Open access
Aug 2026
SLEA: a stochastic saccadic lightweight efficient attention framework with MobileNetV2 for robust and explainable 2D medical image classification
This work introduces saccadic lightweight efficient attention (SLEA), a framework purpose-built for 2D medical image classification and inspired by selective visual processing in the human visual system, intended to reduce dependence on fixed image locations and recurring spatial artefacts.
Williams Ayivi, Xiao-Ling Zhang, A. Aligayev
· Physica Scripta · 0 citations