Uncertainty Estimation in Instance Segmentation with Star-convex Shapes
This work addresses uncertainty estimation for instance segmentation, which is critical for model reliability and decision-making in applications like medical imaging or autonomous driving, but it is incremental as it builds on existing Monte-Carlo Dropout and Deep Ensemble techniques.
The paper tackles the problem of uncertainty estimation in instance segmentation for star-convex shapes, showing that combining spatial and fractional certainty scores improves calibrated estimation, with the Deep Ensemble technique and a novel radial clustering approach proving effective.
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.