Gaze-Guided Class Activation Mapping: Leverage Human Visual Attention for Network Attention in Chest X-rays Classification
Hongzhi Zhu, Septimiu E. Salcudean, Robert Rohling
Abstract
The attention mechanism in artificial neural networks is conceptually interlinked with human visual attention, and studies have shown that either artificial or human attention can facilitate computer vision tasks. However, little research has investigated the visual interpretation of neural network’s attention with the help of human visual attention.
Topics & Concepts
Leverage (statistics)GazeComputer scienceVisual attentionArtificial intelligenceEye trackingComputer visionPsychologyNeuroscienceCognitionCOVID-19 diagnosis using AIArtificial Intelligence in Healthcare and EducationRadiology practices and education