“YOLOv3: An Incremental Improvement”, Joseph Redmon, Ali Farhadi2018-04-08 (CNN; backlinks; similar)⁠:

[cf. YOLOv2, YOLOv4, YOLOv5] We present some updates to YOLOv1!

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 320×320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but 3 times faster. When we look at the old 0.5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Nvidia Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8× faster.

As always, all the code is online at https://pjreddie.com/darknet/yolo/.

Backlinks:

Similar Links: