Pith. sign in

REVIEW 6 cited by

Not yet reviewed by Pith; the record is open.

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

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

classification eess.IV cs.CV
keywords imagemedicaltransformerpuresegmentationswin-unettransformer-basedu-shaped
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

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

  1. ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation

    cs.CV 2026-04 unverdicted novelty 7.0

    A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.

  2. MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention

    cs.CV 2026-04 unverdicted novelty 6.0

    MedFlowSeg is a conditional flow matching model for medical image segmentation that adds dual-branch spatial attention and frequency-aware attention to achieve more efficient inference than diffusion models while impr...

  3. Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling

    cs.CV 2024-03 unverdicted novelty 6.0

    Label dropout mitigates shortcut learning in multi-dataset partially labelled echocardiography segmentation, improving Dice scores by 62% and 25% on two cardiac structures.

  4. 2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models

    eess.IV 2026-06 unverdicted novelty 5.0

    2D diffusion-generated synthetic X-rays enable training of anatomical landmark detectors that generalize to real images with performance rivaling real-data training.

  5. Attention-ResUNet for Automated Fetal Head Segmentation

    cs.CV 2026-04 unverdicted novelty 3.0

    Attention-ResUNet reaches 99.30% mean Dice score on the HC18 fetal head ultrasound dataset, outperforming ResUNet, Attention U-Net, Swin U-Net, U-Net, and U-Net++ with statistical significance.

  6. Sparse Data Tree Canopy Segmentation: Fine-Tuning Leading Pretrained Models on Only 150 Images

    cs.CV 2026-01 unverdicted novelty 3.0

    Convolutional models like YOLOv11 and Mask R-CNN outperform transformer-based models for tree canopy segmentation when fine-tuned on just 150 images.