Did computer vision get worse lately?

M, what? I didn’t say anything bad, and I get what @odole means, though I think some cases are too hard for any kind of intellect. I don’t get tone reference at all.

3 Likes

I’m not part of the iNat staff, just a member of the community. I explained my understanding of how the computer vision model works, but I’m not the person to defend it. I don’t have the power to make them change it to random forest or anything else.

I think it’s remarkable that the computer vision works as well as it does, and I am acutely aware there’s room for improvement. Some of its shortcomings could be overcome with more/better data, and probably some can’t.

I don’t believe iNaturalist is trying to create an authoritative taxonomic classifier. Expert humans, who have real understanding of the organisms, will always be the best. I find it most useful to consider the computer vision suggestions like an enthusiastic amateur identifier, like many members of our community: often right, sometimes confused or mistaken, but ultimately one among many voices who can weigh in on any observation.

8 Likes

Me neither. And I find @trh_blue’s statement quite inappropriate. Sorry, but I do.

@chrisangell thanks for your additional explanations and description of the situation. But then either someone from iNat staff or in iNat’s close circle will try to answer my questions or we are not going to make the slightest progress. I will end up thinking that it is a top secret issue… It would be simple to just say so.

2 Likes

Something we’re working on, but please keep in mind that iNaturalist has a total staff of 8 people, none of whom work on computer vision full-time (and some like me aren’t coders at all). With our current resources, we’re doing what we can. That’s just the reality of where things stand at the moment.

@chrisangell provided some really good answers about how iNat’s CV works and what it is and isn’t, thanks Chris. Not sure I have anything to add there, although we’ve done some experiments that show you which part of the photo is being used to determine a suggestion, which is really cool and would remove some of the “black box” mystery behind CV’s suggestions. Still lots of kinks to work out, though.

Regarding @odole’s bee photo - as I stated earlier, iNaturalist’s computer vision model is trained on iNaturaist photos of organisms. Almost no one uploads combined photos like this one, and I suspect almost no one uploads photos of bees that just show the head - usually most of the body is in the frame. Thus the CV model won’t recognize a photo with a dark blob in one corner and a sharp wide shot of a flower on the other side (or just a blurry bee head close-up) as a photo of a bee. I recommend posting separate photos rather than combining them.

Regarding @trh_blue’s comment, I think she was referring to odole’s sarcastic sour grapes remark (at least it came off as sarcastic to me, as well as others) and that the topic has strayed quite a bit from its original question, which I answered here and here (and others of course gave great responses as well). If someone can find a consistent issue, please file a bug report. I’m going to close the topic as the original question was answered.

8 Likes