{"url":"/method/u-net","slug":"u-net","name":"U-Net","full_name":"U-Net","full_name_withheld":false,"description_markdown":"**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](https://paperswithcode.com/method/relu)) and a 2x2 [max pooling](https://paperswithcode.com/method/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](https://paperswithcode.com/method/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](https://paperswithcode.com/method/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.\r\n\r\n[Original MATLAB Code](https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/u-net-release-2015-10-02.tar.gz)","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":"http://arxiv.org/abs/1505.04597v1","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/milesial/Pytorch-UNet/blob/67bf11b4db4c5f2891bd7e8e7f58bcde8ee2d2db/unet/unet_model.py#L8","code_snippet_url_on_a_code_host":true,"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":2588,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Med-URWKV: Pure RWKV With ImageNet Pre-training For Medical Image Segmentation","date":"2025-06-12","arxiv_id":"2506.10858","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code","date":"2025-06-12","arxiv_id":"2506.10617","n_code_links":0,"syntology":null},{"paper":null,"title":"Prompt-Guided Latent Diffusion with Predictive Class Conditioning for 3D Prostate MRI Generation","date":"2025-06-11","arxiv_id":"2506.10230","n_code_links":0,"syntology":null},{"paper":"/paper/2506-08357","title":"MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion","date":"2025-06-10","arxiv_id":"2506.08357","n_code_links":1,"syntology":null},{"paper":null,"title":"A Machine Learning Approach to Generate Residual Stress Distributions using Sparse Characterization Data in Friction-Stir Processed Parts","date":"2025-06-09","arxiv_id":"2506.08205","n_code_links":0,"syntology":null},{"paper":null,"title":"A Comparative Study of U-Net Architectures for Change Detection in Satellite Images","date":"2025-06-09","arxiv_id":"2506.07925","n_code_links":0,"syntology":null},{"paper":null,"title":"Diffusion Models-Aided Uplink Channel Estimation for RIS-Assisted Systems","date":"2025-06-09","arxiv_id":"2506.07770","n_code_links":0,"syntology":null},{"paper":null,"title":"MAGNet: A Multi-Scale Attention-Guided Graph Fusion Network for DRC Violation Detection","date":"2025-06-08","arxiv_id":"2506.07126","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep histological synthesis from mass spectrometry imaging for multimodal registration","date":"2025-06-05","arxiv_id":"2506.05441","n_code_links":0,"syntology":null},{"paper":null,"title":"U-NetMN and SegNetMN: Modified U-Net and SegNet models for bimodal SAR image segmentation","date":"2025-06-05","arxiv_id":"2506.05444","n_code_links":0,"syntology":null},{"paper":"/paper/simulate-any-radar-attribute-controllable","title":"Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding","date":"2025-06-03","arxiv_id":"2506.03134","n_code_links":1,"syntology":{"ran":1,"of":7,"unverified":6,"pointer_only":0}},{"paper":"/paper/dual-encoding-feature-filtering-generalized","title":"Dual encoding feature filtering generalized attention UNET for retinal vessel segmentation","date":"2025-06-02","arxiv_id":"2506.02312","n_code_links":1,"syntology":null},{"paper":null,"title":"TRUST -- Transformer-Driven U-Net for Sparse Target Recovery","date":"2025-06-01","arxiv_id":"2506.01112","n_code_links":0,"syntology":null},{"paper":null,"title":"BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models","date":"2025-05-28","arxiv_id":"2505.22865","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism","date":"2025-05-27","arxiv_id":"2505.21316","n_code_links":0,"syntology":null},{"paper":"/paper/laparoscopic-image-desmoking-using-the-u-net","title":"Laparoscopic Image Desmoking Using the U-Net with New Loss Function and Integrated Differentiable Wiener Filter","date":"2025-05-27","arxiv_id":"2505.21634","n_code_links":1,"syntology":null},{"paper":null,"title":"Supervised and self-supervised land-cover segmentation & classification of the Biesbosch wetlands","date":"2025-05-27","arxiv_id":"2505.21269","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep learning based spatial aliasing reduction