SPADE

2000년 도입 · 논문 38편에서 사용

SPADE, or Spatially-Adaptive Normalization is a conditional normalization method for semantic image synthesis. Similar to Batch Normalization, the activation is normalized in the channel-wise manner and then modulated with learned scale and bias. In the SPADE, the mask is first projected onto an embedding space and then convolved to produce the modulation parameters $\gamma$ and $\beta .$ Unlike prior conditional normalization methods, $\gamma$ and $\mathbf{\beta}$ are not vectors, but tensors with spatial dimensions. The produced $\gamma$ and $\mathbf{\beta}$ are multiplied and added to the normalized activation element-wise.

출처: Semantic Image Synthesis with Spatially-Adaptive Normalization

소개 논문: Semantic Image Synthesis with Spatially-Adaptive Normalization