.png){kind=icon}
.png){kind=icon}
Return
AugGen: a generative framework for continual generalized zero-shot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132187.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a generative framework for tackling continual generalized zero-shot learning. • DAE enhances unseen class features with large language models-generated attributes. • TFD preserves knowledge by aligning feature spaces across tasks. • Experiments validate the effectiveness of our method.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
View more organizations