A vision classifier is interpreted by masking image patches, computing gradient updates that would improve its prediction, and visualizing the filled-in patches as class prototypes.
Rethinking interpretability Let us focus on the task of image classification, and re-visit how a human recalls from memory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Fill in the blanks: Rethinking Interpretability in vision
A vision classifier is interpreted by masking image patches, computing gradient updates that would improve its prediction, and visualizing the filled-in patches as class prototypes.