Trung Dung Ngo

Trung Ngo, Najwa Laabid, Ville Hautamäki et al.

Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient for disentangling representation but ultimately generating blurry examples. Existing methods narrow the issues to the rate-distortion trade-off between compression and reconstruction. We argue that a good reconstruction model does learn high capacity latents that encode more details, however, its use is hindered by two major issues: the prior is random noise which is completely detached from the posterior and allow no controllability in the generation; mean-field variational inference doesn't enforce hierarchy structure which makes the task of recombining those units into plausible novel output infeasible. As a result, we develop a system that learns a hierarchy of disentangled representation together with a mechanism for recombining the learned representation for generalization. This is achieved by introducing a minimal amount of inductive bias to learn controllable prior for the VAE. The idea is supported by here developed transitive information theory, that is, the mutual information between two target variables could alternately be maximized through the mutual information to the third variable, thus bypassing the rate-distortion bottleneck in VAE design. In particular, we show that our model, named SemafoVAE (inspired by the similar concept in computer science), could generate high-quality examples in a controllable manner, perform smooth traversals of the disentangled factors and intervention at a different level of representation hierarchy.

Ashutosh Singandhupe, Hung La, Trung Dung Ngo et al.

This work focuses on Registration or Alignment of 3D point sets. Although the Registration problem is a well established problem and it's solved using multiple variants of Iterative Closest Point (ICP) Algorithm, most of the approaches in the current state of the art still suffers from misalignment when the \textit{Source} and the \textit{Target} point sets are separated by large rotations and translation. In this work, we propose a variant of the Standard ICP algorithm, where we introduce a Correntropy Relationship Matrix in the computation of rotation and translation component which attempts to solve the large rotation and translation problem between \textit{Source} and \textit{Target} point sets. This matrix is created through correntropy criterion which is updated in every iteration. The correntropy criterion defined in this approach maintains the relationship between the points in the \textit{Source} dataset and the \textit{Target} dataset. Through our experiments and validation we verify that our approach has performed well under various rotation and translation in comparison to the other well-known state of the art methods available in the Point Cloud Library (PCL) as well as other methods available as open source. We have uploaded our code in the github repository for the readers to validate and verify our approach https://github.com/aralab-unr/CoSM-ICP.