# CU-Net: Coupled U-Nets

arXiv: https://arxiv.org/abs/1808.06521 · HTML: https://mlsanity.com/paper/1808.06521/

## Key facts

- Cited by 11 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 20 Aug 2018.

## Built on by (most cited first, 11 of 11)

- [NeoUNet: Towards accurate colon polyp segmentation and neoplasm detection](https://mlsanity.com/paper/2107.05023/) (2021)
- [Supervision by Registration and Triangulation for Landmark Detection](https://mlsanity.com/paper/2101.09866/) (2021)
- [A survey on attention mechanisms for medical applications: are we moving towards better algorithms?](https://mlsanity.com/paper/2204.12406/) (2022)
- [BlazeNeo: Blazing fast polyp segmentation and neoplasm detection](https://mlsanity.com/paper/2203.00129/) (2022)
- [End-to-End Hierarchical Relation Extraction for Generic Form Understanding](https://mlsanity.com/paper/2106.00980/) (2021)
- [AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation](https://mlsanity.com/paper/2105.00402/) (2021)
- [Comparison of 2D vs. 3D U-Net Organ Segmentation in abdominal 3D CT images](https://mlsanity.com/paper/2107.04062/) (2021)
- [End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net](https://mlsanity.com/paper/2106.00952/) (2021)
- [Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation](https://mlsanity.com/paper/2405.07523/) (2024)
- [Crack Semantic Segmentation using the U-Net with Full Attention Strategy](https://mlsanity.com/paper/2104.14586/) (2021)
- [Identification of Physical Processes and Unknown Parameters of 3D Groundwater Contaminant Problems via Theory-guided U-net](https://mlsanity.com/paper/2205.00134/) (2022)

## Abstract (arXiv)

We design a new connectivity pattern for the U-Net architecture. Given several stacked U-Nets, we couple each U-Net pair through the connections of their semantic blocks, resulting in the coupled U-Nets (CU-Net). The coupling connections could make the information flow more efficiently across U-Nets. The feature reuse across U-Nets makes each U-Net very parameter efficient. We evaluate the coupled U-Nets on two benchmark datasets of human pose estimation. Both the accuracy and model parameter number are compared. The CU-Net obtains comparable accuracy as state-of-the-art methods. However, it only has at least 60% fewer parameters than other approaches.