Methods › Computer Vision › Convolutional Neural Networks › DPN

Dual Path Network

DPN

19 papers tagged archive 2025-07-28

Introduced by Yunpeng Chen et al. in Dual Path Networks

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

A Dual Path Network (DPN) is a convolutional neural network which presents a new topology of connection paths internally. The intuition is that ResNets enables feature re-usage while DenseNet enables new feature exploration, and both are important for learning good representations. To enjoy the benefits from both path topologies, Dual Path Networks share common features while maintaining the flexibility to explore new features through dual path architectures.

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.

PaperSourceSee Code · osmr/imgclsmob

In Syntology about another paper, arXiv:2405.17272: repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The lookup matched a paper by its title, arXiv:2405.17272, not a method entry. About another paper: this answer is about arXiv:2405.17272, while the archive credits arXiv:1707.01629.

From the lookup's note on this name: The same name also belongs to “Disparity Proposal Network (DPN)”, a method in the paper “Neural Markov Random Field for Stereo Matching” (arXiv:2403.11193, 68 citations), which the lookup finds cited far more than the paper this answer is about (21 citations), so this answer may be about a different sense of the name. For arXiv:2403.11193: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2405.17272 (its page on this site · its page on Syntology).

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: 19 · with a code link: 10 · where Syntology ran a sample: 2 (1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 19 tagged: 1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 19 of 19, 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 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: 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

Convolutional Neural Networks

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