Methods › Computer Vision › Semantic Segmentation Models › nnFormer

nnFormer

5 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

nnFormer, or not-another transFormer, is a semantic segmentation model with an interleaved architecture based on empirical combination of self-attention and convolution. Firstly, a light-weight convolutional embedding layer ahead is used ahead of transformer blocks. In comparison to directly flattening raw pixels and applying 1D pre-processing, the convolutional embedding layer encodes precise (i.e., pixel-level) spatial information and provide low-level yet high-resolution 3D features. After the embedding block, transformer and convolutional down-sampling blocks are interleaved to fully entangle long-term dependencies with high-level and hierarchical object concepts at various scales, which helps improve the generalization ability and robustness of learned representations.

Source: nnFormer: Interleaved Transformer for Volumetric Segmentation

Papers archive 2025-07-28

5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

A Novel Convolutional-Free Method for 3D Medical Imaging Segmentation
8 Feb 2025 · 0 repositories · arXiv:2502.05396
UU-Mamba: Uncertainty-aware U-Mamba for Cardiovascular Segmentation
22 Sep 2024 · 1 repository · arXiv:2409.14305
UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image Segmentation
25 May 2024 · 1 repository · arXiv:2405.17496
Memory transformers for full context and high-resolution 3D Medical Segmentation
11 Oct 2022 · 0 repositories · arXiv:2210.05313
nnFormer: Interleaved Transformer for Volumetric Segmentation
7 Sep 2021 · 2 repositories · arXiv:2109.03201

Syntology ran 1 of 1 samples · 0 unverified

Tasks archive 2025-07-28

11 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Segmentation	5
Image Segmentation	4
Semantic Segmentation	4
Mamba	2
Medical Image Segmentation	2
3D Medical Imaging Segmentation	1
Domain Adaptation	1
Inductive Bias	1
MRI segmentation	1
Vocal Bursts Intensity Prediction	1
Volumetric Medical Image Segmentation	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (5 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Semantic Segmentation Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections