Vision-CAIR/GRaWD

Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation. CVPR 2022 Workshop, ICCC 2022.

Imaginative Walk (GRaWD)

This repo contains the code for Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation:

• the code to reproduce GZSL results on text-based datasets
• the code to reproduce key results of art generations

[Project Page] [arXiv Paper]