DivShift: Exploring Domain-Specific Distribution Shift in Large-Scale, Volunteer-Collected Biodiversity Datasets (Papers Track)

Elena Sierra (Stanford University); Lauren Gillespie (Stanford University); Salim Soltani (University of Freiburg); Moisés Expósito-Alonso (University of California, Berkeley); Teja Kattenborn (University of Freiburg)

Paper PDF NeurIPS 2024 Recorded Talk Cite
Ecosystems & Biodiversity Earth Observation & Monitoring Computer Vision & Remote Sensing

Abstract

Climate change is negatively impacting the world's biodiversity. To build automated systems to monitor these negative biodiversity impacts, large-scale, volunteer-collected datasets like iNaturalist are built from community-identified, natural imagery. However, such volunteer-based data are opportunistic and lack a structured sampling strategy, resulting in geographic, temporal, observation quality, and socioeconomic, biases that stymie uptake of these models for downstream biodiversity monitoring tasks. Here we introduce DivShift North American West Coast (DivShift-NAWC), a curated dataset of almost 8 million iNaturalist plant images across the western coast of North America, for exploring the effects of these biases on deep learning model performance. We compare model performance across four known biases and observe that they indeed confound model performance. We suggest practical strategies for curating datasets to train deep learning models for monitoring climate change's impacts on the world's biodiversity.