{"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/pelee-a-real-time-object-detection-system-on","title":"Pelee: A Real-Time Object Detection System on Mobile Devices","arxiv_id":"1804.06882","date":"2018-04-18","proceeding":"NeurIPS 2018","authors":["Robert J. Wang","Xiang Li","Charles X. Ling"],"abstract":"An increasing need of running Convolutional Neural Network (CNN) models on\nmobile devices with limited computing power and memory resource encourages\nstudies on efficient model design. A number of efficient architectures have\nbeen proposed in recent years, for example, MobileNet, ShuffleNet, and\nMobileNetV2. However, all these models are heavily dependent on depthwise\nseparable convolution which lacks efficient implementation in most deep\nlearning frameworks. In this study, we propose an efficient architecture named\nPeleeNet, which is built with conventional convolution instead. On ImageNet\nILSVRC 2012 dataset, our proposed PeleeNet achieves a higher accuracy and over\n1.8 times faster speed than MobileNet and MobileNetV2 on NVIDIA TX2. Meanwhile,\nPeleeNet is only 66% of the model size of MobileNet. We then propose a\nreal-time object detection system by combining PeleeNet with Single Shot\nMultiBox Detector (SSD) method and optimizing the architecture for fast speed.\nOur proposed detection system2, named Pelee, achieves 76.4% mAP (mean average\nprecision) on PASCAL VOC2007 and 22.4 mAP on MS COCO dataset at the speed of\n23.6 FPS on iPhone 8 and 125 FPS on NVIDIA TX2. The result on COCO outperforms\nYOLOv2 in consideration of a higher precision, 13.6 times lower computational\ncost and 11.3 times smaller model size.","url_abs":"http://arxiv.org/abs/1804.06882v3","url_pdf":"http://arxiv.org/pdf/1804.06882v3.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":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/Baibaifan/An-Improved-PeleeNet-Algorithm-with-Feature-Pyramid-Networks-for-Image-Detection-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/Qengineering/PeleeNet_SSD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/flytocc/PeleeNet-paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":null},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/koshian2/PeleeNet-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/wpf535236337/pytorch-peleenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/yxlijun/Pelee.Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/PaddlePaddle/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pelee-a-real-time-object-detection-system-on","repo_url":"https://github.com/ginn24/Pelee-TensorRT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.06882","atlas_url":"https://app.syntology.ai/?focus=1804.06882","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":"1804.06882"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.06882\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.06882"},"call":"get_concepts_for_paper(arxiv_id=\"1804.06882\")"}],"by_repo":[{"repo":"Baibaifan/An-Improved-PeleeNet-Algorithm-with-Feature-Pyramid-Networks-for-Image-Detection-","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Qengineering/PeleeNet_SSD","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"flytocc/PeleeNet-paddle","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"koshian2/PeleeNet-Keras","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"osmr/imgclsmob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.08955"],"harvested_for_calls":[{"arxiv_id":"2004.08955","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.08955"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.08955\")"}]},{"repo":"wpf535236337/pytorch-peleenet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yxlijun/Pelee.Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PaddlePaddle/PaddleClas","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ginn24/Pelee-TensorRT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"aa1c35f6ef232694d7783f6d3197ed134578822ab25808625740d50d3277d65e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}