A Comparative Study on Unsupervised Domain Adaptation Approaches for Coffee Crop Mapping

TL;DR

This study compares various unsupervised domain adaptation methods for mapping coffee crops across different regions, highlighting their effectiveness, challenges like negative transfer, and the impact of data normalization.

Contribution

It provides a comprehensive comparison of UDA approaches for coffee crop mapping, revealing their strengths, limitations, and the influence of data normalization techniques.

Findings

Some UDA strategies outperform direct application of trained classifiers.

Negative transfer occurs when domains are too dissimilar.

Normalization significantly affects UDA performance.

Abstract

In this work, we investigate the application of existing unsupervised domain adaptation (UDA) approaches to the task of transferring knowledge between crop regions having different coffee patterns. Given a geographical region with fully mapped coffee plantations, we observe that this knowledge can be used to train a classifier and to map a new county with no need of samples indicated in the target region. Experimental results show that transferring knowledge via some UDA strategies performs better than just applying a classifier trained in a region to predict coffee crops in a new one. However, UDA methods may lead to negative transfer, which may indicate that domains are too different that transferring knowledge is not appropriate. We also verify that normalization affect significantly some UDA methods; we observe a meaningful complementary contribution between coffee crops data; and a visual behavior suggests an existent of a cluster of samples that are more likely to be drawn from a specific data.