Qiangqiang Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiangqiang Shen has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Yongyong Chen
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
16 shared publications - Yongsheng Liang
College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China
10 shared publications - Hanzhang Wang
School of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China
4 shared publications - Tingting Xu
School of computer science and technology, Harbin Institute of Technology shenzhen, Shenzhen, China
3 shared publications Benteng Sun
2 shared publications- Guokai Zhang
School of Safety Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
2 shared publications
Latest Publications
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP  (10) , 1-13
Linearized Tensor Low-rank Convolutional Network
To balance deep learning performance and interpretability, convolutional sparse coding (CSC) has successfully incorporated differentiable optimization layers in place of the standard convolutional layers of traditional deep neural networks (DNN). However, CSC models prefer to fall into local sparsity under the â„“1-norm, whose optimization shows limitations in preserving the geometric structure and global sparsity of tensor data. In this paper, we propose a Linearized Tensor Low-Rank Convolutional Network (LTLRCNet) to refresh the differentiable optimization layers for DNN (e.g., ResNet and UNet), which instead optimizes the tensor low-rank minimization problem for global sparsity without ruining the intrinsic structure of data. Specifically, instead of simply replacing the â„“1-norm with a tensor low-rank regularizer, we first propose a linearized tensor lowrank representation (LTLRR) model optimized by a linearized alternating direction method to decouple the dictionary and code coefficient without introducing an auxiliary variable, whose convergence is proved theoretically. Subsequently, we extend the LTLRR model into a deep unfolding network, such as the LTLRCNet, by engineering a convolutional dictionary that functions as a differentiable optimization layer, effectively substituting the conventional convolutional layer. To match the deep unfolding framework and avoid the gradient explosion, we apply a rank-one tactic bearing the Frank-Wolfe algorithm to solve the tensor low-rank minimization problem instead of conducting the cumbersome full-rank tensor singular value decomposition. Experimental results on image classification and segmentation show the potential of our LTLRCNet with its modeling-based layers to maintain significant performance and interpretability.
- 21 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP  (10) , 1-13
Linearized Tensor Low-rank Convolutional Network
To balance deep learning performance and interpretability, convolutional sparse coding (CSC) has successfully incorporated differentiable optimization layers in place of the standard convolutional layers of traditional deep neural networks (DNN). However, CSC models prefer to fall into local sparsity under the â„“1-norm, whose optimization shows limitations in preserving the geometric structure and global sparsity of tensor data. In this paper, we propose a Linearized Tensor Low-Rank Convolutional Network (LTLRCNet) to refresh the differentiable optimization layers for DNN (e.g., ResNet and UNet), which instead optimizes the tensor low-rank minimization problem for global sparsity without ruining the intrinsic structure of data. Specifically, instead of simply replacing the â„“1-norm with a tensor low-rank regularizer, we first propose a linearized tensor lowrank representation (LTLRR) model optimized by a linearized alternating direction method to decouple the dictionary and code coefficient without introducing an auxiliary variable, whose convergence is proved theoretically. Subsequently, we extend the LTLRR model into a deep unfolding network, such as the LTLRCNet, by engineering a convolutional dictionary that functions as a differentiable optimization layer, effectively substituting the conventional convolutional layer. To match the deep unfolding framework and avoid the gradient explosion, we apply a rank-one tactic bearing the Frank-Wolfe algorithm to solve the tensor low-rank minimization problem instead of conducting the cumbersome full-rank tensor singular value decomposition. Experimental results on image classification and segmentation show the potential of our LTLRCNet with its modeling-based layers to maintain significant performance and interpretability.
