Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods

Buelent Uendes, Shujian Yu, M. Hoogendoorn
2/12/2026

No official code found. Best implementation: BuelentUendes/StartGrad (4 stars, MIT, last commit 2026-01-22).

Semantic Scholar

Code Implementations(1)

BuelentUendes/StartGradCommunity72%
MIT

Code repository of the paper: Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods. Published at ICLR, 2025.

40TeX, ShellFeb 27, 20259 months agoMIT
mask-based-explanationsxai

Similar Papers

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

100% match1 repo502026

Accelerating Neural ODEs: A Variational Formulation-based Approach

99% match1 repo82026

Hybrid Regularization Improves Diffusion-based Inverse Problem Solving

99% match1 repo22026

Instance Correlation Graph-based Naive Bayes

98% match2026

Inner Product-based Neural Network Similarity

98% match2026

Energy-based Backdoor Defense Against Federated Graph Learning

97% match1 repo192026

Cite this paper

@article{uendes2026start,
  title  = {Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods},
  author = {Buelent Uendes and Shujian Yu and M. Hoogendoorn},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:5bb40bfb4c35f8e7228394dda5186df42ca269fa},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/5bb40bfb4c35f8e7228394dda5186df42ca269fa.svg)](https://codeofpaper.com/paper/5bb40bfb4c35f8e7228394dda5186df42ca269fa)

Discussion