Embedding-space perturbation sensitivity, combined with diversity and leave-one-out fairness scores, can flag and localize intentionally biased text-to-image models.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp
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
-
On the Fairness, Diversity and Reliability of Text-to-Image Generative Models
Embedding-space perturbation sensitivity, combined with diversity and leave-one-out fairness scores, can flag and localize intentionally biased text-to-image models.