Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision

Documenti analoghi

• Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision
  di: Pan, Pengcheng, et al.
  Pubblicazione: (2025)
• EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification
  di: Pan, Pengcheng, et al.
  Pubblicazione: (2026)
• Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
  di: Ortega, Jorge Chang, et al.
  Pubblicazione: (2026)
• Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction
  di: Cartella, Giuseppe, et al.
  Pubblicazione: (2025)
• Fairness-aware Vision Transformer via Debiased Self-Attention
  di: Qiang, Yao, et al.
  Pubblicazione: (2023)