Zero-shot evaluation for downstream datasets?

[BIGBALLON]

Firstly, I would like to express my appreciation for the insightful research presented in the paper.

The paper shows the results:

• baseline: training the model without pretraining on MALS
• APTM: training the model with pretraining on MALS

I am interested in understanding the zero-shot performance, where no further training is performed after pretraining on MALS. Specifically, I would like to see evaluation results on the downstream datasets(CUHK-PEDES, ICFG-PEDES, and RST-PReid):

• zero-shot: no training, just the model pretraining on MALS, then test on downstream datasets

[Shuyu-XJTU]

During pre-training, we used the CUHK-PEDES test set for evaluation, which should provide the experimental results you need. You can try it out.