{"url":"/method/nnformer","slug":"nnformer","name":"nnFormer","full_name":"nnFormer","full_name_withheld":false,"description_markdown":"**nnFormer**, or **not-another transFormer**, is a semantic segmentation model with an interleaved architecture based on empirical combination of self-attention and [convolution](https://paperswithcode.com/method/convolution). Firstly, a light-weight convolutional embedding layer ahead is used ahead of [transformer](https://paperswithcode.com/method/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.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2109.03201v6","title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":5,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"A Novel Convolutional-Free Method for 3D Medical Imaging Segmentation","date":"2025-02-08","arxiv_id":"2502.05396","n_code_links":0,"syntology":null},{"paper":"/paper/uu-mamba-uncertainty-aware-u-mamba-for-1","title":"UU-Mamba: Uncertainty-aware U-Mamba for Cardiovascular Segmentation","date":"2024-09-22","arxiv_id":"2409.14305","n_code_links":1,"syntology":null},{"paper":"/paper/uu-mamba-uncertainty-aware-u-mamba-for","title":"UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image Segmentation","date":"2024-05-25","arxiv_id":"2405.17496","n_code_links":1,"syntology":null},{"paper":null,"title":"Memory transformers for full context and high-resolution 3D Medical Segmentation","date":"2022-10-11","arxiv_id":"2210.05313","n_code_links":0,"syntology":null},{"paper":"/paper/nnformer-interleaved-transformer-for","title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","date":"2021-09-07","arxiv_id":"2109.03201","n_code_links":2,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}}],"papers_shown":5,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":5},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":4},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":4},{"task":"/task/mamba","name":"Mamba","papers":2},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":2},{"task":"/task/3d-medical-imaging-segmentation","name":"3D Medical Imaging Segmentation","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":1},{"task":"/task/mri-segmentation","name":"MRI segmentation","papers":1},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":1},{"task":"/task/volumetric-medical-image-segmentation","name":"Volumetric Medical Image Segmentation","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2024","papers":2},{"year":"2025","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/nnformer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}