{"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/faster-r-cnn-features-for-instance-search","title":"Faster R-CNN Features for Instance Search","arxiv_id":"1604.08893","date":"2016-04-29","proceeding":null,"authors":["Amaia Salvador","Xavier Giro-i-Nieto","Ferran Marques","Shin'ichi Satoh"],"abstract":"Image representations derived from pre-trained Convolutional Neural Networks\n(CNNs) have become the new state of the art in computer vision tasks such as\ninstance retrieval. This work explores the suitability for instance retrieval\nof image- and region-wise representations pooled from an object detection CNN\nsuch as Faster R-CNN. We take advantage of the object proposals learned by a\nRegion Proposal Network (RPN) and their associated CNN features to build an\ninstance search pipeline composed of a first filtering stage followed by a\nspatial reranking. We further investigate the suitability of Faster R-CNN\nfeatures when the network is fine-tuned for the same objects one wants to\nretrieve. We assess the performance of our proposed system with the Oxford\nBuildings 5k, Paris Buildings 6k and a subset of TRECVid Instance Search 2013,\nachieving competitive results.","url_abs":"http://arxiv.org/abs/1604.08893v1","url_pdf":"http://arxiv.org/pdf/1604.08893v1.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":"faster-r-cnn-features-for-instance-search","repo_url":"https://github.com/imatge-upc/retrieval-2016-deepvision","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"faster-r-cnn-features-for-instance-search","repo_url":"https://github.com/hbwang1427/image_retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"faster-r-cnn-features-for-instance-search","repo_url":"https://github.com/vohoaiviet/retrieval-2016-deepvision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"instance-search","task_name":"Instance Search"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"retrieval","task_name":"Retrieval"},{"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":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.08893","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}