Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Replacement for the image of Lena #19

Closed
xuv opened this issue Dec 10, 2017 · 4 comments
Closed

Replacement for the image of Lena #19

xuv opened this issue Dec 10, 2017 · 4 comments

Comments

@xuv
Copy link

xuv commented Dec 10, 2017

This is not a technical bug, but an important matter you want to address.

In the selection of example images, you have included the photo known as Lena (or Lenna).

While I'm guessing you might want to show the behavior of your algorithm on human faces, the choice of the image in this case is quite unfortunate and widely discussed as an unwanted picture in today's image processing sets.

Inspired by other projects, please consider using one of these images instead:

Thank you for your help and addressing this report with the most careful attention.

Have a nice day

@DmitryUlyanov
Copy link
Owner

Hi, we understand that this picture is unwanted. We used Lena image only because it serves an example in "Shepard networks" paper, which we compare to. They provide 2 examples of their text inpainting method of which Lena is the most complex and interesting.

So please, understand it from our side: we do not aim to hurt someone's feelings by using inappropriate images, but only produce a scientifically-sound work with a fair comparisons.

We will do our best to make sure future works use other image than Lena when comparing to our work by providing an another text inpainting example.

@xuv
Copy link
Author

xuv commented Dec 11, 2017

Hello @DmitryUlyanov.

Thx for taking the time to look at this and for the explanation on why this image landed in your tests. Thanks also for pointing to the "Shepard networks" paper, it helped me understand better but also realize that you might have a possible solution in it for your comparison.

I believe that Lenna is here to show the behavior of your approach with image "Inpainting". And for that particular case, the paper you are comparing to proposes 2 examples. One is Lenna, but the other one is a picture of fruits and veggies.

Would you please consider using that other example instead? Would that make your comparison still valid while addressing this sexist problem?

Thanks for your help and time.

@DmitryUlyanov
Copy link
Owner

Replaced.

@derkinsurprise
Copy link

prognulsya.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants