search

zqhang / AnomalyCLIP

Official implementation for AnomalyCLIP (ICLR 2024)
MIT License
249 stars 25 forks source link

Issue about reimplementing medical ZSAD performance #41

Open kiyoonjeong0305 opened 1 month ago

kiyoonjeong0305 commented 1 month ago

Hello @zqhang and @tianyu0207,

First of all, I really appreciate for your work! it's really nice and interesting.

But I can't find some implementation details about medical ZSAD.

The paper said "To address this issue, we create such a dataset based on ColonDB (More details see Appendix A), and then optimize the prompts in AnomalyCLIP and VAND using this dataset and evaluate their performance on the medical image datasets.".

So as far as i understood, you finetuned the models with (ColonDB + test split of Endo classfication dataset) and tested medical ZSAD performance of every other medical dataset. Then what is the finetuning dataset for testing ColonDB and Endo dataset?

Since those two datasets were already used in finetuning the models, I think another dataset is needed for testing those two dataset.

I would appreciate every help

zqhang commented 1 month ago

Hi, your understanding is correct. Therefore, we do not test ColonDB and Endo (classification).