Methods › General › Skip Connection Blocks › Dense Block

Dense Block

497 papers tagged archive 2025-07-28

Introduced by Gao Huang et al. in Densely Connected Convolutional Networks

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

A Dense Block is a module used in convolutional neural networks that connects all layers (with matching feature-map sizes) directly with each other. It was originally proposed as part of the DenseNet architecture. To preserve the feed-forward nature, each layer obtains additional inputs from all preceding layers and passes on its own feature-maps to all subsequent layers. In contrast to ResNets, we never combine features through summation before they are passed into a layer; instead, we combine features by concatenating them. Hence, the ℓᵗʰ layer has ℓ inputs, consisting of the feature-maps of all preceding convolutional blocks. Its own feature-maps are passed on to all L-ℓ subsequent layers. This introduces (L(L+1))/2 connections in an L-layer network, instead of just L, as in traditional architectures: "dense connectivity".

PaperSourceSee Code · pytorch/vision

In Syntology for a different name, 'DENSE', about another paper, arXiv:2112.12371: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'DENSE' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2112.12371, while the archive credits arXiv:1608.06993.

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:2112.12371 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples) · 9 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: 497 · with a code link: 203 · where Syntology ran a sample: 34 (27 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (34 of 497 tagged: 27 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 497, 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 347 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
Image Classification81
image-classification66
Classification59
General Classification59
Transfer Learning47
Deep Learning28
Diagnostic27
Semantic Segmentation24
Segmentation20
Super-Resolution17
Data Augmentation15
Image Super-Resolution15
Object Detection15
Binary Classification13
Decoder13
object-detection13
GPU12
Image Segmentation11
Representation Learning10
Computed Tomography (CT)9

Usage over time archive 2025-07-28

Papers per year tagged with Dense Block: 2015 to 2025, peak 94 94 0 2015: 1 paper 2015 2016: 3 papers 2016 2017: 18 papers 2017 2018: 55 papers 2018 2019: 72 papers 2019 2020: 94 papers 2020 2021: 77 papers 2021 2022: 53 papers 2022 2023: 47 papers 2023 2024: 55 papers 2024 2025: 22 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (497 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

Skip Connection BlocksImage Model Blocks

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