VoVNetV2
2000년 도입 · 논문 1편에서 사용
VoVNetV2 is a convolutional neural network that improves upon VoVNet with two effective strategies: (1) residual connection for alleviating the optimization problem of larger VoVNets and (2) effective Squeeze-Excitation (eSE) dealing with the channel information loss problem of the original squeeze-and-excitation module.
출처: CenterMask : Real-Time Anchor-Free Instance Segmentation
소개 논문: CenterMask : Real-Time Anchor-Free Instance Segmentation
Convolutional Neural Networks · Computer Vision