Concept
Bootstrap aggregating
Publications associées (102)
Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange
Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Yi Wu
In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...
2024Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks
Romain Christophe Rémy Fleury, Janez Rus
The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...
2024Composite Relationship Fields with Transformers for Scene Graph Generation
Alexandre Massoud Alahi, David Mizrahi, George Adaimi
Scene graph generation (SGG) methods extract relationships between objects. While most methods focus on improving top-down approaches, which build a scene graph based on detected objects from an off-the-shelf object detector, there is a limited amount of w ...
2023Data-Driven Control and Optimization under Noisy and Uncertain Conditions
Control systems operating in real-world environments often face disturbances arising from measurement noise and model mismatch. These factors can significantly impact the perfor- mance and safety of the system. In this thesis, we aim to leverage data to de ...
EPFL2023Discriminating physiological from non‐physiological interfaces in structures of protein complexes: A community‐wide study
Bruno Emanuel Ferreira De Sousa Correia, Anthony Marchand, Emmanuel Doram Levy, Xiao Wang
Reliably scoring and ranking candidate models of protein complexes and assigning their oligomeric state from the structure of the crystal lattice represent outstanding challenges. A community-wide effort was launched to tackle these challenges. The latest ...
2023