Zhen Wei
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
Zhen Wei has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Yang Lu
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
18 shared publications - Xing Wei
Hefei University of Technology
11 shared publications - Ping Xue
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
5 shared publications - Yiqun Xu
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
5 shared publications - Jingfei Chang
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
4 shared publications - Zhehao Li
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12479-12488
Multi-Task Dense Prediction with Mixture of Unit-Rank Experts
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12479-12488
Open AccessMulti-Task Dense Prediction with Mixture of Unit-Rank Experts
- 20 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 301
Greedy weighted strategy based on logit margin change rate in adversarial training
- 20 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 301
Greedy weighted strategy based on logit margin change rate in adversarial training
- 12 November 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 40 (01)
Region Segmentation-Based Dual Branch Cost Aggregation for Lightweight Stereo Matching
Recently, stereo matching models based on 3D CNNs have achieved excellent performance. However, huge computational burden and memory footprint of deep 3D convolution limit their deployment on edge devices and real-time scenes. Furthermore, given that disparity maps exhibit continuous disparity variations in content regions but sharp disparity variants at edge areas, spatially shared weight mechanism inherent in convolution may struggle to handle both types of regions. In this paper, we propose a lightweight stereo matching model, called DBCANet, with Dual-Branch Cost Aggregation based on region segmentation to reduce the computational burden. Specifically, we divide the cost aggregation module into two branches: the edge branch is to aggregate edge disparity information, and the content branch is to aggregate the disparity information of the content region. 2D convolution reduces the computational burden and dual branch can mitigate the problem caused by convolutional spatially-shared weights to compensate for the accuracy loss. We extensively validate our model on Scene Flow, KITTI datasets, and our model can achieve the lowest multiply-accumulate operations (MACs) among speed-oriented stereo matching models, while its EPE is only 0.59 on Scene Flow dataset, which is ranked second. Our model can achieve a good balance between accuracy and model computation.
- 12 November 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 40 (01)
Region Segmentation-Based Dual Branch Cost Aggregation for Lightweight Stereo Matching
Recently, stereo matching models based on 3D CNNs have achieved excellent performance. However, huge computational burden and memory footprint of deep 3D convolution limit their deployment on edge devices and real-time scenes. Furthermore, given that disparity maps exhibit continuous disparity variations in content regions but sharp disparity variants at edge areas, spatially shared weight mechanism inherent in convolution may struggle to handle both types of regions. In this paper, we propose a lightweight stereo matching model, called DBCANet, with Dual-Branch Cost Aggregation based on region segmentation to reduce the computational burden. Specifically, we divide the cost aggregation module into two branches: the edge branch is to aggregate edge disparity information, and the content branch is to aggregate the disparity information of the content region. 2D convolution reduces the computational burden and dual branch can mitigate the problem caused by convolutional spatially-shared weights to compensate for the accuracy loss. We extensively validate our model on Scene Flow, KITTI datasets, and our model can achieve the lowest multiply-accumulate operations (MACs) among speed-oriented stereo matching models, while its EPE is only 0.59 on Scene Flow dataset, which is ranked second. Our model can achieve a good balance between accuracy and model computation.
- 21 October 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (15) , 1-8
Mitigating adversarial attacks uncertainty through interval analysis
- 21 October 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (15) , 1-8
Mitigating adversarial attacks uncertainty through interval analysis
- Open Access
- 10 July 2025
- Published by Springer Nature in Research Square
Mitigating Adversarial Attacks Uncertainty Through Interval Analysis
The adversarial attack is characterized by a high attack success rate and a fast generation of examples. It is widely used in neural network robustness evaluation and adversarial training. Restricted by the randomness of the initialization of the attack point and the iterative finding algorithm can not guarantee that it can reach the global optimal solution, the existing adversarial attack methods have attack uncertainty in a single attack and need to increase the number of attacks in order to improve the attack success rate. This paper defines the label susceptibility to analyze the attack effect. For adversarial data with high label susceptibility, using interval analysis to find the adversarial examples in its neighbourhood can effectively alleviate the attack uncertainty and improve the attack success rate. Experimental results on multiple datasets show that for white-box and black-box attack methods, our method achieves attack success rates that can surpass those attained by baseline methods requiring significantly more attack attempts while maintaining superior computational efficiency.
