2018/09/19 by Evan Sheehan, Sheehan, Evan, Burak Uzkent +12 · 5 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #cs.CL #cs.CV
paper · pdf · doi:10.48550/arxiv.1809.10236
arxiv created 2018/09/19 · openalex publication_date 2018/09/19 · arxiv updated 2018/09/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped source of rich, georeferenced textual information with global coverage. We construct a novel large-scale, multi-modal dataset by pairing geo-referenced Wikipedia articles with satellite imagery of their corresponding locations. To prove the efficacy of this dataset, we focus on the African continent and train a deep network to classify images based on labels extracted from articles. We then fine-tune the model on a human annotated dataset and demonstrate that this weak form of supervision can drastically reduce the quantity of human annotated labels and time required for downstream tasks.