When I identify on inat I mainly ID earwigs, and lately I’ve been noticing a lot of orthopterans (mainly crickets) misidentified as the earwig subfamily Skendylinae. I have taken a closer look at a lot of these observations and it looks like inat’s suggested identifications are the problem. On almost all of these observations there are a few suggested taxa, including Skendylinae, and a lot of the times never Orthoptera species. Because this is a common reoccurring misidentification happening with inat’s system, I was wondering if there was any way I could report this problem.
I apologize if there’s already a topic like this going, this is my 1st forum post and I couldn’t find anywhere to add this to.
The computer vision (CV) can be summed up as an image matcher. The CV only knows what it knows, so if there is no or very little representation of those types of crickets in the CVs training data. The CV will suggest the next closest looking thing.
When ignoring location, you can see other crickets mostly from other regions suggested.
Really the only way to fix it is to teach it those crickets without representation in the CV exist by identifying them enough the taxa get eligible. If they can’t be identified due to lack of identifiers, difficulty, they are undescribed, etc. There’s not much that can be done.
There are many other forum posts about CV issues. There are also multiple feature requests requesting changes or revamps to how the system works.
