{"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/to-boost-or-not-to-boost-on-the-limits-of","title":"To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection","arxiv_id":"1701.01692","date":"2017-01-06","proceeding":null,"authors":["Eshed Ohn-Bar","Mohan M. Trivedi"],"abstract":"We aim to study the modeling limitations of the commonly employed boosted\ndecision trees classifier. Inspired by the success of large, data-hungry visual\nrecognition models (e.g. deep convolutional neural networks), this paper\nfocuses on the relationship between modeling capacity of the weak learners,\ndataset size, and dataset properties. A set of novel experiments on the Caltech\nPedestrian Detection benchmark results in the best known performance among\nnon-CNN techniques while operating at fast run-time speed. Furthermore, the\nperformance is on par with deep architectures (9.71% log-average miss rate),\nwhile using only HOG+LUV channels as features. The conclusions from this study\nare shown to generalize over different object detection domains as demonstrated\non the FDDB face detection benchmark (93.37% accuracy). Despite the impressive\nperformance, this study reveals the limited modeling capacity of the common\nboosted trees model, motivating a need for architectural changes in order to\ncompete with multi-level and very deep architectures.","url_abs":"http://arxiv.org/abs/1701.01692v1","url_pdf":"http://arxiv.org/pdf/1701.01692v1.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":[],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"LDCF+","rank_in_archive_order":35,"of":40,"metrics":{"AP":"0.564"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"LDCF+","rank_in_archive_order":32,"of":37,"metrics":{"AP":"0.772"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}