach significantly outperforms the previous state-of-the-art on the standard geo-localization benchmark datasets. We also demonstrate that our CRN discovers task-relevant contexts without any additional supervision.

Related Material

[pdf] [Supp] [poster] [video]
author = {Jin Kim, Hyo and Dunn, Enrique and Frahm, Jan-Michael},
title = {Learned Contextual Feature Reweighting for Image Geo-Localization},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}