Home › Code › drop_add_residual_stochastic_depth

drop_add_residual_stochastic_depth

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

drop_add_residual_stochastic_depth appears in the code Syntology harvested for 26 papers, as 15 distinct code bodies found in 29 places (a place is one code body under one paper). At least one of them ran in 7 of the papers; 0 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 drop_add_residual_stochastic_depth 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 6 of the 15 distinct code bodies named drop_add_residual_stochastic_depth; 9 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
3ran · fixture could not drive it
3ran
9unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 7 of the 29 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

26 papers shown of 26, newest first; 29 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 1 papers added by Syntology; 4 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
Pixel-Perfect Visual Geometry Estimation added by Syntology 2026-01 (from id) gangweix/pixel-perfect-depth/ppd/models/depth_anything_v2/dinov2_layers/block.py 85f7ffc01945bb72 unverified Apache-2.0 (permissive)
Streaming 4D Visual Geometry Transformer 15 Jul 2025 wzzheng/streamvggt/src/streamvggt/layers/block.py a2ec87bca0ee4781 unverified licence not identified · pointer only
arXiv:2507.03779 2025-07 (from id) KevinZ0217/fast_dinov2/dinov2/layers/block.py 85f7ffc01945bb72 unverified no licence file found · pointer only
MedITok: A Unified Tokenizer for Medical Image Synthesis and Interpretation 25 May 2025 masaaki-75/meditok/layers/block.py 85f7ffc01945bb72 unverified MIT (permissive)
SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking 24 Mar 2025 WenRuiCai/SPMTrack/trackit/models/methods/SPMTrack/modules/mixformer_attn.py 29d3c222b6dd6659 unverified Apache-2.0 (permissive)
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos 21 Jan 2025 DepthAnything/Video-Depth-Anything/video_depth_anything/dinov2_layers/block.py 85f7ffc01945bb72 unverified Apache-2.0 (permissive)
Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation 15 Jan 2025 jiaqihuang01/detris/model/dinov2/layers/block.py 85f7ffc01945bb72 unverified MIT (permissive)
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving 12 Dec 2024 envision-research/driverecon/dinov2/layers/block.py 85f7ffc01945bb72 unverified no licence file found · pointer only
TIPS: Text-Image Pretraining with Spatial Awareness 21 Oct 2024 google-deepmind/tips/pytorch/image_encoder.py 05a0718e5f236e14 unverified Apache-2.0 (permissive)
SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery 26 Aug 2024 sarahrastegar/selex/models/vision_transformer2.py 167e169f064431a0 ran MIT (permissive)
SpectralEarth: Training Hyperspectral Foundation Models at Scale 15 Aug 2024 panopticon-fm/panopticon/dinov2/layers/block.py 4f9799b98aecb875 unverified Apache-2.0 (permissive)
SCAPE: A Simple and Strong Category-Agnostic Pose Estimator 18 Jul 2024 tiny-smart/SCAPE/scape/models/layers/block.py 85f7ffc01945bb72 unverified no licence file found · pointer only
Accessing Vision Foundation Models at ImageNet-level Costs 15 Jul 2024 bespontaneous/proteus-pytorch/pretrain/models_dinov2.py fe3002776da59ed1 unverified MIT (permissive)
WildGaussians: 3D Gaussian Splatting in the Wild 11 Jul 2024 jkulhanek/wild-gaussians/wildgaussians/dinov2.py bd91e9a4fc420313 ran licence not identified · pointer only
EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models 14 Jun 2024 facebookresearch/efm3d/efm3d/model/dinov2_utils.py 4d7d35dca4659acd ran Apache-2.0 (permissive)
Depth Anything V2 13 Jun 2024 DepthAnything/Depth-Anything-V2/depth_anything_v2/dinov2_layers/block.py 85f7ffc01945bb72 unverified Apache-2.0 (permissive)
Depth Anything V2 13 Jun 2024 fabio-sim/Depth-Anything-ONNX/depth_anything_v2/dinov2_layers/block.py 384c2ee5d2dc2afb unverified Apache-2.0 (permissive)
LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model 7 Jun 2024 kennethwdk/LocLLM/models/dino_layers/block.py 85f7ffc01945bb72 unverified MIT (permissive)
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation 22 Mar 2024 yvanyin/metric3d/mono/model/backbones/ViT_DINO.py 71b3e03a56d81aec ran · fixture could not drive it BSD-2-Clause (permissive)
CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition 29 Feb 2024 Lu-Feng/CricaVPR/backbone/dinov2/block.py 85f7ffc01945bb72 unverified MIT (permissive)
Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations 5 Feb 2024 stefanwm13/just-cluster-it-public/dinov2/layers/block.py 85f7ffc01945bb72 unverified MIT (permissive)
Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks 4 Dec 2023 mohammedsb/dinov2formedical/dinov2/layers/block.py 85f7ffc01945bb72 unverified no licence file found · pointer only
DINOv2: Learning Robust Visual Features without Supervision 14 Apr 2023 ByungKwanLee/Causal-Unsupervised-Segmentation/models/dinov2vit.py ba6d096d6c5fffc9 ran · fixture could not drive it no licence file found · pointer only
DINOv2: Learning Robust Visual Features without Supervision 14 Apr 2023 beneroth13/dinov2/dinov2/layers/block.py 85f7ffc01945bb72 unverified Apache-2.0 (permissive)
DINOv2: Learning Robust Visual Features without Supervision 14 Apr 2023 marrlab/dinobloom/dinov2/layers/block.py 931b30d6ce9e37cb unverified Apache-2.0 (permissive)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 OML-Team/open-metric-learning/oml/models/vit_dino/external_v2/vision_transformer.py 6b47b72596f1a5c3 ran · fixture could not drive it Apache-2.0 (permissive)
arXiv:openreview_eDlsO4kFaX KiiSooo/CODiff/dinov2/layers/block.py e7e8089f932d8d9d unverified MIT (permissive)
arXiv:openreview_YA3AvVx2Ze lytang63/CoGe-GCD/models/vision_transformer2.py 167e169f064431a0 ran MIT (permissive)
arXiv:Xu_MAC-Ego3D_Multi-Agent_Gaussian_Consensus_for_Real-Time_Collaborative_Ego-Motion_and_Photorealistic_CVPR_2025_paper Xiaohao-Xu/MAC-Ego3D/dinov2/layers/block.py 85f7ffc01945bb72 unverified 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