The iNaturalist Species Classification and Detection Dataset
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
The iNaturalist Species Classification and Detection Dataset. / Horn, Grant Van; Aodha, Oisin Mac; Song, Yang; Cui, Yin; Sun, Chen; Shepard, Alex; Adam, Hartwig; Perona, Pietro; Belongie, Serge.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 14.12.2018, p. 8769-8778.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - The iNaturalist Species Classification and Detection Dataset
AU - Horn, Grant Van
AU - Aodha, Oisin Mac
AU - Song, Yang
AU - Cui, Yin
AU - Sun, Chen
AU - Shepard, Alex
AU - Adam, Hartwig
AU - Perona, Pietro
AU - Belongie, Serge
N1 - Publisher Copyright: © 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85062853151&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00914
DO - 10.1109/CVPR.2018.00914
M3 - Conference article
AN - SCOPUS:85062853151
SP - 8769
EP - 8778
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -
ID: 301825294