Can I read Invertible DenseNets on EtoBox?

Invertible DenseNets by Perugachi-Diaz, Yura; Tomczak, Jakub M.; Bhulai, Sandjai is a scholarly article available to read on EtoBox.

What is Invertible DenseNets about?

We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient alternative to Residual Flows. The method relies on an analysis of the Lipschitz continuity of the concatenation in DenseNets, where we enforce the invertibility of the network by satisfying the Lipschitz constraint. Additionally, we extend this method by proposing a learnable concatenation, which not only improves the model performance but also indicates the importance of the concatenated representation. We demonstrate the performance of i-DenseNets and Residual Flows on toy, MNIST, and CIFAR10 data. Both i-DenseNets outperform Residual Flows evaluated in negative log-likelihood, on all considered datasets under an equal parameter budget.

Author

Perugachi-Diaz, Yura; Tomczak, Jakub M.; Bhulai, Sandjai

Published

2020

Language

EN