高光谱成像
判别式
人工智能
计算机科学
模式识别(心理学)
卷积神经网络
核(代数)
空间分析
数学
组合数学
统计
作者
Swalpa Kumar Roy,Suvojit Manna,Tiecheng Song,Lorenzo Bruzzone
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2020-12-24
卷期号:59 (9): 7831-7843
被引量:304
标识
DOI:10.1109/tgrs.2020.3043267
摘要
Hyperspectral images (HSIs) provide rich spectral-spatial information with stacked hundreds of contiguous narrowbands. Due to the existence of noise and band correlation, the selection of informative spectral-spatial kernel features poses a challenge. This is often addressed by using convolutional neural networks (CNNs) with receptive field (RF) having fixed sizes. However, these solutions cannot enable neurons to effectively adjust RF sizes and cross-channel dependencies when forward and backward propagations are used to optimize the network. In this article, we present an attention-based adaptive spectral-spatial kernel improved residual network (A 2 S 2 K-ResNet) with spectral attention to capture discriminative spectral-spatial features for HSI classification in an end-to-end training fashion. In particular, the proposed network learns selective 3-D convolutional kernels to jointly extract spectral-spatial features using improved 3-D ResBlocks and adopts an efficient feature recalibration (EFR) mechanism to boost the classification performance. Extensive experiments are performed on three well-known hyperspectral data sets, i.e., IP, KSC, and UP, and the proposed A 2 S 2 K-ResNet can provide better classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa compared with the existing methods investigated. The source code will be made available at https://github.com/suvojit- 0×55aa/A2S2K-ResNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI