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 | 43 | 6.32% |
| Anomaly Detection | 35 | 5.15% |
| Denoising | 26 | 3.82% |
| Self-Supervised Learning | 24 | 3.53% |
| Image Generation | 21 | 3.09% |
| Semantic Segmentation | 18 | 2.65% |
| Dimensionality Reduction | 18 | 2.65% |
| Quantization | 14 | 2.06% |
| Clustering | 14 | 2.06% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
