Papers › Using Stratified Sampling to Improve LIME Image Explanations

Using Stratified Sampling to Improve LIME Image Explanations

26 Mar 2024arXiv:2403.17742archive 2025-07-28

Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda

We investigate the use of a stratified sampling approach for LIME Image, a popular model-agnostic explainable AI method for computer vision tasks, in order to reduce the artifacts generated by typical Monte Carlo sampling. Such artifacts are due to the undersampling of the dependent variable in the synthetic neighborhood around the image being explained, which may result in inadequate explanations due to the impossibility of fitting a linear regressor on the sampled data. We then highlight a connection with the Shapley theory, where similar arguments about undersampling and sample relevance were suggested in the past. We derive all the formulas and adjustment factors required for an unbiased stratified sampling estimator. Experiments show the efficacy of the proposed approach.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

rashidrao-pk/lime-stratified-examples officialmentioned in papermentioned on GitHubtf report
rashidrao-pk/lime_stratified officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Explanation Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LIME

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections