Domain-invariant attention network for transfer learning between cross-scene hyperspectral images

Minchao Ye, Chenglong Wang, Zhihao Meng, Fengchao Xiong, Yuntao Qian

Abstract: A domain-invariant attention network (DIAN) is proposed to solve the cross-scene classification problem. The DIAN mainly contains two modules. (1) A feature-alignment CNN (FACNN) is applied to extrac...