# Probabilistic Deep Learning for Instance Segmentation

arXiv: https://arxiv.org/abs/2008.10678 · HTML: https://mlsanity.com/paper/2008.10678/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [How Shift Equivariance Impacts Metric Learning for Instance Segmentation](https://mlsanity.com/paper/2101.05846/) (2021)
- [A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation](https://mlsanity.com/paper/2411.16370/) (2024)
- [Panoptic segmentation with highly imbalanced semantic labels](https://mlsanity.com/paper/2203.11692/) (2022)
- [ProPanDL: A Modular Architecture for Uncertainty-Aware Panoptic Segmentation](https://mlsanity.com/paper/2304.08645/) (2023)
- [Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN](https://mlsanity.com/paper/2305.01910/) (2023)

## Abstract (arXiv)

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.