{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/zoom-out-and-in-network-with-map-attention","title":"Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection","arxiv_id":"1709.04347","date":"2017-09-13","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. A key observation is that it is difficult to classify anchors of\ndifferent sizes with the same set of features. Anchors of different sizes\nshould be placed accordingly based on different depth within a network: smaller\nboxes on high-resolution layers with a smaller stride while larger boxes on\nlow-resolution counterparts with a larger stride. Inspired by the conv/deconv\nstructure, we fully leverage the low-level local details and high-level\nregional semantics from two feature map streams, which are complimentary to\neach other, to identify the objectness in an image. A map attention decision\n(MAD) unit is further proposed to aggressively search for neuron activations\namong two streams and attend the most contributive ones on the feature learning\nof the final loss. The unit serves as a decisionmaker to adaptively activate\nmaps along certain channels with the solely purpose of optimizing the overall\ntraining loss. One advantage of MAD is that the learned weights enforced on\neach feature channel is predicted on-the-fly based on the input context, which\nis more suitable than the fixed enforcement of a convolutional kernel.\nExperimental results on three datasets, including PASCAL VOC 2007, ImageNet\nDET, MS COCO, demonstrate the effectiveness of our proposed algorithm over\nother state-of-the-arts, in terms of average recall (AR) for region proposal\nand average precision (AP) for object detection.","url_abs":"http://arxiv.org/abs/1709.04347v2","url_pdf":"http://arxiv.org/pdf/1709.04347v2.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-map-attention","repo_url":"https://github.com/hli2020/zoom_network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.04347","atlas_url":"https://app.syntology.ai/?focus=1709.04347","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1709.04347"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1709.04347\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1709.04347"},"call":"get_concepts_for_paper(arxiv_id=\"1709.04347\")"}],"by_repo":[{"repo":"hli2020/zoom_network","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8a98ecc299646da0f445b2dea267a4a810103992fb3a62195e0e8798f8f6b9b8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}