Invertible 1x1 Convolution

2000년 도입 · 논문 79편에서 사용

The Invertible 1x1 Convolution is a type of convolution used in flow-based generative models that reverses the ordering of channels. The weight matrix is initialized as a random rotation matrix. The log-determinant of an invertible 1 × 1 convolution of a $h \times w \times c$ tensor $h$ with $c \times c$ weight matrix $\mathbf{W}$ is straightforward to compute: $$ \log | \text{det}\left(\frac{d\text{conv2D}\left(\mathbf{h};\mathbf{W}\right)}{d\mathbf{h}}\right) | = h \cdot w \cdot \log | \text{det}\left(\mathbf{W}\right) | $$

출처: Glow: Generative Flow with Invertible 1x1 Convolutions

소개 논문: Glow: Generative Flow with Invertible 1x1 Convolutions