Generative Models
ControlVAE
Introduced by Shao et al. in ControlVAE: Tuning, Analytical Properties, and Performance AnalysisControlVAE is a variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value. It leverages a non-linear PI controller, a variant of the proportional-integral-derivative (PID) control, to dynamically tune the weight of the KL-divergence term in the evidence lower bound (ELBO) using the output KL-divergence as feedback. This allows for control of the KL-divergence to a desired value (set point), which is effective in avoiding posterior collapse and learning disentangled representations.
Source: ControlVAE: Tuning, Analytical Properties, and Performance Analysis
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Disentanglement | 2 | 33.33% |
| Image Generation | 2 | 33.33% |
| Language Modelling | 2 | 33.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
