An assessment of data-centric methods for label noise identification in remote sensing data sets
2026-03-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors looked at how mistakes in labels affect deep learning in remote sensing, a field where this problem hasn’t been studied much. They tested three methods that try to find and fix wrong labels on two data sets with different amounts and types of noise added. Their study showed these methods can both spot incorrect labels and improve the model’s performance. They also explain which method works best depending on the situation and point out where more research is needed to better apply these methods in real remote sensing tasks.
label noisedeep learningremote sensingdata-centric methodslabel noise identificationbenchmark data setsnoise levelstask performancenoise filteringmachine learning
Authors
Felix Kröber, Genc Hoxha, Ribana Roscher
Abstract
Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models. In the field of remote sensing, however, automated treatment of label noise in data sets has received little attention to date. In particular, there is a lack of systematic analysis of the performance of data-centric methods that not only cope with label noise but also explicitly identify and isolate noisy labels. In this paper, we examine three such methods and evaluate their behavior under different label noise assumptions. To do this, we inject different types of label noise with noise levels ranging from 10 to 70% into two benchmark data sets, followed by an analysis of how well the selected methods filter the label noise and how this affects task performances. With our analyses, we clearly prove the value of data-centric methods for both parts - label noise identification and task performance improvements. Our analyses provide insights into which method is the best choice depending on the setting and objective. Finally, we show in which areas there is still a need for research in the transfer of data-centric label noise methods to remote sensing data. As such, our work is a step forward in bridging the methodological establishment of data-centric label noise methods and their usage in practical settings in the remote sensing domain.