Kevinz-code

Hi, prerained models has been released, see README.md.

Thanks for reminding me this error, and we have fixed this part in our code. Best, Ke Zhu

Hi, Thanks for your question. For your first question, can refer to [ASL](https://github.com/Alibaba-MIIL/ASL), [Q2L](https://github.com/SlongLiu/query2labels) for a comprehensive pipeline of multi-label classification code (which contains standard validation code similar to ours)....

Hi, thanks for reproducing our paper. "why set the class token in the code in "VIT_CSRA" ": setting class token at the beginning is the original structure of VIT, which...

Hi Haoli, Sorry for the late reply. The model checkpoints in the links are now fully released, and trial are available with our codebase! Please contact me if necessary. Best,...

Hi xiaodong, Thanks for your comments. I guess it is because the version of LLaVA and transformers. notes: - In our seva codebase, we adopt transformers 4.31.0. - In our...

Hi xiaodong, It is true that the transformers version (4.31 vs 4.37) caused the evaluation mismatch, which we also found during experiment. Our evaluation pipeline follows the below guidance. -...

@ppalantir Hi, thanks for your letter. The version difference are correlated with the llava version. In our current reproduction, llava is set as 1.1.3 [https://github.com/haotian-liu/LLaVA/tree/v1.1.3?tab=readme-ov-file](url), and the transformer version is...