Xinhao Li

icon indicating a website link https://leexinhao.github.io/

icon location Nanjing icon location I am a MS student at Nanjing University. My research interests mainly lie in efficient video/image understanding and generation methods.

Results 4 issues of Xinhao Li

The parameters of BIKE are smaller than the original CLIP ViT-L/14 is that in the BIKE model.

The reason why the parameters of BIKE are smaller than the original CLIP ViT-L/14 is that in the BIKE model, we only utilize the vision encoder from CLIP and do...

How to evaluate 4shot?

Question about T2I recall1 of COCO

![image](https://github.com/AILab-CVC/SEED/assets/48858574/054190a8-de85-4e54-b071-81e1e64c2f50) I have obtained similar results using checkpoint test provided by you, but I only obtained about 46 checkpoints using [BLIP-2 checkpoints](https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained.pth). May I ask what might be the problem?

What does the `trl` folder do?