Learning Instance Segmentation by Interaction

Abstract

Objects are a fundamental component of visual perception. How are humans able to effortlessly reorganize their visual observations into a discrete set of objects is a question that has puzzled researchers for centuries. The Gestalt school of thought put forth the proposition that humans use similarity in color, texture and motion to group pixels into individual objects [21]. Various methods for object segmentation based on color and texture cues have been proposed [3, 6, 7, 14, 16]. These approaches are, however, known to over-segment multi-colored and textured objects.