HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON CO-LEARNING THROUGH DUAL-ARCHITECTURE ENSEMBLE

Hyperspectral image classification is a classic topic aiming to assign the category label of each pixel in hyperspectral images. Some deep learning methods have been introduced and achieved good results, such as the CNN-based architecture, which focuses on local and hierarchical feature extraction to obtain visual information from shallow to deep. Recently, Transformer has been applied to the visual field and also used in the hyperspectral image classification task. Some work applied Transformer to process the spectral information but cannot achieve good results. To optimize the results, a new strategy called co-learning is proposed through a dual-architecture ensemble. The samples selected by the dual-architecture network are iteratively added to increase more reliable training samples. CNN and Transformer use completely different methods to extract features from different views and have great diversity. Experimental results show that this method is better than the algorithm using only a single network.