</> Code with Papers by Syntology

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

Papers archive 2025-07-28

30 shown of 497, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

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