Papers › The iNaturalist Species Classification and Detection Dataset

The iNaturalist Species Classification and Detection Dataset

20 Jul 2017CVPR 2018 6arXiv:1707.06642archive 2025-07-28

Grant Van Horn, Oisin Mac Aodha, Yang song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, Serge Belongie

Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species are more abundant and easier to photograph than others. To encourage further progress in challenging real world conditions we present the iNaturalist species classification and detection dataset, consisting of 859,000 images from over 5,000 different species of plants and animals. It features visually similar species, captured in a wide variety of situations, from all over the world. Images were collected with different camera types, have varying image quality, feature a large class imbalance, and have been verified by multiple citizen scientists. We discuss the collection of the dataset and present extensive baseline experiments using state-of-the-art computer vision classification and detection models. Results show that current non-ensemble based methods achieve only 67% top one classification accuracy, illustrating the difficulty of the dataset. Specifically, we observe poor results for classes with small numbers of training examples suggesting more attention is needed in low-shot learning.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

21 repositories listed; official and paper-mentioned ones first.

Puning97/AUTO-for-OOD-detection mentioned on GitHubpytorch report
aioz-ai/multigraphfl mentioned on GitHubpytorchMIT report
deeplearning-wisc/cider mentioned on GitHubpytorch report
deeplearning-wisc/dice mentioned on GitHubpytorchMIT report
deeplearning-wisc/gradnorm_ood mentioned on GitHubpytorch report
deeplearning-wisc/knn-ood mentioned on GitHubpytorch report
deeplearning-wisc/large_scale_ood mentioned on GitHubpytorch report
deeplearning-wisc/npos mentioned on GitHubpytorch report
deeplearning-wisc/react mentioned on GitHubpytorch report
deeplearning-wisc/snn mentioned on GitHubpytorch report
haoqiwang/vim mentioned on GitHubpytorchNOASSERTION report
jimzai/mode-ood mentioned on GitHubpytorch report
limchaos/likelihood-ood mentioned on GitHubpytorch report
mapleleaf6/zode mentioned on GitHubpytorch report
tensorflow/models mentioned on GitHubtf report
tmlr-group/class_prior mentioned on GitHubpytorch report
tmlr-group/neglabel mentioned on GitHubpytorchApache-2.0 report
xixiliu95/gen mentioned on GitHubpytorchApache-2.0 report
gitlab.com/drti/neco mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationImage Classificationimage-classification

Datasets

Introduced by this paper, per the archive.

iNaturalist

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification iNaturalist IncResNetV2 SE Top 1 Accuracy 67.3% #14 of 19 Archive leaderboard report
Image Classification iNaturalist IncResNetV2 SE Top 5 Accuracy 87.5% #14 of 19 Archive leaderboard report
Image Classification iNaturalist 2018 Inception-V3 Top-1 Accuracy 60.20% #54 of 60 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections