Methods › Computer Vision › Image Model Blocks › ResNeXt Block

ResNeXt Block

132 papers tagged archive 2025-07-28

Introduced by Saining Xie et al. in Aggregated Residual Transformations for Deep Neural Networks

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

A ResNeXt Block is a type of residual block used as part of the ResNeXt CNN architecture. It uses a "split-transform-merge" strategy (branched paths within a single module) similar to an Inception module, i.e. it aggregates a set of transformations. Compared to a Residual Block, it exposes a new dimension, cardinality (size of set of transformations) C, as an essential factor in addition to depth and width.

Formally, a set of aggregated transformations can be represented as: ℱ(x)=∑ᵢ₌₁^C𝒯ᵢ(x), where 𝒯ᵢ(x) can be an arbitrary function. Analogous to a simple neuron, 𝒯ᵢ should project x into an (optionally low-dimensional) embedding and then transform it.

PaperSourceSee Code · pytorch/vision

In Syntology for a different name, 'ResNeXt': repository known, no verified implementation (declared_code; repositories: 5 listed of 57 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'ResNeXt' (resolution: token_match); this answer is about that name. This answer is about arXiv:1611.05431, the paper the archive credits with this method.

Origin paper of this answer, arXiv:1611.05431 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified (of 80 harvested samples) · 13 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.

Papers archive 2025-07-28

archive papers tagged: 132 · with a code link: 82 · where Syntology ran a sample: 39 (34 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (39 of 132 tagged: 34 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 132, 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 161 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
Object Detection39
Image Classification28
object-detection25
Semantic Segmentation24
Segmentation20
General Classification19
image-classification16
Instance Segmentation15
Object14
Classification8
Transfer Learning8
Action Recognition7
Panoptic Segmentation6
Image Segmentation5
Neural Architecture Search5
Real-Time Object Detection5
2D Object Detection4
Action Classification4
Deep Learning4
GPU4

Usage over time archive 2025-07-28

Papers per year tagged with ResNeXt Block: 2016 to 2025, peak 43 43 0 2016: 2 papers 2016 2017: 8 papers 2017 2018: 27 papers 2018 2019: 43 papers 2019 2020: 19 papers 2020 2021: 18 papers 2021 2022: 4 papers 2022 2023: 3 papers 2023 2024: 6 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (132 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

Image Model BlocksSkip 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