Convolutions
Invertible 1x1 Convolution
Introduced by Kingma et al. in Glow: Generative Flow with Invertible 1x1 ConvolutionsThe 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:
$$ \log | \text{det}\left(\frac{d\text{conv2D}\left(\mathbf{h};\mathbf{W}\right)}{d\mathbf{h}}\right) | = h \cdot w \cdot \log | \text{det}\left(\mathbf{W}\right) | $$
Source: Glow: Generative Flow with Invertible 1x1 Convolutions
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Text to Speech | 5 | 9.80% |
| Flare Removal | 3 | 5.88% |
| Image Enhancement | 3 | 5.88% |
| Speech Synthesis | 3 | 5.88% |
| Federated Learning | 2 | 3.92% |
| Denoising | 2 | 3.92% |
| Low-Light Image Enhancement | 2 | 3.92% |
| Zero-Shot Learning | 2 | 3.92% |
| Image Dehazing | 2 | 3.92% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
