Semantic segmentation of an image is
to partition the image into semantically meaningful parts, and to classify each part into one of the pre-determined classes. You can also achieve the same goal by classifying each pixel (rather than the entire image/segment).
Is anyone familiar with an image dataset that contains semantic segmentation of eyewear (glasses)? That is, dataset of semantic segmentation in which one of the classes is glasses? Could be sun-glasses or any other type of glasses.