{"url":"/method/mixconv","slug":"mixconv","name":"MixConv","full_name":"Mixed Depthwise Convolution","full_name_withheld":false,"description_markdown":"**MixConv**, or **Mixed Depthwise Convolution**, is a type of [depthwise convolution](https://paperswithcode.com/method/depthwise-convolution) that naturally mixes up multiple kernel sizes in a single [convolution](https://paperswithcode.com/method/convolution). It is based on the insight that depthwise convolution applies a single kernel size to all channels, which MixConv overcomes by combining the benefits of multiple kernel sizes. It does this by partitioning channels into groups and applying a different kernel size to each group.","description_state":"present","introduced_year":null,"introduced_by":{"title":"MixConv: Mixed Depthwise Convolutional Kernels","paper":"/paper/mixnet-mixed-depthwise-convolutional-kernels","first_author":"Mingxing Tan","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mixnet-mixed-depthwise-convolutional-kernels"},"source":{"url":"https://arxiv.org/abs/1907.09595v3","title":"MixConv: Mixed Depthwise Convolutional Kernels","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/rwightman/pytorch-image-models/blob/e0685dd41585a75385c2f62352669cf5e1df278f/timm/models/layers/mixed_conv2d.py#L20","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":12,"archive_num_papers":12,"papers_newest_first":[{"paper":null,"title":"Thermal Image-based Fault Diagnosis in Induction Machines via Self-Organized Operational Neural Networks","date":"2024-12-08","arxiv_id":"2412.05901","n_code_links":0,"syntology":null},{"paper":"/paper/mixnet-joining-force-of-classical-and-modern","title":"MixNet: Joining Force of Classical and Modern Approaches Toward the Comprehensive Pipeline in Motor Imagery EEG Classification","date":"2024-09-06","arxiv_id":"2409.04104","n_code_links":1,"syntology":null},{"paper":null,"title":"Residual-NeRF: Learning Residual NeRFs for Transparent Object Manipulation","date":"2024-05-10","arxiv_id":"2405.06181","n_code_links":0,"syntology":null},{"paper":"/paper/mixnet-towards-effective-and-efficient-uhd","title":"MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration","date":"2024-01-19","arxiv_id":"2401.10666","n_code_links":2,"syntology":null},{"paper":"/paper/mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","arxiv_id":"2308.12817","n_code_links":1,"syntology":null},{"paper":null,"title":"Semi-Supervised Learning for Image Classification using Compact Networks in the BioMedical Context","date":"2022-05-19","arxiv_id":"2205.09678","n_code_links":0,"syntology":null},{"paper":null,"title":"A Mixture of Expert Based Deep Neural Network for Improved ASR","date":"2021-12-02","arxiv_id":"2112.01025","n_code_links":0,"syntology":null},{"paper":null,"title":"DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking","date":"2021-04-23","arxiv_id":"2104.11585","n_code_links":0,"syntology":null},{"paper":null,"title":"ImageNet Pretrained CNNs for JPEG Steganalysis","date":"2020-11-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/lsq-improving-low-bit-quantization-through","title":"LSQ+: Improving low-bit quantization through learnable offsets and better initialization","date":"2020-04-20","arxiv_id":"2004.09576","n_code_links":4,"syntology":{"ran":3,"of":10,"unverified":7,"pointer_only":10}},{"paper":null,"title":"Learned Threshold Pruning","date":"2020-02-28","arxiv_id":"2003.00075","n_code_links":0,"syntology":null},{"paper":"/paper/mixnet-mixed-depthwise-convolutional-kernels","title":"MixConv: Mixed Depthwise Convolutional Kernels","date":"2019-07-22","arxiv_id":"1907.09595","n_code_links":13,"syntology":{"ran":1,"of":3,"unverified":2,"pointer_only":0}}],"papers_shown":12,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/automl","name":"AutoML","papers":1},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/brain-computer-interface","name":"Brain Computer Interface","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deblurring","name":"Deblurring","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/eeg-1","name":"EEG","papers":1},{"task":"/task/fault-diagnosis","name":"Fault Diagnosis","papers":1},{"task":"/task/image-deblurring","name":"Image Deblurring","papers":1},{"task":"/task/image-enhancement","name":"Image Enhancement","papers":1},{"task":"/task/image-restoration","name":"Image Restoration","papers":1},{"task":"/task/image-steganography","name":"Image Steganography","papers":1},{"task":"/task/low-light-image-enhancement","name":"Low-Light Image Enhancement","papers":1},{"task":"/task/mixture-of-experts","name":"Mixture-of-Experts","papers":1},{"task":"/task/motor-imagery","name":"Motor Imagery","papers":1}],"tasks_shown":20,"n_tasks":33,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":3},{"year":"2021","papers":2},{"year":"2022","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mixconv"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}