{"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/cad-net-a-context-aware-detection-network-for","title":"CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery","arxiv_id":"1903.00857","date":"2019-03-03","proceeding":null,"authors":["Gongjie Zhang","Shijian Lu","Wei zhang"],"abstract":"Accurate and robust detection of multi-class objects in optical remote\nsensing images is essential to many real-world applications such as urban\nplanning, traffic control, searching and rescuing, etc. However,\nstate-of-the-art object detection techniques designed for images captured using\nground-level sensors usually experience a sharp performance drop when directly\napplied to remote sensing images, largely due to the object appearance\ndifferences in remote sensing images in term of sparse texture, low contrast,\narbitrary orientations, large scale variations, etc. This paper presents a\nnovel object detection network (CAD-Net) that exploits attention-modulated\nfeatures as well as global and local contexts to address the new challenges in\ndetecting objects from remote sensing images. The proposed CAD-Net learns\nglobal and local contexts of objects by capturing their correlations with the\nglobal scene (at scene-level) and the local neighboring objects or features (at\nobject-level), respectively. In addition, it designs a spatial-and-scale-aware\nattention module that guides the network to focus on more informative regions\nand features as well as more appropriate feature scales. Experiments over two\npublicly available object detection datasets for remote sensing images\ndemonstrate that the proposed CAD-Net achieves superior detection performance.\nThe implementation codes will be made publicly available for facilitating\nfuture researches.","url_abs":"http://arxiv.org/abs/1903.00857v1","url_pdf":"http://arxiv.org/pdf/1903.00857v1.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":"cad-net-a-context-aware-detection-network-for","repo_url":"https://github.com/ZhangGongjie/CAD-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"novel-object-detection","task_name":"Novel Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.00857","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}