A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps
This work addresses the need for more efficient and biologically inspired visual processing in AI, though it is incremental as it builds on existing Vision Transformer and saliency methods.
The paper tackled the problem of inefficient image processing in AI by drawing inspiration from human saccadic eye movements, using DINO Vision Transformer attention maps to selectively focus on key regions, which preserved most of ImageNet classification performance and sometimes outperformed full-image processing.
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, more efficient image processing models. Using DINO, a self-supervised Vision Transformer that produces attention maps strikingly similar to human gaze patterns, we explore a saccade inspired method to focus the processing of information on key regions in visual space. To do so, we use the ImageNet dataset in a standard classification task and measure how each successive saccade affects the model's class scores. This selective-processing strategy preserves most of the full-image classification performance and can even outperform it in certain cases. By benchmarking against established saliency models built for human gaze prediction, we demonstrate that DINO provides superior fixation guidance for selecting informative regions. These findings highlight Vision Transformer attention as a promising basis for biologically inspired active vision and open new directions for efficient, neuromorphic visual processing.