Deep Recursive Embedding

Recursive representation learning for high-dimensional data embedding (IEEE TVCG 2022)

Deep Recursive Embedding (DRE) embeds high-dimensional data into low-dimensional space (typically 2D for visualization). IEEE TVCG 2022. [Paper] · [Code]

DRE leverages latent data representations for boosted embedding performance, maps out-of-sample data, and scales to extremely large datasets — improving both local and global structure preservation over the state of the art.

Deep Recursive Embedding architecture.
DRE optimization process embedding the MNIST dataset.
The DRE optimization process on the MNIST dataset.

References