# A Lightweight U-like Network Utilizing Neural Memory Ordinary Differential Equations for Slimming the Decoder

arXiv: https://arxiv.org/abs/2412.06262 · HTML: https://mlsanity.com/paper/2412.06262/

## Key facts

- Cited by 5 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 9 Dec 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Augmented Neural ODEs](https://mlsanity.com/paper/1904.01681/) (2019)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation](https://mlsanity.com/paper/2102.08005/) (2021)
- [UNeXt: MLP-based Rapid Medical Image Segmentation Network](https://mlsanity.com/paper/2203.04967/) (2022)
- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [Shallow Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2108.00882/) (2021)
- [MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation](https://mlsanity.com/paper/2211.01784/) (2022)
- [EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentation](https://mlsanity.com/paper/2307.08473/) (2023)
- [SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks](https://mlsanity.com/paper/2307.02953/) (2023)

## Built on by (most cited first, 5 of 5)

- [FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks](https://mlsanity.com/paper/2506.05821/) (2025)
- [DCSNet: Multiscale Feature Aggregation for Small Medical Object Segmentation with Detection-guided Hierarchical Cropping](https://mlsanity.com/paper/2606.28402/) (2026)
- [Enhancing Layer Interaction Using Key-Correlated Layer Attention](https://mlsanity.com/paper/2606.28405/) (2026)
- [BP-TTA: Balanced and Prototype-Guided Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2606.31420/) (2026)
- [Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention](https://mlsanity.com/paper/2607.00057/) (2026)

## Abstract (arXiv)

In recent years, advanced U-like networks have demonstrated remarkable performance in medical image segmentation tasks. However, their drawbacks, including excessive parameters, high computational complexity, and slow inference speed, pose challenges for practical implementation in scenarios with limited computational resources. Existing lightweight U-like networks have alleviated some of these problems, but they often have pre-designed structures and consist of inseparable modules, limiting their application scenarios. In this paper, we propose three plug-and-play decoders by employing different discretization methods of the neural memory Ordinary Differential Equations (nmODEs). These decoders integrate features at various levels of abstraction by processing information from skip connections and performing numerical operations on upward path. Through experiments on the PH2, ISIC2017, and ISIC2018 datasets, we embed these decoders into different U-like networks, demonstrating their effectiveness in significantly reducing the number of parameters and FLOPs while maintaining performance. In summary, the proposed discretized nmODEs decoders are capable of reducing the number of parameters by about 20% ~ 50% and FLOPs by up to 74%, while possessing the potential to adapt to all U-like networks. Our code is available at https://github.com/nayutayuki/Lightweight-nmODE-Decoders-For-U-like-networks.