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.
Source: MixConv: Mixed Depthwise Convolutional KernelsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 3 | 18.75% |
Image Enhancement | 1 | 6.25% |
Image Restoration | 1 | 6.25% |
Low-Light Image Enhancement | 1 | 6.25% |
Scene Text Detection | 1 | 6.25% |
Text Detection | 1 | 6.25% |
Automatic Speech Recognition (ASR) | 1 | 6.25% |
Speech Recognition | 1 | 6.25% |
Object Tracking | 1 | 6.25% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |