Sijia Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sijia Chen has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Hanwen Yu
University of Electronic Science and Technology of China
3 shared publications - Anna Song
Tianjin Key Laboratory for Advanced Signal Processing, Civil Aviation University of China, Tianjin, China
2 shared publications - Lei Yang
Civil Aviation University of China
2 shared publications - Taoli Yang
School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Yan Yan
University of Electronic Science and Technology of China
2 shared publications - Changjun Zhao
School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China
1 shared publication
Latest Publications
- 26 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 5209015
A Physically Interpretable Neural Optimization Solver for InSAR Phase Unwrapping
Phase unwrapping (PU) is a fundamental yet ill-posed problem in interferometric synthetic aperture radar (In-SAR), where the measured wrapped phase must be converted into a continuous absolute phase field. Conventional path-following and optimization-based PU methods often suffer from degraded performance in areas with abrupt interferometric fringe change. Moreover, most weighted norm formulations are susceptible to numerical imbalance, while deep learning (DL)-based models often suffer from limited interpretability and physical consistency. To overcome these limitations, this paper proposes a physically interpretable neural optimization solver, termed adaptive neural iterative solver (ANISolver), for InSAR PU. First, a geometric tessellation regularization (GTR) is introduced to represent the topographic surface as locally planar patches, encouraging differentiability of the phase surface. Second, an adaptive reweighted fidelity (ARF) mechanism is developed to stabilize numerical imbalance in traditional weighted norm optimization and to dynamically adjust fidelity weights based on phase gradient field. Third, an artificial intelligence (AI)-based interpretable optimization solver is designed, where an untrained convolutional neural network (UCNN) acts as a physics-guided optimizer integrated with a fast approximate conjugate gradient (FA-CG) algorithm, enabling efficient computation without the need for training data. Both theoretical analysis and experimental validation demonstrate the efficacy and efficiency of the proposed method.
- 26 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 5209015
A Physically Interpretable Neural Optimization Solver for InSAR Phase Unwrapping
Phase unwrapping (PU) is a fundamental yet ill-posed problem in interferometric synthetic aperture radar (In-SAR), where the measured wrapped phase must be converted into a continuous absolute phase field. Conventional path-following and optimization-based PU methods often suffer from degraded performance in areas with abrupt interferometric fringe change. Moreover, most weighted norm formulations are susceptible to numerical imbalance, while deep learning (DL)-based models often suffer from limited interpretability and physical consistency. To overcome these limitations, this paper proposes a physically interpretable neural optimization solver, termed adaptive neural iterative solver (ANISolver), for InSAR PU. First, a geometric tessellation regularization (GTR) is introduced to represent the topographic surface as locally planar patches, encouraging differentiability of the phase surface. Second, an adaptive reweighted fidelity (ARF) mechanism is developed to stabilize numerical imbalance in traditional weighted norm optimization and to dynamically adjust fidelity weights based on phase gradient field. Third, an artificial intelligence (AI)-based interpretable optimization solver is designed, where an untrained convolutional neural network (UCNN) acts as a physics-guided optimizer integrated with a fast approximate conjugate gradient (FA-CG) algorithm, enabling efficient computation without the need for training data. Both theoretical analysis and experimental validation demonstrate the efficacy and efficiency of the proposed method.
- 18 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- Vol. 14 (1) , 446-452
From Panda Land to Global GRSS: The 2025 Multidimensional Growth of the IEEE GRSS Student Branch Chapter at UESTC [Chapters]
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
- 18 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- Vol. 14 (1) , 446-452
From Panda Land to Global GRSS: The 2025 Multidimensional Growth of the IEEE GRSS Student Branch Chapter at UESTC [Chapters]
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
- 27 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-17
MAFNet: Deep Merged Autofocusing Network for SAR Recognition Under Defocused and Noised Dataset
Airborne synthetic aperture radar (SAR) imagery is susceptible to non-systematic motion errors, which will definitely defocus the target image and degrade the recognition accordingly. Representations learned from conventional convolutional neural networks (CNNs) do not emphasize much about the intrinsic features of the data distribution, which collapses the purposefulness of feature extraction. To this end, a deep Merged Auto-Focusing Network (MAFNet) is proposed for adaptively removing the defocusing effect from the input SAR data used for target recognition. Specifically, we propose an end-to-end architecture consisting of one focusing module and one recognition module. The focusing module contains a U-shaped sub-network based on the cross convolution to ensure the phase history coherence of the extracted features, and a deep unfolding method is devised to improve the mathematical generalization of focusing and sparse features so as to enhance the purposefulness of feature extraction. In particular, a compact surrogate function is designed for the non-convex feature quantization problem in the focusing module, which leads to closed-form solutions. The recognition module simply consists of a classifier. By building a multivariate loss function consisting of a cross-entropy loss function and a novel focusing loss function, MAFNet achieves accurate target recognition even when the input data is contaminated by non-systematic phase errors and additive noises. MSTAR data set is utilized to validate the effectiveness of MAFNet, and comparisons with conventional algorithms are performed to demonstrate the superiority of the proposed network.
