Methods › Computer Vision › Image Model Blocks › ShuffleNet V2 Block
ShuffleNet V2 Block
Introduced by Ningning Ma et al. in ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ShuffleNet V2 Block is an image model block used in the ShuffleNet V2 architecture, where speed is the metric optimized for (instead of indirect ones like FLOPs). It utilizes a simple operator called channel split. At the beginning of each unit, the input of c feature channels are split into two branches with c - c′ and c′ channels, respectively. Following G3, one branch remains as identity. The other branch consists of three convolutions with the same input and output channels to satisfy G1. The two 1×1 convolutions are no longer group-wise, unlike the original ShuffleNet. This is partially to follow G2, and partially because the split operation already produces two groups. After convolution, the two branches are concatenated. So, the number of channels keeps the same (G1). The same “channel shuffle” operation as in ShuffleNet is then used to enable information communication between the two branches.
The motivation behind channel split is that alternative architectures, where pointwise group convolutions and bottleneck structures are used, lead to increased memory access cost. Additionally more network fragmentation with group convolutions reduces parallelism (less friendly for GPU), and the element-wise addition operation, while they have low FLOPs, have high memory access cost. Channel split is an alternative where we can maintain a large number of equally wide channels (equally wide minimizes memory access cost) without having dense convolutions or too many groups.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: CRN v2; ACE v2; Adam-v2; ANAH-v2; AEHM-v2; Evan_V2; LiFR v2; ViTok-v2.
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: 21 · with a code link: 9 · where Syntology ran a sample: 5 (4 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 (5 of 21 tagged: 4 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 21 of 21, 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.
-
Rethinking Information Loss in Medical Image Segmentation with Various-sized Targets 28 Mar 2024 · 0 repositories · arXiv:2403.19177
-
Fragility, Robustness and Antifragility in Deep Learning 15 Dec 2023 · 0 repositories · arXiv:2312.09821
-
A Non-monotonic Smooth Activation Function 16 Oct 2023 · 0 repositories · arXiv:2310.10126
-
Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality 4 Jul 2022 · 0 repositories · arXiv:2207.01296
-
SMU: smooth activation function for deep networks using smoothing maximum technique 8 Nov 2021 · 6 repositories · arXiv:2111.04682
-
SAU: Smooth activation function using convolution with approximate identities 27 Sep 2021 · 0 repositories · arXiv:2109.13210
-
ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions 9 Sep 2021 · 0 repositories · arXiv:2109.04386
-
Rethinking Image Deraining via Rain Streaks and Vapors 3 Aug 2020 · 1 repository · arXiv:2008.00823Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Egocentric Human Segmentation for Mixed Reality 25 May 2020 · 0 repositories · arXiv:2005.12074
-
DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks 22 Apr 2020 · 0 repositories · arXiv:2004.10694
-
CNN-CASS: CNN for Classification of Coronary Artery Stenosis Score in MPR Images 23 Jan 2020 · 1 repository · arXiv:2001.08593
-
Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks 21 Oct 2019 · 0 repositories · arXiv:1910.09455
-
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices 1 Oct 2019 · 0 repositories
-
Mish: A Self Regularized Non-Monotonic Activation Function 23 Aug 2019 · 9 repositories · arXiv:1908.08681Syntology official (archive's flag): 6 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 1 pointer-only (licence)
-
DiCENet: Dimension-wise Convolutions for Efficient Networks 8 Jun 2019 · 2 repositories · arXiv:1906.03516Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Butterfly Transform: An Efficient FFT Based Neural Architecture Design 5 Jun 2019 · 1 repository · arXiv:1906.02256
-
ThunderNet: Towards Real-time Generic Object Detection 28 Mar 2019 · 3 repositories · arXiv:1903.11752
-
DetNAS: Backbone Search for Object Detection 26 Mar 2019 · 2 repositories · arXiv:1903.10979Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 3 pointer-only (licence)
-
ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search 7 Dec 2018 · 0 repositories · arXiv:1812.02975
-
DSNet for Real-Time Driving Scene Semantic Segmentation 6 Dec 2018 · 0 repositories · arXiv:1812.07049
-
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design 30 Jul 2018 · 35 repositories · arXiv:1807.11164Syntology 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified (of 30 harvested samples) · 3 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 24 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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