A modified gradient-attribution method on frozen CLIP, using negative attributions, localizes misaligned words in image-text pairs and yields a fine-grained alignment score.
R.; Angeli, G.; Potts, C.; and Manning, C
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Extract Free Dense Misalignment from CLIP
A modified gradient-attribution method on frozen CLIP, using negative attributions, localizes misaligned words in image-text pairs and yields a fine-grained alignment score.