Hierarchical Attention Fusion for Geo-Localization
This work improves geo-localization for computer vision applications, but it appears incremental as it builds on existing retrieval-based approaches with a novel fusion method.
The paper tackles geo-localization as a 2D image retrieval task, addressing robustness issues with scale variations by introducing a hierarchical attention fusion network using multi-scale features, and reports outperforming state-of-the-art methods on benchmarks.
Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. Code is available here: \url{https://github.com/YanLiqi/HAF}.