Methods › General › Skip Connection Blocks › DPN Block

DPN Block

19 papers tagged archive 2025-07-28

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

A Dual Path Network block is an image model block used in convolutional neural network. The idea of this module is to enable sharing of common features while maintaining the flexibility to explore new features through dual path architectures. In this sense it combines the benefits of ResNets and DenseNets. It was proposed as part of the DPN CNN architecture.

We formulate such a dual path architecture as follows:

xᵏ = ∑ₜ₌₁ᵏ⁻¹ fₜᵏ(hᵗ) ,

yᵏ = ∑ₜ₌₁ᵏ⁻¹ vₜ(hᵗ) = yᵏ⁻¹ + ϕᵏ⁻¹(yᵏ⁻¹) ,

rᵏ = xᵏ + yᵏ ,

hᵏ = gᵏ ( rᵏ ) ,

where xᵏ and yᵏ denote the extracted information at k-th step from individual path, vₜ(·) is a feature learning function as fₜᵏ(·). The first equation refers to the densely connected path that enables exploring new features. The second equation refers to the residual path that enables common features re-usage. The third equation defines the dual path that integrates them and feeds them to the last transformation function in the last equation.

Source: Dual Path NetworksSee Code · rwightman/pytorch-dpn-pretrained

Papers archive 2025-07-28

19 shown of 19, 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 47 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 Classification3
image-classification3
Classification2
Data Augmentation2
Decoder2
General Classification2
Segmentation2
Semantic Segmentation2
Action Classification1
Action Recognition1
Anomaly Detection1
Audio Generation1
Audio Synthesis1
Click-Through Rate Prediction1
Computed Tomography (CT)1
Diagnostic1
GPU1
Image Segmentation1
Language Modeling1
Language Modelling1

Usage over time archive 2025-07-28

Papers per year tagged with DPN Block: 2017 to 2025, peak 3 3 0 2017: 2 papers 2017 2018: 3 papers 2018 2019: 1 paper 2019 2020: 3 papers 2020 2021: 3 papers 2021 2022: 3 papers 2022 2023: 0 papers 2023 2024: 1 paper 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (19 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 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