Methods › Computer Vision › Convolutional Neural Networks › ResNeSt
ResNeSt
Introduced by Hang Zhang et al. in ResNeSt: Split-Attention Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A ResNest is a variant on a ResNet, which instead stacks Split-Attention blocks. The cardinal group representations are then concatenated along the channel dimension: V = Concat{V¹,V²,⋯Vᴷ}. As in standard residual blocks, the final output Y of otheur Split-Attention block is produced using a shortcut connection: Y=V+X, if the input and output feature-map share the same shape. For blocks with a stride, an appropriate transformation 𝒯 is applied to the shortcut connection to align the output shapes: Y=V+𝒯(X). For example, 𝒯 can be strided convolution or combined convolution-with-pooling.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2004.08955'). Repositories: 36 listed of 36 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2004.08955, not a method entry. This answer is about arXiv:2004.08955, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2004.08955 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified (of 48 harvested samples) · 23 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: 13 · with a code link: 7 · where Syntology ran a sample: 2 (2 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 (2 of 13 tagged: 2 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.
-
Supervised domain adaptation for building extraction from off-nadir aerial images 7 Nov 2023 · 0 repositories · arXiv:2311.03867
-
TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection 19 Apr 2023 · 2 repositories · arXiv:2304.09421
-
Early detection of hip periprosthetic joint infections through CNN on Computed Tomography images 18 Apr 2023 · 0 repositories · arXiv:2304.08942
-
OMSN and FAROS: OCTA Microstructure Segmentation Network and Fully Annotated Retinal OCTA Segmentation Dataset 26 Dec 2022 · 0 repositories · arXiv:2212.13059
-
Anomaly Detection in Automatic Generation Control Systems Based on Traffic Pattern Analysis and Deep Transfer Learning 16 Sep 2022 · 0 repositories · arXiv:2209.08099
-
OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation 25 Jul 2022 · 1 repository · arXiv:2207.12238
-
ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees 10 Nov 2021 · 4 repositories · arXiv:2111.05496
-
Solution for Large-scale Long-tailed Recognition with Noisy Labels 20 Jun 2021 · 1 repository · arXiv:2106.10683
-
AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation 2 May 2021 · 1 repository · arXiv:2105.00402
-
Searching for Fast Model Families on Datacenter Accelerators 10 Feb 2021 · 0 repositories · arXiv:2102.05610
-
Bottleneck Transformers for Visual Recognition 27 Jan 2021 · 13 repositories · arXiv:2101.11605Syntology 26 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 23 unverified (of 49 harvested samples) · 8 pointer-only (licence)
-
2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020 21 Oct 2020 · 0 repositories · arXiv:2010.10957
-
ResNeSt: Split-Attention Networks 19 Apr 2020 · 36 repositories · arXiv:2004.08955Syntology official (archive's flag): 5 ran · 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified (of 48 harvested samples) · 23 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 27 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