NAS-Guided Lightweight Multiscale Attention Fusion Network for Hyperspectral Image Classification
NAS-Guided Lightweight Multiscale Attention Fusion Network for Hyperspectral Image Classification
复制标题
NAS 引导的轻量级多尺度注意力融合网络用于高光谱图像分类
DOI：
10.1109/tgrs.2021.3049377
复制
发表时间：
2021-10-01
影响因子：
8.2
通讯作者：
Jiao, Licheng
中科院分区：
文献类型：
--
作者：
Wang, Jianing;Huang, Runhu;Jiao, Licheng
深度学习已成为高光谱图像分类研究领域的热点。然而，随着深度学习方法的深度和规模不断增加，其在移动的和嵌入式视觉应用中的应用带来了巨大的挑战。在这篇文章中，我们解决了一个网络架构搜索（NAS）引导的轻量级频谱空间注意力特征融合网络（LMAFN）的HSI分类。该网络的整体架构由NAS的几个结论指导，通过利用多尺度Ghost分组与高效信道注意力（ECA）模块自适应调整不同信道的权重，实现更少的参数和更低的计算成本与更深的网络结构。该方法有助于充分提取谱-空鉴别特征，避免降维操作的信息损失。具体来说，提出了一种多层特征融合方法，通过考虑不同层次结构的互补信息，提取每层谱空特征的融合信息。因此，随着图层的增加和图层间的融合，高等级的光谱-空间属性沿着被逐步开发。在3个真实的HSI数据集上的实验验证表明，该框架具有更深的网络结构和更小的参数大小，具有更好的分类性能和效率。
Deep learning (DL) has become a hot topic in the research field of hyperspectral image (HSI) classification. However, with increasing depth and size of deep learning methods, its application in mobile and embedded vision applications has brought great challenges. In this article, we address a network architecture search (NAS)-guided lightweight spectral–spatial attention feature fusion network (LMAFN) for HSI classification. The overall architecture of the proposed network is guided by several conclusions of NAS, which achieves fewer parameters and lower computation cost with deeper network structure by exploiting multiscale Ghost grouped with efficient channel attention (ECA) module for adaptively adjusting the weights of different channels. It helps fully extract spectral–spatial discriminant features to avoid information loss of the dimension reduction operation. Specifically, a multilayer feature fusion method is proposed to extract the fusion information of the spectral–spatial features of each layer by considering complementary information of different hierarchical structures. Therefore, high-lever spectral–spatial attributes are gradually exploited along with the increase in layers and the fusion of layers. The experimental verification on three real HSI data sets demonstrates that the proposed framework presents more satisfying classification performance and efficiency with deeper network structure and lower parameter size.