Hacker News new | ask | show | jobs
by natpat 1862 days ago
> One of our conclusions is that not everything on Twitter is a good candidate for an algorithm, and in this case, how to crop an image is a decision best made by people.

This seems like it should have been a foregone conclusion. What was the driving force in the first place to think cropping images with an AI model was desirable? Seems like ML was a solution looking for a problem here, and I'm glad they've realised that.
2 comments
klodolph 1862 days ago
It seems obvious in retrospect. Calling it a foregone conclusion is too harsh.

Twitter crops photos to fit their preview formats. It seems like an obvious improvement to show people's faces when cropping, etc.

link
the_gastropod 1862 days ago
Right but... we've been cropping images in web applications since... y'know, pretty much ever. Using ML to do this was always pretty ridiculous overkill. Give the users an image cropper, and be done with it.
link
klodolph 1862 days ago
I can't see why this is overkill. You're eliminating a step from the image posting process, and making it so users don't have to crop an image twice (once for the full image, and a second time for the preview). That makes sense when you're writing a CMS or blogging platform like Wordpress, but for Twitter it adds some friction.

So, previously, the preview was just cropped in the center. But this made some images look funny, since people's faces would get chopped off.

Coming up with a workable solution to this with ML is not especially hard. You can get things like face detection off the shelf, maybe just tell your autocropper, "crop closer to the face" and have a demo within a couple days (and then much more effort to productionize it). From there, you can start introducing ML models to improve on your basic face detection. (I'm not counting face detection as ML.)

This is not a case where some massive ML model is being brought in to save two seconds of your time. This is a very natural and obvious application of ML, at a company which already does ML at scale, in a way that sounds like it has a good chance at improving the appearance of the site without introducing additional friction.

Instragram gets around this by encouraging everyone to take square photos.

link
eyelidlessness 1862 days ago
I don’t think anyone is saying “I will always prefer to crop every photo and everyone else should too”. I think the point is closer to, if I may borrow a Simpsons line, “I liked your half-assed underparenting a lot more than your half-assed overparenting”. It’s actually impressive that Twitter didn’t object “but I was using my whole ass”, which is basically their default trope when they address user complaints.
link
klodolph 1862 days ago
> I don’t think anyone is saying “I will always prefer to crop every photo and everyone else should too”.

The parent comments are basically saying that, just not in such an exaggerated way. "Give the users an image cropper, and be done with it."

link
Thorrez 1862 days ago
Look at the before and after pictures of when they released the ML crop:

https://blog.twitter.com/engineering/en_us/topics/infrastruc...

All those examples show large improvement. Of course they might cherrypick images with large improvement for their blog advertising the feature. But still, it illustrates why people would think it's a good idea.

Of course they don't seem to consider the idea of not cropping at all.

link