YOLOv3: An Incremental Improvement.
arXiv: Computer Vision and Pattern Recognition(2018)
摘要
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network thatu0027s pretty swell. Itu0027s a little bigger than last time but more accurate. Itu0027s still fast though, donu0027t worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8x faster. As always, all the code is online at this https URL
更多查看译文
关键词
yolov3,incremental improvement
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络