Residual SRM

2000년 도입 · 논문 1편에서 사용

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.

출처: SRM : A Style-based Recalibration Module for Convolutional Neural Networks

소개 논문: SRM : A Style-based Recalibration Module for Convolutional Neural Networks