Go to NeurIPS 2025 Datasets and Benchmarks Track homepageOpen-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring
Keywords: Biodiversity; Ecology; Species Recognition; Open-set Recognition; Open-world Machine Learning; Entomology
TL;DR: We propose a new open-set recognition dataset, Open-Insect, and evaluate 38 algorithms for new species detection on geographical open-set splits with varying difficulty.
Abstract: Global biodiversity is declining at an unprecedented rate, yet little information is
known about most species and how their populations are changing. Indeed, some
90% Earth’s species are estimated to be completely unknown. Machine learning has
recently emerged as a promising tool to facilitate long-term, large-scale biodiversity
monitoring, including algorithms for fine-grained classification of species from
images. However, such algorithms typically are not designed to detect examples
from categories unseen during training – the problem of open-set recognition
(OSR) – limiting their applicability for highly diverse, poorly studied taxa such as
insects. To address this gap, we introduce Open-Insect, a large-scale, fine-grained
dataset to evaluate unknown species detection across different geographic regions
with varying difficulty. We benchmark 38 OSR algorithms across three categories:
post-hoc, training-time regularization, and training with auxiliary data, finding that
simple post-hoc approaches remain a strong baseline. We also demonstrate how to
leverage auxiliary data to improve species discovery in regions with limited data.
Our results provide timely insights to guide the development of computer vision
methods for biodiversity monitoring and species discovery.
Croissant File: zip
Dataset URL: https://huggingface.co/datasets/yuyan-chen/open-insect
Code URL: https://github.com/RolnickLab/Open-Insect
Primary Area: AL/ML Datasets & Benchmarks for life sciences (e.g. climate, health, life sciences, physics, social sciences)
Submission Number: 426
Loading