Understanding Representation Gaps Across Scales in Tropical Tree Species Classification from Drone Imagery
Sulagna Saha, Arthur Ouaknine, Etienne Lalibert\'e, Carol Altimas, Evan M. Gora, Adriane Esquivel Muelbert, Ian R. McGregor, Cesar Gutierrez, Vanessa E. Rubio, and David Rolnick

TL;DR
This paper investigates the challenges of classifying tropical tree species from UAV imagery at different resolutions, highlighting the potential of self-supervised methods to bridge the performance gap.
Contribution
It evaluates existing models on paired UAV imagery at different scales and proposes self-supervised representation alignment to improve canopy-level classification.
Findings
Classification accuracy is higher on close-up images than on top-view imagery.
The performance gap widens for rare species.
Self-supervised alignment can integrate fine-grained details into canopy-level models.
Abstract
Accurate classification of tropical tree species from unoccupied aerial vehicle (UAV) imagery remains challenging due to high species diversity and strong visual similarity among species at typical image resolutions (centimeters per pixel). In contrast, models trained on close-up citizen science photographs captured with smartphones achieve strong plant species classification performance. Recent advances in UAV data acquisition now enable the collection of close-up images that are spatially registered with top-view aerial imagery and approach the level of visual detail found in smartphone photographs, with the trade-off that such high-resolution photos cannot be acquired for many trees. In this work, we evaluate the performance of existing methods using paired top-view and close-up UAV imagery collected in a species-rich tropical forest. Through fine-tuning experiments, we quantify the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
