publications

2024

1. ACM MM Oral

   Diffusion Posterior Proximal Sampling for Image Restoration

   Hongjie Wu, Linchao He, Mingqin Zhang, Dongdong Chen, Kunming Luo, Mengting Luo, Ji-Zhe Zhou , Hu Chen, and Jiancheng Lv

   Proceedings of the 32st ACM International Conference on Multimedia, 2024

   Oral Presentation [Top 3%]

   Paper Abs Code Website

   Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we introduce a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. Besides, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate the effectiveness of our proposed approach across diverse image restoration tasks.

2. PRL

   Self-Supervised Domain Adaptation with Significance-Oriented Masking for Pelvic Organ Prolapse Detection

   Shichang Li, Hongjie Wu, Chenwei Tang, Dongdong Chen , Yueyue Chen, Ling Mei, Fan Yang, and Jiancheng Lv

   Pattern Recognition Letters (in press), 2024
3. IEEE TKDE

   Euclidean Distance Is Not Your Swiss Army Knife

   Yuze Tan, Yixi Liu, Hongjie Wu, Shudong Huang, Zenglin Xu, Ivor W Tsang, and Jiancheng Lv

   IEEE Transactions on Knowledge and Data Engineering, 2024

   Paper
4. arXiv

   Fast and Stable Diffusion Inverse Solver with History Gradient Update

   Linchao He, Hongyu Yan, Mengting Luo, Hongjie Wu, Kunming Luo, Wang Wang, Wenchao Du , Hu Chen, Hongyu Yang, Yi Zhang, and Jiancheng Lv

   arXiv preprint, 2024

   Paper Abs

   Diffusion models have recently been recognised as efficient inverse problem solvers due to their ability to produce high-quality reconstruction results without relying on pairwise data training. Existing diffusion-based solvers utilize Gradient Descent strategy to get a optimal sample solution. However, these solvers only calculate the current gradient and have not utilized any history information of sampling process, thus resulting in unstable optimization progresses and suboptimal solutions. To address this issue, we propose to utilize the history information of the diffusion-based inverse solvers. In this paper, we first prove that, in previous work, using the gradient descent method to optimize the data fidelity term is convergent. Building on this, we introduce the incorporation of historical gradients into this optimization process, termed History Gradient Update (HGU). We also provide theoretical evidence that HGU ensures the convergence of the entire algorithm. It’s worth noting that HGU is applicable to both pixel-based and latent-based diffusion model solvers. Experimental results demonstrate that, compared to previous sampling algorithms, sampling algorithms with HGU achieves state-of-the-art results in medical image reconstruction, surpassing even supervised learning methods. Additionally, it achieves competitive results on natural images.

2023

1. ACM MM

   Preserving Local and Global Information: An Effective Metric-based Subspace Clustering

   Yixi Liu, Yuze Tan, Hongjie Wu, Shudong Huang, Yazhou Ren, and Jiancheng Lv

   In Proceedings of the 31st ACM International Conference on Multimedia , 2023

   Paper
2. AAAI

   Metric multi-view graph clustering

   Yuze Tan, Yixi Liu, Hongjie Wu, Jiancheng Lv, and Shudong Huang

   In Proceedings of the AAAI Conference on Artificial Intelligence , 2023

   Paper Code
3. PR

   Pure graph-guided multi-view subspace clustering

   Hongjie Wu, Shudong Huang, Chenwei Tang, Yancheng Zhang, and Jiancheng Lv

   Pattern Recognition, 2023

   Paper Code
4. IJCNN

   ST-CA YOLOv5: Improved YOLOv5 based on Swin Transformer and Coordinate Attention for Surface Defect Detection

   Wen Yang, Hongjie Wu, Chenwei Tang, and Jiancheng Lv

   International Joint Conference on Neural Networks (IJCNN), 2023

   Paper

2022

1. NeurIPS Spotlight

   Multi-view subspace clustering on topological manifold

   Shudong Huang^*, Hongjie Wu^*, Yazhou Ren, Ivor Tsang, Zenglin Xu, Wentao Feng, and Jiancheng Lv

   Advances in Neural Information Processing Systems, 2022

   Spotlight Presentation [Top 5%]

   Paper Code
2. Mathematics

   Multi-view graph clustering by adaptive manifold learning

   Peng Zhao^*, Hongjie Wu^*, and Shudong Huang

   Mathematics, 2022

   Paper

2021

1. IJCNN

   Automatic Cataract Detection with Multi-task Learning

   Hongjie Wu, Jiancheng Lv, and Jian Wang

   International Joint Conference on Neural Networks (IJCNN), 2021

   Paper