A Selective Kernel Convolution is a convolution that enables neurons to adaptively adjust their RF sizes among multiple kernels with different kernel sizes. Specifically, the SK convolution has three operators – Split, Fuse and Select. Multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer
Source: Selective Kernel NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 5 | 8.93% |
Object Detection | 4 | 7.14% |
Object | 3 | 5.36% |
Image Classification | 3 | 5.36% |
Lesion Segmentation | 2 | 3.57% |
Object Detection In Aerial Images | 2 | 3.57% |
Point Cloud Completion | 2 | 3.57% |
Denoising | 2 | 3.57% |
Image Denoising | 2 | 3.57% |
Component | Type |
|
---|---|---|
![]() |
Normalization | |
![]() |
Attention Mechanisms | |
![]() |
Convolutions | |
![]() |
Activation Functions | |
![]() |
Output Functions |