{"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/focal-loss-in-3d-object-detection","title":"Focal Loss in 3D Object Detection","arxiv_id":"1809.06065","date":"2018-09-17","proceeding":null,"authors":["Peng Yun","Lei Tai","Yu-An Wang","Chengju Liu","Ming Liu"],"abstract":"3D object detection is still an open problem in autonomous driving scenes.\nWhen recognizing and localizing key objects from sparse 3D inputs, autonomous\nvehicles suffer from a larger continuous searching space and higher\nfore-background imbalance compared to image-based object detection. In this\npaper, we aim to solve this fore-background imbalance in 3D object detection.\nInspired by the recent use of focal loss in image-based object detection, we\nextend this hard-mining improvement of binary cross entropy to\npoint-cloud-based object detection and conduct experiments to show its\nperformance based on two different 3D detectors: 3D-FCN and VoxelNet. The\nevaluation results show up to 11.2AP gains through the focal loss in a wide\nrange of hyperparameters for 3D object detection.","url_abs":"http://arxiv.org/abs/1809.06065v3","url_pdf":"http://arxiv.org/pdf/1809.06065v3.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":"focal-loss-in-3d-object-detection","repo_url":"https://github.com/pyun-ram/FL3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"focal-loss","method_name":"Focal Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.06065","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}