{"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/pooling-pyramid-network-for-object-detection","title":"Pooling Pyramid Network for Object Detection","arxiv_id":"1807.03284","date":"2018-07-09","proceeding":null,"authors":["Pengchong Jin","Vivek Rathod","Xiangxin Zhu"],"abstract":"We'd like to share a simple tweak of Single Shot Multibox Detector (SSD)\nfamily of detectors, which is effective in reducing model size while\nmaintaining the same quality. We share box predictors across all scales, and\nreplace convolution between scales with max pooling. This has two advantages\nover vanilla SSD: (1) it avoids score miscalibration across scales; (2) the\nshared predictor sees the training data over all scales. Since we reduce the\nnumber of predictors to one, and trim all convolutions between them, model size\nis significantly smaller. We empirically show that these changes do not hurt\nmodel quality compared to vanilla SSD.","url_abs":"http://arxiv.org/abs/1807.03284v1","url_pdf":"http://arxiv.org/pdf/1807.03284v1.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":"pooling-pyramid-network-for-object-detection","repo_url":"https://github.com/minus31/BlazeFace","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pooling-pyramid-network-for-object-detection","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"ssd","method_name":"SSD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}