A token-discarding method for vision transformers measures whether predictions rely on features outside the object's bounding box, identifying spurious correlations and problematic ImageNet classes.
Emerging properties in self-supervised vision transform- ers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
A token-discarding method for vision transformers measures whether predictions rely on features outside the object's bounding box, identifying spurious correlations and problematic ImageNet classes.