paper-with-me

SENet

2000년 도입 · 논문 47편에서 사용

A SENet is a convolutional neural network architecture that employs squeeze-and-excitation blocks to enable the network to perform dynamic channel-wise feature recalibration.

출처: Squeeze-and-Excitation Networks

소개 논문: Squeeze-and-Excitation Networks

Convolutional Neural Networks · Computer Vision