ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution
ConEx ties vision saliency maps to automatically discovered concepts using unsupervised concept activation vectors.
1 stories, newest first · one card per story
ConEx ties vision saliency maps to automatically discovered concepts using unsupervised concept activation vectors.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views