Papers › Maximizing Invariant Data Perturbation with Stochastic Optimization

Maximizing Invariant Data Perturbation with Stochastic Optimization

12 Jul 2018arXiv:1807.05077archive 2025-07-28

Kouichi Ikeno, Satoshi Hara

Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach for the perturbation-based feature attribution method. While the original optimization problem of the perturbation-based feature attribution is difficult to solve because of the complex constraints, we propose to reformulate the problem as the maximization of a differentiable function, which can be solved using gradient-based algorithms. In particular, stochastic optimization is well-suited for the proposed reformulation, and we can solve the problem using popular algorithms such as SGD, RMSProp, and Adam. The experiment on the image classification with VGG16 shows that the proposed method could identify relevant parts of the images effectively.

PaperPDFCode

Code

sato9hara/PertMap officialmentioned in papermentioned on GitHubtfMIT 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

General ClassificationImage ClassificationStochastic Optimizationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamRMSPropSGD

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