Find False Positive Predictions

Instances with mismatched predictions & annotations

Description

You can use Nucleus to debug your model predictions to find false positive samples by using mismatch with ground truth annotations.

Pre-reqs: Dataset, Annotations, Predictions

Steps

  1. Open a dataset with annotations & predictions uploaded
  2. Go to the objects tab and open the search options sidebar
  3. Under the model filter select the model you want to use
  4. Under the object filter select false positives i.e. (prediction & annotation mismatch)

The final results will show samples which have been assigned the wrong labels by the model. These items can be used to re-train and improve the model further.