{"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/pp-yolov2-a-practical-object-detector","title":"PP-YOLOv2: A Practical Object Detector","arxiv_id":"2104.10419","date":"2021-04-21","proceeding":null,"authors":["Xin Huang","Xinxin Wang","Wenyu Lv","Xiaying Bai","Xiang Long","Kaipeng Deng","Qingqing Dang","Shumin Han","Qiwen Liu","Xiaoguang Hu","dianhai yu","Yanjun Ma","Osamu Yoshie"],"abstract":"Being effective and efficient is essential to an object detector for practical use. To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged. This paper will analyze a collection of refinements and empirically evaluate their impact on the final model performance through incremental ablation study. Things we tried that didn't work will also be discussed. By combining multiple effective refinements, we boost PP-YOLO's performance from 45.9% mAP to 49.5% mAP on COCO2017 test-dev. Since a significant margin of performance has been made, we present PP-YOLOv2. In terms of speed, PP-YOLOv2 runs in 68.9FPS at 640x640 input size. Paddle inference engine with TensorRT, FP16-precision, and batch size = 1 further improves PP-YOLOv2's infer speed, which achieves 106.5 FPS. Such a performance surpasses existing object detectors with roughly the same amount of parameters (i.e., YOLOv4-CSP, YOLOv5l). Besides, PP-YOLOv2 with ResNet101 achieves 50.3% mAP on COCO2017 test-dev. Source code is at https://github.com/PaddlePaddle/PaddleDetection.","url_abs":"https://arxiv.org/abs/2104.10419v1","url_pdf":"https://arxiv.org/pdf/2104.10419v1.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":"pp-yolov2-a-practical-object-detector","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"bottom-up-path-augmentation","method_name":"Bottom-up Path Augmentation"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"coordconv","method_name":"CoordConv"},{"method_slug":"deformable-convolution","method_name":"Deformable Convolution"},{"method_slug":"dropblock","method_name":"DropBlock"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grid-sensitive","method_name":"Grid Sensitive"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"matrix-nms","method_name":"Matrix NMS"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"mixup","method_name":"Mixup"},{"method_slug":"pafpn","method_name":"PAFPN"},{"method_slug":"pp-yolo","method_name":"PP-YOLO"},{"method_slug":"pp-yolov2","method_name":"PP-YOLOv2"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pp-yolov2","name":"PP-YOLOv2","full_name":"PP-YOLOv2"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.10419","atlas_url":"https://app.syntology.ai/?focus=2104.10419","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":"2104.10419"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.10419\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.10419"},"call":"get_concepts_for_paper(arxiv_id=\"2104.10419\")"}],"by_repo":[{"repo":"PaddlePaddle/PaddleDetection","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.16250"],"harvested_for_calls":[{"arxiv_id":"2203.16250","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.16250"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.16250\")"}]}],"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":"02778196eebba9fde4a4e33badbc2b92e16f044ff3cdef71a906e07fa54f3cfb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}