Jianfei Li
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
Research Subjects
Jianfei Li has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Han Feng
Department of Mathematics, City University of Hong Kong, Hong Kong, China
4 shared publications - Xiaosheng Zhuang
City University of Hong Kong
2 shared publications - Aina Sui
School of Computer and Cyber Sciences, Communication University of China, Beijing 100024, China
1 shared publication - Chaoyan Huang
Department of Mathematics, the Chinese University of Hong Kong, Hong Kong
1 shared publication Ding-Xuan Zhou
1 shared publication- Ding-Xuan Zhou
School of Mathematics and Statistics, University of Sydney, Sydney, Australia
1 shared publication
Latest Publications
- 19 June 2026
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
In this work, we explore the intersection of sparse coding theory and deep learning to enhance our understanding of feature extraction capabilities in advanced neural network architectures. We begin by introducing a novel class of Deep Sparse Coding (DSC) models and establish a thorough theoretical analysis of their uniqueness and stability properties. By applying iterative algorithms to these DSC models, we derive convergence rates for convolutional neural networks (CNNs) in their ability to extract sparse features. This provides a strong theoretical foundation for the use of CNNs in sparse feature-learning tasks. We additionally extend this convergence analysis to more general neural network architectures, including those with diverse activation functions, as well as self-attention and transformer-based models. This broadens the applicability of our findings to a wide range of deep learning methods for the extraction of deep-sparse features. