Anchor Boxes

https://towardsdatascience.com/anchor-boxes-the-key-to-quality-object-detection-ddf9d612d4f9

Anchor boxes allows learning algorithm to specialize tall skinny objects, and wide objects.

Anchor boxes sizes are chosen.

K-Means Clustering algorithm to choose size of anchor boxes.

Detect multiple objects.

Anchor box algorithm:

• Each object in training image is assigned to grid cell that contains object’s midpoint and anchor box for the grid cell with the highest IoU.
• (grid cell, anchor box)

State of the art object detection systems currently do the following:

1. Create thousands of “anchor boxes” or “prior boxes” for each predictor that represent the ideal location, shape and size of the object it specializes in predicting.
2. For each anchor box, calculate which object’s bounding box has the highest IoU.
3. If the highest IOU is greater than 50%, tell the anchor box that it should detect the object that gave the highest IOU.
4. Otherwise if the IOU is greater than 40%, tell the neural network that the true detection is ambiguous and not to learn from that example.
5. If the highest IOU is less than 40%, then the anchor box should predict that there is no object.