# The iNaturalist Species Classification and Detection Dataset

arXiv: https://arxiv.org/abs/1707.06642 · HTML: https://mlsanity.com/paper/1707.06642/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2017.

## Built on by (most cited first, 29 of 29)

- [Incorporating Convolution Designs into Visual Transformers](https://mlsanity.com/paper/2103.11816/) (2021)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Three things everyone should know about Vision Transformers](https://mlsanity.com/paper/2203.09795/) (2022)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [Semi-supervised Vision Transformers at Scale](https://mlsanity.com/paper/2208.05688/) (2022)
- [NECO: NEural Collapse Based Out-of-distribution detection](https://mlsanity.com/paper/2310.06823/) (2023)
- [LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content](https://mlsanity.com/paper/2403.05854/) (2024)
- [MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition](https://mlsanity.com/paper/2308.09922/) (2023)
- [Masked Modeling for Self-supervised Representation Learning on Vision and Beyond](https://mlsanity.com/paper/2401.00897/) (2023)
- [TopoImb: Toward Topology-level Imbalance in Learning from Graphs](https://mlsanity.com/paper/2212.08689/) (2022)
- [The Curious Layperson: Fine-Grained Image Recognition without Expert Labels](https://mlsanity.com/paper/2111.03651/) (2021)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Train/Test-Time Adaptation with Retrieval](https://mlsanity.com/paper/2303.14333/) (2023)
- [Threshold-Consistent Margin Loss for Open-World Deep Metric Learning](https://mlsanity.com/paper/2307.04047/) (2023)
- [Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens](https://mlsanity.com/paper/2412.04680/) (2024)
- [Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2206.05335/) (2022)
- [LTRL: Boosting Long-tail Recognition via Reflective Learning](https://mlsanity.com/paper/2407.12568/) (2024)
- [Leveraging Intermediate Representations for Better Out-of-Distribution Detection](https://mlsanity.com/paper/2502.12849/) (2025)
- [Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models](https://mlsanity.com/paper/2405.11301/) (2024)
- [A Functional Data Perspective and Baseline On Multi-Layer Out-of-Distribution Detection](https://mlsanity.com/paper/2306.03522/) (2023)
- [EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention](https://mlsanity.com/paper/2310.06629/) (2023)
- [Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution Detection](https://mlsanity.com/paper/2406.16045/) (2024)
- [Falcon Perception](https://mlsanity.com/paper/2603.27365/) (2026)
- [Size Matters](https://mlsanity.com/paper/2102.01582/) (2021)
- [Improving self-supervised representation learning via sequential adversarial masking](https://mlsanity.com/paper/2212.08277/) (2022)
- [Predicting Internet Connectivity in Schools: A Feasibility Study Leveraging Multi-modal Data and Location Encoders in Low-Resource Settings](https://mlsanity.com/paper/2412.12188/) (2024)
- [TSRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detection](https://mlsanity.com/paper/2511.17636/) (2025)
- [Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection](https://mlsanity.com/paper/2603.22660/) (2026)
- [HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification](https://mlsanity.com/paper/2610.11534/) (2026)

## Abstract (arXiv)

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.