A Residual SRM is a module for convolutional neural networks that uses a Style-based Recalibration Module within a residual block like structure. The Style-based Recalibration Module (SRM) adaptively recalibrates intermediate feature maps by exploiting their styles.
Source: SRM : A Style-based Recalibration Module for Convolutional Neural NetworksPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
![]() |
Skip Connections | |
![]() |
Image Model Blocks |