Sampling-based Uncertainty Estimation for an Instance Segmentation Network
This work addresses uncertainty quantification for instance segmentation, which is important for applications like medical imaging or autonomous driving, but it appears incremental as it builds on existing Mask-RCNN and MC-Dropout methods.
The paper tackles the problem of uncertainty estimation in instance segmentation networks by proposing a Bayesian Gaussian Mixture approach to cluster Monte-Carlo Dropout predictions, achieving improved uncertainty approximation for each object instance with graphical visualization.
The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.