# Probabilistic Deep Learning for Instance Segmentation

@inproceedings{Rumberger2020ProbabilisticDL, title={Probabilistic Deep Learning for Instance Segmentation}, author={Josef Lorenz Rumberger and Lisa Mais and Dagmar Kainmueller}, booktitle={ECCV Workshops}, year={2020} }

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… Expand

#### One Citation

How Shift Equivariance Impacts Metric Learning for Instance Segmentation

- Computer Science, Engineering
- ArXiv
- 2021

It is proved that a standard encoder-decoder network that takes d-dimensional images as input, with l pooling layers and pooling factor f , has the capacity to distinguish at most f same-looking objects, and it is shown that this upper limit can be reached. Expand

#### References

SHOWING 1-10 OF 35 REFERENCES

Evaluating Bayesian Deep Learning Methods for Semantic Segmentation

- Computer Science
- ArXiv
- 2018

This work modify DeepLab-v3+, one of the state-of-the-art deep neural networks, and create its Bayesian counterpart using MC dropout and Concrete dropout as inference techniques, and compares and test these two inference techniques on the well-known Cityscapes dataset using the suggested metrics. Expand

Semantic Instance Segmentation with a Discriminative Loss Function

- Computer Science
- ArXiv
- 2017

This work proposes an approach of combining an off-the-shelf network with a principled loss function inspired by a metric learning objective that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step. Expand

A Probabilistic U-Net for Segmentation of Ambiguous Images

- Computer Science, Mathematics
- NeurIPS
- 2018

A generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses and reproduces the possible segmentation variants as well as the frequencies with which they occur significantly better than published approaches. Expand

Instance Segmentation of Biological Images Using Harmonic Embeddings

- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020

This work presents a new instance segmentation approach tailored to biological images, where instances may correspond to individual cells, organisms or plant parts, achieving state-of-the-art performance on a popular CVPPP benchmark. Expand

Semi-convolutional Operators for Instance Segmentation

- Computer Science
- ECCV
- 2018

It is shown theoretically and empirically that constructing dense pixel embeddings that can separate object instances cannot be easily achieved using convolutional operators, and that simple modifications, which are called semi-convolutional, have a much better chance of succeeding at this task. Expand

Deep Watershed Transform for Instance Segmentation

- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017

This paper presents a simple yet powerful end-to-end convolutional neural network that achieves more than double the performance over the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task. Expand

Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction

- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2019

A method combining affinity prediction with region agglomeration, which improves significantly upon the state of the art of neuron segmentation from electron microscopy (EM) in accuracy and scalability, and suggests that a single method can be applied to both nearly isotropic block-face EM data and anisotropic serial sectioned EM data. Expand

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

- Computer Science
- NIPS
- 2017

A Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty is presented, which makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks. Expand

Semantic Instance Segmentation via Deep Metric Learning

- Computer Science
- ArXiv
- 2017

A new method for semantic instance segmentation is proposed, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together, based on a deep, fully convolutional embedding model. Expand

Crowd Counting with Decomposed Uncertainty

- Computer Science
- AAAI
- 2020

This work proposes a scalable neural network framework with quantification of decomposed uncertainty using a bootstrap ensemble and demonstrates that the proposed uncertainty quantification method provides additional insight to the crowd counting problem and is simple to implement. Expand