Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification
Pengcheng Pan, Yonekura Shogo, Kuniyoshi Yasuo
Optimizing vision models purely for classification accuracy can impose an alignment tax, degrading human-like scanpaths and limiting interpretability. We introduce EVA, a neuroscie…
cs.CV2026
Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision
Pengcheng Pan, Yonekura Shogo, Yasuo Kuniyosh
Human eye movements in visual recognition reflect a balance between foveal sampling and peripheral context. Task-driven hard-attention models for vision are often evaluated by how…
cs.CV2025
Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision
Pengcheng Pan, Yonekura Shogo, Yasuo Kuniyoshi
Inspired by foveal vision, hard attention models promise interpretability and parameter economy. However, existing models like the Recurrent Model of Visual Attention (RAM) and Dee…