{"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/dafne-a-one-stage-anchor-free-deep-model-for","title":"DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection","arxiv_id":"2109.06148","date":"2021-09-13","proceeding":null,"authors":["Steven Lang","Fabrizio Ventola","Kristian Kersting"],"abstract":"We present DAFNe, a Dense one-stage Anchor-Free deep Network for oriented object detection. As a one-stage model, it performs bounding box predictions on a dense grid over the input image, being architecturally simpler in design, as well as easier to optimize than its two-stage counterparts. Furthermore, as an anchor-free model, it reduces the prediction complexity by refraining from employing bounding box anchors. With DAFNe we introduce an orientation-aware generalization of the center-ness function for arbitrarily oriented bounding boxes to down-weight low-quality predictions and a center-to-corner bounding box prediction strategy that improves object localization performance. Our experiments show that DAFNe outperforms all previous one-stage anchor-free models on DOTA 1.0, DOTA 1.5, and UCAS-AOD and is on par with the best models on HRSC2016.","url_abs":"https://arxiv.org/abs/2109.06148v4","url_pdf":"https://arxiv.org/pdf/2109.06148v4.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":"dafne-a-one-stage-anchor-free-deep-model-for","repo_url":"https://github.com/steven-lang/dafne","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"one-stage-anchor-free-oriented-object-1","task_name":"One-stage Anchor-free Oriented Object Detection"},{"task_slug":"oriented-object-detection","task_name":"Oriented Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"dafne","method_name":"DAFNe"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.06148","atlas_url":"https://app.syntology.ai/?focus=2109.06148","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}