Methods › General › Miscellaneous Components › Channel Shuffle
Channel Shuffle
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Channel Shuffle is an operation to help information flow across feature channels in convolutional neural networks. It was used as part of the ShuffleNet architecture.
If we allow a group convolution to obtain input data from different groups, the input and output channels will be fully related. Specifically, for the feature map generated from the previous group layer, we can first divide the channels in each group into several subgroups, then feed each group in the next layer with different subgroups.
The above can be efficiently and elegantly implemented by a channel shuffle operation: suppose a convolutional layer with g groups whose output has g ×n channels; we first reshape the output channel dimension into (g, n), transposing and then flattening it back as the input of next layer. Channel shuffle is also differentiable, which means it can be embedded into network structures for end-to-end training.
In Syntology verified reference implementation at level V3; retrieve with get_reference_implementation(name='Channel Shuffle'). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2007.13040) is about this method is not checked.
Origin paper of this answer, arXiv:2007.13040 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 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.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 80 · with a code link: 38 · where Syntology ran a sample: 15 (13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (15 of 80 tagged: 13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 80 of 80, 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.
-
Multispectral Detection Transformer with Infrared-Centric Sensor Fusion 21 May 2025 · 1 repository · arXiv:2505.15137
-
Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues 1 Feb 2025 · 0 repositories · arXiv:2502.00397
-
Comparison of Neural Models for X-ray Image Classification in COVID-19 Detection 8 Jan 2025 · 0 repositories · arXiv:2501.04196
-
Advancing Green AI: Efficient and Accurate Lightweight CNNs for Rice Leaf Disease Identification 3 Aug 2024 · 0 repositories · arXiv:2408.01752
-
Faster Metallic Surface Defect Detection Using Deep Learning with Channel Shuffling 19 Jun 2024 · 0 repositories · arXiv:2406.14582
-
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
-
Generalizability of CNN Architectures for Face Morph Presentation Attack 17 Oct 2023 · 0 repositories · arXiv:2310.11105
-
A Non-monotonic Smooth Activation Function 16 Oct 2023 · 0 repositories · arXiv:2310.10126
-
Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers 9 Oct 2023 · 0 repositories · arXiv:2310.05642
-
Multi-Transfer Learning Techniques for Detecting Auditory Brainstem Response 29 Aug 2023 · 0 repositories · arXiv:2308.16203
-
RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection 31 Jul 2023 · 1 repository · arXiv:2307.16412Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
JetSeg: Efficient Real-Time Semantic Segmentation Model for Low-Power GPU-Embedded Systems 19 May 2023 · 1 repository · arXiv:2305.11419
-
PSDNet: Determination of Particle Size Distributions Using Synthetic Soil Images and Convolutional Neural Networks 7 Mar 2023 · 0 repositories · arXiv:2303.04269
-
Use Cases for Time-Frequency Image Representations and Deep Learning Techniques for Improved Signal Classification 22 Feb 2023 · 0 repositories · arXiv:2302.11093
-
QLABGrad: a Hyperparameter-Free and Convergence-Guaranteed Scheme for Deep Learning 1 Feb 2023 · 0 repositories · arXiv:2302.00252
-
Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: Achieving SOTA predictive performance with fewer data using Swin Transformer 22 Aug 2022 · 0 repositories · arXiv:2208.10495
-
MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing 12 Jul 2022 · 0 repositories · arXiv:2207.05621
-
Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality 4 Jul 2022 · 0 repositories · arXiv:2207.01296
-
Design and Analysis of Novel Bit-flip Attacks and Defense Strategies for DNNs 24 Jun 2022 · 1 repository
-
Structured Pruning is All You Need for Pruning CNNs at Initialization 4 Mar 2022 · 0 repositories · arXiv:2203.02549
-
Multimodal registration of FISH and nanoSIMS images using convolutional neural network models 14 Jan 2022 · 0 repositories · arXiv:2201.05545
-
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections 9 Jan 2022 · 1 repository · arXiv:2201.03013
-
Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique 1 Jan 2022 · 0 repositories
-
SMU: smooth activation function for deep networks using smoothing maximum technique 8 Nov 2021 · 6 repositories · arXiv:2111.04682
-
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework 29 Sep 2021 · 0 repositories
-
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
-
High performing ensemble of convolutional neural networks for insect pest image detection 28 Aug 2021 · 0 repositories · arXiv:2108.12539
-
Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images 18 Aug 2021 · 1 repository · arXiv:2108.08157
-
Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion 11 Aug 2021 · 1 repository · arXiv:2108.05009Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 11 harvested samples)
-
Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System 1 Aug 2021 · 0 repositories · arXiv:2108.00392
