A Novel Detector for Adaptive Detection of Weak and Small Ships in Compact Polarimetric SAR

Zhang, Linlin; Gao, Gui; Duan, Dingfeng; Zhang, Xi; Yao, Libo; Liu, Jia

doi:10.1109/jmass.2022.3204772

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One positive pair is generated by the data augmentation module accompanied with 2(N − 1) negative pairs. Then the 2N pairlabeled samples are encoded into an embedding space as latent features (3), which can also be called as SSRs in this paper.…”

Section: A Pre-training the Network With Contrastive Learningmentioning

confidence: 99%

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

Pei,

Su,

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Nowadays, the developed deep neural networks (DNN) have been widely applied to synthetic aperture radar (SAR) image interpretation, such as target classification and recognition, which can automatically learn high-level semantic features in data-driven and task-driven manners. For the supervised learning methods, abundant labeled samples are required to avoid the over-fitting of designed networks, which is usually difficult for SAR image applications. To address these issues, a novel two-stage algorithm based on contrastive learning (CL) is proposed for SAR image target classification. In the pretraining stage, to extract self-supervised representations (SSRs) from an unlabeled train set, a convolutional neural network (CNN)-based encoder is first pre-trained using a contrasting strategy. This encoder can convert SAR images into a discriminative embedding space. Meanwhile, the optimal encoder can be determined using a linear evaluation protocol, which can indirectly confirm the transferability of pre-learned SSRs to downstream tasks. Therefore, in the fine-tuning stage, a SAR target classifier can be adequately trained using a few labeled SSRs in a supervised manner, which benefits from the powerful pre-trained encoder. Numerical experiments are carried out on the shared MSTAR dataset to demonstrate that the model based on the proposed self-supervised feature learning algorithm is superior to the conventional supervised methods under labeled data constraints. In addition, knowledge transfer experiments are also conducted on the openSARship dataset, showing that the encoder pre-trained from the MSTAR dataset can support the classifier training with high efficiency and precision. These results demonstrate the excellent training convergence and classification performance of the proposed algorithm.

show abstract

Section: A Pre-training the Network With Contrastive Learningmentioning

confidence: 99%

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

Pei,

Su,

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…With the booming of deep learning, several advanced deep learning methods are being used for synthetic aperture radar (SAR) image detection [12][13][14] and classification [15][16][17][18][19][20][21][22][23][24]. For SAR image classification, some frameworks for few-shot learning [16][17][18] map SAR images to the embedding space, and then implement classification using distance metric in the embedding space.…”

Section: Introductionmentioning

confidence: 99%

CLISAR-Net: A Deformation-Robust ISAR Image Classification Network Using Contrastive Learning

Liu

Pei

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The inherent unknown deformations of inverse synthetic aperture radar (ISAR) images, such as translation, scaling, and rotation, pose great challenges to space target classification. To achieve high-precision classification for ISAR images, a deformation-robust ISAR image classification network using contrastive learning (CL), i.e., CLISAR-Net, is proposed for deformation ISAR image classification. Unlike traditional supervised learning methods, CLISAR-Net develops a new unsupervised pretraining phase, which means that the method uses a two-phase training strategy to achieve classification. In the unsupervised pretraining phase, combined with data augmentation, positive and negative sample pairs are constructed using unlabeled ISAR images, and then the encoder is trained to learn discriminative deep representations of deformation ISAR images by means of CL. In the fine-tuning phase, based on the deep representations obtained from pretraining, a classifier is fine-tuned using a small number of labeled ISAR images, and finally, the deformation ISAR image classification is realized. In the experimental analysis, CLISAR-Net achieves higher classification accuracy than supervised learning methods for unknown scaled, rotated, and combined deformations. It implies that CLISAR-Net learned more robust deep features of deformation ISAR images through CL, which ensures the performance of the subsequent classification.

show abstract

Precision Terrain Modeling Approach in Complex Mountainous Areas Based on Compact UAV Ka-InSAR Data

Liu

Li²,

Jing³

et al. 2023

IEEE J. Miniat. Air Space Syst.

View full text Add to dashboard Cite

A Novel Detector for Adaptive Detection of Weak and Small Ships in Compact Polarimetric SAR

Cited by 4 publications

References 18 publications

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

CLISAR-Net: A Deformation-Robust ISAR Image Classification Network Using Contrastive Learning

Precision Terrain Modeling Approach in Complex Mountainous Areas Based on Compact UAV Ka-InSAR Data

Contact Info

Product

Resources

About