- 27 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-17
MAFNet: Deep Merged Autofocusing Network for SAR Recognition Under Defocused and Noised Dataset
Airborne synthetic aperture radar (SAR) imagery is susceptible to non-systematic motion errors, which will definitely defocus the target image and degrade the recognition accordingly. Representations learned from conventional convolutional neural networks (CNNs) do not emphasize much about the intrinsic features of the data distribution, which collapses the purposefulness of feature extraction. To this end, a deep Merged Auto-Focusing Network (MAFNet) is proposed for adaptively removing the defocusing effect from the input SAR data used for target recognition. Specifically, we propose an end-to-end architecture consisting of one focusing module and one recognition module. The focusing module contains a U-shaped sub-network based on the cross convolution to ensure the phase history coherence of the extracted features, and a deep unfolding method is devised to improve the mathematical generalization of focusing and sparse features so as to enhance the purposefulness of feature extraction. In particular, a compact surrogate function is designed for the non-convex feature quantization problem in the focusing module, which leads to closed-form solutions. The recognition module simply consists of a classifier. By building a multivariate loss function consisting of a cross-entropy loss function and a novel focusing loss function, MAFNet achieves accurate target recognition even when the input data is contaminated by non-systematic phase errors and additive noises. MSTAR data set is utilized to validate the effectiveness of MAFNet, and comparisons with conventional algorithms are performed to demonstrate the superiority of the proposed network.
- Open Access
- 25 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 10162-10174
Enhanced SAR Imagery by Autoblocking Approach Using Morphology Amoeba in ADMM Manner
For conventional structure-guaranteed Synthetic Aperture Radar (SAR) imagery problems, some of them are modeled as ℓ 1 /ℓ 2 mixed norm regularization, and some are modeled as a group of least absolute shrinkage and selection operator (GLasso). However, due to the inflexible prior based on the Euclidean distance blocking, the target of interests and the background noise are easily attributed into the same block, which will consequently be retained or removed simultaneously. Therefore, it is difficult to distinguish the target with rich structures in a complicated environment. In this paper, to realize the elaborated structure feature enhancement of interested targets in the echoed SAR data, a novel Morphological AutoBlocking-Alternating Direction Method of Multipliers (MAB-ADMM) SAR imaging algorithm is proposed with a hybrid Frobenius and morphology ℓ F /ℓ M norm regularization. To realize the flexible blocking, an auto-blocking mechanism is constructed by Spatially-Variant Morphological Amoeba (SVMA) in the ℓ F /ℓ M mixed norm. In the auto-blocking mechanism, the geodesic distance of SVMA is utilized to accurately and flexibly fit the target structure and guarantee the elaborated structure. Moreover, in the proposed MAB-ADMM algorithm, the flexibly blocking structure feature and intra-block sparse feature are jointly optimized by the ℓ F /ℓ M and ℓ 1 norm. In the experiments, both simulated and raw SAR data collected by an airborne SAR are applied to qualitatively evaluate the proposed algorithm. Comparisons with conventional methods are carried out to reveal the superiority of the proposed algorithm. Moreover, the phase transition diagram (PTD) is shown to verify the proposed algorithm in terms of quantitative aspects.
- 25 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 10162-10174
Open AccessEnhanced SAR Imagery by Autoblocking Approach Using Morphology Amoeba in ADMM Manner
For conventional structure-guaranteed Synthetic Aperture Radar (SAR) imagery problems, some of them are modeled as ℓ 1 /ℓ 2 mixed norm regularization, and some are modeled as a group of least absolute shrinkage and selection operator (GLasso). However, due to the inflexible prior based on the Euclidean distance blocking, the target of interests and the background noise are easily attributed into the same block, which will consequently be retained or removed simultaneously. Therefore, it is difficult to distinguish the target with rich structures in a complicated environment. In this paper, to realize the elaborated structure feature enhancement of interested targets in the echoed SAR data, a novel Morphological AutoBlocking-Alternating Direction Method of Multipliers (MAB-ADMM) SAR imaging algorithm is proposed with a hybrid Frobenius and morphology ℓ F /ℓ M norm regularization. To realize the flexible blocking, an auto-blocking mechanism is constructed by Spatially-Variant Morphological Amoeba (SVMA) in the ℓ F /ℓ M mixed norm. In the auto-blocking mechanism, the geodesic distance of SVMA is utilized to accurately and flexibly fit the target structure and guarantee the elaborated structure. Moreover, in the proposed MAB-ADMM algorithm, the flexibly blocking structure feature and intra-block sparse feature are jointly optimized by the ℓ F /ℓ M and ℓ 1 norm. In the experiments, both simulated and raw SAR data collected by an airborne SAR are applied to qualitatively evaluate the proposed algorithm. Comparisons with conventional methods are carried out to reveal the superiority of the proposed algorithm. Moreover, the phase transition diagram (PTD) is shown to verify the proposed algorithm in terms of quantitative aspects.