YOLOv3: An Incremental Improvement

作者：Joseph Redmon, Ali Farhadi · 发表于：arXiv (Cornell University) · 年份：2018 · DOI：10.48550/arxiv.1804.02767 · 被引用次数：5883 · 研究领域：Advanced Image and Video Retrieval Techniques、Advanced Neural Network Applications、Retinal Imaging and Analysis

We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't 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 https://pjreddie.com/yolo/