{
  "id": 905,
  "url": "https://arxiv.org/abs/2606.17646v1",
  "title": "SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches",
  "summary": "Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap. We argue that AI explanations should be intuitive -- coherent to user knowledge, yet simple and selective to accelerate interpretation. Inspired by artistic drawings, we propose SketchXplain to generate sketch-based visual explanations for intuitive image-based explainable AI (XAI). Combining techniques in saliency maps,",
  "authors": "Wencan Zhang, Mario Michelessa, Xuejun Zhao, Brian Y. Lim",
  "category": "research",
  "topics": "safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-16T08:05:26.000Z",
  "fetched_at": "2026-07-14T14:14:54.531Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/905",
  "original_url": "https://arxiv.org/abs/2606.17646v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}