{"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/ron-reverse-connection-with-objectness-prior","title":"RON: Reverse Connection with Objectness Prior Networks for Object Detection","arxiv_id":"1707.01691","date":"2017-07-06","proceeding":"CVPR 2017 7","authors":["Tao Kong","Fuchun Sun","Anbang Yao","Huaping Liu","Ming Lu","Yurong Chen"],"abstract":"We present RON, an efficient and effective framework for generic object\ndetection. Our motivation is to smartly associate the best of the region-based\n(e.g., Faster R-CNN) and region-free (e.g., SSD) methodologies. Under fully\nconvolutional architecture, RON mainly focuses on two fundamental problems: (a)\nmulti-scale object localization and (b) negative sample mining. To address (a),\nwe design the reverse connection, which enables the network to detect objects\non multi-levels of CNNs. To deal with (b), we propose the objectness prior to\nsignificantly reduce the searching space of objects. We optimize the reverse\nconnection, objectness prior and object detector jointly by a multi-task loss\nfunction, thus RON can directly predict final detection results from all\nlocations of various feature maps. Extensive experiments on the challenging\nPASCAL VOC 2007, PASCAL VOC 2012 and MS COCO benchmarks demonstrate the\ncompetitive performance of RON. Specifically, with VGG-16 and low resolution\n384X384 input size, the network gets 81.3% mAP on PASCAL VOC 2007, 80.7% mAP on\nPASCAL VOC 2012 datasets. Its superiority increases when datasets become larger\nand more difficult, as demonstrated by the results on the MS COCO dataset. With\n1.5G GPU memory at test phase, the speed of the network is 15 FPS, 3X faster\nthan the Faster R-CNN counterpart.","url_abs":"http://arxiv.org/abs/1707.01691v1","url_pdf":"http://arxiv.org/pdf/1707.01691v1.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":"ron-reverse-connection-with-objectness-prior","repo_url":"https://github.com/taokong/RON","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.01691","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}