DECAT classifies multimodal representations into four diagnostic scenarios using null-referenced metrics and a rule-based procedure to detect shared biology versus confounders without knowing the confounder identity.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
ReshapeOT improves optimal transport reliability for distribution shifts by replacing the Euclidean ground metric with a Mahalanobis distance derived from observed displacement second moments.
CFKD generates counterfactuals for human-guided correction of Clever Hans predictors in image classifiers, removing the need for confounder labels while scaling to multiple spurious correlations.
citing papers explorer
-
When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework
DECAT classifies multimodal representations into four diagnostic scenarios using null-referenced metrics and a rule-based procedure to detect shared biology versus confounders without knowing the confounder identity.
-
Reliable Modeling of Distribution Shifts via Displacement-Reshaped Optimal Transport
ReshapeOT improves optimal transport reliability for distribution shifts by replacing the Euclidean ground metric with a Mahalanobis distance derived from observed displacement second moments.
-
Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
CFKD generates counterfactuals for human-guided correction of Clever Hans predictors in image classifiers, removing the need for confounder labels while scaling to multiple spurious correlations.