The tree-based ensembles are known for their outstanding performance for classification and regression problems characterized by feature vectors represented by mixed-type variables from various ranges and domains.
By using rehearsal and reconstruction as regularization methods of the learning process, our approach achieves a significant decrease of catastrophic forgetting compared to the existing solutions on several most popular point cloud datasets considering two continual learning settings: when a task is known beforehand, and in the challenging scenario of when task information is unknown to the model.
Few-shot models aim at making predictions using a minimal number of labeled examples from a given task.
This makes the GP posterior locally non-Gaussian, therefore we name our method Non-Gaussian Gaussian Processes (NGGPs).
Generative models have gained many researchers' attention in the last years resulting in models such as StyleGAN for human face generation or PointFlow for the 3D point cloud generation.
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling.
This way, we can sample a mesh quad on that sphere and project it back onto the object's manifold.
Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans.
To exploit similarities between same-class objects and to improve model performance, we turn to weight sharing: networks that model densities of points belonging to objects in the same family share all parameters with the exception of a small, object-specific embedding vector.
To that end, we devise a generative model that uses a hypernetwork to return the weights of a Continuous Normalizing Flows (CNF) target network.
The main idea of our HyperCloud method is to build a hyper network that returns weights of a particular neural network (target network) trained to map points from a uniform unit ball distribution into a 3D shape.
This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models.
In traditional generative modeling, good data representation is very often a base for a good machine learning model.
In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner.
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds.