{"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/relief-r-cnn-utilizing-convolutional-features","title":"Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection","arxiv_id":"1601.06719","date":"2016-01-25","proceeding":null,"authors":["Guiying Li","Junlong Liu","Chunhui Jiang","Liangpeng Zhang","Minlong Lin","Ke Tang"],"abstract":"R-CNN style methods are sorts of the state-of-the-art object detection\nmethods, which consist of region proposal generation and deep CNN\nclassification. However, the proposal generation phase in this paradigm is\nusually time consuming, which would slow down the whole detection time in\ntesting. This paper suggests that the value discrepancies among features in\ndeep convolutional feature maps contain plenty of useful spatial information,\nand proposes a simple approach to extract the information for fast region\nproposal generation in testing. The proposed method, namely Relief R-CNN\n(R2-CNN), adopts a novel region proposal generator in a trained R-CNN style\nmodel. The new generator directly generates proposals from convolutional\nfeatures by some simple rules, thus resulting in a much faster proposal\ngeneration speed and a lower demand of computation resources. Empirical studies\nshow that R2-CNN could achieve the fastest detection speed with comparable\naccuracy among all the compared algorithms in testing.","url_abs":"http://arxiv.org/abs/1601.06719v4","url_pdf":"http://arxiv.org/pdf/1601.06719v4.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":"relief-r-cnn-utilizing-convolutional-features","repo_url":"https://github.com/IdiosyncraticDragon/relief_rcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"r-cnn","method_name":"R-CNN"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}