Hybrid Dense Network With Attention Mechanism for Hyperspectral Image Classification

Abstract

The nonlinear relation between the spectral information and the corresponding objects (complex physiognomies) makes pixelwise classification challenging for conventional methods. To deal with nonlinearity issues in hyperspectral image classification (HSIC), convolutional neural networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution of different kernel size networks may overcome this problem by capturing more discriminating and relevant information. In light of this, the proposed solution aims at combining the core idea of 3-D and 2-D inception net with the attention mechanism to boost the HSIC CNN performance in a hybrid scenario. The resulting attention-fused hybrid network (AfNet) is based on three attention-fused parallel hybrid subnets with different kernels in each block repeatedly using high-level features to enhance the final ground-truth maps. In short, AfNet is able to selectively filter out the discriminative features critical for classification. Several tests on HSI datasets provided competitive results for AfNet compared to state-of-the-art models.