# Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation

arXiv: https://arxiv.org/abs/1804.10343 · HTML: https://mlsanity.com/paper/1804.10343/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2018.

## Built on by (most cited first, 9 of 9)

- [Accelerating Sparse Deep Neural Networks](https://mlsanity.com/paper/2104.08378/) (2021)
- [Stacked U-Nets with Self-Assisted Priors Towards Robust Correction of Rigid Motion Artifact in Brain MRI](https://mlsanity.com/paper/2111.06401/) (2021)
- [SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations](https://mlsanity.com/paper/2403.19507/) (2024)
- [Mimetic Neural Networks: A unified framework for Protein Design and Folding](https://mlsanity.com/paper/2102.03881/) (2021)
- [Search Spaces for Neural Model Training](https://mlsanity.com/paper/2105.12920/) (2021)
- [Hierarchical-embedding autoencoder with a predictor (HEAP) as efficient architecture for learning long-term evolution of complex multi-scale physical systems](https://mlsanity.com/paper/2505.18857/) (2025)
- [Unsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer](https://mlsanity.com/paper/2105.07322/) (2021)
- [PMR-Net: Parallel Multi-Resolution Encoder-Decoder Network Framework for Medical Image Segmentation](https://mlsanity.com/paper/2409.12678/) (2024)
- [Deep Wave Network for Modeling Multi-Scale Physical Dynamics](https://mlsanity.com/paper/2605.04198/) (2026)

## Abstract (arXiv)

Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for semantic segmentation and object detection tasks, a network must provide higher-resolution pixel-level outputs. To globalize information while preserving resolution, many researchers propose the inclusion of sophisticated auxiliary blocks, but these come at the cost of a considerable increase in network size and computational cost. This paper proposes stacked u-nets (SUNets), which iteratively combine features from different resolution scales while maintaining resolution. SUNets leverage the information globalization power of u-nets in a deeper network architectures that is capable of handling the complexity of natural images. SUNets perform extremely well on semantic segmentation tasks using a small number of parameters.