Fixed-noise refinement with one-step Pixel Mean Flow prediction produces visual counterfactuals about 3x faster than the strongest diffusion baseline while keeping image quality and localization competitive or better.
Exploring simple Siamese representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
FiRe: Fixed-Noise Refinement for Visual Counterfactual Explanations
Fixed-noise refinement with one-step Pixel Mean Flow prediction produces visual counterfactuals about 3x faster than the strongest diffusion baseline while keeping image quality and localization competitive or better.