TY - JOUR
T1 - Rotation awareness based self-supervised learning for SAR target recognition with limited training samples
AU - Wen, Zaidao
AU - Liu, Zhunga
AU - Zhang, Shuai
AU - Pan, Quan
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - The scattering signatures of a synthetic aperture radar (SAR) target image will be highly sensitive to different azimuth angles/poses, which aggravates the demand for training samples in learning-based SAR image automatic target recognition (ATR) algorithms, and makes SAR ATR a more challenging task. This paper develops a novel rotation awareness-based learning framework termed RotANet for SAR ATR under the condition of limited training samples. First, we propose an encoding scheme to characterize the rotational pattern of pose variations among intra-class targets. These targets will constitute several ordered sequences with different rotational patterns via permutations. By further exploiting the intrinsic relation constraints among these sequences as the supervision, we develop a novel self-supervised task which makes RotANet learn to predict the rotational pattern of a baseline sequence and then autonomously generalize this ability to the others without external supervision. Therefore, this task essentially contains a learning and self-validation process to achieve human-like rotation awareness, and it serves as a task-induced prior to regularize the learned feature domain of RotANet in conjunction with an individual target recognition task to improve the generalization ability of the features. Extensive experiments on moving and stationary target acquisition and recognition benchmark database demonstrate the effectiveness of our proposed framework. Compared with other state-of-the-art SAR ATR algorithms, RotANet will remarkably improve the recognition accuracy especially in the case of very limited training samples without performing any other data augmentation strategy.
AB - The scattering signatures of a synthetic aperture radar (SAR) target image will be highly sensitive to different azimuth angles/poses, which aggravates the demand for training samples in learning-based SAR image automatic target recognition (ATR) algorithms, and makes SAR ATR a more challenging task. This paper develops a novel rotation awareness-based learning framework termed RotANet for SAR ATR under the condition of limited training samples. First, we propose an encoding scheme to characterize the rotational pattern of pose variations among intra-class targets. These targets will constitute several ordered sequences with different rotational patterns via permutations. By further exploiting the intrinsic relation constraints among these sequences as the supervision, we develop a novel self-supervised task which makes RotANet learn to predict the rotational pattern of a baseline sequence and then autonomously generalize this ability to the others without external supervision. Therefore, this task essentially contains a learning and self-validation process to achieve human-like rotation awareness, and it serves as a task-induced prior to regularize the learned feature domain of RotANet in conjunction with an individual target recognition task to improve the generalization ability of the features. Extensive experiments on moving and stationary target acquisition and recognition benchmark database demonstrate the effectiveness of our proposed framework. Compared with other state-of-the-art SAR ATR algorithms, RotANet will remarkably improve the recognition accuracy especially in the case of very limited training samples without performing any other data augmentation strategy.
KW - Automatic target recognition
KW - Data augmentation
KW - Equivariant feature
KW - Limited training samples
KW - Rotation awareness
KW - Self-supervised learning
KW - Synthetic aperture radar
KW - Weakly supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85113261055&partnerID=8YFLogxK
U2 - 10.1109/TIP.2021.3104179
DO - 10.1109/TIP.2021.3104179
M3 - 文章
C2 - 34403341
AN - SCOPUS:85113261055
SN - 1057-7149
VL - 30
SP - 7266
EP - 7279
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
M1 - 9515580
ER -