- Open Access
Deep LoRA-Unfolding Networks for Image Restoration
Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging reconstruction, compressive sensing and super-resolution.It unfolds the iterative optimization steps into a stack of sequentially linked blocks.Each block consists of a Gradient Descent Module (GDM) and a Proximal Mapping Module (PMM) which is equivalent to a denoiser from a Bayesian perspective, operating on Gaussian noise with a known level.However, existing DUNs suffer from two critical limitations: (i) their PMMs share identical architectures and denoising objectives across stages, ignoring the need for stage-specific adaptation to varying noise levels; and (ii) their chain of structurally repetitive blocks results in severe parameter redundancy and high memory consumption, hindering deployment in large-scale or resource-constrained scenarios.To address these challenges, we introduce generalized Deep Low-rank Adaptation (LoRA) Unfolding Networks for image restoration, named LoRun, harmonizing denoising objectives and adapting different denoising levels between stages with compressed memory usage for more efficient DUN.LoRun introduces a novel paradigm where a single pretrained base denoiser is shared across all stages, while lightweight, stage-specific LoRA adapters are injected into the PMMs to dynamically modulate denoising behavior according to the noise level at each unfolding step.This design decouples the core restoration capability from task-specific adaptation, enabling precise control over denoising intensity without duplicating full network parameters and achieving up to $N$ times parameter reduction for an $N$-stage DUN with on-par or better performance.Extensive experiments conducted on three IR tasks validate the efficiency of our method.Open AccessDeep LoRA-Unfolding Networks for Image Restoration
Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging reconstruction, compressive sensing and super-resolution.It unfolds the iterative optimization steps into a stack of sequentially linked blocks.Each block consists of a Gradient Descent Module (GDM) and a Proximal Mapping Module (PMM) which is equivalent to a denoiser from a Bayesian perspective, operating on Gaussian noise with a known level.However, existing DUNs suffer from two critical limitations: (i) their PMMs share identical architectures and denoising objectives across stages, ignoring the need for stage-specific adaptation to varying noise levels; and (ii) their chain of structurally repetitive blocks results in severe parameter redundancy and high memory consumption, hindering deployment in large-scale or resource-constrained scenarios.To address these challenges, we introduce generalized Deep Low-rank Adaptation (LoRA) Unfolding Networks for image restoration, named LoRun, harmonizing denoising objectives and adapting different denoising levels between stages with compressed memory usage for more efficient DUN.LoRun introduces a novel paradigm where a single pretrained base denoiser is shared across all stages, while lightweight, stage-specific LoRA adapters are injected into the PMMs to dynamically modulate denoising behavior according to the noise level at each unfolding step.This design decouples the core restoration capability from task-specific adaptation, enabling precise control over denoising intensity without duplicating full network parameters and achieving up to $N$ times parameter reduction for an $N$-stage DUN with on-par or better performance.Extensive experiments conducted on three IR tasks validate the efficiency of our method. - 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 1858-1869
Deep LoRA-Unfolding Networks for Image Restoration
Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging reconstruction, compressive sensing and super-resolution. It unfolds the iterative optimization steps into a stack of sequentially linked blocks. Each block consists of a Gradient Descent Module (GDM) and a Proximal Mapping Module (PMM) which is equivalent to a denoiser from a Bayesian perspective, operating on Gaussian noise with a known level. However, existing DUNs suffer from two critical limitations: (i) their PMMs share identical architectures and denoising objectives across stages, ignoring the need for stage-specific adaptation to varying noise levels; and (ii) their chain of structurally repetitive blocks results in severe parameter redundancy and high memory consumption, hindering deployment in large-scale or resource-constrained scenarios. To address these challenges, we introduce generalized Deep Low-rank Adaptation (LoRA) Unfolding Networks for image restoration, named LoRun, harmonizing denoising objectives and adapting different denoising levels between stages with compressed memory usage for more efficient DUN. LoRun introduces a novel paradigm where a single pretrained base denoiser is shared across all stages, while lightweight, stage-specific LoRA adapters are injected into the PMMs to dynamically modulate denoising behavior according to the noise level at each unfolding step. This design decouples the core restoration capability from task-specific adaptation, enabling precise control over denoising intensity without duplicating full network parameters and achieving up to N times parameter reduction for an N-stage DUN with on-par or better performance. Extensive experiments conducted on three IR tasks validate the efficiency of our method.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 1858-1869
