# ConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particles

arXiv: https://arxiv.org/abs/2204.04635 · HTML: https://mlsanity.com/paper/2204.04635/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 10 Apr 2022.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [Cell Detection with Star-convex Polygons](https://mlsanity.com/paper/1806.03535/) (2018)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/1903.00348/) (2019)
- [Deep Watershed Transform for Instance Segmentation](https://mlsanity.com/paper/1611.08303/) (2016)
- [Semantic Segmentation using Adversarial Networks](https://mlsanity.com/paper/1611.08408/) (2016)
- [Deep Co-Training for Semi-Supervised Image Segmentation](https://mlsanity.com/paper/1903.11233/) (2019)
- [Universal Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1811.10323/) (2018)
- [Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model](https://mlsanity.com/paper/1808.03887/) (2018)
- [Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy](https://mlsanity.com/paper/1908.03636/) (2019)
- [Weakly- and Semi-Supervised Panoptic Segmentation](https://mlsanity.com/paper/1808.03575/) (2018)
- [PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond](https://mlsanity.com/paper/2105.02184/) (2021)
- [Semi-Supervised Segmentation of Concrete Aggregate Using Consensus Regularisation and Prior Guidance](https://mlsanity.com/paper/2104.11028/) (2021)

## Built on by (most cited first, 1 of 1)

- [Segmenting Low-Contrast XCTs of Concrete: An Unsupervised Approach](https://mlsanity.com/paper/2603.00127/) (2026)

## Abstract (arXiv)

We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelled data by enforcing consistency between predicted instance representations and semantic segmentations during training in order to improve the segmentation performance. To this end, we also propose new types of instance representations that can be predicted by one simple forward path through a fully convolutional network (FCN), delivering a convenient and simple-to-train framework for panoptic segmentation. More specifically, we propose the prediction of a three-dimensional instance orientation map as intermediate representation and two complementary distance transform maps as final representation, providing unique instance representations for a panoptic segmentation. We test our method on two challenging data sets of both, hardened and fresh concrete, the latter being proposed by the authors in this paper demonstrating the effectiveness of our approach, outperforming the results achieved by state-of-the-art methods for semi-supervised segmentation. In particular, we are able to show that by leveraging completely unlabeled data in our semi-supervised approach the achieved overall accuracy (OA) is increased by up to 5% compared to an entirely supervised training using only labeled data. Furthermore, we exceed the OA achieved by state-of-the-art semi-supervised methods by up to 1.5%.