mlsanityData to 7 Oct 2026

MaLViL: Multi-axis Low-rank Vision-LSTM for Medical Image Segmentation

arXiv 2608.17635 ↗First posted 18 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision-LSTM (ViL) enables efficient global modeling, but its cost still scales with the number of spatial tokens, so existing segmenters confine ViL to a coarse bottleneck and lose fine anatomical detail. Rasterizing 2D features into a 1D sequence further breaks adjacency across the orthogonal scan axis. We propose MaLViL, a Multi-axis Low-rank Vision-LSTM network that extends ViL across decoder resolutions. Bidirectional low-rank ViL (Bi-LRViL) reasons on a compact orthonormal subspace and preserves detail through an orthogonal residual; scale-aware SaLViL restores cross-axis neighbors before serialization; and a Cross-Directional Mixer (CDM) fuses orthogonal horizontal and vertical traversal paths. Statistics-Guided Skip Modulation (SGSM) further retains boundary cues in encoder skips. On skin-lesion, ultrasound, and multi-organ CT benchmarks, MaLViL achieves competitive or state-of-the-art segmentation accuracy, while reducing ViL operator memory by up to 83× at fine decoder resolutions. Code is available at: https://github.com/xmindflow/malvil.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 26 references that are in the map. First posted on arXiv 18 Aug 2026.

Builds on

22 of 26 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  4. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  5. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  6. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  7. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  8. 2024xLSTM: Extended Long Short-Term Memorycited by 320
  9. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 286
  10. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  11. 2021UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformercited by 197
  12. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 176
10 more
  1. 2024EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentationcited by 64
  2. 2023EGE-UNet: an Efficient Group Enhanced UNet for skin lesion segmentationcited by 53
  3. 2024Vision-LSTM: xLSTM as Generic Vision Backbonecited by 51
  4. 2024UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentationcited by 45
  5. 2023CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objectscited by 43
  6. 2024VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentationcited by 39
  7. 2023Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentationcited by 30
  8. 2023DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineationcited by 12
  9. 2024xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba Counterpartcited by 12
  10. 2024MSA2Net: Multi-scale Adaptive Attention-guided Network for Medical Image Segmentationcited by 5

Built on by

Not cited yet.