{"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/stuffnet-using-stuff-to-improve-object","title":"StuffNet: Using 'Stuff' to Improve Object Detection","arxiv_id":"1610.05861","date":"2016-10-19","proceeding":null,"authors":["Samarth Brahmbhatt","Henrik I. Christensen","James Hays"],"abstract":"We propose a Convolutional Neural Network (CNN) based algorithm - StuffNet -\nfor object detection. In addition to the standard convolutional features\ntrained for region proposal and object detection [31], StuffNet uses\nconvolutional features trained for segmentation of objects and 'stuff'\n(amorphous categories such as ground and water). Through experiments on Pascal\nVOC 2010, we show the importance of features learnt from stuff segmentation for\nimproving object detection performance. StuffNet improves performance from\n18.8% mAP to 23.9% mAP for small objects. We also devise a method to train\nStuffNet on datasets that do not have stuff segmentation labels. Through\nexperiments on Pascal VOC 2007 and 2012, we demonstrate the effectiveness of\nthis method and show that StuffNet also significantly improves object detection\nperformance on such datasets.","url_abs":"http://arxiv.org/abs/1610.05861v2","url_pdf":"http://arxiv.org/pdf/1610.05861v2.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":"stuffnet-using-stuff-to-improve-object","repo_url":"https://github.com/samarth-robo/py-faster-rcnn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}