Deep LoRA-Unfolding Networks for Image Restoration
Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging reconstruction, compressive sensing and super-resolution. It unfolds the iterative optimization steps into a stack of sequentially linked blocks. Each block consists of a Gradient Descent Module (GDM) and a Proximal Mapping Module (PMM) which is equivalent to a denoiser from a Bayesian perspective, operating on Gaussian noise with a known level. However, existing DUNs suffer from two critical limitations: (i) their PMMs share identical architectures and denoising objectives across stages, ignoring the need for stage-specific adaptation to varying noise levels; and (ii) their chain of structurally repetitive blocks results in severe parameter redundancy and high memory consumption, hindering deployment in large-scale or resource-constrained scenarios. To address these challenges, we introduce generalized Deep Low-rank Adaptation (LoRA) Unfolding Networks for image restoration, named LoRun, harmonizing denoising objectives and adapting different denoising levels between stages with compressed memory usage for more efficient DUN. LoRun introduces a novel paradigm where a single pretrained base denoiser is shared across all stages, while lightweight, stage-specific LoRA adapters are injected into the PMMs to dynamically modulate denoising behavior according to the noise level at each unfolding step. This design decouples the core restoration capability from task-specific adaptation, enabling precise control over denoising intensity without duplicating full network parameters and achieving up to N times parameter reduction for an N-stage DUN with on-par or better performance. Extensive experiments conducted on three IR tasks validate the efficiency of our method.
- 7 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (4) , 4275-4286
Anchor-Induced Serial Tensor Representation for Multi-View Clustering
Multi-view clustering (MVC) has emerged as a powerful approach for integrating diverse sources of information from complex datasets. Nevertheless, existing methods struggle to accurately capture the global correlations and high-order structures in the data, and employ anchor-based techniques within a single dimension, limiting their representation. To address these issues, we propose an Anchor-induced Serial Tensor Representation (ASTR) framework, which effectively harnesses serial tensor representation to capture comprehensive multi-view information while reducing approximation errors and enhancing clustering performance. Specifically, ASTR begins with projection learning to explore low-dimensional latent spaces in multi-view data. Then, we introduce multi-anchor learning, where multiple anchor configurations are generated within the latent spaces, yielding a set of corresponding bipartite graphs. Besides, we organize these bipartite graphs into a sequence of global tensors, forming the serial tensor representation that encapsulates high-order inter- and intra-view relationships. Furthermore, we introduce the Laplace function to achieve a more accurate tensor rank approximation, complemented by a thorough theoretical analysis. Finally, a one-step clustering process, guided by adaptive weights, directly fuses the learned graphs to produce the final clustering indicator matrix. Experimental results demonstrate that ASTR possesses superior clustering accuracy and comparable efficiency.
- 7 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (4) , 4275-4286
Anchor-Induced Serial Tensor Representation for Multi-View Clustering
Multi-view clustering (MVC) has emerged as a powerful approach for integrating diverse sources of information from complex datasets. Nevertheless, existing methods struggle to accurately capture the global correlations and high-order structures in the data, and employ anchor-based techniques within a single dimension, limiting their representation. To address these issues, we propose an Anchor-induced Serial Tensor Representation (ASTR) framework, which effectively harnesses serial tensor representation to capture comprehensive multi-view information while reducing approximation errors and enhancing clustering performance. Specifically, ASTR begins with projection learning to explore low-dimensional latent spaces in multi-view data. Then, we introduce multi-anchor learning, where multiple anchor configurations are generated within the latent spaces, yielding a set of corresponding bipartite graphs. Besides, we organize these bipartite graphs into a sequence of global tensors, forming the serial tensor representation that encapsulates high-order inter- and intra-view relationships. Furthermore, we introduce the Laplace function to achieve a more accurate tensor rank approximation, complemented by a thorough theoretical analysis. Finally, a one-step clustering process, guided by adaptive weights, directly fuses the learned graphs to produce the final clustering indicator matrix. Experimental results demonstrate that ASTR possesses superior clustering accuracy and comparable efficiency.