-
ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks 17 Jun 2021 · 0 repositories · arXiv:2106.09358
-
Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework 16 Jun 2021 · 0 repositories · arXiv:2106.09121
-
Lite-HRNet: A Lightweight High-Resolution Network 13 Apr 2021 · 17 repositories · arXiv:2104.06403Syntology community repositories only · 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified (of 29 harvested samples) · 13 pointer-only (licence)
-
ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators 12 Apr 2021 · 0 repositories · arXiv:2104.05217
-
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning 5 Feb 2021 · 1 repository · arXiv:2102.03214Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps 29 Dec 2020 · 2 repositories · arXiv:2012.14966Syntology official (archive's flag): 16 ran · 16 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified (of 23 harvested samples)
-
FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion 15 Dec 2020 · 0 repositories · arXiv:2012.08270
-
Ensemble-CVDNet: A Deep Learning based End-to-End Classification Framework for COVID-19 Detection using Ensembles of Networks 9 Dec 2020 · 1 repository · arXiv:2012.09132
-
Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs 6 Nov 2020 · 1 repository · arXiv:2011.04475
-
MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization 19 Oct 2020 · 1 repository · arXiv:2010.09278
-
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)
-
Improving Generalization in Meta-learning via Task Augmentation 26 Jul 2020 · 1 repository · arXiv:2007.13040Syntology official (archive's flag): 1 ran · 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 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
-
Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle 19 Feb 2020 · 1 repository · arXiv:2002.08127
-
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations 17 Feb 2020 · 1 repository · arXiv:2002.07136Syntology official (archive's flag): 9 ran · 9 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)
-
Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks 29 Jan 2020 · 1 repository · arXiv:2001.10710
-
CNN-CASS: CNN for Classification of Coronary Artery Stenosis Score in MPR Images 23 Jan 2020 · 1 repository · arXiv:2001.08593
-
Quantisation and Pruning for Neural Network Compression and Regularisation 14 Jan 2020 · 1 repository · arXiv:2001.04850
-
ZeroQ: A Novel Zero Shot Quantization Framework 1 Jan 2020 · 3 repositories · arXiv:2001.00281Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified (of 19 harvested samples) · 2 pointer-only (licence)
-
LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation 13 Dec 2019 · 2 repositories · arXiv:1912.06683
-
Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks 21 Oct 2019 · 0 repositories · arXiv:1910.09455
-
A Pre-defined Sparse Kernel Based Convolution for Deep CNNs 2 Oct 2019 · 0 repositories · arXiv:1910.00724
-
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices 1 Oct 2019 · 0 repositories
-
EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing 30 Sep 2019 · 1 repository · arXiv:1909.13522
-
Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions 23 Sep 2019 · 0 repositories · arXiv:1909.10431
-
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)
-
RRNet: Repetition-Reduction Network for Energy Efficient Decoder of Depth Estimation 23 Jul 2019 · 0 repositories · arXiv:1907.09707
-
Deep Single Image Deraining Via Estimating Transmission and Atmospheric Light in rainy Scenes 22 Jun 2019 · 0 repositories · arXiv:1906.09433
-
HGC: Hierarchical Group Convolution for Highly Efficient Neural Network 9 Jun 2019 · 0 repositories · arXiv:1906.03657
-
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
-
Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information 9 May 2019 · 0 repositories · arXiv:1905.03466
-
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)
-
Learnable Embedding Space for Efficient Neural Architecture Compression 1 Feb 2019 · 2 repositories · arXiv:1902.00383Syntology community repositories only · 1 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; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Slimmable Neural Networks 21 Dec 2018 · 4 repositories · arXiv:1812.08928Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 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
-
Shift-based Primitives for Efficient Convolutional Neural Networks 22 Sep 2018 · 0 repositories · arXiv:1809.08458
-
MBS: Macroblock Scaling for CNN Model Reduction 18 Sep 2018 · 0 repositories · arXiv:1809.06569
-
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)
-
Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications 24 Mar 2018 · 2 repositories · arXiv:1803.09127
-
HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage 7 Mar 2018 · 1 repository · arXiv:1803.02742
-
RTSeg: Real-time Semantic Segmentation Comparative Study 7 Mar 2018 · 2 repositories · arXiv:1803.02758
-
FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy 11 Feb 2018 · 3 repositories · arXiv:1802.03750
-
EffNet: An Efficient Structure for Convolutional Neural Networks 19 Jan 2018 · 3 repositories · arXiv:1801.06434
-
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices 4 Jul 2017 · 38 repositories · arXiv:1707.01083
Tasks archive 2025-07-28
20 shown of 85 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