> We can clearly see that YOLOv6s detects more objects in the image and has higher confidence about their label.
If actually look at the images they provide directly above:
In the first image, the older one detects one extra tie. In the second image, the objects detected are the same. In the third image, the older one detects a stop sign, and this new network (no, let's not call it YOLOv6) appears to get confused by the two cars behind one another and detects two objects, but the bounding boxes of the objects includes both, it doesn't look like it actually separates them. But to be fair to them, they do detect an additional person on the left.
If actually look at the images they provide directly above:
In the first image, the older one detects one extra tie. In the second image, the objects detected are the same. In the third image, the older one detects a stop sign, and this new network (no, let's not call it YOLOv6) appears to get confused by the two cars behind one another and detects two objects, but the bounding boxes of the objects includes both, it doesn't look like it actually separates them. But to be fair to them, they do detect an additional person on the left.