Generative models synthesize unseen visual features and convert ZSL into a classical supervised learning problem . LsrGAN is a generative model that leverages Semantic Relationship between seen and unseen categories and explicitly performs knowledge transfer by incorporating a novel Semantic Regularized Loss (SR-Loss) The SR-loss guides the LSRGAN to generate visual features that mirror the semantic relationships between seen classes and unseen classes . Experiments on seven benchmark datasets, including the challenging Wikipedia text-based CUB and NABirds splits, and Attribute-based AWA, CUB, and SUN, demonstrates the superiority of the LrsGAN compared to previous state-of-the-art approaches under both ZSL and GZSL . Code is available at https://://://github.com/ Maunil/ LrGAN Lrgan and http://

Links: PDF - Abstract

Code :

None

Keywords : unseen - semantic - generative - loss - learning -

Leave a Reply

Your email address will not be published. Required fields are marked *

error

Enjoy this blog? Please spread the word :)