Abstract: As a commonly used model for anomaly detection, the autoencoder model for anomaly detection does not train the objective for extracted features, which is a downside of autoencoder model. In ...

Abstract: A stacked autoencoder (SAE) is a widely used deep network. However, existing deep SAEs focus on original samples without considering the hierarchical structural information between samples.

SVG Autoencoder - Uses a frozen representation encoder with a residual branch to compensate the information loss and a learned convolutional decoder to transfer the SVG latent space to pixel space.

What’s the Latent Space ? An Autoencoder is made of two components: an Encoder & a Decoder. The Encoder brings the input data from a high dimensional representation to a bottleneck layer, where the ...