loading page

Contrastive Learning approach for blind Hyperspectral Unmixing (CLHU)
  • +7
  • Abian Hernandez-Guedes ,
  • Ryodai Fukushima ,
  • Toshihiro Takamatsu ,
  • Himar Fabelo ,
  • samuel ortega ,
  • Nobuyoshi Takeshita ,
  • Hiro Hasegawa ,
  • Juan Ruiz-Alzola ,
  • Hiroshi Takemura ,
  • Gustavo M. Callico
Abian Hernandez-Guedes
University of Las Palmas de Gran Canaria

Corresponding Author:[email protected]

Author Profile
Ryodai Fukushima
Author Profile
Toshihiro Takamatsu
Author Profile
Himar Fabelo
Author Profile
samuel ortega
Author Profile
Nobuyoshi Takeshita
Author Profile
Hiro Hasegawa
Author Profile
Juan Ruiz-Alzola
Author Profile
Hiroshi Takemura
Author Profile
Gustavo M. Callico
Author Profile

Abstract

The Contrastive Learning for blind Hyperspectral Unmixing (CLHU) is a self-supervised deep learning approach for blind hyperspectral unmixing by jointly estimating the endmembers and fractional abundances. Unlike existing deep learning methods that rely on reconstruction capabilities, CLHU leverages the input-endmembers relationship for abundance estimation. Extensive experiments demonstrate CLHU’s effectiveness, achieving state-of-the-art performance in hyperspectral unmixing.  Furthermore, the experimental findings indicate that endmember interactions are considered during the estimation process by the proposed method, particularly in non-linear problem contexts. This novel approach offers a promising perspective for the field and holds potential for further enhancements in hyperspectral unmixing tasks.
27 Feb 2024Submitted to TechRxiv
04 Mar 2024Published in TechRxiv