Counterfactual stress testing with causal generative models offers a more accurate proxy than simple perturbations for predicting medical image model performance under distribution shifts.
PLOS Digital Health1(3), e0000022 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Counterfactual Stress Testing for Image Classification Models
Counterfactual stress testing with causal generative models offers a more accurate proxy than simple perturbations for predicting medical image model performance under distribution shifts.