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (1) , 37-50
Dual Tensor Low-Rank Representation for Subspace Clustering
Benefiting from the powerful tensor techniques, the tensor low-rank representation has been proposed to construct sophisticated subspace clustering models. Existing tensor low-rank representation methods predominantly rely on a single low-rank prior to reconstruct the row space, which is instrumental in determining the subspace membership of samples by the row space information. However, this strategy neglects the column space and would lead to a subspace information loss. To address this issue, we propose a Dual Tensor Low-Rank Representation method (DTLRR), the first subspace clustering framework to theoretically recover both row and column subspaces simultaneously. Particularly, not simply formulating a dual self-representation model, we instead prove the recovery of both row and column spaces via a unified theoretical framework. Then, we impose low-rank constraints on the two corresponding affinity tensors to effectively capture high-order correlations. Meanwhile, we theoretically demonstrate the existence of compact dictionary tensors within the dual self-representation framework, which effectively eliminates the null spaces of the affinity tensors and significantly reduces computational complexity. Furthermore, an efficient Alternating Direction Method of Multipliers (ADMM) algorithm is designed to solve the proposed DTLRR model with guaranteed convergence. Extensive experiments validate the superior performance of the proposed DTLRR in data clustering, hyperspectral image denoising, and hyperspectral anomaly detection.
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (1) , 37-50
Dual Tensor Low-Rank Representation for Subspace Clustering
Benefiting from the powerful tensor techniques, the tensor low-rank representation has been proposed to construct sophisticated subspace clustering models. Existing tensor low-rank representation methods predominantly rely on a single low-rank prior to reconstruct the row space, which is instrumental in determining the subspace membership of samples by the row space information. However, this strategy neglects the column space and would lead to a subspace information loss. To address this issue, we propose a Dual Tensor Low-Rank Representation method (DTLRR), the first subspace clustering framework to theoretically recover both row and column subspaces simultaneously. Particularly, not simply formulating a dual self-representation model, we instead prove the recovery of both row and column spaces via a unified theoretical framework. Then, we impose low-rank constraints on the two corresponding affinity tensors to effectively capture high-order correlations. Meanwhile, we theoretically demonstrate the existence of compact dictionary tensors within the dual self-representation framework, which effectively eliminates the null spaces of the affinity tensors and significantly reduces computational complexity. Furthermore, an efficient Alternating Direction Method of Multipliers (ADMM) algorithm is designed to solve the proposed DTLRR model with guaranteed convergence. Extensive experiments validate the superior performance of the proposed DTLRR in data clustering, hyperspectral image denoising, and hyperspectral anomaly detection.
- Open Access
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18  (19391404) , 3713-3727
$\mathrm{D}^{3}$T: Deep Denoising Dictionary Tensor for Hyperspectral Anomaly Detection
Hyperspectral anomaly detection (HAD) approaches with tensor low-rank representation (TLRR) have shown engaging performance, which are capable of capturing abundant spectral and spatial information, and hence extracting sparse anomalies from the low-rank background without ruining the intrinsic geometric structures of tensor data. However, existing HAD approaches construct the low-rank representation by a handcrafted dictionary that still contains the anomalies, resulting in an invalid representation. To this end, we propose a Deep Denoising Dictionary Tensor for Hyperspectral Anomaly Detection (D3T), which can balance performance and interpretability by fusing two intuitive priors, i.e., low-rankness and deep denoising, into the dictionary tensor and coefficient tensor. In particular, the proposed D3T first designs a tensor recovery module for dividing the low-rank background and sparse anomalies, where the background is optimized as a denoising dictionary tensor by the joint low-rankness and deep denoising. Following that, we build the TLRR model based on the denoising dictionary tensor to explore the latent representation of the input HSIs, and hence each background pixel is represented by the other clear background pixels in place of the anomaly pixels. Meanwhile, the coefficient tensor in TLRR is also optimized by the two priors to fully explore the spatial and spectral correlations in the background, and hence the anomalies can be accurately detected. Numerous experimental results from various real-world datasets validate the effectiveness of our D3T.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18  (19391404) , 3713-3727
