Journal
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
Volume 19, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2021.3061726
Keywords
Oils; Vegetation; Feature extraction; Remote sensing; Training; Image reconstruction; Satellites; Deep learning; domain generalization (DG); multiple sources; oil palm; tree crown detection
Categories
Funding
- National Key Research and Development Plan of China [2017YFA0604500, 2017YFB0202204, 2017YFA0604401]
- National Natural Science Foundation of China [51761135015, U1839206]
- National Key Scientific and Technological Infrastructure Project Earth System Science Numerical Simulator Facility (EarthLab)
- Center for High Performance Computing and System Simulation, Pilot National Laboratory for Marine Science and Technology (Qingdao)
Ask authors/readers for more resources
Providing accurate and timely oil palm information is crucial for economic development and ecological significance. However, large-scale and cross-regional oil palm tree detection is challenging due to the variety and volume of data, as well as environmental heterogeneity. This study proposes a new multisource domain generalization method that achieves promising performance in unknown target domains.
Providing accurate and timely oil palm information on a large scale is essential for both economic development and ecological significance. However, owing to different sensors, photograph acquisition conditions, and environmental heterogeneity, the large volume and the variety of the data make it extremely challenging for large-scale and cross-regional oil palm tree detection. It is computationally expensive to train a model from images covering large heterogeneous regions and all environmental conditions for continuously accumulated multisource remote sensing data. In this letter, we propose a new multisource domain generalization (DG) method, Maximum Mean Discrepancy Deep Reconstruction Classification Network (MMD-DRCN). It learns representations from multiple source domains and obtains inspiring performance in an unknown and unseen target domain. Besides classification loss, our MMD-DRCN distills more representative features through reconstruction loss and aligns multisource latent features by MMD loss, both of which effectively enhance the capacity of generalization. MMD-DRCN achieves an average F1-score of 82.70% in all transfer tasks, attaining a 5.83% gain compared to Baseline (a straightforward convolutional neural network (CNN) model). Experimental results demonstrate DG poses a promising potential for large-scale and cross-regional oil palm tree detection without any information of the target domain.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available