# A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation

arXiv: https://arxiv.org/abs/1906.06148 · HTML: https://mlsanity.com/paper/1906.06148/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 16 of 16)

- [Reversible Vision Transformers](https://mlsanity.com/paper/2302.04869/) (2023)
- [Automatic airway segmentation from Computed Tomography using robust and efficient 3-D convolutional neural networks](https://mlsanity.com/paper/2103.16328/) (2021)
- [Learning from partially labeled data for multi-organ and tumor segmentation](https://mlsanity.com/paper/2211.06894/) (2022)
- [InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion](https://mlsanity.com/paper/2103.14158/) (2021)
- [Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation](https://mlsanity.com/paper/2203.08964/) (2022)
- [OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data](https://mlsanity.com/paper/2110.10640/) (2021)
- [Continuous U-Net: Faster, Greater and Noiseless](https://mlsanity.com/paper/2302.00626/) (2023)
- [Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference](https://mlsanity.com/paper/2205.04227/) (2022)
- [RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network](https://mlsanity.com/paper/2206.14098/) (2022)
- [Training Transformers Together](https://mlsanity.com/paper/2207.03481/) (2022)
- [Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation](https://mlsanity.com/paper/2104.09648/) (2021)
- [Residual Channel Attention Network for Brain Glioma Segmentation](https://mlsanity.com/paper/2205.10758/) (2022)
- [Memory-efficient Segmentation of High-resolution Volumetric MicroCT Images](https://mlsanity.com/paper/2205.15941/) (2022)
- [MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation](https://mlsanity.com/paper/2105.04508/) (2021)
- [Medical Image Analysis using Deep Relational Learning](https://mlsanity.com/paper/2303.16099/) (2023)
- [ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference](https://mlsanity.com/paper/2508.01223/) (2025)

## Abstract (arXiv)

One of the key drawbacks of 3D convolutional neural networks for segmentation is their memory footprint, which necessitates compromises in the network architecture in order to fit into a given memory budget. Motivated by the RevNet for image classification, we propose a partially reversible U-Net architecture that reduces memory consumption substantially. The reversible architecture allows us to exactly recover each layer's outputs from the subsequent layer's ones, eliminating the need to store activations for backpropagation. This alleviates the biggest memory bottleneck and enables very deep (theoretically infinitely deep) 3D architectures. On the BraTS challenge dataset, we demonstrate substantial memory savings. We further show that the freed memory can be used for processing the whole field-of-view (FOV) instead of patches. Increasing network depth led to higher segmentation accuracy while growing the memory footprint only by a very small fraction, thanks to the partially reversible architecture.