leakaudit
From MaRDI portal
Leakaudit
Description
Detects near-duplicate images across dataset splits using perceptual hashing, reports the resulting train/validation/test contamination, and produces a corrected, leak-free split assignment. Intended for machine learning researchers who need to verify that image classification splits do not share near-duplicate samples across partitions before reporting model metrics.
This page was built for software: leakaudit
