Jingxuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jingxuan Zhang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Lei Dai
Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China
3 shared publications - Zhihua Chen
Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China
3 shared publications - Bin Sheng
Shanghai Jiao Tong University
2 shared publications - Ping Li
The Hong Kong Polytechnic University
2 shared publications - Fei Ye
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Xiaokang Yang
Shanghai Jiao Tong University
1 shared publication
Latest Publications
- Top Cited Papers
- 6 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Dataset Distillation via a Noise-Unconstrained Generative Model
Dataset distillation (DD) aims to synthesize a more compact dataset than the original one and models trained on it are expected to have the same generalization capabilities as on the original dataset. Previous work via a generative model (GM) faces several limitations. First, GM struggles to generate representative samples due to a lack of constraints. Second, it overlooks the relationships between generated samples, limiting its effectiveness. In this paper, a new noise-unconstrained GM-based DD framework is proposed. In the distillation stage, an adaptive matching coefficient is introduced to align generated images with representative class elements and the MiniMax loss function is extended to reduce the optimization difficulty. In the deployment stage, features among each generative image are ensembled by gradient-matching based DD. Theoretical analysis based on McDiarmid's inequality demonstrates that the proposed components can reduce the generalization error of the original baseline method. We also provide insights into the potential of generated images as an effective proxy dataset for DD. For example, on the ImageWoof dataset with 50 distilled images per class using a 6-layer ConvNet for evaluation, generated images outperform 25%, 50%, and 75% original images by 8.4%, 6.3%, and 8.3% in distillation performance. Our method effectively handles both low- and high-resolution datasets, with experiments on 11 benchmarks demonstrating its efficacy.
- 6 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-18
Top Cited PapersDataset Distillation via a Noise-Unconstrained Generative Model
Dataset distillation (DD) aims to synthesize a more compact dataset than the original one and models trained on it are expected to have the same generalization capabilities as on the original dataset. Previous work via a generative model (GM) faces several limitations. First, GM struggles to generate representative samples due to a lack of constraints. Second, it overlooks the relationships between generated samples, limiting its effectiveness. In this paper, a new noise-unconstrained GM-based DD framework is proposed. In the distillation stage, an adaptive matching coefficient is introduced to align generated images with representative class elements and the MiniMax loss function is extended to reduce the optimization difficulty. In the deployment stage, features among each generative image are ensembled by gradient-matching based DD. Theoretical analysis based on McDiarmid's inequality demonstrates that the proposed components can reduce the generalization error of the original baseline method. We also provide insights into the potential of generated images as an effective proxy dataset for DD. For example, on the ImageWoof dataset with 50 distilled images per class using a 6-layer ConvNet for evaluation, generated images outperform 25%, 50%, and 75% original images by 8.4%, 6.3%, and 8.3% in distillation performance. Our method effectively handles both low- and high-resolution datasets, with experiments on 11 benchmarks demonstrating its efficacy.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7050-7064
Unleashing the Power of Each Distilled Image
Dataset distillation (DD) aims to accelerate the training speed of neural networks (NNs) by synthesizing a reduced dataset. NNs trained on the smaller dataset are expected to obtain almost the same test set accuracy as they do on the larger one. Previous DD research treated the obtained distilled dataset as a regular dataset for training, neglecting the overfitting issue caused by the limited number of original distilled images. In this paper, we propose a new DD paradigm. Specifically, in the deployment stage, distilled images are augmented by amplifying their local information since the teacher network can produce diverse supervision signals when receiving inputs from different regions. Efficient and diverse augmentation methods for each distilled image are devised, while ensuring the authenticity of augmented samples. Additionally, to alleviate the increased training cost caused by data augmentation, we design a bi-directional dynamic dataset pruning technique to prune the original distilled dataset and augmented distilled dataset. A new pruning strategy and scheduling are proposed based on experimental findings. Experiments on 9 benchmark datasets (CIFAR10, CIFAR100, ImageWoof, ImageCat, ImageFruit, ImageNette, ImageNet10, ImageNet100 and ImageNet1K) demonstrate the effectiveness of our approach. For instance, on the ImageNet1K dataset with a ResNet18 architecture and 50 distilled images per class, our algorithm surpasses the second-ranked MiniMax algorithm by 7.6%, achieving a distilled accuracy of 66.2%.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7050-7064
Unleashing the Power of Each Distilled Image
Dataset distillation (DD) aims to accelerate the training speed of neural networks (NNs) by synthesizing a reduced dataset. NNs trained on the smaller dataset are expected to obtain almost the same test set accuracy as they do on the larger one. Previous DD research treated the obtained distilled dataset as a regular dataset for training, neglecting the overfitting issue caused by the limited number of original distilled images. In this paper, we propose a new DD paradigm. Specifically, in the deployment stage, distilled images are augmented by amplifying their local information since the teacher network can produce diverse supervision signals when receiving inputs from different regions. Efficient and diverse augmentation methods for each distilled image are devised, while ensuring the authenticity of augmented samples. Additionally, to alleviate the increased training cost caused by data augmentation, we design a bi-directional dynamic dataset pruning technique to prune the original distilled dataset and augmented distilled dataset. A new pruning strategy and scheduling are proposed based on experimental findings. Experiments on 9 benchmark datasets (CIFAR10, CIFAR100, ImageWoof, ImageCat, ImageFruit, ImageNette, ImageNet10, ImageNet100 and ImageNet1K) demonstrate the effectiveness of our approach. For instance, on the ImageNet1K dataset with a ResNet18 architecture and 50 distilled images per class, our algorithm surpasses the second-ranked MiniMax algorithm by 7.6%, achieving a distilled accuracy of 66.2%.
- 5 July 2025
- Published by Elsevier in Neural Networks
- Vol. 191, 107819
Gradient amplification for gradient matching based dataset distillation
- 5 July 2025
- Published by Elsevier in Neural Networks
- Vol. 191, 107819
Gradient amplification for gradient matching based dataset distillation