Search Results for author: Hongjin Lin

Found 2 papers, 0 papers with code

PCTreeS: 3D Point Cloud Tree Species Classification Using Airborne LiDAR Images

no code implementations6 Dec 2024 Hongjin Lin, Matthew Nazari, Derek Zheng

Reliable large-scale data on the state of forests is crucial for monitoring ecosystem health, carbon stock, and the impact of climate change.

Consistent Explanations in the Face of Model Indeterminacy via Ensembling

no code implementations9 Jun 2023 Dan Ley, Leonard Tang, Matthew Nazari, Hongjin Lin, Suraj Srinivas, Himabindu Lakkaraju

This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (nearly) equally well-performing models for a given dataset and task.

Cannot find the paper you are looking for? You can Submit a new open access paper.