A saccade-inspired approach to image classification using visiontransformer attention maps

ArXi:2603.09613v1 Announce Type: new Human vision achieves remarkable perceptual performance while operating under strict metabolic constraints. A key ingredient is the selective attention mechanism, driven by rapid saccadic eye movements that constantly reposition the high-resolution fovea onto task-relevant locations, unlike conventional AI systems that process entire images with equal emphasis. Our work aims to draw inspiration from the human visual system to create smarter, efficient image processing models.