CVPR 2022

VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

VGSE discovers semantic embeddings with discriminative visual properties without any human annotation, by clustering local image regions from seen classes and relating those clusters to unseen classes.

Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, Zeynep Akata