SpatialDropout

2000년 도입 · 논문 28편에서 사용

SpatialDropout is a type of dropout for convolutional networks. For a given convolution feature tensor of size $n\_{\text{feats}}$×height×width, we perform only $n\_{\text{feats}}$ dropout trials and extend the dropout value across the entire feature map. Therefore, adjacent pixels in the dropped-out feature map are either all 0 (dropped-out) or all active as illustrated in the figure to the right.

출처: Efficient Object Localization Using Convolutional Networks

소개 논문: Efficient Object Localization Using Convolutional Networks