Uncertainty Estimation in Instance Segmentation with Star-convex Shapes

TL;DR

This paper introduces methods for estimating and calibrating uncertainty in star-convex shape instance segmentation, demonstrating improved reliability through combined certainty scores and ensemble techniques.

Contribution

It proposes a novel approach to quantify and calibrate spatial certainty in instance segmentation with star-convex shapes, using clustering and ensemble methods.

Findings

Deep Ensemble with radial clustering improves uncertainty calibration.

Combining spatial and fractional certainty enhances prediction reliability.

Calibrated certainty estimates support better decision-making.

Abstract

Instance segmentation has witnessed promising advancements through deep neural network-based algorithms. However, these models often exhibit incorrect predictions with unwarranted confidence levels. Consequently, evaluating prediction uncertainty becomes critical for informed decision-making. Existing methods primarily focus on quantifying uncertainty in classification or regression tasks, lacking emphasis on instance segmentation. Our research addresses the challenge of estimating spatial certainty associated with the location of instances with star-convex shapes. Two distinct clustering approaches are evaluated which compute spatial and fractional certainty per instance employing samples by the Monte-Carlo Dropout or Deep Ensemble technique. Our study demonstrates that combining spatial and fractional certainty scores yields improved calibrated estimation over individual certainty scores. Notably, our experimental results show that the Deep Ensemble technique alongside our novel radial clustering approach proves to be an effective strategy. Our findings emphasize the significance of evaluating the calibration of estimated certainties for model reliability and decision-making.