{"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/object-detection-via-a-multi-region-semantic","title":"Object detection via a multi-region & semantic segmentation-aware CNN model","arxiv_id":"1505.01749","date":"2015-05-07","proceeding":null,"authors":["Spyros Gidaris","Nikos Komodakis"],"abstract":"We propose an object detection system that relies on a multi-region deep\nconvolutional neural network (CNN) that also encodes semantic\nsegmentation-aware features. The resulting CNN-based representation aims at\ncapturing a diverse set of discriminative appearance factors and exhibits\nlocalization sensitivity that is essential for accurate object localization. We\nexploit the above properties of our recognition module by integrating it on an\niterative localization mechanism that alternates between scoring a box proposal\nand refining its location with a deep CNN regression model. Thanks to the\nefficient use of our modules, we detect objects with very high localization\naccuracy. On the detection challenges of PASCAL VOC2007 and PASCAL VOC2012 we\nachieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published\nwork by a significant margin.","url_abs":"http://arxiv.org/abs/1505.01749v3","url_pdf":"http://arxiv.org/pdf/1505.01749v3.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":"object-detection-via-a-multi-region-semantic","repo_url":"https://github.com/gidariss/mrcnn-object-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.01749","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}