[image] Concern about # of observations Every photo that you upload may improve our computer vision suggestion (photos of rarer taxa help more, but every photo helps) Speaking of, how many more spiders do I need to upload here so Owen and friends are in the next CV version https://www.inatural…

[image] egordon88: how many more spiders do I need to upload If you want the model to actually learn this taxon, then your best bet is to be patient. I see that you’re already responsible for 50% of the observations of that taxon. Based on that, the vision model may learn things about how yo…

They weren’t just all taken in the same month; the 13 with precise time stamps on 2021-10-13 were taken within just two minutes of each other, and the 64 on 2021-10-12 don’t have precise timestamps but assuming approximately the same rate of photo taking were probably taken within ~10 minutes of eac…

[image] alex: If you want the model to actually learn this taxon, then your best bet is to be patient. Tough ask :slightly_smiling_face: [image] alex: I see that you’re already responsible for 50% of the observations of that taxon. That happens when ~50 live around the garden and they…

Leaving aside the issue of images from a single observer misleading CV into learning spurious identifying traits, perhaps @alex can confirm the current threshold for inclusion in CV? I recall reading that a species is included if there are at least 100 observations that are either verifiable, or wou…

Thanks for splitting this off, Tony.

@alex I would also like to know whether and how photos are prioritized for selection; if a species has, say, 1000 RG observations, 1000 needs ID observations, and 1000 casual-but-verifiable-if-not-captive observations, do I need to worry about reviewing for mis-IDs in the casual pool to prevent them…

We will use more than one photo from each observation, but not too many from each. 100 is our minimum number of photos, but we will train on as many as 1,000 photos of a taxon. As the model sees more distinct examples of a taxon during training, it generally gets better at correctly suggesting that…

[image] wildskyflower: if a species has, say, 1000 RG observations, 1000 needs ID observations, and 1000 casual-but-verifiable-if-not-captive observations I’m also interested to know the answer to this. If there are enough RG photos, does the model use only RG? I would think it should, even i…

Well I think it is tricky to say for certain whether they should be completely excluded because sometimes carefully selected cultivars in manicured gardens can look quite different from their wild counterparts. Therefore, removing them from the training could significantly degrade the median accura…

How are photos selected for CV training?

General

tiwane June 9, 2023, 1:49am 6

(Split this off of the original topic)

Topic		Replies	Views
Comparing CV Outcomes in a Pair of near-Cryptic Moth Species General question	60	1545	October 24, 2024
Possible simple way to improve CV for many creatures General	19	743	July 18, 2026
"Helping" the computer vision - is this wrong? General	36	2881	July 12, 2020
Use computer vision on each photo in an observation Feature Requests web , under-review	48	3656	December 15, 2025
New Computer Vision model released! News and Updates	42	6320	October 4, 2024

How are photos selected for CV training?

Related topics