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

Environmental changes can profoundly impact the performance of artificial intelligence
systems operating in the real world, with effects ranging from overt catastrophic failures to …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Recent self-supervised methods for image representation learning are based on maximizing
the agreement between embedding vectors from different views of the same image. A trivial …

Current deep learning methods are regarded as favorable if they empirically perform well on
dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual …

Anomaly detection can be conceived either through generative modelling of regular training
data or by discriminating with respect to negative training data. These two approaches …

Deep learning is pushing the state-of-the-art in many computer vision applications.
However, it relies on large annotated data repositories, and capturing the unconstrained …

Traditional supervised learning aims to train a classifier in the closed-set world, where
training and test samples share the same label space. In this paper, we target a more …

In open set recognition, deep neural networks encounter object classes that were unknown
during training. Existing open set classifiers distinguish between known and unknown …

We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a
challenging category-incremental learning setting where the goal is to develop models that …