Detecting Cars in Posted Images: Adjusting Model's Softmax Threshold for Increased Precision

Adjusting Model's Softmax Threshold

Question

You work for a social media company.

You need to detect whether posted images contain cars.

Each training example is a member of exactly one class.

You have trained an object detection neural network and deployed the model version to AI Platform Prediction for evaluation.

Before deployment, you created an evaluation job and attached it to the AI Platform Prediction model version.

You notice that the precision is lower than your business requirements allow.

How should you adjust the model's final layer softmax threshold to increase precision?

Answers

Explanations

Click on the arrows to vote for the correct answer

A. B. C. D.

D.

To increase precision in the context of object detection, we need to decrease the number of false positives, which means reducing the probability of misclassifying non-car objects as cars. This can be achieved by adjusting the model's final layer softmax threshold.

The softmax threshold is the minimum probability that the model requires to assign a particular class to an object. By increasing the threshold, we increase the model's confidence in its predictions and reduce the likelihood of false positives.

Therefore, the correct answer is D. Decrease the number of false negatives.