Review On YOLOv3

Original article was published on Deep Learning on Medium

In this article we will go through YOLOv3 paper by Joseph Redmon and Ali Farhadi. Before going through this article I would recommend you to go through my reviews on YOLOv1 and YOLOv2.

YOLOv3 was published with few incremental improvements on YOLOv2.The main 2 improvements were.

  • Started using Darknet-53 as backbone instead of Darknet19
  • Feature map up sampling and concatenation

We will divide the article to 5 parts:

  1. Bounding box prediction
  2. Class prediction
  3. Prediction across different scales
  4. Darknet-53
  5. Performance

Now we will get into much more depth.First we will discuss about bounding box predictions