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 | 34 | 5.14% |
Self-Supervised Learning | 28 | 4.24% |
Denoising | 25 | 3.78% |
Image Generation | 19 | 2.87% |
Dimensionality Reduction | 17 | 2.57% |
Semantic Segmentation | 17 | 2.57% |
Disentanglement | 14 | 2.12% |
Clustering | 13 | 1.97% |
Quantization | 13 | 1.97% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |