Chen Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chen Yang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Shuyuan Yang
Xidian University
8 shared publications - Zhixi Feng
Xidian University
4 shared publications Huiling Liu
School of Artificial Intelligence, Xidian University, Xian, China
2 shared publicationsJie Sun
2 shared publications- Junxiao Wang
PetroChina Changqing Oilfield Company, Xian, Shaanxi, China
2 shared publications - Min Wang
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China
2 shared publications
Latest Publications
- 7 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
A consistency regularization training method for automatic modulation classification under incomplete information
- 7 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
A consistency regularization training method for automatic modulation classification under incomplete information
- 3 October 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Progressive cross-validation learning for signal classification with noisy labels
- 3 October 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Progressive cross-validation learning for signal classification with noisy labels
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 657-669
Negative Class Guided Spatial Consistency Network for Sparsely Supervised Semantic Segmentation of Remote Sensing Images
Deep neural networks (DNNs) have been successfully applied in the remote sensing semantic segmentation. However, training DNNs requires a large number of densely labeled samples, which is laborious and time-consuming. Sparsely supervised semantic segmentation (SSSS) can train deep segmentation networks using only sparse annotations. In this paper, we propose a negative class guided spatial consistency network (NCG-SCNet) for semantic segmentation with sparse annotations. Specifically, we introduce a spatial consistency enhancement module (SCEM) to enhance network features by non-linearly combining spatially similar features. Thus, it could provide better representations of the boundaries and the shape of the target. Additionally, a channel compression module (CCM) is proposed to reduce channel redundancy while preserving the network’s feature extraction capability. A negative class guided loss function (NCG Loss) is constructed to provide extra supervisory information, where the negative classes are defined as the classes with lower probability in the prediction. Extensive experiments on two widely used remote sensing datasets show that the proposed NCG-SCNet outperforms the comparison methods.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 657-669
Negative Class Guided Spatial Consistency Network for Sparsely Supervised Semantic Segmentation of Remote Sensing Images
Deep neural networks (DNNs) have been successfully applied in the remote sensing semantic segmentation. However, training DNNs requires a large number of densely labeled samples, which is laborious and time-consuming. Sparsely supervised semantic segmentation (SSSS) can train deep segmentation networks using only sparse annotations. In this paper, we propose a negative class guided spatial consistency network (NCG-SCNet) for semantic segmentation with sparse annotations. Specifically, we introduce a spatial consistency enhancement module (SCEM) to enhance network features by non-linearly combining spatially similar features. Thus, it could provide better representations of the boundaries and the shape of the target. Additionally, a channel compression module (CCM) is proposed to reduce channel redundancy while preserving the network’s feature extraction capability. A negative class guided loss function (NCG Loss) is constructed to provide extra supervisory information, where the negative classes are defined as the classes with lower probability in the prediction. Extensive experiments on two widely used remote sensing datasets show that the proposed NCG-SCNet outperforms the comparison methods.
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (5) , 8853-8866
Open-ICL: Open-Set Modulation Classification via Incremental Contrastive Learning
Open-set modulation classification (OMC) of signals is a challenging task for handling “unknown” modulation types that are not included in the training dataset. This article proposes an incremental contrastive learning method for OMC, called Open-ICL, to accurately identify unknown modulation types of signals. First, a dual-path 1-D network (DONet) with a classification path (CLP) and a contrast path (COP) is designed to learn discriminative signal features cooperatively. In the COP, the deep features of the input signal are compared with the semantic feature centers (SFCs) of known classes calculated from the network, to infer its signal novelty. An unknown signal bank (USB) is defined to store unknown signals, and a novel moving intersection algorithm (MIA) is proposed to dynamically select reliable unknown signals for the USB. The “unknown” instances, together with SFCs, are continuously optimized and updated, facilitating the process of incremental learning. Furthermore, a dynamic adaptive threshold (DAT) strategy is proposed to enable Open-ICL to adaptively learn changing signal distributions. Extensive experiments are performed on two benchmark datasets, and the results demonstrate the effectiveness of Open-ICL for OMC.
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (5) , 8853-8866
Open-ICL: Open-Set Modulation Classification via Incremental Contrastive Learning
Open-set modulation classification (OMC) of signals is a challenging task for handling “unknown” modulation types that are not included in the training dataset. This article proposes an incremental contrastive learning method for OMC, called Open-ICL, to accurately identify unknown modulation types of signals. First, a dual-path 1-D network (DONet) with a classification path (CLP) and a contrast path (COP) is designed to learn discriminative signal features cooperatively. In the COP, the deep features of the input signal are compared with the semantic feature centers (SFCs) of known classes calculated from the network, to infer its signal novelty. An unknown signal bank (USB) is defined to store unknown signals, and a novel moving intersection algorithm (MIA) is proposed to dynamically select reliable unknown signals for the USB. The “unknown” instances, together with SFCs, are continuously optimized and updated, facilitating the process of incremental learning. Furthermore, a dynamic adaptive threshold (DAT) strategy is proposed to enable Open-ICL to adaptively learn changing signal distributions. Extensive experiments are performed on two benchmark datasets, and the results demonstrate the effectiveness of Open-ICL for OMC.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (10) , 18281-18291
Open-Set Radar Emitter Recognition via Deep Metric Autoencoder
In the non-cooperative electromagnetic environment, new radar emitters will emerge unexpectedly during the test phase, which brings the “Open-Set” Radar Emitter Recognition (OS-RER). Conventional classifiers cannot identify new radar emitters that do not exist in the training dataset. Therefore, in this paper, a novel Deep Metric Auto-Encoder (DMAE) is proposed for OS-RER. In DMAE, deep metric learning learns new non-linear mappings in the metric space to measure the similarity between instances. The dual-path deep auto-encoder is designed to reduce the open space risk by learning a low-dimensional manifold and a discriminative representation of known instances. Specifically, DMAE models known classes, and measures class belongingness through the reconstruction error of the AE and the entropy of the classifier. The deep metric network learns a more precise distance metric by minimizing the distance between the known class instances and the corresponding reconstruction. To accurately detect unknown instances, the classifier and the deep metric network are used together to preliminarily detect unknown instances. Finally, the detected unknown instances are used to further train the classifier to recognize the radar emitter in the open-set scenarios. The DMAE learns the discriminative representation through end-to-end learning. Extensive experiments conducted on real radar datasets and simulated radar datasets show that DMAE can identify unknown emitters and significantly outperforms existing open-set classification methods.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (10) , 18281-18291
Open-Set Radar Emitter Recognition via Deep Metric Autoencoder
In the non-cooperative electromagnetic environment, new radar emitters will emerge unexpectedly during the test phase, which brings the “Open-Set” Radar Emitter Recognition (OS-RER). Conventional classifiers cannot identify new radar emitters that do not exist in the training dataset. Therefore, in this paper, a novel Deep Metric Auto-Encoder (DMAE) is proposed for OS-RER. In DMAE, deep metric learning learns new non-linear mappings in the metric space to measure the similarity between instances. The dual-path deep auto-encoder is designed to reduce the open space risk by learning a low-dimensional manifold and a discriminative representation of known instances. Specifically, DMAE models known classes, and measures class belongingness through the reconstruction error of the AE and the entropy of the classifier. The deep metric network learns a more precise distance metric by minimizing the distance between the known class instances and the corresponding reconstruction. To accurately detect unknown instances, the classifier and the deep metric network are used together to preliminarily detect unknown instances. Finally, the detected unknown instances are used to further train the classifier to recognize the radar emitter in the open-set scenarios. The DMAE learns the discriminative representation through end-to-end learning. Extensive experiments conducted on real radar datasets and simulated radar datasets show that DMAE can identify unknown emitters and significantly outperforms existing open-set classification methods.
