We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...
A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs), providing high-fidel ...
IEEE Institute of Electrical and Electronics Engineers2021
We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular approach consists of using a Conditional Variational Autoencoder (CVAE). How ...
Human detection and pose estimation are essential components for any artificial system responsive to the presence of humans and that react according to human-centered tasks. Robotic systems are typical examples, for which the body pose represents fine grai ...
Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes. We thus present a novel objective function to evaluate the locality of an image edit. By introducing the supervision from a pre-traine ...
Throughout this thesis, we are interested in modeling music composition. To do so, we study the association of music theory concepts with the learning capabilities of recurrent neural networks. Especially, we explore numerical formalizations of music so th ...
Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables us to learn and discover latent relationships between interesting lyrics and accompanying melodies. Unfortunately, the limi ...
While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edit ...
