Predicting Performance of Object Detection Models in Electron Microscopy Using Random Forests

TL;DR

This paper presents a method using random forests to predict the performance of object detection models in electron microscopy images, helping assess model reliability on new datasets.

Contribution

It introduces a novel approach to estimate object detection accuracy using features from model predictions, enabling quick performance assessment on unlabeled TEM images.

Findings

Mean absolute error of 0.09 in F1 score prediction

R^2 score of 0.77 indicating strong correlation

Robust performance across diverse TEM datasets

Abstract

Quantifying prediction uncertainty when applying object detection models to new, unlabeled datasets is critical in applied machine learning. This study introduces an approach to estimate the performance of deep learning-based object detection models for quantifying defects in transmission electron microscopy (TEM) images, focusing on detecting irradiation-induced cavities in TEM images of metal alloys. We developed a random forest regression model that predicts the object detection F1 score, a statistical metric used to evaluate the ability to accurately locate and classify objects of interest. The random forest model uses features extracted from the predictions of the object detection model whose uncertainty is being quantified, enabling fast prediction on new, unlabeled images. The mean absolute error (MAE) for predicting F1 of the trained model on test data is 0.09, and the $R^2$ score is 0.77, indicating there is a significant correlation between the random forest regression model predicted and true defect detection F1 scores. The approach is shown to be robust across three distinct TEM image datasets with varying imaging and material domains. Our approach enables users to estimate the reliability of a defect detection and segmentation model predictions and assess the applicability of the model to their specific datasets, providing valuable information about possible domain shifts and whether the model needs to be fine-tuned or trained on additional data to be maximally effective for the desired use case.