CaltechAUTHORS
  A Caltech Library Service

The iNaturalist Species Classification and Detection Dataset

Van Horn, Grant and Mac Aodha, Oisin and Song, Yang and Cui, Yin and Sun, Chen and Shepard, Alex and Adam, Hartwig and Perona, Pietro and Belongie, Serge (2018) The iNaturalist Species Classification and Detection Dataset. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE , Piscataway, NJ, pp. 8769-8778. ISBN 978-1-5386-6420-9. https://resolver.caltech.edu/CaltechAUTHORS:20180614-123754546

[img] PDF - Accepted Version
See Usage Policy.

7Mb
[img] PDF - Submitted Version
See Usage Policy.

7Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20180614-123754546

Abstract

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.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/CVPR.2018.00914DOIArticle
https://arxiv.org/abs/1707.06642arXivDiscussion Paper
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2018 IEEE. This work was supported by a Google Focused Research Award. We would like to thank: Scott Loarie and Ken-ichi Ueda from iNaturalist; Steve Branson, David Rolnick, Weijun Wang, and Nathan Frey for their help with the dataset; Wendy Kan and Maggie Demkin from Kaggle; the iNat2017 competitors, and the FGVC2017 workshop organizers. We also thank NVIDIA and Amazon Web Services for their donations.
Funders:
Funding AgencyGrant Number
GoogleUNSPECIFIED
NVIDIAUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Record Number:CaltechAUTHORS:20180614-123754546
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20180614-123754546
Official Citation:G. V. Horn et al., "The iNaturalist Species Classification and Detection Dataset," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 8769-8778. doi: 10.1109/CVPR.2018.00914
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:87114
Collection:CaltechAUTHORS
Deposited By: Caroline Murphy
Deposited On:14 Jun 2018 20:43
Last Modified:03 Oct 2019 19:52

Repository Staff Only: item control page