Pith. sign in

REVIEW 19 cited by

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.05537 v1 pith:KAHWL3FW submitted 2021-05-12 eess.IV cs.CV

Hu Cao , Yueyue Wang , Joy Chen , Dongsheng Jiang , Xiaopeng Zhang , Qi Tian , Manning Wang This is my paper · ORCID
classification eess.IVcs.CV
keywords imagemedicaltransformerpuresegmentationswin-unettransformer-basedu-shaped
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architecture and skip-connections have been widely applied in a variety of medical image tasks. However, although CNN has achieved excellent performance, it cannot learn global and long-range semantic information interaction well due to the locality of the convolution operation. In this paper, we propose Swin-Unet, which is an Unet-like pure Transformer for medical image segmentation. The tokenized image patches are fed into the Transformer-based U-shaped Encoder-Decoder architecture with skip-connections for local-global semantic feature learning. Specifically, we use hierarchical Swin Transformer with shifted windows as the encoder to extract context features. And a symmetric Swin Transformer-based decoder with patch expanding layer is designed to perform the up-sampling operation to restore the spatial resolution of the feature maps. Under the direct down-sampling and up-sampling of the inputs and outputs by 4x, experiments on multi-organ and cardiac segmentation tasks demonstrate that the pure Transformer-based U-shaped Encoder-Decoder network outperforms those methods with full-convolution or the combination of transformer and convolution. The codes and trained models will be publicly available at https://github.com/HuCaoFighting/Swin-Unet.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning in Deep Networks under Dale's Constraint

    cs.AI 2026-08 reject novelty 7.0 of 10

    An on-off two-channel network with fixed-sign synapses and local Hebbian learning is claimed to recover backpropagation exactly under symmetric weights and to beat comparable vanilla networks on Tiny ImageNet.

  2. Fast Fourier Convolutional GAN for 30 m Clear-Sky Land Surface Temperature Gap-Free Reconstruction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    An FFC-based GAN guided by SAR and topographic data reconstructs 30 m clear-sky land-surface temperature in cloud-covered Landsat pixels with typical RMSE 0.8–1.8 K.

  3. CRIS: Cross-Plane Self-Supervised Isotropic Restoration for Anisotropic Volumetric Imaging Across Modalities

    cs.CV 2026-06 conditional novelty 6.0 of 10

    A single self-supervised stripe-completion model restores isotropic MRI and volume EM from anisotropic inputs without paired isotropic targets or per-gap retraining.

  4. Tuning Vision Foundation Model via Test-Time Prompt-Guided Training for VFSS Segmentations

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Point-prompt-based test-time training adapts MedSAM to medical video segmentation, achieving 0.868 average Dice on VFSS anatomy segmentation.

  5. Invisible Yet Detected: PelFANet with Attention-Guided Anatomical Fusion for Pelvic Fracture Diagnosis

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A dual-stream network that fuses raw pelvic X-rays with segmented bone images reports strong visible-fracture accuracy and higher-than-baseline AUC on CT-confirmed invisible fractures, but the invisible test set has o...

  6. DM-SegNet: Dual-Mamba Architecture for 3D Medical Image Segmentation with Global Context Modeling

    eess.IV 2025-06 conditional novelty 5.0 of 10

    DM-SegNet combines four-direction Mamba scanning, gated spatial convolutions, and a Mamba decoder to reach reported state-of-the-art Dice scores on Synapse and BraTS2023.

  7. Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decoding

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A Transformer-Mamba hybrid with multi-cross attention and multi-scan state-space fusion reports state-of-the-art PSNR and SSIM on synthetic burst super-resolution benchmarks.

  8. RFMedSAM 2: Automatic Prompt Refinement for Enhanced Volumetric Medical Image Segmentation with SAM 2

    cs.CV 2025-02 conditional novelty 5.0 of 10

    RFMedSAM 2, a SAM 2 variant with adapters and a U-Net prompt generator, reports state-of-the-art Dice scores on AMOS2022 (90.7%) and BTCV (86.7%).

  9. Estimating forest carbon stocks from high-resolution remote sensing imagery by reducing domain shift with style transfer

    cs.CV 2025-02 reject novelty 5.0 of 10

    The authors propose MSwin-Pix2Pix, a Swin-Transformer-based Pix2Pix variant with mask and median filter, to estimate forest carbon stocks from multi-temporal satellite imagery, reporting R2 of 0.71 and an increasing c...

  10. EPRA U-Net: An Efficient Pyramid Residual Attention Framework for Accurate Infarct Segmentation in Diffusion-Weighted MRI

    cs.CV 2026-07 conditional novelty 4.0 of 10

    A hybrid EfficientNet-R2-ASPP-dual-attention U-Net with Tversky loss reduces missed acute infarcts on DWI relative to common baselines on a 167-patient in-house dataset.

  11. Barlow-Swin: Toward a novel siamese-based segmentation architecture using Swin-Transformers

    cs.CV 2025-09 reject novelty 4.0 of 10

    Barlow-Swin is a hybrid medical segmenter that pairs a Barlow Twins-pretrained Swin encoder with a U-Net-like decoder, claiming competitive accuracy with fewer parameters.

  12. ReCoSeg++:Extended Residual-Guided Cross-Modal Diffusion for Brain Tumor Segmentation

    eess.IV 2025-08 reject novelty 4.0 of 10

    ReCoSeg++ extends ReCoSeg to BraTS 2021, feeding diffusion-derived T1ce residual maps to a 2D U-Net and reporting 93.02 Dice and 86.7 IoU for whole-tumor segmentation.

  13. MLRU++: Multiscale Lightweight Residual UNETR++ with Attention for Efficient 3D Medical Image Segmentation

    eess.IV 2025-07 reject novelty 4.0 of 10

    MLRU++ reports small Dice gains over UNETR++ on three public benchmarks using a lighter attention module and multiscale depthwise blocks.

  14. FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks

    cs.CV 2025-07 reject novelty 4.0 of 10

    FORTRESS combines depthwise separable convolutions and a gated Kolmogorov-Arnold module to report F1 of 0.771 and mIoU of 0.677 on the CSDD benchmark, but the core KAN contribution is not isolated by ablation.

  15. MedLiteNet: Lightweight Hybrid Medical Image Segmentation Model

    cs.CV 2025-09 reject novelty 3.0 of 10

    A compact encoder-decoder that combines MobileNetV2-style blocks with bottleneck self-attention, ASPP and SCSE reaches about 0.90 Dice and 0.83 IoU on ISIC 2018 with around 3.2M parameters.

  16. Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptation

    cs.CV 2025-02 conditional novelty 3.0 of 10

    Self-Prompt-SAM automatically generates point, box, and mask prompts for a fine-tuned SAM and reports state-of-the-art Dice scores on three medical segmentation benchmarks.

  17. Image Segmentation: Inducing graph-based learning

    cs.CV 2025-01 conditional novelty 3.0 of 10

    Adding a GNN bottleneck to U-Net improves segmentation IoU on fisheye, natural, and dermoscopic images, with the largest gains on fisheye imagery.

  18. Hybrid(Transformer+CNN)-based Polyp Segmentation

    eess.IV 2025-08 reject novelty 2.0 of 10

    A Swin Transformer plus CNN decoder reports 0.9555 recall and 0.9849 accuracy on Kvasir-SEG, but lower F1 and precision than DUCK-Net, with claimed attention innovations absent from the architecture.

  19. Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning

    math.NA 2025-01 conditional novelty 2.0 of 10

    A review that maps the field of Scientific Machine Learning and presents the authors' own cardiac simulation program as its flagship application.

Pith tools