# Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation

arXiv: https://arxiv.org/abs/2603.02727 · HTML: https://mlsanity.com/paper/2603.02727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 3 Mar 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (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)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Efficient Attention: Attention with Linear Complexities](https://mlsanity.com/paper/1812.01243/) (2018)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [VM-UNet: Vision Mamba UNet for Medical Image Segmentation](https://mlsanity.com/paper/2402.02491/) (2024)
- [Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free](https://mlsanity.com/paper/2505.06708/) (2025)
- [Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel](https://mlsanity.com/paper/1908.11775/) (2019)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer](https://mlsanity.com/paper/2109.04335/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Demystify Mamba in Vision: A Linear Attention Perspective](https://mlsanity.com/paper/2405.16605/) (2024)
- [The Devil in Linear Transformer](https://mlsanity.com/paper/2210.10340/) (2022)
- [Mixed Transformer U-Net For Medical Image Segmentation](https://mlsanity.com/paper/2111.04734/) (2021)
- [HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation](https://mlsanity.com/paper/2207.08518/) (2022)
- [EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation](https://mlsanity.com/paper/2405.06880/) (2024)
- [MogaNet: Multi-order Gated Aggregation Network](https://mlsanity.com/paper/2211.03295/) (2022)
- [CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects](https://mlsanity.com/paper/2301.13366/) (2023)
- [Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation](https://mlsanity.com/paper/2303.16892/) (2023)
- [Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation](https://mlsanity.com/paper/2309.00121/) (2023)
- [MSA2Net: Multi-scale Adaptive Attention-guided Network for Medical Image Segmentation](https://mlsanity.com/paper/2407.21640/) (2024)
- [CENet: Context Enhancement Network for Medical Image Segmentation](https://mlsanity.com/paper/2505.18423/) (2025)

## Abstract (arXiv)

Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers capture long-range dependencies but incur quadratic attention cost, whereas CNNs are efficient but less effective at global reasoning. Linear attention offers (O(N)) scaling, but often produces diffuse feature aggregation that weakens boundary-sensitive prediction. We introduce a gated differential linear-attention mixer for medical image segmentation. Its global path, Gated Differential Linear Attention (GDLA), performs differential subtraction between two kernelized attention branches over complementary query/key subspaces to suppress redundant responses, and employs a data-dependent gate for token refinement. A parallel local token-mixing branch with depthwise convolution strengthens neighborhood interactions for better refinement, and the two branches are fused while preserving (O(N)) complexity. When instantiated in a pretrained Pyramid Vision Transformer (PVT)-based encoder--decoder model, name achieves state-of-the-art results on the evaluated 2D medical segmentation benchmarks spanning CT, MRI, ultrasound, and dermoscopy, with a favorable accuracy--efficiency trade-off over closely related baselines. The code is publicly available at hrefhttps://github.com/xmindflow/gdlahttps://github.com/xmindflow/gdla.