`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning

arXiv:2404.08761v1 Announce Type: cross
Abstract: Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image. This is an oversimplification of the process of novel category recognition, where different regions of the image may have properties from different seen classes and thus have different predominant attributes. With this in mind, we take a fundamentally different approach: a pre-trained Vision-Language detector (VINVL) sensitive to attribute information is …

abstract arxiv class cs.cv cs.lg current fox generalized image network novel part process recognition representation type vector zero-shot