{"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/zoom-out-and-in-network-with-recursive","title":"Zoom Out-and-In Network with Recursive Training for Object Proposal","arxiv_id":"1702.05711","date":"2017-02-19","proceeding":null,"authors":["Hongyang Li","Yu Liu","Wanli Ouyang","Xiaogang Wang"],"abstract":"In this paper, we propose a zoom-out-and-in network for generating object\nproposals. We utilize different resolutions of feature maps in the network to\ndetect object instances of various sizes. Specifically, we divide the anchor\ncandidates into three clusters based on the scale size and place them on\nfeature maps of distinct strides to detect small, medium and large objects,\nrespectively. Deeper feature maps contain region-level semantics which can help\nshallow counterparts to identify small objects. Therefore we design a zoom-in\nsub-network to increase the resolution of high level features via a\ndeconvolution operation. The high-level features with high resolution are then\ncombined and merged with low-level features to detect objects. Furthermore, we\ndevise a recursive training pipeline to consecutively regress region proposals\nat the training stage in order to match the iterative regression at the testing\nstage. We demonstrate the effectiveness of the proposed method on ILSVRC DET\nand MS COCO datasets, where our algorithm performs better than the\nstate-of-the-arts in various evaluation metrics. It also increases average\nprecision by around 2% in the detection system.","url_abs":"http://arxiv.org/abs/1702.05711v1","url_pdf":"http://arxiv.org/pdf/1702.05711v1.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":"zoom-out-and-in-network-with-recursive","repo_url":"https://github.com/hli2020/zoom_network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}