An 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 NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Anomaly Detection | 32 | 4.88% |
Self-Supervised Learning | 27 | 4.12% |
Denoising | 25 | 3.81% |
Image Generation | 19 | 2.90% |
Dimensionality Reduction | 17 | 2.59% |
Semantic Segmentation | 17 | 2.59% |
Disentanglement | 14 | 2.13% |
Clustering | 13 | 1.98% |
Quantization | 13 | 1.98% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |