The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 1329–1335, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1329-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 1329–1335, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1329-2020

  14 Aug 2020

14 Aug 2020

NEIGHBOUR-BASED DOMAIN ADAPTATION FOR INVESTIGATION OF TRANSFERABLE ABILITY OF PREVIOUSLY LABELED DATA FOR LAND-COVER CLASSIFICATION OF AERIAL IMAGES

R. Zhu and L. Yan R. Zhu and L. Yan
  • School of Geodesy and Geomatics, Wuhan Univeristy, China

Keywords: domain adaptation, reliable target pseudo-labelled data, select source labelled data, augment the training dataset

Abstract. Existing land-cover classification methods are usually based on adequate labelled data. But annotating enough training samples is hard and time-consuming. Therefore, we need to investigate how existing labelled data can help to increase land-cover classification. Source labelled data are proposed to be selected by calculating the target center of reliable target pseudo-labelled data for each class in this paper. Then we augment the training dataset with reliable target pesudo-labeled data and selected source labelled data to improve the quality and quantity of training dataset. We also investigate the amount of source labelled data that should be selected and the number of limited target labelled data that can produce good transfer learning performance. The UC Merced dataset is employed as the target dataset to evaluate the proposed approach while the NWPU-RESISC45 dataset is considered as the source labelled data. The experimental results show that selected source labelled data and reliable target pesudo-labeled data may improve the land-cover classification performance if selected source labelled data and reliable target pesudo-labeled data are augmented with the limited target labelled data respectively.