Official implementation of the paper: "Boosting Active Prompt Learning via Discriminative Self-Training Dual-Curriculum Learning"
We recommend placing all datasets in the same directory (say $DATA) looks like
$DATA/
|–– dtd/
|–– oxford_pets/
|–– eurosat/
We consider 8 datasets for evaluation the effectiveness of the proposed method:
If you have any questions, feel free to create an issue in this repository.
We will release the code on GitHub upon acceptance of the paper.
Our gratitude goes to the authors of PCB and CoOp/CoCoOp for sharing their work through open-source implementation.