iNaturalist

Introduced by Horn et al. in The iNaturalist Species Classification and Detection Dataset

The iNaturalist 2017 dataset (iNat) contains 675,170 training and validation images from 5,089 natural fine-grained categories. Those categories belong to 13 super-categories including Plantae (Plant), Insecta (Insect), Aves (Bird), Mammalia (Mammal), and so on. The iNat dataset is highly imbalanced with dramatically different number of images per category. For example, the largest super-category “Plantae (Plant)” has 196,613 images from 2,101 categories; whereas the smallest super-category “Protozoa” only has 381 images from 4 categories.

Source: Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Classification	iNaturalist 2018	OmniVec
Long-tail Learning	iNaturalist 2018	GML
Image Classification	iNaturalist 2019	Hiera-H
Image Classification	iNaturalist	Hiera-H
Image Retrieval	iNaturalist	Unicom+ViT-L@336px
Image Generation	iNaturalist 2019	StyeGAN2 + NoisyTwins
Few-Shot Image Classification	iNaturalist (227-way multi-shot)	LaplacianShot
Image Classification	iNat2021-mini	WaveMix-256/16
Fine-Grained Image Classification	iNaturalist	TASN
Few-Shot Image Classification	iNaturalist 2018 - 1-shot	MAWS
Few-Shot Image Classification	iNaturalist 2018 - 5-shot	MAWS
Few-Shot Image Classification	iNaturalist 2018 - 10-shot	MAWS