Object figure-ground segmentation using zero-shot learning

Shujon Naha, Yang Wang

Abstract: We consider the problem of object figure-ground segmentation when the object categories are not available during training (i.e. zero-shot). During training, we learn standard segmentation models for a handful of object categories (called “source objects”) using existing semantic segmentation datasets. During testing, we are given images of objects (called “target objects”) that are unseen during training. Our goal is to segment the target objects from the background. Our method learns to transfer the knowledge from the source objects to the target objects. Our experimental results demonstrate the effectiveness of our approach.