Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Abstract Explainable Artificial Intelligence (XAI) is an emerging research field bringing
transparency to highly complex and opaque machine learning (ML) models. Despite the …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

We introduce D omain-specific M asks for G eneralization, a model for improving both in-
domain and out-of-domain generalization performance. For domain generalization, the goal …

Recently, developing automated video surveillance systems (VSSs) has become crucial to
ensure the security and safety of the population, especially during events involving large …

The rise of deep neural networks has led to several breakthroughs for semantic
segmentation. In spite of this, a model trained on source domain often fails to work properly …

Existing bias mitigation methods for DNN models primarily work on learning debiased
encoders. This process not only requires a lot of instance-level annotations for sensitive …

Generalizing visual recognition models trained on a single distribution to unseen input
distributions (ie domains) requires making them robust to superfluous correlations in the …

Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable
classification by associating predictions with a set of training prototypes, which we refer to as …

Data-driven machine learning (ML) is promoted as one potential technology to be used in
next-generation wireless systems. This led to a large body of research work that applies ML …