- 10 July 2025
- Published by Springer Nature in Research Square
Open AccessMitigating Adversarial Attacks Uncertainty Through Interval Analysis
The adversarial attack is characterized by a high attack success rate and a fast generation of examples. It is widely used in neural network robustness evaluation and adversarial training. Restricted by the randomness of the initialization of the attack point and the iterative finding algorithm can not guarantee that it can reach the global optimal solution, the existing adversarial attack methods have attack uncertainty in a single attack and need to increase the number of attacks in order to improve the attack success rate. This paper defines the label susceptibility to analyze the attack effect. For adversarial data with high label susceptibility, using interval analysis to find the adversarial examples in its neighbourhood can effectively alleviate the attack uncertainty and improve the attack success rate. Experimental results on multiple datasets show that for white-box and black-box attack methods, our method achieves attack success rates that can surpass those attained by baseline methods requiring significantly more attack attempts while maintaining superior computational efficiency.
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. PP, 1-14
Storage Scalability Oriented Segment Allocation Based on Cost Clustering in Sharding Blockchains
Blockchain technology has garnered significant attention from academia and industry, with scalability remaining a key challenge. Sharding is a promising solution, dividing the blockchain into smaller partitions called shards, each processing a portion of the transactions to increase throughput. This approach is critical for enabling efficient Proof of Stake (PoS) consensus mechanisms, as demonstrated by the transition of Dogecoin to PoS, where sharding reduces the computational burden on validators and enhances scalability. However, sharding introduces high storage redundancy, as nodes in each shard must collectively maintain a copy of the entire blockchain, imposing substantial storage pressure. To address this, segments are introduced to divide the main chain into smaller parts distributed across nodes. Existing methods, however, randomly assign segments to nodes, resulting in high costs for node setup and segment queries. This paper investigates the optimal allocation of segments within shards to minimize these costs, proposing a Segment Allocation algorithm based on Cost Clustering (SACC). Theoretical analysis and simulations demonstrate that SACC achieves lower setup, query, and total costs while maintaining security and scalability, offering a more efficient solution for sharding-based PoS blockchains like Dogecoin.
- 1 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. PP, 1-14
Storage Scalability Oriented Segment Allocation Based on Cost Clustering in Sharding Blockchains
Blockchain technology has garnered significant attention from academia and industry, with scalability remaining a key challenge. Sharding is a promising solution, dividing the blockchain into smaller partitions called shards, each processing a portion of the transactions to increase throughput. This approach is critical for enabling efficient Proof of Stake (PoS) consensus mechanisms, as demonstrated by the transition of Dogecoin to PoS, where sharding reduces the computational burden on validators and enhances scalability. However, sharding introduces high storage redundancy, as nodes in each shard must collectively maintain a copy of the entire blockchain, imposing substantial storage pressure. To address this, segments are introduced to divide the main chain into smaller parts distributed across nodes. Existing methods, however, randomly assign segments to nodes, resulting in high costs for node setup and segment queries. This paper investigates the optimal allocation of segments within shards to minimize these costs, proposing a Segment Allocation algorithm based on Cost Clustering (SACC). Theoretical analysis and simulations demonstrate that SACC achieves lower setup, query, and total costs while maintaining security and scalability, offering a more efficient solution for sharding-based PoS blockchains like Dogecoin.
- 17 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (3) , 1052-1067
Optimized Consensus Group Selection Focused on Node Transmission Delay in Sharding Blockchains
Sharding presents an enticing path toward improving blockchain scalability. However, the consensus mechanism within individual shards faces mounting security challenges due to the restricted number of consensus nodes and the reliance on conventional, unchanging nodes for consensus. Common strategies to enhance shard consensus security often involve increasing the number of consensus nodes per shard. While effective in bolstering security, this approach also leads to a notable rise in consensus delay within each shard, potentially offsetting the scalability advantages of sharding. Hence, it becomes imperative to strategically select nodes to form dedicated consensus groups for each shard. These groups should not only enhance shard consensus security but also do so without exacerbating consensus delay. In this article, we propose a novel consensus group selection based on transmission delay between nodes (CGSTD) to address this challenge, with the goal of minimizing the overall consensus delay across the system. CGSTD intelligently selects nodes from various shards to form distinct consensus groups for each shard, thereby enhancing shard security while maintaining optimal system-wide consensus efficiency. We conduct a rigorous theoretical analysis to evaluate the security properties of CGSTD and derive approximation ratios under various operational scenarios. Simulation results validate the superior performance of CGSTD compared to baseline algorithms, showcasing reductions in total consensus delay, mitigated increases in shard-specific delay, optimized block storage utilization per node, and streamlined participation of nodes in consensus groups.
