Mask Interpreter models and example data

Deep learning models often operate as "black boxes," making it difficult to understand which input features drive their predictions. MaskInterpreter addresses this by learning a mask generator network that identifies important regions through a novel training objective: Preserve predictions: Important regions (high mask values) should be sufficient to maintain the model's original prediction Minimize mask size: The mask should be as minimal as possible, highlighting only truly essential regions Target correlation: Predictions on masked inputs should maintain a specified correlation with original predictions Key Features Self-supervised training - No ground truth explanations needed Model-agnostic - Works with any differentiable predictor (classifiers, regressors, image-to-image models) Quantifiable explanations - Mask efficacy measured via Pearson Correlation Coefficient (PCC) The Repo includes Trained models Example data Train and test lists of the full data