I am new to AI/CV domain.
I see a lot of tutorials on "training a YOLOv5 on custom dataset".
As per my knowledge,
Basically, YOLO is a giant neural network trained on a particular set of training images with a particular set of labels. This neural network is trained and has a set of weights.
If the neural network is trained on a particular set of labels (lets say car, plane, ball, etc), how can I train it for my totally different labels/images (lets say I want to build a classifier on bald vs non bald men).
How is that possible?
Is it Transfer Learning which we are doing when we train it on custom dataset?
And why to use YOLO architecture on small label set if its made to work on a big label set?