Active learning on large hyperspectral datasets: a preprocessing method
| Autor: | R. Thoreau, V. Achard, L. Risser, B. Berthelot, X. Briottet |
|---|---|
| Přispěvatelé: | Magellium, ONERA / DOTA, Université de Toulouse [Toulouse], ONERA-PRES Université de Toulouse, Institut de Mathématiques de Toulouse UMR5219 (IMT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
APPRENTISSAGE AUTOMATIQUE
Hyperspectral imaging SEMANTIQUE SEGMENTATION SPECTROSCOPIE Large dataset Remote sensing ALGORITHME APPRENTISSAGE Semantics ACTIVE LEARNING [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] Machine learning Semantic Segmentation IMAGERIE HYPERSPECTRALE [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC] BASE DONNEES TELEDETECTION [SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces environment Learning algorithm Spectroscopy |
| Zdroj: | XXIV ISPRS Congress XXIV ISPRS Congress, Jun 2022, Nice, France. pp.435-442, ⟨10.5194/isprs-archives-XLIII-B3-2022-435-2022⟩ |
| DOI: | 10.5194/isprs-archives-XLIII-B3-2022-435-2022⟩ |
| Popis: | Machine learning algorithms demonstrated promising results for hyperspectral semantic segmentation. However, they strongly rely on the quality of training datasets. As far as the annotation of hyperspectral images is often expensive and time-consuming, only a few thousand pixels can be labeled. In this context, active learning algorithms select the most informative pixels to be labeled. In the machine learning community, recent active learning methods have overcome the performance of conventional algorithms but do not always scale to large remote sensing images. Therefore, we introduce in this paper a preprocessing method that allows the use of computationally intensive active learning algorithms without significant impacts on their effectiveness. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|