Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances
hinders them from being deployed in safety-critical and complex applications, such as …

Anomaly segmentation is a critical task for driving applications, and it is approached
traditionally as a per-pixel classification problem. However, reasoning individually about …

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are
usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle …

Deep neural networks (DNNs) for the semantic segmentation of images are usually trained
to operate on a predefined closed set of object classes. This is in contrast to the"" open …

Deployment of modern data-driven machine learning methods, most often realized by deep
neural networks (DNNs), in safety-critical applications such as health care, industrial plant …

As deep learning continues to dominate all state-of-the-art computer vision tasks, it is
increasingly becoming an essential building block for robotic perception. This raises …

Most dense recognition approaches bring a separate decision in each particular pixel.
These approaches deliver competitive performance in usual closed-set setups. However …

In this work, we for the first time present a method for detecting labeling errors in image
datasets with semantic segmentation, ie, pixel-wise class labels. Annotation acquisition for …

While automated driving is often advertised with better-than-human driving performance, this
chapter reviews that it is nearly impossible to provide direct statistical evidence on the …