Deep Learning for Autonomous Systems and Smart Cities
MARVEL will participate in the Deep Learning for Autonomous Systems and Smart Cities summer school organized by AU from 23 to 26 May 2023.
Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?
Detailed info Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection? AuthorsAndrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Elisa RicciTitleAre We Missing Confidence in Pseudo-LiDAR…
Within-layer Diversity Reduces Generalization Gap
Detailed info Within-layer Diversity Reduces Generalization Gap AuthorsFiras Laakom, Jenni Raitoharju, Alexandros Iosifidis and Moncef GabboujTitleWithin-layer Diversity Reduces Generalization GapAbstractNeural networks are composed of multiple layers arranged in a hierarchical…
MARVEL at the Orbit Lad webinar: Live from Behind the Walls
The Machine Learning and Computational Intelligence group at Aarhus University organized a webinar presenting the current research efforts of the group.
Multi-Exit Vision Transformer for Dynamic Inference
Underspecification and fairness in machine learning (ML) applications have recently become two prominent issues in the ML community. Acoustic scene classification (ASC) applications have so far remained unaffected by this discussion, but are now becoming increasingly used in real-world systems where fairness and reliability are critical aspects.
Automated social distance estimation in smart cities using deep learning
It is without a doubt that current technologies can greatly aid the process of monitoring and ensuring the health and safety of citizens, especially when seamlessly integrated within the context of smart cities.
