Home › Code › PatchMerging

PatchMerging

Syntologyentry name in harvested coderead from the graph 2026-09-24

PatchMerging appears in the code Syntology harvested for 31 papers, as 39 distinct code bodies found in 39 places (a place is one code body under one paper). At least one of them ran in 31 of the papers; 4 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named PatchMerging do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 37 of the 39 distinct code bodies named PatchMerging; 2 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
37ran
2unverified
4fingerprinted

Licence is a property of each copy, so it is counted per place: 14 of the 39 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

31 papers shown of 31, newest first; 39 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 1 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
ECHOSAT: Estimating Canopy Height Over Space and Time added by Syntology 2026-02 (from id) ai4forest/echosat/fine-tuning/models/swin_video_unet.py af1e123128214397 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Extreme Weather Nowcasting via Local Precipitation Pattern Prediction added by Syntology 2026-02 (from id) tony890048/exPreCast/model.py 9c00eb036e17df62 ran · metamorphic tier: deterministic no licence file found · pointer only
Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation added by Syntology 2025-09 (from id) JinPLu/VeloxSeg/model/VeloxSeg.py d2d79060f425c5b1 ran no licence file found · pointer only
HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery 22 Jul 2025 vvangfaye/HoliTracer/holitracer/vector/models/base.py d0a21c32ae0a99e5 ran · metamorphic tier: invariant MIT (permissive)
arXiv:2507.00698 2025-07 (from id) qhfan/MALA/classfication_release/model.py 9954039dc2a22670 ran no licence file found · pointer only
Demystify Mamba in Vision: A Linear Attention Perspective 26 May 2024 LeapLabTHU/MLLA/models/mlla.py aea9c35eb5503710 ran · metamorphic tier: deterministic MIT (permissive)
KVQ: Kwai Video Quality Assessment for Short-form Videos 11 Feb 2024 lixinustc/kvq-challenge-cvpr-ntire2024/models/backbones/KSVQE_model.py 092afab2341fa8d8 ran · metamorphic tier: deterministic no licence file found · pointer only
SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design 29 Jan 2024 ysj9909/SHViT/model/shvit.py 7f0dd3b9287448aa ran · metamorphic tier: invariant licence not identified · pointer only
Context-Guided Spatio-Temporal Video Grounding 3 Jan 2024 HengLan/CGSTVG/models/pipeline.py 4b91ef1761c7be10 ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only
SG-Former: Self-guided Transformer with Evolving Token Reallocation 23 Aug 2023 OliverRensu/SG-Former/sgformer.py ce0a0df3d2b72b58 ran no licence file found · pointer only
Hidden Biases of End-to-End Driving Models 13 Jun 2023 autonomousvision/carla_garage/team_code/transfuser.py aa4f65952e82e439 ran MIT (permissive)
CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation 6 Jun 2023 SR0920/CiT-Net/CiT_Net_T.py fe9e67cb1896b8e5 ran no licence file found · pointer only
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention 11 May 2023 microsoft/cream/EfficientViT/classification/model/efficientvit.py 5e59ce2cf4f9a679 ran MIT (permissive)
LipsFormer: Introducing Lipschitz Continuity to Vision Transformers 19 Apr 2023 idea-research/lipsformer/models/lipsformer_swin.py d9360a58bc57b6fa ran Apache-2.0 (permissive)
Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos 15 Mar 2023 afcedf/SOONet/src/models/model.py ecf9240b030414ab ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only
Masked Image Modeling with Local Multi-Scale Reconstruction 9 Mar 2023 huawei-noah/Efficient-Computing/Self-supervised/LocalMIM/Swin/models_mim.py df31273be2dcb4cf ran no licence file found · pointer only
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks 7 Mar 2023 jierunchen/fasternet/models/fasternet.py 3ddc356f2175eea6 ran · metamorphic tier: invariant no licence file found · pointer only
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects 7 Aug 2022 PKU-EPIC/DREDS/CatePoseEstimation/networks/SwinDRNet.py be586c7612ce6beb ran · metamorphic tier: deterministic no licence file found · pointer only
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation 22 Jul 2022 Seokju-Cho/Volumetric-Aggregation-Transformer/model/vat.py 688a7c109b6a8925 ran MIT (permissive)
TinyViT: Fast Pretraining Distillation for Small Vision Transformers 21 Jul 2022 microsoft/cream/TinyViT/models/tiny_vit.py 9b97bb4dd7832495 ran MIT (permissive)
Reinforced Swin-Convs Transformer for Underwater Image Enhancement 1 May 2022 TingdiRen/URSCT-SESR/model/URSCT_model.py d9a6ce06291f48bf ran MIT (permissive)
K-LITE: Learning Transferable Visual Models with External Knowledge 20 Apr 2022 microsoft/klite/model/model.py 89e08495ccdd55f4 ran MIT (permissive)
Visual Prompt Tuning 23 Mar 2022 heekhero/DTL/classification/models/swin_transformer.py dce20c2c623e0f35 ran · metamorphic tier: deterministic no licence file found · pointer only
Auto-scaling Vision Transformers without Training 24 Feb 2022 vita-group/asvit/lib/models/cell_infers/transformer.py 79896f75d32dcb33 ran MIT (permissive)
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond 21 Feb 2022 yangyucheng000/papercode-2/STViT-Mindspore-main/models/stvit.py e8f2f05db5500fa5 ran fingerprinted Apache-2.0 (permissive)
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism 26 Jan 2022 microsoft/SPACH/models/shiftvit.py 9d0d874136a0ef10 ran · metamorphic tier: deterministic MIT (permissive)
SimMIM: A Simple Framework for Masked Image Modeling 18 Nov 2021 impiga/plain-detr/models/swin_transformer_v2.py a5518beb9daf7d60 ran · metamorphic tier: deterministic MIT (permissive)
Efficient Self-supervised Vision Transformers for Representation Learning 17 Jun 2021 microsoft/esvit/models/swin_transformer.py fd8f760f4a030218 ran · metamorphic tier: invariant MIT (permissive)
RegionViT: Regional-to-Local Attention for Vision Transformers 4 Jun 2021 dc3ea9f/RegionViT/models/region_vit.py 77415c05ec9a1664 ran MIT (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 shkarupa-alex/tfswin/tfswin/model.py 581e7ffa9c9316a6 ran MIT (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 SwinTransformer/Transformer-SSL/models/swin_transformer.py 3056cb457a463605 ran · metamorphic tier: deterministic MIT (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 towhee-io/towhee/towhee/models/swin_transformer/model.py 2ed9017b0ab73090 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 sayakpaul/swin-transformers-tf/swins/models.py b9bd7459c6f5b8e9 ran Apache-2.0 (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 yangyangxu0/demt/src/model/backbones/swin.py eeb6c8d71fa21dc5 ran no licence file found · pointer only
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 pytorch/vision/torchvision/models/swin_transformer.py 071c035b6c4da4df ran BSD-3-Clause (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 berniwal/swin-transformer-pytorch/swin_transformer_pytorch/swin_transformer.py ce5ff4b0dfaf3e68 ran fingerprinted MIT (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 DarshanDeshpande/jax-models/jax_models/models/swin_transformer.py 2b0633eb94058203 unverified Apache-2.0 (permissive)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows 25 Mar 2021 rishigami/Swin-Transformer-TF/swintransformer/model.py 8ec15b24c9f54c8f unverified Apache-2.0 (permissive)
Attention Is All You Need 12 Jun 2017 HzcIrving/DeepLearning_PlayGround/Swin-Transformer/Model.py 673204d97a651fd0 ran MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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