Likelihood-Based Generative Models
GLOW
Introduced by Kingma et al. in Glow: Generative Flow with Invertible 1x1 ConvolutionsGLOW is a type of flow-based generative model that is based on an invertible $1 \times 1$ convolution. This builds on the flows introduced by NICE and RealNVP. It consists of a series of steps of flow, combined in a multi-scale architecture; see the Figure to the right. Each step of flow consists of Act Normalization followed by an invertible $1 \times 1$ convolution followed by an affine coupling layer.
Source: Glow: Generative Flow with Invertible 1x1 Convolutions
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Flare Removal | 3 | 7.32% |
| Image Enhancement | 3 | 7.32% |
| Image Dehazing | 3 | 7.32% |
| Federated Learning | 2 | 4.88% |
| Denoising | 2 | 4.88% |
| Low-Light Image Enhancement | 2 | 4.88% |
| Zero-Shot Learning | 2 | 4.88% |
| Text to Speech | 2 | 4.88% |
| Intrusion Detection | 1 | 2.44% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Activation Normalization
|
Normalization | |
Affine Coupling
|
Bijective Transformation | |
Invertible 1x1 Convolution
|
Convolutions | |
Normalizing Flows
|
Distribution Approximation |
