YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection. (arXiv:2308.05480v1 [cs.CV])

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 …

aim arxiv community core design detection investigations kernel objects performance real-time representation representation learning scale series strategy yolo