Methods › Computer Vision › Semantic Segmentation Models › U-Net
U-Net
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
U-Net is an architecture for semantic segmentation. It consists of a contracting path and an expansive path. The contracting path follows the typical architecture of a convolutional network. It consists of the repeated application of two 3x3 convolutions (unpadded convolutions), each followed by a rectified linear unit (ReLU) and a 2x2 max pooling operation with stride 2 for downsampling. At each downsampling step we double the number of feature channels. Every step in the expansive path consists of an upsampling of the feature map followed by a 2x2 convolution (“up-convolution”) that halves the number of feature channels, a concatenation with the correspondingly cropped feature map from the contracting path, and two 3x3 convolutions, each followed by a ReLU. The cropping is necessary due to the loss of border pixels in every convolution. At the final layer a 1x1 convolution is used to map each 64-component feature vector to the desired number of classes. In total the network has 23 convolutional layers.
Papers archive 2025-07-28
30 shown of 2,588, 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.
-
Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation 12 Jun 2025 · 0 repositories · arXiv:2506.10858
-
Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code 12 Jun 2025 · 0 repositories · arXiv:2506.10617
-
Prompt-Guided Latent Diffusion with Predictive Class Conditioning for 3D Prostate MRI Generation 11 Jun 2025 · 0 repositories · arXiv:2506.10230
-
MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion 10 Jun 2025 · 1 repository · arXiv:2506.08357
-
A Machine Learning Approach to Generate Residual Stress Distributions using Sparse Characterization Data in Friction-Stir Processed Parts 9 Jun 2025 · 0 repositories · arXiv:2506.08205
-
A Comparative Study of U-Net Architectures for Change Detection in Satellite Images 9 Jun 2025 · 0 repositories · arXiv:2506.07925
-
Diffusion Models-Aided Uplink Channel Estimation for RIS-Assisted Systems 9 Jun 2025 · 0 repositories · arXiv:2506.07770
-
MAGNet: A Multi-Scale Attention-Guided Graph Fusion Network for DRC Violation Detection 8 Jun 2025 · 0 repositories · arXiv:2506.07126
-
Deep histological synthesis from mass spectrometry imaging for multimodal registration 5 Jun 2025 · 0 repositories · arXiv:2506.05441
-
U-NetMN and SegNetMN: Modified U-Net and SegNet models for bimodal SAR image segmentation 5 Jun 2025 · 0 repositories · arXiv:2506.05444
-
Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding 3 Jun 2025 · 1 repository · arXiv:2506.03134Syntology ran 1 of 7 samples · 6 unverified
-
Dual encoding feature filtering generalized attention UNET for retinal vessel segmentation 2 Jun 2025 · 1 repository · arXiv:2506.02312
-
TRUST -- Transformer-Driven U-Net for Sparse Target Recovery 1 Jun 2025 · 0 repositories · arXiv:2506.01112
-
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models 28 May 2025 · 0 repositories · arXiv:2505.22865
-
Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism 27 May 2025 · 0 repositories · arXiv:2505.21316
-
Laparoscopic Image Desmoking Using the U-Net with New Loss Function and Integrated Differentiable Wiener Filter 27 May 2025 · 1 repository · arXiv:2505.21634
-
Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands 27 May 2025 · 0 repositories · arXiv:2505.21269
-
Deep learning based spatial aliasing reduction in beamforming for audio capture 26 May 2025 · 0 repositories · arXiv:2505.19781
-
Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers 25 May 2025 · 0 repositories · arXiv:2505.19122
-
Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection 23 May 2025 · 1 repository · arXiv:2505.17683
-
EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion 23 May 2025 · 0 repositories · arXiv:2505.17367
-
F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles 23 May 2025 · 1 repository · arXiv:2505.18106
-
MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity 23 May 2025 · 1 repository · arXiv:2505.17591
-
Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training 23 May 2025 · 0 repositories · arXiv:2505.17638
-
Assessing the generalization performance of SAM for ureteroscopy scene understanding 22 May 2025 · 0 repositories · arXiv:2505.17210
-
Deep mineralogical segmentation of thin section images based on QEMSCAN maps 22 May 2025 · 1 repository · arXiv:2505.17008
-
AquaSignal: An Integrated Framework for Robust Underwater Acoustic Analysis 20 May 2025 · 1 repository · arXiv:2505.14285
-
LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction 20 May 2025 · 1 repository · arXiv:2505.14747
-
A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound Simulation 19 May 2025 · 1 repository · arXiv:2505.12998
-
Segmentation of temporomandibular joint structures on mri images using neural networks for diagnosis of pathologies 19 May 2025 · 0 repositories · arXiv:2505.12963
Tasks archive 2025-07-28
20 shown of 768 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 | 855 |
| Semantic Segmentation | 659 |
| Image Segmentation | 450 |
| Medical Image Segmentation | 263 |
| Decoder | 248 |
| Denoising | 171 |
| Deep Learning | 144 |
| Image Generation | 123 |
| Tumor Segmentation | 122 |
| Data Augmentation | 101 |
| Computed Tomography (CT) | 81 |
| Diagnostic | 81 |
| Lesion Segmentation | 77 |
| Medical Image Analysis | 77 |
| Transfer Learning | 72 |
| Brain Tumor Segmentation | 64 |
| Super-Resolution | 64 |
| SSIM | 61 |
| GPU | 60 |
| Generative Adversarial Network | 51 |
Usage over time archive 2025-07-28
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
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