Methods › Computer Vision › Semantic Segmentation Models › U-Net

U-Net

2,588 papers tagged archive 2025-07-28

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.

Original MATLAB Code

Source: U-Net: Convolutional Networks for Biomedical Image SegmentationSee Code · milesial/Pytorch-UNet

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 484 in the graph, strongest link: mentioned on GitHub). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1505.04597) is about this method is not checked.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1505.04597 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified (of 757 harvested samples) · 426 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 2,588 · with a code link: 1,017 · where Syntology ran a sample: 156 (127 with a run with no instrument failure, 29 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (156 of 2,588 tagged: 127 with a run with no instrument failure, 29 where every run was a failure of Syntology's instrument)

Page 1 of 26: papers 1 to 100 of 2,588, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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.

TaskPapers
Segmentation855
Semantic Segmentation659
Image Segmentation450
Medical Image Segmentation263
Decoder248
Denoising171
Deep Learning144
Image Generation123
Tumor Segmentation122
Data Augmentation101
Computed Tomography (CT)81
Diagnostic81
Lesion Segmentation77
Medical Image Analysis77
Transfer Learning72
Brain Tumor Segmentation64
Super-Resolution64
SSIM61
GPU60
Generative Adversarial Network51

Usage over time archive 2025-07-28

Papers per year tagged with U-Net: 2015 to 2025, peak 523 523 0 2015: 1 paper 2015 2016: 1 paper 2016 2017: 35 papers 2017 2018: 126 papers 2018 2019: 225 papers 2019 2020: 332 papers 2020 2021: 343 papers 2021 2022: 345 papers 2022 2023: 420 papers 2023 2024: 523 papers 2024 2025: 237 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (2,588 dated). Bars are counts, not a trend claim.

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

Semantic Segmentation Models

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