YOLOv3 is a popular and fast object detection algorithm, but unfortunately not as accurate as RetinaNet or Faster RCNN, which you can see in the image below. In this article I will discuss two simple yet powerful approaches suggested in recent object detection literature to improve YOLOv3. These are: 1) Different Training Heuristics for Object Detection, and 2) Adaptive Spatial Fusion of Feature Pyramids. We will look at them one by one. Let's dig into it.
This is a companion discussion topic for the original entry at https://blog.paperspace.com/improving-yolo