TY - JOUR
T1 - Few-Shot Hyperspectral Image Classification Using Meta Learning and Regularized Finetuning
AU - Li, Wenmei
AU - Liu, Qing
AU - Zhang, Yu
AU - Wang, Yu
AU - Yuan, Yuan
AU - Jia, Yan
AU - He, Yuhong
N1 - Publisher Copyright:
© 1980-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - The use of deep learning (DL)-based hyperspectral image (HSI) classification has been made remarkable progress in recent years. However, obtaining sufficient labeled samples for training DL models remains a challenge. Transfer learning is effective in addressing the problem of HSI classification with limited labeled samples. However, cross-domain HSI classification using transfer learning remain difficult, as differences in ground object categories between two datasets make it challenging to transfer and learn accurate. To address this issue, we propose a simple yet effective method for HSI classification using model-agnostic meta-learning (MAML) and Regularized Fine-tuning (MRFSL). Our method uses optimized 3-D convolutional neural networks (3D-CNNs) model, aided by MAML and cutout data augmentation to enable cross-domain transfer learning and carry out the HSI classification with limited target samples. Experiments conducted on three HSI datasets demonstrate that the MRFSL method achieves excellent results compared to existing methods. Specifically, the overall accuracy (OA) of our proposed MRFSL method reached 91.81%, 71.04%, and 88.35%, when only five labeled samples for each category were randomly extracted from the Salinas, Indian Pines (IPs), and University of Pavia (UP) datasets, respectively.
AB - The use of deep learning (DL)-based hyperspectral image (HSI) classification has been made remarkable progress in recent years. However, obtaining sufficient labeled samples for training DL models remains a challenge. Transfer learning is effective in addressing the problem of HSI classification with limited labeled samples. However, cross-domain HSI classification using transfer learning remain difficult, as differences in ground object categories between two datasets make it challenging to transfer and learn accurate. To address this issue, we propose a simple yet effective method for HSI classification using model-agnostic meta-learning (MAML) and Regularized Fine-tuning (MRFSL). Our method uses optimized 3-D convolutional neural networks (3D-CNNs) model, aided by MAML and cutout data augmentation to enable cross-domain transfer learning and carry out the HSI classification with limited target samples. Experiments conducted on three HSI datasets demonstrate that the MRFSL method achieves excellent results compared to existing methods. Specifically, the overall accuracy (OA) of our proposed MRFSL method reached 91.81%, 71.04%, and 88.35%, when only five labeled samples for each category were randomly extracted from the Salinas, Indian Pines (IPs), and University of Pavia (UP) datasets, respectively.
KW - Cross-domain
KW - few-shot learning (FSL)
KW - hyperspectral image (HSI) classification
KW - meta-learning
KW - regularized finetuning
UR - http://www.scopus.com/inward/record.url?scp=85177082496&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2023.3328263
DO - 10.1109/TGRS.2023.3328263
M3 - 文章
AN - SCOPUS:85177082496
SN - 0196-2892
VL - 61
SP - 1
EP - 14
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
M1 - 5529514
ER -