- 17 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (3) , 1052-1067
Optimized Consensus Group Selection Focused on Node Transmission Delay in Sharding Blockchains
Sharding presents an enticing path toward improving blockchain scalability. However, the consensus mechanism within individual shards faces mounting security challenges due to the restricted number of consensus nodes and the reliance on conventional, unchanging nodes for consensus. Common strategies to enhance shard consensus security often involve increasing the number of consensus nodes per shard. While effective in bolstering security, this approach also leads to a notable rise in consensus delay within each shard, potentially offsetting the scalability advantages of sharding. Hence, it becomes imperative to strategically select nodes to form dedicated consensus groups for each shard. These groups should not only enhance shard consensus security but also do so without exacerbating consensus delay. In this article, we propose a novel consensus group selection based on transmission delay between nodes (CGSTD) to address this challenge, with the goal of minimizing the overall consensus delay across the system. CGSTD intelligently selects nodes from various shards to form distinct consensus groups for each shard, thereby enhancing shard security while maintaining optimal system-wide consensus efficiency. We conduct a rigorous theoretical analysis to evaluate the security properties of CGSTD and derive approximation ratios under various operational scenarios. Simulation results validate the superior performance of CGSTD compared to baseline algorithms, showcasing reductions in total consensus delay, mitigated increases in shard-specific delay, optimized block storage utilization per node, and streamlined participation of nodes in consensus groups.
- 7 December 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (1) , 1-29
Proposal-level reliable feature-guided contrastive learning for SFOD
- 7 December 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (1) , 1-29
Proposal-level reliable feature-guided contrastive learning for SFOD
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 32813-32821
PDTE: Pseudo Dual-View Contrastive Learning via Taylor Expansion Optimization for Remote Sensing Image Clustering
Image clustering is a crucial task in remote sensing data processing. Nevertheless, relying solely on traditional machine learning algorithms is insufficient for processing large amounts of images and accurately clustering them. Some recent works have successfully applied deep learning to remote sensing image clustering, significantly improving clustering performance. However, current deep clustering methods struggle to correctly assign boundary samples that are close to multiple clusters, as their features are very similar to samples in different clusters. To this end, we propose a method called Pseudo Dual-view Contrastive Learning via Taylor Expansion Optimization for Remote Sensing Image Clustering, namely, PDTE. Specifically, we introduce the pseudo dual-view contrastive learning framework with random aggressive augmentation to explore the potential information and subtle feature differences of images, and optimize its objective function using Taylor expansion to enlarge the difference in distance between boundary samples and each cluster. This allows us to assign boundary samples accurately and improves the clustering performance. Extensive experiments conducted on five datasets show that PDTE has superior clustering performance.
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 32813-32821
PDTE: Pseudo Dual-View Contrastive Learning via Taylor Expansion Optimization for Remote Sensing Image Clustering
Image clustering is a crucial task in remote sensing data processing. Nevertheless, relying solely on traditional machine learning algorithms is insufficient for processing large amounts of images and accurately clustering them. Some recent works have successfully applied deep learning to remote sensing image clustering, significantly improving clustering performance. However, current deep clustering methods struggle to correctly assign boundary samples that are close to multiple clusters, as their features are very similar to samples in different clusters. To this end, we propose a method called Pseudo Dual-view Contrastive Learning via Taylor Expansion Optimization for Remote Sensing Image Clustering, namely, PDTE. Specifically, we introduce the pseudo dual-view contrastive learning framework with random aggressive augmentation to explore the potential information and subtle feature differences of images, and optimize its objective function using Taylor expansion to enlarge the difference in distance between boundary samples and each cluster. This allows us to assign boundary samples accurately and improves the clustering performance. Extensive experiments conducted on five datasets show that PDTE has superior clustering performance.
- 14 August 2024
- Published by Springer Nature
- p. 49-61
3D Convolution Channel Compression for Stereo Matching
- 14 August 2024
- Published by Springer Nature
- p. 49-61
3D Convolution Channel Compression for Stereo Matching