Methods › Computer Vision › Convolutional Neural Networks › RepVGG
RepVGG
Introduced by Xiaohan Ding et al. in RepVGG: Making VGG-style ConvNets Great Again
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
RepVGG is a VGG-style convolutional architecture. It has the following advantages:
- The model has a VGG-like plain (a.k.a. feed-forward) topology 1 without any branches. I.e., every layer takes the output of its only preceding layer as input and feeds the output into its only following layer.
- The model’s body uses only 3 × 3 conv and ReLU.
- The concrete architecture (including the specific depth and layer widths) is instantiated with no automatic search, manual refinement, compound scaling, nor other heavy designs.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 24 in the graph, strongest link: official). This answer is about arXiv:2101.03697, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2101.03697 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 16 harvested samples) · 6 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.
Papers archive 2025-07-28
archive papers tagged: 13 · with a code link: 4 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 13 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 13 of 13, 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.
-
On the Vulnerability of Skip Connections to Model Inversion Attacks 3 Sep 2024 · 0 repositories · arXiv:2409.01696
-
Oracle Bone Script Similiar Character Screening Approach Based on Simsiam Contrastive Learning and Supervised Learning 13 Aug 2024 · 0 repositories · arXiv:2408.06811
-
RepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detection 6 May 2024 · 1 repository · arXiv:2405.03541
-
Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks 11 Feb 2024 · 0 repositories · arXiv:2402.07200
-
NeRCC: Nested-Regression Coded Computing for Resilient Distributed Prediction Serving Systems 6 Feb 2024 · 0 repositories · arXiv:2402.04377
-
Detection of Small Targets in Sea Clutter Based on RepVGG and Continuous Wavelet Transform 14 Nov 2023 · 0 repositories · arXiv:2311.07912
-
UNISOUND System for VoxCeleb Speaker Recognition Challenge 2023 24 Aug 2023 · 0 repositories · arXiv:2308.12526
-
A region and category confidence-based multi-task network for carotid ultrasound image segmentation and classification 2 Jul 2023 · 0 repositories · arXiv:2307.00583
-
Make RepVGG Greater Again: A Quantization-aware Approach 3 Dec 2022 · 2 repositories · arXiv:2212.01593
-
Artificial Intelligence for Automatic Detection and Classification Disease on the X-Ray Images 14 Nov 2022 · 0 repositories · arXiv:2211.08244
-
RMNet: Equivalently Removing Residual Connection from Networks 1 Nov 2021 · 1 repository · arXiv:2111.00687
-
Fast query-by-example speech search using separable model 18 Sep 2021 · 0 repositories · arXiv:2109.08870
-
RepVGG: Making VGG-style ConvNets Great Again 11 Jan 2021 · 25 repositories · arXiv:2101.03697Syntology official (archive's flag): 2 ran · 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 16 harvested samples) · 6 pointer-only (licence)
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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