Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume 59, Issue 11, Pages 9646-9660Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3046756
Keywords
Manifolds; Hyperspectral imaging; Support vector machines; Training; Task analysis; Learning systems; Correlation; Cross-scene; distribution alignment; domain adaption; hyperspectral image (HSI) classification; subspace alignment (SA)
Categories
Funding
- National Natural Science Foundation of China [61871177]
- Beijing Natural Science Foundation [JQ20021]
- National Natural Science Foundation of Guangdong [2018B030311046]
Ask authors/readers for more resources
The study introduces a new domain adaptive method, discriminative cooperative alignment (DCA) of subspace and distribution, to address the challenge of cross-scene HSI classification. Experimental results demonstrate that the DCA method significantly outperforms other domain-adaptive approaches.
Cross-scene classification is one of the major challenges for hyperspectral image (HSI) classification, especially for target scenes without label samples. Most traditional domain adaptive methods learn a domain invariant subspace to reduce statistical shift while ignoring the fact that there may not exist a shared subspace when marginal distributions of source and target domains are very different. In addition, it is important for HSI classification to preserve discriminant information in the original space. To solve this issue, discriminative cooperative alignment (DCA) of subspace and distribution is proposed to cooperatively reduce the geometric and statistical shift. In the proposed framework, both geometrical and statistical alignments are considered to learn subspaces of the two domains with preserving discrimination information. Furthermore, a reconstruction constraint is imposed to enhance the robustness of subspace projection. Experimental results on three cross-scene HSI data sets demonstrate that the proposed DCA is significantly better than some state-of-the-art domain-adaptive approaches.
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