{"url":"/method/pp-yolo","slug":"pp-yolo","name":"PP-YOLO","full_name":"PP-YOLO","full_name_withheld":false,"description_markdown":"**PP-YOLO** is an object detector based on [YOLOv3](https://paperswithcode.com/method/yolov3). It mainly tries to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged. Some of these changes include:\r\n\r\n- Changing the [DarkNet-53](https://paperswithcode.com/method/darknet-53) backbone with ResNet50-vd. Some of the convolutional layers in ResNet50-vd are also replaced with [deformable convolutional layers](https://paperswithcode.com/method/deformable-convolution).\r\n- A larger batch size is used - changing from 64 to 192.\r\n- An exponentially moving average is used for the parameters.\r\n- [DropBlock](https://paperswithcode.com/method/dropblock) is applied to the [FPN](https://paperswithcode.com/method/fpn).\r\n- An IoU loss is used.\r\n- An IoU prediction branch is added to measure the accuracy of localization.\r\n- [Grid Sensitive](https://paperswithcode.com/method/grid-sensitive) is used, similar to [YOLOv4](https://paperswithcode.com/method/yolov4).\r\n- [Matrix NMS](https://paperswithcode.com/method/matrix-nms) is used.\r\n- [CoordConv](https://paperswithcode.com/method/coordconv) is used for the [FPN](https://paperswithcode.com/method/fpn), replacing the 1x1 convolution layer, and also the first convolution layer in the detection head.\r\n- [Spatial Pyramid Pooling](https://paperswithcode.com/method/spatial-pyramid-pooling) is used for the top feature map.","description_state":"present","introduced_year":null,"introduced_by":{"title":"PP-YOLO: An Effective and Efficient Implementation of Object Detector","paper":"/paper/pp-yolo-an-effective-and-efficient","first_author":"Xiang Long","n_authors":11,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pp-yolo-an-effective-and-efficient"},"source":{"url":"https://arxiv.org/abs/2007.12099v3","title":"PP-YOLO: An Effective and Efficient Implementation of Object Detector","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"One-Stage Object Detection Models","url":"/methods/category/one-stage-object-detection-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Object Detection Models","url":"/methods/category/object-detection-models","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","title":"PP-YOLOE: An evolved version of YOLO","date":"2022-03-30","arxiv_id":"2203.16250","n_code_links":8,"syntology":{"ran":5,"of":27,"unverified":22,"pointer_only":0}},{"paper":null,"title":"In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos","date":"2022-01-27","arxiv_id":"2201.11450","n_code_links":0,"syntology":null},{"paper":"/paper/pp-yolov2-a-practical-object-detector","title":"PP-YOLOv2: A Practical Object Detector","date":"2021-04-21","arxiv_id":"2104.10419","n_code_links":1,"syntology":null},{"paper":"/paper/pp-yolo-an-effective-and-efficient","title":"PP-YOLO: An Effective and Efficient Implementation of Object Detector","date":"2020-07-23","arxiv_id":"2007.12099","n_code_links":5,"syntology":null}],"papers_shown":4,"tasks":[{"task":"/task/object","name":"Object","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":2},{"task":"/task/2d-object-detection","name":"2D Object Detection","papers":1},{"task":"/task/dense-object-detection","name":"Dense Object Detection","papers":1},{"task":"/task/multi-object-tracking","name":"Multi-Object Tracking","papers":1},{"task":"/task/multiple-object-tracking","name":"Multiple Object Tracking","papers":1},{"task":"/task/online-multi-object-tracking","name":"Online Multi-Object Tracking","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pp-yolo"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}