{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hierarchical-attention-fusion-for-geo","title":"Hierarchical Attention Fusion for Geo-Localization","arxiv_id":"2102.09186","date":"2021-02-18","proceeding":null,"authors":["Liqi Yan","Yiming Cui","Yingjie Chen","Dongfang Liu"],"abstract":"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}.","url_abs":"https://arxiv.org/abs/2102.09186v1","url_pdf":"https://arxiv.org/pdf/2102.09186v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hierarchical-attention-fusion-for-geo","repo_url":"https://github.com/YanLiqi/HAF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"geo-localization","task_name":"geo-localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.09186","atlas_url":"https://app.syntology.ai/?focus=2102.09186","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}