Large-scale vision-language models (VLMs) like CLIP successfully find correspondences
between images and text. Through the standard deterministic mapping process, an image or …

Failure to recognize samples from the classes unseen during training is a major limitation of
artificial intelligence in the real-world implementation for recognition and classification of …

Reliable confidence estimation is a challenging yet fundamental requirement in many risk-
sensitive applications. However, modern deep neural networks are often overconfident for …

Safety-critical 3D scene understanding tasks necessitate not only accurate but also
confident predictions from 3D perception models. This study introduces Calib3D, a …

Abstract Among Bayesian methods, Monte Carlo dropout provides principled tools for
evaluating the epistemic uncertainty of neural networks. Its popularity recently led to seminal …

In monocular depth estimation, uncertainty estimation approaches mainly target the data
uncertainty introduced by image noise. In contrast to prior work, we address the uncertainty …

Uncertainty quantification is critical for deploying deep neural networks (DNNs) in real-world
applications. An Auxiliary Uncertainty Estimator (AuxUE) is one of the most effective means …

Dense regression is a widely used approach in computer vision for tasks such as image
super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation …

The automated analysis of medical time series, such as the electrocardiogram (ECG),
electroencephalogram (EEG), pulse oximetry, etc, has the potential to serve as a valuable …

Recent advances in deep learning have shown that uncertainty estimation is becoming
increasingly important in applications such as medical imaging, natural language …