-1

I want to retrain the object detector Yolov4 to recognize figures of the board game Ticket to Ride. While gathering pictures i was searching for an idea to reduce the amount of needed pictures.

I was wondering if more instances of an object/class in a picture means more "training per picture" which leads to "i need less pictures"

Is this correct? If not could you try to explain in simple terms?

Fomps
  • 1
  • 2

1 Answers1

0

On the roboflow page, they say that the YOLOv4 breaks detecting objects into two pieces:

  1. regression to identify object positioning via bounding boxes;
  2. classification to classify the objects into classes.

Regression (analysis) is - in short - a method of analysis that tries to find the data (images in your case) that is relevant. Classification - on the other hand - transforms the ‘interesting’ images from the previous step into a class (which is ’train piece’, ’tracks’, ’station’ or something else that is worth separating from the rest).

Now, to answer your question: “no, you need more pictures.” When taking more pictures, YOLOv4 is using more samples make / test a more accurate classification. Yet, you have to be careful what you want to classify. You do want the algorithm to extract a ’train’ class from an image, but not an ‘ocean’ class for example. To prevent this, make more (different) pictures of the classes you want to have!

desertnaut
  • 57,590
  • 26
  • 140
  • 166
acyclone
  • 58
  • 6
  • So it's better to have pictures in various settings with a single figure if than having many figures in the same amount of pictures – Fomps Apr 01 '21 at 17:31
  • A good way to create classes is having a number of pictures per class. So, for example, 10 pictures of the board, 10 pictures of `trains`, 10 pictures of `tracks`, etc. – acyclone Apr 01 '21 at 17:49