An Explicit Local and Global Representation Disentanglement Framework with Applications in Deep Clustering and Unsupervised Object Detection

1 code implementation • 24 Jan 2020 • Rujikorn Charakorn, Yuttapong Thawornwattana, Sirawaj Itthipuripat, Nick Pawlowski, Poramate Manoonpong, Nat Dilokthanakul

In this work, we propose a framework, called SPLIT, which allows us to disentangle local and global information into two separate sets of latent variables within the variational autoencoder (VAE) framework.

Clustering Deep Clustering +5