DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
It is okay to not be okay: Overcoming emotional bias in affective image cap- tioning by contrastive data collection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.