A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps

TL;DR

This paper introduces a biologically inspired saccade-like method for image classification using Vision Transformer attention maps, improving efficiency and performance by focusing on key image regions.

Contribution

The work leverages DINO's attention maps to guide selective image processing, demonstrating a novel saccade-inspired approach that enhances classification efficiency and outperforms some existing methods.

Findings

Selective processing preserves most classification accuracy.

DINO's attention maps outperform traditional saliency models.

The approach suggests a new direction for neuromorphic visual systems.

Abstract

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.