Papers › Mapping the Mind of an Instruction-based Image Editing using SMILE

Mapping the Mind of an Instruction-based Image Editing using SMILE

20 Dec 2024arXiv:2412.16277archive 2025-07-28

Zeinab Dehghani, Koorosh Aslansefat, Adil Khan, Adín Ramírez Rivera, Franky George, Muhammad Khalid

Despite recent advancements in Instruct-based Image Editing models for generating high-quality images, they are known as black boxes and a significant barrier to transparency and user trust. To solve this issue, we introduce SMILE (Statistical Model-agnostic Interpretability with Local Explanations), a novel model-agnostic for localized interpretability that provides a visual heatmap to clarify the textual elements' influence on image-generating models. We applied our method to various Instruction-based Image Editing models like Pix2Pix, Image2Image-turbo and Diffusers-Inpaint and showed how our model can improve interpretability and reliability. Also, we use stability, accuracy, fidelity, and consistency metrics to evaluate our method. These findings indicate the exciting potential of model-agnostic interpretability for reliability and trustworthiness in critical applications such as healthcare and autonomous driving while encouraging additional investigation into the significance of interpretability in enhancing dependable image editing models.

PaperPDFCode

Code

dependable-intelligent-systems-lab/xwhy officialmentioned in papermentioned on GitHub report
rishidarkdevil/daam-i2i officialmentioned in paperpytorchMIT 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

Autonomous Driving

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationConcatenated Skip ConnectionConvolutionDropoutHeatmapPatchGANPix2PixReLUSigmoid Activation

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