Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental
requirement in high-stakes applications. Unfortunately, modern deep neural networks are …

Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-
of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural …

Deep neural networks are known to be overconfident for what they don't know in the wild
which is undesirable for decision-making in high-stakes applications. Despite quantities of …

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

In open-world recognition of safety-critical applications, providing reliable prediction for
deep neural networks has become a critical requirement. Many methods have been …

For a machine learning model deployed in real world scenarios, the ability of detecting out-
of-distribution (OOD) samples is indispensable and challenging. Most existing OOD …

Class-incremental learning (CIL) aims to recognize new classes incrementally while
maintaining the discriminability of old classes. Most existing CIL methods are exemplar …

Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories,
has gained prominence in practical scenarios. Recently, the advent of vision-language …

Reliable and robust evaluation methods are a necessary first step towards developing
machine learning models that are themselves robust and reliable. Unfortunately, current …

Abstract Out-of-distribution (OOD) detection is critical for ensuring AI quality and reliability,
particularly with the rise of large models characterized by immense parameters and complex …