A new Computer Vision Model including 1,465 new taxa in 40 days

We released a new computer vision model today. It has 69,966 taxa, up from 68,853.

This new model (v1.6) was trained on data exported exported last month on December 11th and added 1,465 new taxa.

Taxa differences to previous model

The charts below summarize these 1,465 new taxa using the same groupings we described in past release posts.

By category, most of these 1,465 new taxa were insects and plants

Here are species level examples of new species added for each category:

Click on the links to see these taxa in the Explore page to see these samples rendered as species lists. Remember, to see if a particular species is included in the currently live computer vision model, you can look at the “About” section of its taxon page.

We couldn't do it without you

Thank you to everyone in the iNaturalist community who makes this work possible! Sometimes the computer vision suggestions feel like magic, but it’s truly not possible without people. None of this would work without the millions of people who have shared their observations and the knowledgeable experts who have added identifications.

In addition to adding observations and identifications, here are other ways you can help:

  • Share your Machine Learning knowledge: iNaturalist’s computer vision features wouldn’t be possible without learning from many colleagues in the machine learning community. If you have machine learning expertise, these are two great ways to help:
  • Participate in the annual iNaturalist challenges: Our collaborators Grant Van Horn and Oisin Mac Aodha continue to run machine learning challenges with iNaturalist data as part of the annual Computer Vision and Pattern Recognition conference. By participating you can help us all learn new techniques for improving these models.
  • Start building your own model with the iNaturalist data now: If you can’t wait for the next CVPR conference, thanks to the Amazon Open Data Program you can start downloading iNaturalist data to train your own models now. Please share with us what you’ve learned by contributing to iNaturalist on Github.
  • Donate to iNaturalist: For the rest of us, you can help by donating! Your donations help offset the substantial staff and infrastructure costs associated with training, evaluating, and deploying model updates. Thank you for your support!
Posted on 20 de janeiro de 2023, 06:59 PM by loarie loarie

Comentários

I'm always excited when I read about the model updates. Thank you!

Publicado por alisonnorthup cerca de 1 ano antes

Love it! Some of my observed species made it into the new model as I see. Love those lists!

Publicado por ajott cerca de 1 ano antes

So exciting! Thank you all.

Publicado por mbwildlife cerca de 1 ano antes

So rewarding - I also see mine on the new list!

Publicado por dianastuder cerca de 1 ano antes

Can someone explain, why for example Ciconia microscelis wasn't included in the model before if it has over 1000 observations?

Publicado por kildor cerca de 1 ano antes

@kildor if you click that About tab, it IS Included.

Publicado por dianastuder cerca de 1 ano antes

@dianastuder if you look to "species level examples of new species added for each category: Aves", the list does include C. microscelis, so I suppose it has not been included before. Or there are some errors in the list?

Publicado por kildor cerca de 1 ano antes

@kildor usually when a taxa with more than 1000 observations is added, it was probably the result of some taxonomic changes. In this case, it appears that C. microscelis had been split from C. episcopus, and therefore this new species had to be added to the model. C. microscelis wasn't added until now because it wasn't recognized as its own species until now.

http://datazone.birdlife.org/species/factsheet/african-woollyneck-ciconia-microscelis/details

Publicado por mabuva2021 cerca de 1 ano antes

@mabuva2021, ok, now it is clear. I thought it should be something connected with taxon changes, but wasn't sure.
Thank you for explanation!

Publicado por kildor cerca de 1 ano antes

I've been trying to capture things like that stork in the 'taxon changes' bin - but clearly missed that one, there are cases when the taxonomy changes in a way thats difficult for us to detect the origin of a taxa (if it came from a taxon change or not) I likely missed that stork. Apologies for the confusion

Publicado por loarie cerca de 1 ano antes

Thank you so much again for continuing to improve the Cv!

Publicado por yayemaster cerca de 1 ano antes

Amazing! I love the graphics and thanks so much y'all are amazing.

Publicado por wildlife13 cerca de 1 ano antes

Great!

Publicado por huttonia cerca de 1 ano antes

I recently get many more super-off suggestions (like a bird suggestion for an insect etc.); not sure if any connection to the new model …

Publicado por portioid cerca de 1 ano antes

First link leads to the model v1.4, not v1.5. Here is the correct link: https://www.inaturalist.org/posts/72692-a-new-computer-vision-model-including-1-403-new-taxa-in-32-days

Publicado por apseregin cerca de 1 ano antes

updated thanks

Publicado por loarie cerca de 1 ano antes

Adicionar um Comentário

Iniciar Sessão ou Registar-se to add comments