MinENet: A Dilated CNN for Semantic Segmentation of Eye Features

Abstract

Fast and accurate eye tracking is a critical task for a range of research in virtual and augmented reality, attention tracking, mobile applications, and medical analysis. While deep neural network models excel at image analysis tasks, existing approaches to segmentation often consider only one class, emphasize classification over segmentation, or come with prohibitively high resource costs. In this work, we propose MinENet, a minimized efficient neural network architecture designed for fast multi-class semantic segmentation. We demonstrate performance of MinENet on the OpenEDS Semantic Segmentation Challenge dataset, against a baseline model as well as standard state-of-the-art neural network architectures - a convolutional neural network (CNN) and a dilated CNN. Our encoder-decoder architecture improves accuracy of multi-class segmentation of eye features in this large-scale high-resolution dataset, while also providing a design that is demonstrably lightweight and efficient.