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 |
---|---|---|
Decoder | 49 | 7.06% |
Anomaly Detection | 39 | 5.62% |
Self-Supervised Learning | 27 | 3.89% |
Denoising | 24 | 3.46% |
Image Generation | 19 | 2.74% |
Dimensionality Reduction | 18 | 2.59% |
Semantic Segmentation | 18 | 2.59% |
Clustering | 14 | 2.02% |
Quantization | 13 | 1.87% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |