Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Published in Advances in Neural Information Processing Systems, 2022
This project aims to minimize the manual labeling expenses associated with Zero-Shot Learning (ZSL) classification tasks. To achieve this, we have proposed a novel decompose-and-reassemble approach. I am delighted to share that our work has been accepted at NeurIPS 2022, a prestigious conference in the field. This accomplishment highlights our contribution to advancing research in ZSL and underscores our commitment to finding innovative solutions for reducing labeling costs.
Recommended citation: @inproceedings{li2022make, title={Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis}, author={Li, Yu Hsuan and Chao, Tzu-Yin and Huang, Ching-Chun and Chen, Pin-Yu and Chiu, Wei-Chen}, booktitle={Advances in Neural Information Processing Systems}, year={2022} }
Paper Link | Slides Link | Project Page | Code