TY - GEN
T1 - Pixel- and Patch-Wise Context-Aware Learning with CNN and GCN Collaboration for Hyperspectral Image Classification
AU - Wang, H.
AU - Gao, K.
AU - Zhang, X.
AU - Wang, J.
AU - Hu, Z.
AU - Yang, Z.
AU - Mao, Y.
AU - Liu, Y.
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Graph convolutional network (GCN) gains increasing attention in the hyperspectral image (HSI) classification by the ability to flexibly capture arbitrarily irregular objects. However, due to expensive computation, the graph construction is usually based on superpixel-wise nodes, which ignore the subtle pixel-wise features. In contrast, the convolution neural network (CNN) can mine pixel-wise spectral-spatial features but is limited to capturing local features in small square windows. In this paper, we design a new CNN and GCN collaborative network to simultaneously introduce pixel- and patch-wise contextual information. Concretely, we use the depthwise separable convolution to perform pixel-wise local feature extraction. To further mine the long-range contextual information between land covers, we concatenate a GCN. Finally, we further fuse the complementary features and decode them to obtain the classification map. Extensive experiments reveal that our method achieves competitive performance.
AB - Graph convolutional network (GCN) gains increasing attention in the hyperspectral image (HSI) classification by the ability to flexibly capture arbitrarily irregular objects. However, due to expensive computation, the graph construction is usually based on superpixel-wise nodes, which ignore the subtle pixel-wise features. In contrast, the convolution neural network (CNN) can mine pixel-wise spectral-spatial features but is limited to capturing local features in small square windows. In this paper, we design a new CNN and GCN collaborative network to simultaneously introduce pixel- and patch-wise contextual information. Concretely, we use the depthwise separable convolution to perform pixel-wise local feature extraction. To further mine the long-range contextual information between land covers, we concatenate a GCN. Finally, we further fuse the complementary features and decode them to obtain the classification map. Extensive experiments reveal that our method achieves competitive performance.
KW - CNN and GCN collaboration
KW - Hyperspectral image classification
KW - context-aware learning
KW - pixel- and patch-wise
UR - http://www.scopus.com/inward/record.url?scp=85178322826&partnerID=8YFLogxK
U2 - 10.1109/IGARSS52108.2023.10282995
DO - 10.1109/IGARSS52108.2023.10282995
M3 - Conference contribution
AN - SCOPUS:85178322826
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 7555
EP - 7558
BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Y2 - 16 July 2023 through 21 July 2023
ER -