in beamforming for audio capture","date":"2025-05-26","arxiv_id":"2505.19781","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers","date":"2025-05-25","arxiv_id":"2505.19122","n_code_links":0,"syntology":null},{"paper":"/paper/dual-attention-residual-u-net-for-accurate","title":"Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection","date":"2025-05-23","arxiv_id":"2505.17683","n_code_links":1,"syntology":null},{"paper":null,"title":"EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion","date":"2025-05-23","arxiv_id":"2505.17367","n_code_links":0,"syntology":null},{"paper":"/paper/f-ancgan-an-attention-enhanced-cycle","title":"F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles","date":"2025-05-23","arxiv_id":"2505.18106","n_code_links":1,"syntology":null},{"paper":"/paper/minkunext-si-improving-point-cloud-based","title":"MinkUNeXt-SI: Improving point cloud-based place recognition including spherical coordinates and LiDAR intensity","date":"2025-05-23","arxiv_id":"2505.17591","n_code_links":1,"syntology":null},{"paper":null,"title":"Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training","date":"2025-05-23","arxiv_id":"2505.17638","n_code_links":0,"syntology":null},{"paper":null,"title":"Assessing the generalization performance of SAM for ureteroscopy scene understanding","date":"2025-05-22","arxiv_id":"2505.17210","n_code_links":0,"syntology":null},{"paper":"/paper/deep-mineralogical-segmentation-of-thin","title":"Deep mineralogical segmentation of thin section images based on QEMSCAN maps","date":"2025-05-22","arxiv_id":"2505.17008","n_code_links":1,"syntology":null},{"paper":"/paper/aquasignal-an-integrated-framework-for-robust","title":"AquaSignal: An Integrated Framework for Robust Underwater Acoustic Analysis","date":"2025-05-20","arxiv_id":"2505.14285","n_code_links":1,"syntology":null},{"paper":"/paper/lod1-3d-city-model-from-lidar-the-impact-of","title":"LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction","date":"2025-05-20","arxiv_id":"2505.14747","n_code_links":1,"syntology":null},{"paper":"/paper/a-skull-adaptive-framework-for-ai-based-3d","title":"A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound Simulation","date":"2025-05-19","arxiv_id":"2505.12998","n_code_links":1,"syntology":null},{"paper":null,"title":"Segmentation of temporomandibular joint structures on mri images using neural networks for diagnosis of pathologies","date":"2025-05-19","arxiv_id":"2505.12963","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":855},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":659},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":450},{"task":"/task/medical-image-segmentation","name":"Medical Image Segmentation","papers":263},{"task":"/task/decoder","name":"Decoder","papers":248},{"task":"/task/denoising","name":"Denoising","papers":171},{"task":"/task/deep-learning","name":"Deep Learning","papers":144},{"task":"/task/image-generation","name":"Image Generation","papers":123},{"task":"/task/tumor-segmentation","name":"Tumor Segmentation","papers":122},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":101},{"task":"/task/computed-tomography-ct","name":"Computed Tomography (CT)","papers":81},{"task":"/task/diagnostic","name":"Diagnostic","papers":81},{"task":"/task/lesion-segmentation","name":"Lesion Segmentation","papers":77},{"task":"/task/medical-image-analysis","name":"Medical Image Analysis","papers":77},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":72},{"task":"/task/brain-tumor-segmentation","name":"Brain Tumor Segmentation","papers":64},{"task":"/task/super-resolution","name":"Super-Resolution","papers":64},{"task":"/task/ssim","name":"SSIM","papers":61},{"task":null,"name":"GPU","papers":60},{"task":null,"name":"Generative Adversarial Network","papers":51}],"tasks_shown":20,"n_tasks":768,"usage_by_year":[{"year":"2015","papers":1},{"year":"2016","papers":1},{"year":"2017","papers":35},{"year":"2018","papers":126},{"year":"2019","papers":225},{"year":"2020","papers":332},{"year":"2021","papers":343},{"year":"2022","papers":345},{"year":"2023","papers":420},{"year":"2024","papers":523},{"year":"2025","papers":237}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/u-net"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}