Home /
Research
Showing 739 - 744 / 904
Modular Primitives for High-Performance Differentiable Rendering
SamuliLaine, JanneHellsten, TeroKarras....
Published date-11/06/2020
We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines. Our design supports all crucial operations in a …
Feature Removal Is a Unifying Principle for Model Explanation Methods
IanCovert, ScottLundberg, Su-InLee....
Published date-11/06/2020
Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We examine the …
Learning to Orient Surfaces by Self-supervised Spherical CNNs
RiccardoSpezialetti, FedericoStella, MarlonMarcon....
Published date-11/06/2020
Defining and reliably finding a canonical orientation for 3D surfaces is key to many Computer Vision and Robotics applications. This task is commonly addressed by handcrafted algorithms exploiting geometric cues …
Learning with Molecules beyond Graph Neural Networks
GustavSourek, FilipZelezny, OndrejKuzelka....
Published date-11/06/2020
We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show …
Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?
ChaoqiWang, ShengyangSun, RogerGrosse....
Published date-11/06/2020
ActiveLearning
While uncertainty estimation is a well-studied topic in deep learning, most such work focuses on marginal uncertainty estimates, i.e. the predictive mean and variance at individual input locations. But it …
Massively Parallel Graph Drawing and Representation Learning
ChristianBöhm, ClaudiaPlant....
Published date-11/06/2020
GraphEmbedding, GraphRepresentationLearning, RepresentationLearning
To fully exploit the performance potential of modern multi-core processors, machine learning and data mining algorithms for big data must be parallelized in multiple ways. Today's CPUs consist of multiple …