Deep supervised models have an unprecedented capacity to absorb large
qu...
Training semantic segmentation models on multiple datasets has sparked a...
Anomaly detection can be conceived either through generative modelling o...
Standard machine learning is unable to accommodate inputs which do not b...
Deep supervised models have an unprecedented capacity to absorb large
qu...
Deep convolutional models often produce inadequate predictions for input...
Today's deep models are often unable to detect inputs which do not belon...
We present our submission to the semantic segmentation contest of the Ro...
Recent success on realistic road driving datasets has increased interest...
Recent success of semantic segmentation approaches on demanding road dri...
This paper considers dense detection of out-of-distribution pixels. As a...
We present semantic segmentation experiments with a model capable to per...