Open Access$\mathrm{D}^{3}$T: Deep Denoising Dictionary Tensor for Hyperspectral Anomaly Detection
Hyperspectral anomaly detection (HAD) approaches with tensor low-rank representation (TLRR) have shown engaging performance, which are capable of capturing abundant spectral and spatial information, and hence extracting sparse anomalies from the low-rank background without ruining the intrinsic geometric structures of tensor data. However, existing HAD approaches construct the low-rank representation by a handcrafted dictionary that still contains the anomalies, resulting in an invalid representation. To this end, we propose a Deep Denoising Dictionary Tensor for Hyperspectral Anomaly Detection (D3T), which can balance performance and interpretability by fusing two intuitive priors, i.e., low-rankness and deep denoising, into the dictionary tensor and coefficient tensor. In particular, the proposed D3T first designs a tensor recovery module for dividing the low-rank background and sparse anomalies, where the background is optimized as a denoising dictionary tensor by the joint low-rankness and deep denoising. Following that, we build the TLRR model based on the denoising dictionary tensor to explore the latent representation of the input HSIs, and hence each background pixel is represented by the other clear background pixels in place of the anomaly pixels. Meanwhile, the coefficient tensor in TLRR is also optimized by the two priors to fully explore the spatial and spectral correlations in the background, and hence the anomalies can be accurately detected. Numerous experimental results from various real-world datasets validate the effectiveness of our D3T.
- 13 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9  (1) , 455-467
Dual Completion Learning for Incomplete Multi-View Clustering
Incomplete Multi-View Clustering (IMVC) offers a way to analyze incomplete data, facilitating the inference of unobserved and missing data points through completion techniques. However, existing IMVC methods, predominantly depending on either data completion or similarity matrix completion, failed to uncover the inherent geometric structure and potential complementary information between intra- and inter-views, causing incomplete similarity matrices to further tear apart the connections between views. To address this problem, we propose Dual Completion Learning for Incomplete Multi-view Clustering (DCIMC), which elaborately designs data completion and similarity tensor completion, and fuses both of them into a unified model to effectively recover the missing samples and similarities. Concretely, in data completion, DCIMC utilizes subspace clustering to recover the missing and unknown instances directly. Meanwhile, in similarity tensor completion, DCIMC introduces the idea of tensor completion to make better use of the high-order complementary information from multi-view data. By fusing the dual completions, missing information and complementary information in each completion are fully explored by each other, reciprocally enhancing one another to boost the accuracy of our clustering algorithm. Experimental results on various datasets show the effectiveness of the proposed DCIMC. Moreover, our DCIMC also achieved superior or comparable performance in an extended comparison with recent deep learning-based multi-view clustering algorithms.
- 13 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9  (1) , 455-467
Dual Completion Learning for Incomplete Multi-View Clustering
Incomplete Multi-View Clustering (IMVC) offers a way to analyze incomplete data, facilitating the inference of unobserved and missing data points through completion techniques. However, existing IMVC methods, predominantly depending on either data completion or similarity matrix completion, failed to uncover the inherent geometric structure and potential complementary information between intra- and inter-views, causing incomplete similarity matrices to further tear apart the connections between views. To address this problem, we propose Dual Completion Learning for Incomplete Multi-view Clustering (DCIMC), which elaborately designs data completion and similarity tensor completion, and fuses both of them into a unified model to effectively recover the missing samples and similarities. Concretely, in data completion, DCIMC utilizes subspace clustering to recover the missing and unknown instances directly. Meanwhile, in similarity tensor completion, DCIMC introduces the idea of tensor completion to make better use of the high-order complementary information from multi-view data. By fusing the dual completions, missing information and complementary information in each completion are fully explored by each other, reciprocally enhancing one another to boost the accuracy of our clustering algorithm. Experimental results on various datasets show the effectiveness of the proposed DCIMC. Moreover, our DCIMC also achieved superior or comparable performance in an extended comparison with recent deep learning-based multi-view clustering algorithms.
