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 …
Y Himeur, S Al-Maadeed, H Kheddar… - … Applications of Artificial …, 2023 - Elsevier
Recently, developing automated video surveillance systems (VSSs) has become crucial to ensure the security and safety of the population, especially during events involving large …
J Kim, J Lee, J Park, D Min… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …
I Cugu, M Mancini, Y Chen… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …