Description
MixConv, or Mixed Depthwise Convolution, is a type of depthwise convolution that naturally mixes up multiple kernel sizes in a single 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.
Papers Using This Method
Thermal Image-based Fault Diagnosis in Induction Machines via Self-Organized Operational Neural Networks2024-12-08MixNet: Joining Force of Classical and Modern Approaches Toward the Comprehensive Pipeline in Motor Imagery EEG Classification2024-09-06Residual-NeRF: Learning Residual NeRFs for Transparent Object Manipulation2024-05-10MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration2024-01-19MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild2023-08-23Semi-Supervised Learning for Image Classification using Compact Networks in the BioMedical Context2022-05-19A Mixture of Expert Based Deep Neural Network for Improved ASR2021-12-02DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking2021-04-23ImageNet Pretrained CNNs for JPEG Steganalysis2020-11-24LSQ+: Improving low-bit quantization through learnable offsets and better initialization2020-04-20Learned Threshold Pruning2020-02-28MixConv: Mixed Depthwise Convolutional Kernels2019-07-22