Litcius/Paper detail

YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection

Yuming Chen, Xinbin Yuan, Jiabao Wang, Ruiqi Wu, Xiang Li, Qibin Hou, Ming‐Ming Cheng

2025IEEE Transactions on Pattern Analysis and Machine Intelligence162 citationsDOI

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 multi-branch features of the basic block and convolutions with different kernel sizes affect the detection performance of objects at different scales. The outcome is a new strategy that can significantly enhance multi-scale feature representations of real-time object detectors. To verify the effectiveness of our work, 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, RTMDet, and YOLO-v8. Taking the XS version of YOLO-MS as an example, it can achieve an AP score of 42+% on MS COCO, which is about 2% higher than RTMDet with the same model size. Furthermore, our work can also serve as a plug-and-play module for other YOLO models. Typically, our method significantly advances the APs, APl, and AP of YOLOv8-N from 18%+, 52%+, and 37%+ to 20%+, 55%+, and 40%+, respectively, with even fewer parameters and MACs.

Topics & Concepts

Artificial intelligenceObject detectionComputer scienceScale (ratio)Representation (politics)Object (grammar)Computer visionCognitive neuroscience of visual object recognitionPattern recognition (psychology)Machine learningLawPolitical sciencePoliticsPhysicsQuantum mechanicsAdvanced Image and Video Retrieval TechniquesAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning