Heatmap-based Out-of-Distribution Detection. (arXiv:2211.08115v1 [cs.CV])

Our work investigates out-of-distribution (OOD) detection as a neural network
output explanation problem. We learn a heatmap representation for detecting OOD
images while visualizing in- and out-of-distribution image regions at the same
time. Given a trained and fixed classifier, we train a decoder neural network
to produce heatmaps with zero response for in-distribution samples and high
response heatmaps for OOD samples, based on the classifier features and the
class prediction. Our main innovation lies in the heatmap definition for an …

arxiv detection distribution heatmap