How to use “ignore” class with tensorflow object detection API?

2
votes

I have trained tensorflow object detection model (for num_steps:50000) using SSD (mobilenet-v1) on custom dataset. I got mAP@.50IOU ~0.98 and loss ~1.17. The dataset consist of uno playing card images (skip, reverse, and draw four). On all these cards, model performs pretty well as I have trained model only on these 3 card (around 278 images with 829 bounding boxes (25% bounding box used for testing i.e. validation) collected using mobile phone).

However, I haven’t trained model on any other card but still it detects other cards (inference using webcam).

How can I fix this? Should I also collect other class images (anything other than skip, reverse and draw four cards) and ignore this class in operation? So that model sees this class i.e. Label: Other images during training and doesn’t put any label during inference.

I am not sure how to inform tensorflow object detection API that it should ignore images from Other class.

Can anyone please provide pointer?

Please share your views!

1
pythontensorflowobject-detectionobject-detection-api
It is true that you can add more training samples; but also you can play with the detection score to see if some boxes are relevant to be drawn or not – edkeveked
For the cards skip, reverse and draw four, the trained model doesn't make any faulty detection. However for the unseen cards such as 4,8,9 etc algorithm detects as skip or reverse. – Saurabh Chauhan
What is the detection score or 4, 8 and 9 ? – edkeveked
4,8 and 9 are other cards (in Uno there are cards ranging from 0 to 9, special cards such as skip, reverse, draw two and draw four, wild cards). I have set threshold for the detection score i.e 0.5 – Saurabh Chauhan
Maybe that you can increase your threshold. But there is a risk that it might not detect some of the cards of interest. Adding more training sample as well might help – edkeveked

1 Answers

1
votes

Yes, you need to have another Class which is the object you don't want to detect.

If you don't have this Other Class which includes everything that is not to be detected. The model will compare it to the existing class which is almost identical to the cards of interest.

Some of the factors are:

  1. Similarity of Shape
  2. Similarity of Color
  3. Similarity of Symbols

This is why even though it is not the card of interest (Skip, Reverse, and Draw 4), it would somehow have high "belongingness" to these three classes.

Having another Class to dump all of these can significantly lessen the "belongingness" to the three classes of interest and as much as possible provide A LOT of Data during Training.

If you don't want to have another class.

You could overfit Skip, Reverse, and Draw 4 cards (close to 100%), then increase your threshold value of detection to (70-90%).

Hope this will help you.