Generative Models
AutoEncoder
Introduced by Hinton et al. in Reducing the Dimensionality of Data with Neural NetworksAn Autoencoder is a bottleneck architecture that turns a high-dimensional input into a latent low-dimensional code (encoder), and then performs a reconstruction of the input with this latent code (the decoder).
Image: Michael Massi
Source: Reducing the Dimensionality of Data with Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Decoder | 49 | 7.14% |
| Anomaly Detection | 38 | 5.54% |
| Self-Supervised Learning | 27 | 3.94% |
| Denoising | 24 | 3.50% |
| Image Generation | 19 | 2.77% |
| Semantic Segmentation | 17 | 2.48% |
| Dimensionality Reduction | 17 | 2.48% |
| Clustering | 14 | 2.04% |
| Disentanglement | 13 | 1.90% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
