Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

The crux of semi-supervised semantic segmentation is to assign pseudo-labels to the pixels
of unlabeled images. A common practice is to select the highly confident predictions as the …

For any video codecs, the coding efficiency highly relies on whether the current signal to be
encoded can find the relevant contexts from the previous reconstructed signals. Traditional …

Deep Learning (DL), a groundbreaking branch of Machine Learning (ML), has emerged as a
driving force in both theoretical and applied Artificial Intelligence (AI). DL algorithms, rooted …

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Reliable uncertainty from deterministic single-forward pass models is sought after because
conventional methods of uncertainty quantification are computationally expensive. We take …

Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of
challenging problems. However, since deep learning methods operate as black boxes, the …

Uncertainty estimation in healthcare involves quantifying and understanding the inherent
uncertainty or variability associated with medical predictions, diagnoses, and treatment …

Outstanding steps towards intelligent transportation systems with autonomous vehicles have
been taken in the past few years. Nevertheless, the safety issue in autonomous vehicles is …