When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models

Documenti analoghi

• Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
  di: Zhang, Naifu, et al.
  Pubblicazione: (2025)
• Multi-task convolutional neural network for image aesthetic assessment
  di: Soydaner, Derya, et al.
  Pubblicazione: (2023)
• When Visuals Aren't the Problem: Evaluating Vision-Language Models on Misleading Data Visualizations
  di: Lalai, Harsh Nishant, et al.
  Pubblicazione: (2026)
• Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving
  di: Theodoridis, Nikos, et al.
  Pubblicazione: (2026)
• Seeing Faces in Things: A Model and Dataset for Pareidolia
  di: Hamilton, Mark, et al.
  Pubblicazione: (2024)