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (1) , 252-263
Deep Contrastive Clustering for Signal Deinterleaving
In the complex electromagnetic environment, radar signal deinterleaving (RSD) is a challenging task. In this paper, a deep contrastive clustering algorithm (DCCA) is advanced in a new self-supervised paradigm, for accurate RSD without any prior information of radar emitters. First, a contrastive self-supervised deep attention network (CSDAN) is constructed to learn signal representations, by using self-defined pseudo-labels of augmented signals as supervision. We use CSDAN to learn the differences between different radiation source data and generate deep features suitable for clustering. Three metrics are then used to automatically determine the number of clusters for the subsequent clustering. Extensive experiments are performed on several datasets containing different numbers of emitters. The results show that the proposed DCCA can accurately determine the number of emitters and deinterleave radar pulses. Furthermore, CSDAN can extract discriminative features of emitters with low intra-class similarity and high inter-class similarity
- 9 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (1) , 252-263
Deep Contrastive Clustering for Signal Deinterleaving
In the complex electromagnetic environment, radar signal deinterleaving (RSD) is a challenging task. In this paper, a deep contrastive clustering algorithm (DCCA) is advanced in a new self-supervised paradigm, for accurate RSD without any prior information of radar emitters. First, a contrastive self-supervised deep attention network (CSDAN) is constructed to learn signal representations, by using self-defined pseudo-labels of augmented signals as supervision. We use CSDAN to learn the differences between different radiation source data and generate deep features suitable for clustering. Three metrics are then used to automatically determine the number of clusters for the subsequent clustering. Extensive experiments are performed on several datasets containing different numbers of emitters. The results show that the proposed DCCA can accurately determine the number of emitters and deinterleave radar pulses. Furthermore, CSDAN can extract discriminative features of emitters with low intra-class similarity and high inter-class similarity
- 28 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-8
Quadruplet Convolution Neural Network With C3 Loss (C3-QCNN) for Signal Classification
In this letter, a new Quadruplet Convolution Neural Network (QCNN) is proposed to cooperatively and contrastively learn deep features of raw radio signals for accurate Automatic Modulation Classification (AMC), when very few labeled samples are available. Four convolutional channels with shared weights are constructed to deal with the In-phase (I) path and Quadrature (Q) path of signals. Moreover, a new C3-loss function that contains the cooperative loss, contrastive loss and classification loss, is designed for QCNN to extract discriminative and concise features of signals. Some experiments are taken on the public dataset generated with GNU Radio, which has eleven types of modulation signals with different signal-to-noise ratios. The experimental results show that C3-QCNN achieves high classification accuracy and outperform its counterparts.
- 28 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-8
Quadruplet Convolution Neural Network With C3 Loss (C3-QCNN) for Signal Classification
In this letter, a new Quadruplet Convolution Neural Network (QCNN) is proposed to cooperatively and contrastively learn deep features of raw radio signals for accurate Automatic Modulation Classification (AMC), when very few labeled samples are available. Four convolutional channels with shared weights are constructed to deal with the In-phase (I) path and Quadrature (Q) path of signals. Moreover, a new C3-loss function that contains the cooperative loss, contrastive loss and classification loss, is designed for QCNN to extract discriminative and concise features of signals. Some experiments are taken on the public dataset generated with GNU Radio, which has eleven types of modulation signals with different signal-to-noise ratios. The experimental results show that C3-QCNN achieves high classification accuracy and outperform its counterparts.
- Open Access
- 30 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 181744-181750
Separable Attention Capsule Network for Signal Classification
In this paper, a new Separable Attention Capsule Network (SACN) is proposed for signal classification. SACN is a light-weight network composed of multi-channel separable convolution layer, attention module and classification layer. First, depth-wise convolution is employed to extract features of signals in a low-complexity manner, and the multi-channel network structure is designed to increase the network width to improve the diversity of features of signals. Then a channel attention module is followed by a capsule network whose element contains a group of neurons. This attention module can explore the interdependence among channels to use global information to selectively strengthen some important channels, thus achieving the improvement of generalization ability of SACN. Some experiments are taken on several datasets with communication and radar signals, and the comparison results prove the efficiency of SACN and the superiority to its counterparts.
- 30 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 181744-181750
Open AccessSeparable Attention Capsule Network for Signal Classification
In this paper, a new Separable Attention Capsule Network (SACN) is proposed for signal classification. SACN is a light-weight network composed of multi-channel separable convolution layer, attention module and classification layer. First, depth-wise convolution is employed to extract features of signals in a low-complexity manner, and the multi-channel network structure is designed to increase the network width to improve the diversity of features of signals. Then a channel attention module is followed by a capsule network whose element contains a group of neurons. This attention module can explore the interdependence among channels to use global information to selectively strengthen some important channels, thus achieving the improvement of generalization ability of SACN. Some experiments are taken on several datasets with communication and radar signals, and the comparison results prove the efficiency of SACN and the superiority to its counterparts.