# UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections

arXiv: https://arxiv.org/abs/2412.18276 · HTML: https://mlsanity.com/paper/2412.18276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises](https://mlsanity.com/paper/2008.09104/) (2020)
- [UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer](https://mlsanity.com/paper/2109.04335/) (2021)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Mask Guided Matting via Progressive Refinement Network](https://mlsanity.com/paper/2012.06722/) (2020)
- [Sparse Instance Activation for Real-Time Instance Segmentation](https://mlsanity.com/paper/2203.12827/) (2022)
- [Privacy-Preserving Portrait Matting](https://mlsanity.com/paper/2104.14222/) (2021)
- [KBNet: Kernel Basis Network for Image Restoration](https://mlsanity.com/paper/2303.02881/) (2023)
- [Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution](https://mlsanity.com/paper/2204.08397/) (2022)
- [ACC-UNet: A Completely Convolutional UNet model for the 2020s](https://mlsanity.com/paper/2308.13680/) (2023)
- [DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2310.12570/) (2023)
- [Tailor: Altering Skip Connections for Resource-Efficient Inference](https://mlsanity.com/paper/2301.07247/) (2023)

## Abstract (arXiv)

U-Net models with encoder, decoder, and skip-connections components have demonstrated effectiveness in a variety of vision tasks. The skip-connections transmit fine-grained information from the encoder to the decoder. It is necessary to maintain the feature maps used by the skip-connections in memory before the decoding stage. Therefore, they are not friendly to devices with limited resource. In this paper, we propose a universal method and architecture to reduce the memory consumption and meanwhile generate enhanced feature maps to improve network performance. To this end, we design a simple but effective Multi-Scale Information Aggregation Module (MSIAM) in the encoder and an Information Enhancement Module (IEM) in the decoder. The MSIAM aggregates multi-scale feature maps into single-scale with less memory. After that, the aggregated feature maps can be expanded and enhanced to multi-scale feature maps by the IEM. By applying the proposed method on NAFNet, a SOTA model in the field of image restoration, we design a memory-efficient and feature-enhanced network architecture, UNet--. The memory demand by the skip-connections in the UNet-- is reduced by 93.3%, while the performance is improved compared to NAFNet. Furthermore, we show that our proposed method can be generalized to multiple visual tasks, with consistent improvements in both memory consumption and network accuracy compared to the existing efficient architectures.