Jiazhen Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiazhen Xu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chong Wang
Ningbo University
2 shared publications - Jiafei Wu
Zhejiang University, Hangzhou, China
2 shared publications - Jiangbo Qian
Ningbo University
2 shared publications - Sunqi Lin
Merchants Guild Economics and Cultural Intelligent Computing Laboratory of Ningbo University, Ningbo, China
1 shared publication - Wenxiu Huang
Merchants Guild Economics and Cultural Intelligent Computing Laboratory, Ningbo University, Ningbo, China
1 shared publication - Yuqi Li
Ningbo University
1 shared publication
Latest Publications
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP (23798920) , 1-14
PS-KD: PatchMix Simulation for High-Fidelity Knowledge Distillation
Knowledge Distillation (KD) is a widely used model compression technique that primarily transfers knowledge by aligning the predictions of a student model with those of a teacher model. Besides the traditional logit-based KD, combining data augmentation techniques, like MixUp, is another effective way to improve the distillation efficiency. However, as a powerful data augmentation method, PatchMix has shown limited effectiveness in CNN-based knowledge distillation. It is likely due to constraints in the CNN teacher’s receptive field and the absence of PatchMix-retrained teacher models. In this paper, we explore why PatchMix tends to be less effective than MixUp, and further introduce a novel framework called PatchMix Simulation Knowledge Distillation (PS-KD). The proposed new framework simulates a PatchMix-retrained teacher using an vanilla one to guide the student’s training, ensuring the high-fidelity information distillation in feature space. By revisiting the use of PatchMix in CNNs and reducing information distortion, our model is capable to enhance CNN’s spatial invariance and increase the fidelity of network representations. Extensive experiments demonstrate the superiority of our approach, enabling the network to identify discriminative regions in images with greater accuracy. The Code will be released soon.
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP (23798920) , 1-14
PS-KD: PatchMix Simulation for High-Fidelity Knowledge Distillation
Knowledge Distillation (KD) is a widely used model compression technique that primarily transfers knowledge by aligning the predictions of a student model with those of a teacher model. Besides the traditional logit-based KD, combining data augmentation techniques, like MixUp, is another effective way to improve the distillation efficiency. However, as a powerful data augmentation method, PatchMix has shown limited effectiveness in CNN-based knowledge distillation. It is likely due to constraints in the CNN teacher’s receptive field and the absence of PatchMix-retrained teacher models. In this paper, we explore why PatchMix tends to be less effective than MixUp, and further introduce a novel framework called PatchMix Simulation Knowledge Distillation (PS-KD). The proposed new framework simulates a PatchMix-retrained teacher using an vanilla one to guide the student’s training, ensuring the high-fidelity information distillation in feature space. By revisiting the use of PatchMix in CNNs and reducing information distortion, our model is capable to enhance CNN’s spatial invariance and increase the fidelity of network representations. Extensive experiments demonstrate the superiority of our approach, enabling the network to identify discriminative regions in images with greater accuracy. The Code will be released soon.
- 26 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (6) , 3248-3258
KR-SWP: Knowledge Reuse for Stripe-Wise Pruning
Pruning neural networks presents a promising avenue for compressing and accelerating contemporary deep convolutional networks. Recently, researchers have increasingly focused on a new kind of stripe-wise pruning (SWP) methods, which offers finer granularity compared to traditional techniques. However, most prior network pruning methods, including SWP, suffer from the issue of “wrong pruning.” During model training, particularly in its early stages, pruning decisions are often sub-optimal, leading to the premature elimination of crucial weights. To mitigate this problem, we propose a novel framework that re-utilizes knowledge from pruned stripe-wise weights for SWP. The unique stripe repair phases are inserted into the standard training process to identify and repair those mis-pruned stripes. Additionally, halfway-pruned models with varying structures are also selectively reused a self-knowledge distillation manner. Comprehensive experiments conducted on three public datasets demonstrate the effectiveness of our proposed model. The code will be released subsequently.
- 26 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (6) , 3248-3258
KR-SWP: Knowledge Reuse for Stripe-Wise Pruning
Pruning neural networks presents a promising avenue for compressing and accelerating contemporary deep convolutional networks. Recently, researchers have increasingly focused on a new kind of stripe-wise pruning (SWP) methods, which offers finer granularity compared to traditional techniques. However, most prior network pruning methods, including SWP, suffer from the issue of “wrong pruning.” During model training, particularly in its early stages, pruning decisions are often sub-optimal, leading to the premature elimination of crucial weights. To mitigate this problem, we propose a novel framework that re-utilizes knowledge from pruned stripe-wise weights for SWP. The unique stripe repair phases are inserted into the standard training process to identify and repair those mis-pruned stripes. Additionally, halfway-pruned models with varying structures are also selectively reused a self-knowledge distillation manner. Comprehensive experiments conducted on three public datasets demonstrate the effectiveness of our proposed model. The code will be released subsequently.