The high capacity of neural networks allows fitting models to data with high precision, but
makes generalization to unseen data a challenge. If a domain shift exists, ie differences in …

We present a novel approach to the detection of unknown objects in the context of
autonomous driving. The problem is formulated as anomaly detection, since we assume that …

We propose a transfer learning-based solution for the problem of multiple class novelty
detection. In particular, we propose an end-to-end deep-learning based approach in which …

As science attempts to close the gap between man and machine by building systems
capable of learning, we must embrace the importance of the unknown. The ability to …

When neural networks process images which do not resemble the distribution seen during
training, so called out-of-distribution images, they often make wrong predictions, and do so …

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned
by the models during training. In this paper, we provide a survey of existing works about …

Domain shift is a significant problem in histopathology. There can be large differences in
data characteristics of whole-slide images between medical centers and scanners, making …

Neural-network classifiers achieve high accuracy when predicting the class of an input that
they were trained to identify. Maintaining this accuracy in dynamic environments, where …

Neural-network classifiers achieve high accuracy when predicting the class of an input that
they were trained to identify. Maintaining this accuracy in dynamic environments, where …

Many companies, such as credit granting companies, have to decide on granting or denying
customer or invoice loans on a daily basis. Increasingly, machine learning is used to learn …