{"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/yolo-ms-rethinking-multi-scale-representation","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","arxiv_id":"2308.05480","date":"2023-08-10","proceeding":null,"authors":["Yuming Chen","Xinbin Yuan","Ruiqi Wu","Jiabao Wang","Qibin Hou","Ming-Ming Cheng"],"abstract":"We aim at providing the object detection community with an efficient and performant object detector, termed YOLO-MS. The core design is based on a series of investigations on how convolutions with different kernel sizes affect the detection performance of objects at different scales. The outcome is a new strategy that can strongly enhance multi-scale feature representations of real-time object detectors. To verify the effectiveness of our strategy, we build a network architecture, termed YOLO-MS. We train our YOLO-MS on the MS COCO dataset from scratch without relying on any other large-scale datasets, like ImageNet, or pre-trained weights. Without bells and whistles, our YOLO-MS outperforms the recent state-of-the-art real-time object detectors, including YOLO-v7 and RTMDet, when using a comparable number of parameters and FLOPs. Taking the XS version of YOLO-MS as an example, with only 4.5M learnable parameters and 8.7G FLOPs, it can achieve an AP score of 43%+ on MS COCO, which is about 2%+ higher than RTMDet with the same model size. Moreover, our work can also be used as a plug-and-play module for other YOLO models. Typically, our method significantly improves the AP of YOLOv8 from 37%+ to 40%+ with even fewer parameters and FLOPs. Code is available at https://github.com/FishAndWasabi/YOLO-MS.","url_abs":"https://arxiv.org/abs/2308.05480v1","url_pdf":"https://arxiv.org/pdf/2308.05480v1.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":"yolo-ms-rethinking-multi-scale-representation","repo_url":"https://github.com/fishandwasabi/yolo-ms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"rtmdet","method_name":"RTMDet"},{"method_slug":"yolov8","method_name":"YOLOv8"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.05480","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}