The annotation of large new datasets for machine learning is a very time-consuming and
expensive process. This is particularly true for pixel-accurate labelling of eg segmentation
masks. Prompt-based methods have been developed to accelerate this label generation
process by allowing the model to incorporate additional clues from other sources such as
humans. The recently published Segment Anything foundation model (SAM) extends this
approach by providing a flexible framework with a model that was trained on more than 1 …

… title = {SAM meets Gaze: Passive Eye Tracking for Prompt-based Instance Segmentation}, …