Tweet
Tweet

Slide 1

Slide 1 text

Deep Learning for Conservation Alex Shepard [email protected] California Academy of Sciences

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

What is iNaturalist?

Slide 4

Slide 4 text

188 0 1900 192 0 194 0 196 0 198 0 2000 2020 2,000 1,000 0 iNaturalist Other iNaturalist Other 93% of all Monarch Butterfly records this decade are from iNaturalist GBIF Monarch Butterfly Records / month iNaturalist generates a significant portion of the world’s biodiversity data

Slide 5

Slide 5 text

No content

Slide 6

Slide 6 text

iNaturalist is doubling every year

Slide 7

Slide 7 text

5 million images of wildlife 13k species with > 20 observations Train Val Test iNaturalist Deep Learning Dataset

Slide 8

Slide 8 text

Inception v3 Original Random Crop Flipped Cropped Color distorted iNaturalist Deep Learning Training Pipeline

Slide 9

Slide 9 text

Inception v3 iNaturalist Deep Learning: Prediction

Slide 10

Slide 10 text

http://appstore.com/inaturalist iNaturalist Deep Learning Deployed in iOS

Slide 11

Slide 11 text

Top 1 Accuracy 57% Top 2 Accuracy 66% Top 10 Accuracy 78% Common Ancestor Accuracy 93% Vision Accuracy Curve Full System Accuracy iNaturalist Deep Learning: Results

Slide 12

Slide 12 text

iNaturalist Deep Learning: Future Challenges

Slide 13

Slide 13 text

Thanks! https://inaturalist.org [email protected] https://github.com/inaturalist https://github.com/visipedia