Out-of-distribution (OOD) detection has received much attention lately due to its importance
in the safe deployment of neural networks. One of the key challenges is that models lack …

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

Nowadays, there are outstanding strides towards a future with autonomous vehicles on our
roads. While the perception of autonomous vehicles performs well under closed-set …

Detecting out-of-distribution examples is important for safety-critical machine learning
applications such as detecting novel biological phenomena and self-driving cars. However …

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

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 …

Test-time adaptation (TTA) methods, which generally rely on the model's predictions (eg,
entropy minimization) to adapt the source pretrained model to the unlabeled target domain …

Abstract State-of-the-art (SOTA) anomaly segmentation approaches on complex urban
driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or …

Standard semantic segmentation models owe their success to curated datasets with a fixed
set of semantic categories, without contemplating the possibility of identifying unknown …

Detecting out-of-distribution (OOD) samples are crucial for machine learning models
deployed in open-world environments. Classifier-based scores are a standard approach for …