- Open Access
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18  (8) , 1-23
Data Completion-Guided Unified Graph Learning for Incomplete Multi-View Clustering
Due to its heterogeneous property, multi-view data has been widely concerned over single-view data for performance improvement. Unfortunately, some instances may be with partially available information because of some uncontrollable factors, for which the incomplete multi-view clustering (IMVC) problem is raised. IMVC aims to partition unlabeled incomplete multi-view data into their clusters by exploiting the heterogeneity of multi-view data and overcoming the difficulty of data loss. However, most existing IMVC methods like BSV, MIC, OMVC, and IVC tend to conduct basic completion processing on the input data, without taking advantage of the correlation between samples and information redundancy. To overcome the above issue, we propose one novel IMVC method named data completion-guided unified graph learning (DCUGL), which could complete the data of missing views and fuse multiple learned view-specific similarity matrices into one unified graph. Specifically, we first reduce the dimension of the input data to learn multiple view-specific similarity matrices. By stacking all view-specific similarity matrices, DCUGL constructs a third-order tensor with the low-rank constraint, such that sample correlation within and between views can be well explored. Finally, by dividing the original data into observed data and unobserved data, DCUGL can infer and complete the missing data according to the view-specific similarity matrices, and obtain a unified graph, which can be directly used for clustering. To solve the proposed model, we design an iterative algorithm, which is based on the alternating direction method of multipliers framework. The proposed model proves to be superior by benchmarking on six challenging datasets compared with state-of-the-art IMVC methods.
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18  (8) , 1-23
Open AccessData Completion-Guided Unified Graph Learning for Incomplete Multi-View Clustering
Due to its heterogeneous property, multi-view data has been widely concerned over single-view data for performance improvement. Unfortunately, some instances may be with partially available information because of some uncontrollable factors, for which the incomplete multi-view clustering (IMVC) problem is raised. IMVC aims to partition unlabeled incomplete multi-view data into their clusters by exploiting the heterogeneity of multi-view data and overcoming the difficulty of data loss. However, most existing IMVC methods like BSV, MIC, OMVC, and IVC tend to conduct basic completion processing on the input data, without taking advantage of the correlation between samples and information redundancy. To overcome the above issue, we propose one novel IMVC method named data completion-guided unified graph learning (DCUGL), which could complete the data of missing views and fuse multiple learned view-specific similarity matrices into one unified graph. Specifically, we first reduce the dimension of the input data to learn multiple view-specific similarity matrices. By stacking all view-specific similarity matrices, DCUGL constructs a third-order tensor with the low-rank constraint, such that sample correlation within and between views can be well explored. Finally, by dividing the original data into observed data and unobserved data, DCUGL can infer and complete the missing data according to the view-specific similarity matrices, and obtain a unified graph, which can be directly used for clustering. To solve the proposed model, we design an iterative algorithm, which is based on the alternating direction method of multipliers framework. The proposed model proves to be superior by benchmarking on six challenging datasets compared with state-of-the-art IMVC methods.
- 29 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33  (10577149) , 1272-1284
Pick-and-Place Transform Learning for Fast Multi-View Clustering
To manipulate large-scale data, anchor-based multi-view clustering methods have grown in popularity owing to their linear complexity in terms of the number of samples. However, these existing approaches pay less attention to two aspects. 1) They target at learning a shared affinity matrix by using the local information from every single view, yet ignoring the global information from all views, which may weaken the ability to capture complementary information. 2) They do not consider the removal of feature redundancy, which may affect the ability to depict the real sample relationships. To this end, we propose a novel fast multi-view clustering method via pick-and-place transform learning named PPTL, which could capture insightful global features to characterize the sample relationships quickly. Specifically, PPTL first concatenates all the views along the feature direction to produce a global matrix. Considering the redundancy of the global matrix, we design a pick-and-place transform with â„“ 2,p -norm regularization to abandon the poor features and consequently construct a compact global representation matrix. Thus, by conducting anchor-based subspace clustering on the compact global representation matrix, PPTL can learn a consensus skinny affinity matrix with a discriminative clustering structure. Numerous experiments performed on small-scale to large-scale datasets demonstrate that our method is not only faster but also achieves superior clustering performance over state-of-the-art methods across a majority of the datasets.
