Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Interpretable Diffusion via Information Decomposition
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1069
Stable Diffusion v2.1's compositional understanding on the ARO benchmark is significantly higher than previously reported by MMSE-based scoring
IC-1070
In Stable Diffusion v2.1, attention maps do not reliably predict the effect of prompt interventions on generated images, while conditional mutual information does
IC-1071
Stable Diffusion v2.1's pixel-wise conditional mutual information localizes abstract words (adjectives, adverbs, verbs) more effectively than attention, but is less effective than attention for object segmentation