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 | 48 | 7.11% |
Anomaly Detection | 40 | 5.93% |
Self-Supervised Learning | 25 | 3.70% |
Denoising | 24 | 3.56% |
Image Generation | 22 | 3.26% |
Dimensionality Reduction | 18 | 2.67% |
Semantic Segmentation | 17 | 2.52% |
Clustering | 14 | 2.07% |
Quantization | 13 | 1.93% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |