{"url":"/method/channel-shuffle","slug":"channel-shuffle","name":"Channel Shuffle","full_name":"Channel Shuffle","full_name_withheld":false,"description_markdown":"**Channel Shuffle** is an operation to help information flow across feature channels in convolutional neural networks. It was used as part of the [ShuffleNet](https://paperswithcode.com/method/shufflenet) architecture. \r\n\r\nIf we allow a group [convolution](https://paperswithcode.com/method/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. \r\n\r\nThe above can be efficiently and elegantly implemented by a channel shuffle operation: suppose a convolutional layer with $g$ groups whose output has $g \\times n$ channels; we first reshape the output channel dimension into $\\left(g, n\\right)$, 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.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1707.01083v2","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/osmr/imgclsmob/blob/c03fa67de3c9e454e9b6d35fe9cbb6b15c28fda7/pytorch/pytorchcv/models/common.py#L862","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Miscellaneous Components","url":"/methods/category/miscellaneous-components","pwc_aliases":[]}],"n_papers_tagged":80,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/multispectral-detection-transformer-with","title":"Multispectral Detection Transformer with Infrared-Centric Sensor Fusion","date":"2025-05-21","arxiv_id":"2505.15137","n_code_links":1,"syntology":null},{"paper":null,"title":"Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues","date":"2025-02-01","arxiv_id":"2502.00397","n_code_links":0,"syntology":null},{"paper":null,"title":"Comparison of Neural Models for X-ray Image Classification in COVID-19 Detection","date":"2025-01-08","arxiv_id":"2501.04196","n_code_links":0,"syntology":null},{"paper":null,"title":"Advancing Green AI: Efficient and Accurate Lightweight CNNs for Rice Leaf Disease Identification","date":"2024-08-03","arxiv_id":"2408.01752","n_code_links":0,"syntology":null},{"paper":null,"title":"Faster Metallic Surface Defect Detection Using Deep Learning with Channel Shuffling","date":"2024-06-19","arxiv_id":"2406.14582","n_code_links":0,"syntology":null},{"paper":null,"title":"Rethinking Information Loss in Medical Image Segmentation with Various-sized Targets","date":"2024-03-28","arxiv_id":"2403.19177","n_code_links":0,"syntology":null},{"paper":null,"title":"Fragility, Robustness and Antifragility in Deep Learning","date":"2023-12-15","arxiv_id":"2312.09821","n_code_links":0,"syntology":null},{"paper":null,"title":"Generalizability of CNN Architectures for Face Morph Presentation Attack","date":"2023-10-17","arxiv_id":"2310.11105","n_code_links":0,"syntology":null},{"paper":null,"title":"A Non-monotonic Smooth Activation Function","date":"2023-10-16","arxiv_id":"2310.10126","n_code_links":0,"syntology":null},{"paper":null,"title":"Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers","date":"2023-10-09","arxiv_id":"2310.05642","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-Transfer Learning Techniques for Detecting Auditory Brainstem Response","date":"2023-08-29","arxiv_id":"2308.16203","n_code_links":0,"syntology":null},{"paper":"/paper/rcs-yolo-a-fast-and-high-accuracy-object","title":"RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection","date":"2023-07-31","arxiv_id":"2307.16412","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":"/paper/jetseg-efficient-real-time-semantic","title":"JetSeg: Efficient Real-Time Semantic Segmentation Model for Low-Power GPU-Embedded Systems","date":"2023-05-19","arxiv_id":"2305.11419","n_code_links":1,"syntology":null},{"paper":null,"title":"PSDNet: Determination of Particle Size Distributions Using Synthetic Soil Images and Convolutional Neural Networks","date":"2023-03-07","arxiv_id":"2303.04269","n_code_links":0,"syntology":null},{"paper":null,"title":"Use Cases for Time-Frequency Image Representations and Deep Learning Techniques for Improved Signal Classification","date":"2023-02-22","arxiv_id":"2302.11093","n_code_links":0,"syntology":null},{"paper":null,"title":"QLABGrad: a Hyperparameter-Free and Convergence-Guaranteed Scheme for Deep Learning","date":"2023-02-01","arxiv_id":"2302.00252","n_code_links":0,"syntology":null},{"paper":null,"title":"Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: Achieving SOTA predictive performance with fewer data using Swin Transformer","date":"2022-08-22","arxiv_id":"2208.10495","n_code_links":0,"syntology":null},{"paper":null,"title":"MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing","date":"2022-07-12","arxiv_id":"2207.05621","n_code_links":0,"syntology":null},{"paper":null,"title":"Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality","date":"2022-07-04","arxiv_id":"2207.01296","n_code_links":0,"syntology":null},{"paper":"/paper/design-and-analysis-of-novel-bit-flip-attacks","title":"Design and Analysis of Novel Bit-flip Attacks and Defense Strategies for DNNs","date":"2022-06-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","date":"2022-03-04","arxiv_id":"2203.02549","n_code_links":0,"syntology":null},{"paper":null,"title":"Multimodal registration of FISH and nanoSIMS images using convolutional neural network models","date":"2022-01-14","arxiv_id":"2201.05545","n_code_links":0,"syntology":null},{"paper":"/paper/threshnet-an-efficient-densenet-using","title":"ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections","date":"2022-01-09","arxiv_id":"2201.03013","n_code_links":1,"syntology":null},{"paper":null,"title":"Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique","date":"2022-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/smu-smooth-activation-function-for-deep","title":"SMU: smooth activation function for deep networks using smoothing maximum technique","date":"2021-11-08","arxiv_id":"2111.04682","n_code_links":6,"syntology":null},{"paper":null,"title":"Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"SAU: Smooth activation function using convolution with approximate identities","date":"2021-09-27","arxiv_id":"2109.13210","n_code_links":0,"syntology":null},{"paper":null,"title":"ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions","date":"2021-09-09","arxiv_id":"2109.04386","n_code_links":0,"syntology":null},{"paper":null,"title":"High performing ensemble of convolutional neural networks for insect pest image detection","date":"2021-08-28","arxiv_id":"2108.12539","n_code_links":0,"syntology":null},{"paper":"/paper/towards-deep-and-efficient-a-deep-siamese","title":"Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images","date":"2021-08-18","arxiv_id":"2108.08157","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":13},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":13},{"task":"/task/image-classification","name":"Image Classification","papers":11},{"task":"/task/object-detection-1","name":"object-detection","papers":11},{"task":"/task/image-classification","name":"image-classification","papers":8},{"task":"/task/segmentation","name":"Segmentation","papers":6},{"task":"/task/deep-learning","name":"Deep Learning","papers":5},{"task":"/task/classification","name":"General Classification","papers":5},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":5},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","papers":5},{"task":"/task/decoder","name":"Decoder","papers":4},{"task":null,"name":"GPU","papers":4},{"task":"/task/model-compression","name":"Model Compression","papers":4},{"task":"/task/object","name":"Object","papers":4},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":4},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":3},{"task":"/task/diagnostic","name":"Diagnostic","papers":3},{"task":"/task/efficient-neural-network","name":"Efficient Neural Network","papers":3},{"task":"/task/network-pruning","name":"Network Pruning","papers":3},{"task":"/task/all","name":"All","papers":2}],"tasks_shown":20,"n_tasks":85,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":11},{"year":"2019","papers":16},{"year":"2020","papers":15},{"year":"2021","papers":13},{"year":"2022","papers":8},{"year":"2023","papers":10},{"year":"2024","papers":3},{"year":"2025","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/channel-shuffle"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}