Sanghyuk Chun

Hi, thanks for your question. > if the sample is created by mixing cat and dog, model should predict labels other than either of the cat or dog? Yes, we...

Closing the issue, assuming the answer resolves the problem. Please re-open the issue as necessary.

Closing the issue, assuming the answer resolves the problem. Please re-open the issue as necessary.

It seems a duplicate issue with https://github.com/clovaai/lffont/issues/22#issuecomment-876285041 Please check the issue, and please let me know if you still have the same issue

Closing the issue, assuming the answer resolves the problem. Please re-open the issue as necessary.

Hi, thanks for your question. First, I would like to clarify that this function is not used for PCME++, but only for sampling-based one, PCME. Hence it does not change...

This answer is wrong. Please check my additional comment below. ---------- It is because `sigmoid` is defined as a compressed version in this paper, i.e., $\text{sigmoid} (x) = \frac{\exp x...

@ahustr Hi, while I updated the camera-ready paper, I found that your original derivation was correct and my derivation was wrong. First, the compressed sigmoid is not used in PCME++....

@zl535320706 **Quick solution**: do not filter top-k for your retrieved items, but use the full items as follows: Current example ([from the current example code based on CLIP](https://github.com/naver-ai/eccv-caption/blob/main/examples/clip_example_run.py#L78-L96)): ``` K...

Can you attach your `i2t_retrieved_items` and `t2i_retrieved_items` without filtering (using google drive or dropbox?)? It is impossible to presume what the problem is with only the table.