The iNaturalist Species Classification and Detection Dataset
Citations Over TimeTop 1% of 2018 papers
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.
Related Papers
- → Intelligent Detection of Missing and Unattended Objects in Complex Scene of Surveillance Videos(2012)10 cited
- → Surface-based general 3D object detection and pose estimation(2014)5 cited
- → Towards Object Detection from Motion(2019)1 cited
- → 2A1-S02 Unknown Object Detection and Picking Based on Impacting and Keypoint Tracking(2015)
- MULTIPLE HUMAN OBJECT MOTION TRACKING BASED ON BACKGROUND SUBTRACTION AND SHADOW REMOVAL(2021)