Use Case: False Positives of a Particular Class

Overview

There may be times when a Model has multiple False Positives for a particular Class. This article will help you:

• Identify the signal and error
• Diagnose the root cause
• Implement the fix

Identify the Signal and Error

When you analyze your Model and notice a high amount of False Positives, look through your data to confirm these False Positives.

Error Signal

If the Model has several False Positives, you may notice these signs:

• Several False Positives of a particular Class
• The Model identifies a specific Class, but that Class is not in the image

Diagnose the Root Cause

You can diagnose the root cause by parsing through your training data. For this use case of False Positives of a particular Class, there are five potential causes:

1. There are too many of one type of example, like NG examples, so the dataset induces bias in the Model.
2. The Segmentation output has small patches/pixels of "noise".
3. The Confidence Threshold is too low.
4. The environmental noise causes OK regions to look like detectable areas.
5. The labeling convention does not differentiate between OK and NG regions, or the labelers accidentally drew extra labels.

Take a look at the example image below. The Model detected several areas that it should not have; thus, this image has multiple False Positives.

There Are Several False Positive Instances 

Fix

Now that you've learned how to identify the signal and diagnose the cause, you can iterate your data to achieve higher accuracy by following these tips: