Paperpile

Referenced Papers (4)

Nigeria - National forest (carbon) inventory field manual

FAO

, 2020

"The speaker uses this specific FAO publication to illustrate the diverse agro-ecological zones within Nigeria, relevant to agricultural practices."

Referenced at: 12:40

Detection of data drift and outliers affecting machine learning model performance over time

Samuel Ackerman, E Farchi, Orna Raz, Marcel Zalmanovici, Parijat Dube

ArXiv, 2020

"The speaker cites this arXiv preprint to highlight common types of data drift (data, domain, concept, model) that can occur when transitioning machine learning models from development to production in diverse agricultural contexts."

Referenced at: 20:47

Masked Autoencoders Are Scalable Vision Learners

Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick

arXiv [cs.CV], 2021

"The speaker introduces this paper on Masked Autoencoders (MAE) as a foundational work in visual learning that inspired similar approaches for satellite imagery, enabling powerful feature learning."

Referenced at: 45:57

SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery

Yezhen Cong, Samarth Khanna, Chenlin Meng, Patrick Liu, Erik Rozi, Yutong He

Neural Inf Process Syst, 2022

"The speaker references this paper as an application of masked autoencoders, specifically Satmae, for pre-training transformers on temporal and multi-spectral satellite imagery, extending MAE principles to remote sensing data."

Referenced at: 45:57