iNat2021 (iNaturalist 2021)

Introduced by Horn et al. in Benchmarking Representation Learning for Natural World Image Collections

iNat2021 is a large-scale image dataset collected and annotated by community scientists that contains over 2.7M images from 10k different species.

To make the dataset more accessible the authors have also created a "mini" training dataset with 50 examples per species for a total of 500K images. Each species has 10 validation images, for a total of 100k validation images. There are a total of 500,000 test images. In addition to its overall scale, the main distinguishing feature of iNat2021 is that it contains at least 152 images in the training set for each species.


Paper Code Results Date Stars

Dataset Loaders


Similar Datasets


  • Custom (research-only)