Methods › Computer Vision › Vision Transformers › Swin Transformer

Swin Transformer

416 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

The Swin Transformer is a type of Vision Transformer. It builds hierarchical feature maps by merging image patches (shown in gray) in deeper layers and has linear computation complexity to input image size due to computation of self-attention only within each local window (shown in red). It can thus serve as a general-purpose backbone for both image classification and dense recognition tasks. In contrast, previous vision Transformers produce feature maps of a single low resolution and have quadratic computation complexity to input image size due to computation of self-attention globally.

Source: Swin Transformer: Hierarchical Vision Transformer using...See Code · microsoft/Swin-Transformer

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 79 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2103.14030) 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:2103.14030 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified (of 207 harvested samples) · 45 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: 416 · with a code link: 207 · where Syntology ran a sample: 58 (50 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (58 of 416 tagged: 50 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 416, 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 353 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
Semantic Segmentation91
Image Classification55
Object Detection50
Decoder47
Segmentation47
image-classification39
object-detection35
Image Segmentation29
Instance Segmentation25
Super-Resolution23
Transfer Learning23
Medical Image Segmentation22
Classification21
Data Augmentation20
Object19
Diagnostic15
Denoising13
Image Super-Resolution13
GPU12
Image Restoration12

Usage over time archive 2025-07-28

Papers per year tagged with Swin Transformer: 2021 to 2025, peak 109 109 0 2021: 45 papers 2021 2022: 107 papers 2022 2023: 109 papers 2023 2024: 106 papers 2024 2025: 49 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (416 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

Vision Transformers

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