- 29 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33  (10577149) , 1272-1284
Pick-and-Place Transform Learning for Fast Multi-View Clustering
To manipulate large-scale data, anchor-based multi-view clustering methods have grown in popularity owing to their linear complexity in terms of the number of samples. However, these existing approaches pay less attention to two aspects. 1) They target at learning a shared affinity matrix by using the local information from every single view, yet ignoring the global information from all views, which may weaken the ability to capture complementary information. 2) They do not consider the removal of feature redundancy, which may affect the ability to depict the real sample relationships. To this end, we propose a novel fast multi-view clustering method via pick-and-place transform learning named PPTL, which could capture insightful global features to characterize the sample relationships quickly. Specifically, PPTL first concatenates all the views along the feature direction to produce a global matrix. Considering the redundancy of the global matrix, we design a pick-and-place transform with â„“ 2,p -norm regularization to abandon the poor features and consequently construct a compact global representation matrix. Thus, by conducting anchor-based subspace clustering on the compact global representation matrix, PPTL can learn a consensus skinny affinity matrix with a discriminative clustering structure. Numerous experiments performed on small-scale to large-scale datasets demonstrate that our method is not only faster but also achieves superior clustering performance over state-of-the-art methods across a majority of the datasets.
- 4 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-12
Generalized Nonconvex Low-Rank Tensor Representation for Hyperspectral Anomaly Detection
Low-rank tensor representation (LRTR) methods have attracted great interest for their powerful ability to separate backgrounds and anomalies. However, most of the current LRTR models use the popular and convex surrogate tensor nuclear norm to solve optimization problems, which results in a loose approximation and suboptimal solver for the original problem. Besides, most existing methods solve the nonconvex optimization problems case-by-case, consequently losing one unified solver. To solve the above issues, we propose the Generalized Nonconvex Low-rank Tensor Representation (GNLTR) for hyperspectral anomaly detection (HAD), a unified solver not case-by-case one of existing nonconvex optimization problems. Compared to the tensor nuclear norm, GNLTR contains many popular nonconvex penalty functions as tighter regularizers of the tensor tubal rank to constrain the low rank of the background. Moreover, the L 2,1 norm has been integrated into the GNLTR model for the sparse anomalies. For the optimization problem, it is handled quickly and efficiently through a well-organized alternating direction method of multipliers (ADMM). The experiments on several real-world hyperspectral data sets demonstrate the superior performance of the GNLTR model in comparison with some state-of-the-art anomaly detection models.
- 4 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-12
Generalized Nonconvex Low-Rank Tensor Representation for Hyperspectral Anomaly Detection
Low-rank tensor representation (LRTR) methods have attracted great interest for their powerful ability to separate backgrounds and anomalies. However, most of the current LRTR models use the popular and convex surrogate tensor nuclear norm to solve optimization problems, which results in a loose approximation and suboptimal solver for the original problem. Besides, most existing methods solve the nonconvex optimization problems case-by-case, consequently losing one unified solver. To solve the above issues, we propose the Generalized Nonconvex Low-rank Tensor Representation (GNLTR) for hyperspectral anomaly detection (HAD), a unified solver not case-by-case one of existing nonconvex optimization problems. Compared to the tensor nuclear norm, GNLTR contains many popular nonconvex penalty functions as tighter regularizers of the tensor tubal rank to constrain the low rank of the background. Moreover, the L 2,1 norm has been integrated into the GNLTR model for the sparse anomalies. For the optimization problem, it is handled quickly and efficiently through a well-organized alternating direction method of multipliers (ADMM). The experiments on several real-world hyperspectral data sets demonstrate the superior performance of the GNLTR model in comparison with some state-of-the-art anomaly detection models.