{"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/adaptive-object-detection-using-adjacency-and","title":"Adaptive Object Detection Using Adjacency and Zoom Prediction","arxiv_id":"1512.07711","date":"2015-12-24","proceeding":"CVPR 2016 6","authors":["Yongxi Lu","Tara Javidi","Svetlana Lazebnik"],"abstract":"State-of-the-art object detection systems rely on an accurate set of region\nproposals. Several recent methods use a neural network architecture to\nhypothesize promising object locations. While these approaches are\ncomputationally efficient, they rely on fixed image regions as anchors for\npredictions. In this paper we propose to use a search strategy that adaptively\ndirects computational resources to sub-regions likely to contain objects.\nCompared to methods based on fixed anchor locations, our approach naturally\nadapts to cases where object instances are sparse and small. Our approach is\ncomparable in terms of accuracy to the state-of-the-art Faster R-CNN approach\nwhile using two orders of magnitude fewer anchors on average. Code is publicly\navailable.","url_abs":"http://arxiv.org/abs/1512.07711v2","url_pdf":"http://arxiv.org/pdf/1512.07711v2.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":"adaptive-object-detection-using-adjacency-and","repo_url":"https://github.com/luyongxi/az-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"prediction","task_name":"Prediction"},{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}