Probabilistic Deep Learning for Instance Segmentation
Preprint
Abstract
Probabilistic convolutional neural networks, which predict distributions of predictions instead of point estimates, led to recent advances in many areas of computer vision, from image reconstruction to semantic segmentation. Besides state of the art benchmark results, these networks made it possible to quantify local uncertainties in the predictions. These were used in active learning frameworks to target the labeling efforts of specialist annotators or to assess the quality of a prediction in a safety-critical environment. However, for instance segmentation problems these methods are not frequently used so far. We seek to close this gap by proposing a generic method to obtain model-inherent uncertainty estimates within proposal-free instance segmentation models. Furthermore, we analyze the quality of the uncertainty estimates with a metric adapted from semantic segmentation. We evaluate our method on the BBBC010 C.\ elegans dataset, where it yields competitive performance while also predicting uncertainty estimates that carry information about object-level inaccuracies like false splits and false merges. We perform a simulation to show the potential use of such uncertainty estimates in guided proofreading.Keywords
All Related Versions
- Version 1, 2020-08-24, ArXiv
- Version 2, 2020-12-17, ArXiv
- Published version: , 445.
This publication has 6 references indexed in Scilit:
- Crowd Counting with Decomposed UncertaintyProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Content-aware image restoration: pushing the limits of fluorescence microscopyNature Methods, 2018
- Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome ReconstructionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- An image analysis toolbox for high-throughput C. elegans assaysNature Methods, 2012
- The estimation of the gradient of a density function, with applications in pattern recognitionIEEE Transactions on Information Theory, 1975
- Algorithms for the Assignment and Transportation ProblemsJournal of the Society for Industrial and Applied Mathematics, 1957