Skip to main content
Advertisement

< Back to Article

Improving the accuracy of automated labeling of specimen images datasets via a confidence-based process

Fig 2

Overview of the confidence-based workflow.

By only considering labels over a certain probability threshold, we increase the final accuracy of the model at the cost of coverage on the overall dataset (red: wrong label, green: true label, gray: rejected label).

Fig 2

doi: https://doi.org/10.1371/journal.pcbi.1013650.g002