# Semi-supervised Instance Segmentation with a Learned Shape Prior

arXiv: https://arxiv.org/abs/2309.04888 · HTML: https://mlsanity.com/paper/2309.04888/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 9 Sep 2023.

## Builds on (most cited first, 7 of 7)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Cell Detection with Star-convex Polygons](https://mlsanity.com/paper/1806.03535/) (2018)
- [Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation](https://mlsanity.com/paper/1705.08302/) (2017)
- [Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation](https://mlsanity.com/paper/1903.03148/) (2019)
- [Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders](https://mlsanity.com/paper/1906.02343/) (2019)
- [Instance Segmentation of Biomedical Images with an Object-aware Embedding Learned with Local Constraints](https://mlsanity.com/paper/2004.09821/) (2020)

## Built on by (most cited first, 2 of 2)

- [Deep Learning based Systems for Crater Detection: A Review](https://mlsanity.com/paper/2310.07727/) (2023)
- [Relational Prior Knowledge Graphs for Detection and Instance Segmentation](https://mlsanity.com/paper/2310.07573/) (2023)

## Abstract (arXiv)

To date, most instance segmentation approaches are based on supervised learning that requires a considerable amount of annotated object contours as training ground truth. Here, we propose a framework that searches for the target object based on a shape prior. The shape prior model is learned with a variational autoencoder that requires only a very limited amount of training data: In our experiments, a few dozens of object shape patches from the target dataset, as well as purely synthetic shapes, were sufficient to achieve results en par with supervised methods with full access to training data on two out of three cell segmentation datasets. Our method with a synthetic shape prior was superior to pre-trained supervised models with access to limited domain-specific training data on all three datasets. Since the learning of prior models requires shape patches, whether real or synthetic data, we call this framework semi-supervised learning.