Computer vision clean-up (archive)

Ah, found it, it was further back than I expected.

Added Pleroma heteromallum. It has a bunch of synonyms, including Tibouchina heteromalla. (It’s a bit of a mess on iNat right now, because many of the synonyms (like this, this, and this) are currently listed as separate species.

It’s pretty distinctive - it has large leaves with short petioles and silky hairs, large clusters of flowers with relatively small flowers. It tends to be misidentified as Tibouchina urvilleana/Pleroma urvilleanum or Tibouchina semidecandra/Pleroma semidecandrum.

Sometimes Clematis gets misidentified as Tibouchina/Pleroma as well, but that’s a separate issue.

Would it not be best to make all needed taxon changes before cleaning this one up?

I suppose so. I will note that there are some observations where different synonyms are used (e.g. somebody suggests Tibouchina grandifolia, then somebody else suggests Pleroma heteromallum). These get automatically fixed, right?

Hi everyone, I’ve tracked down a bunch of (cultivated) Sciadopitys verticillata misidentified as other plants. This is pretty easy to identify - long thick leathery leaves (technically cladodes, but whatever) found in whorls. Reddish fibrous bark and distinctive cones may also help in identification. Here are some photos for reference.

https://www.inaturalist.org/observations/identify?quality_grade=needs_id%2Ccasual&ident_taxon_id=129057&without_taxon_id=129057

3 Likes

Have to add that moss problem if changed not too much and Pseudanomodon attenuatus is still applied to any green moss sas it’s #1 suggestion and system doesn’t even suggest higher groups, only a bunch of species of mosses.

1 Like

I added Pilea to the list. Two things to note:

Pilea peperomioides is commonly grown as a houseplant, but CV usually thinks it’s Hydrocotyle. This plant has peltate leaves with an entire margin and a circular-ish outline. (Note that it can be confused with some Peperomia such as P. polybotrya and P. tristachya, which have more pointed leaf tips.)

Meanwhile, Pilea cadierei seems to have the opposite problem: many plants with variegated white and green leaves are mistakenly identified as Pilea cadierei. I also came across a bunch of plants in Ecuador that I can’t identify, so if anybody knows that would be much appreciated!

Pilea peperomioides: https://www.inaturalist.org/observations/identify?quality_grade=casual%2Cneeds_id&order_by=updated_at&ident_taxon_id=125439&without_taxon_id=125439

Pilea cadierei: https://www.inaturalist.org/observations/identify?quality_grade=casual%2Cneeds_id&order_by=updated_at&ident_taxon_id=278679&without_taxon_id=278679

2 Likes

Sorry, it appears I’ve severely missed the point of this thread. I’m supposed to be discussing identification in flags instead of in the comments :sweat_smile:

I have another question though. Since a misidentification necessarily involves two taxa, which one do you put? If multiple species are mistaken for species X or species X is mistaken for multiple species, it probably makes sense to put the one species X. But what if species X is consistently mistaken for species Y?

Add one that is suggested by the programm, as those observations need revision.

2 Likes

EDIT: I just went ahead and added it in. I can take it off if I misinterpreted the rules. :grin:

I’m not sure if this would fit the criteria exactly, but should I add Pennisetum clandestinum to the list?

I ask since it’s a CV misID, but it often jumps drastically in number when students use iNat to ID grass, which means it’s spreading as a suggestion every time some tries to ID grass species. I can’t quite figure out which IDs are legitly this species and when they’re not, but i do know it can’t survive temperatures that are more common in northern climates.

2 Likes

I added Haworthia to the list.

Some time ago, it was split up into several genera - Haworthia, Haworthiopsis, and Tulista. However, many species split off as Haworthiopsis are very commonly grown as houseplants. So it looks like CV tends to over-suggest Haworthia, and it might also be affecting the wild observations too.

1 Like

Hi folks,

Just wanted to say that I really appreciate all of the work that goes into this wiki issue.

It’s been an article of faith for those of us who train these vision systems that the easy answer to failed predictions/suggestions is simply more data. I’m not totally sure how well placed that faith is, but it’s broadly been true for vision suggestions at iNat over the past few years.

At any rate, as we continue to train a new model, I’m starting to think about how to evaluate our current model and the new model using the taxa on this list to try to understand things like: did we increase our dataset size on these problem taxa? Did that image count growth correlate with an increase in our suggestion accuracy? If not, can we figure out why?

Thanks for the hard work. I’ll keep the forum in the loop once the new model is finished training (a few months away) and we can evaluate the new model, and hopefully we can show some progress.

Best,
alex

11 Likes

Kashubian Buttercup, Ranunculus cassubicus, has basal leaves very different from stem leaves. The computer seems to be confused, suggesting this species for plants as different as Garlic Mustard and Goldenrods. I cleaned up the North American records; the actual species isn’t known from this area. I’m not sure this is a common problem, but it is a problem.

1 Like

Great to hear that the model is being updated soon!

I think the issues with problem taxa highlighted on this thread aren’t necessarily just the result of suggestion inaccuracy by the model though. I think they are also dependent on the current UI design.

For example, on complex taxa, the “pretty sure” of model suggestion might be 100% correct and places the observation at genus level (where it belongs without a more detailed image)… but nevertheless, the observer opts to take the top species level ID instead, as they know no better.
e.g. Like on this observation.

This is also coupled with the issue mentioned here.
The problem taxa tend to be high up on the list of species-level suggestions when the model isn’t “pretty sure” of anything whatsoever. Ideally, if its not pretty sure of anything, the UI should present this as a red flag (or autosuggest a very coarse ID) not make things worse by still suggesting something wildly specific.

Perhaps small alterations in the design of the UI around the autosuggest might go further towards fixing many of the taxa on this thread than the development of the model itself.

3 Likes

Though in many cases system can’t decide what is best, it doesn’t show a genus to choose from, only a list of species, and sometimes top one is right, but often all of the mwrong or right one is in the bottom. Maybe adding an additional line appearing like “we are not sure what it is, id it your way” would help.

2 Likes

This is a good suggestion. This should say and spell out that “You should check this suggestion before you use it”. And it should explicitly say how to check it. However, as it is most users just click on the first thumbnail that “looks right”.

3 Likes

Yes… this sort of statement is already a feature on the iOS app I think, so at the least should be replicated on the main browser version.

I guess the problem is, explaining to the average user how to check complex taxa is not so simple in a few words. I came across an identifier this week with thousands of IDs even, many of which were noted as been used as they were visually similar to an autosuggest, resulting in many incorrect and maverick species-level IDs. At least two of the Diptera species are on the list in this wiki…visual similarity just doesn’t cut it.

Perhaps the use of an autosuggested species-level ID could trigger a prompt of some sort, checking if the observation actually shows the diagnostic features.

As so few of the most common Diptera are possible to ID from a quick visual comparison, I wonder if it would be better in some ways if there were no species-level autosuggestions whatsoever in complex taxa. Or at least, if they were more hidden from novice access.

1 Like

Hi, I know Lupinus nanus and Lupinus bicolor are difficult for the computer vision to tell apart, but I am unsure if there are over 100 observations mis-identified due to this, but I guess probably. I stopped fighting the fight a few years ago after being swamped and burned out on correcting them. So, maybe they should be on the list, I just don’t know without looking through 2000+ observations.

1 Like

Added Arion rufus/ vulgaris, both distributed across Europe and virtually indistinguishable from each other

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.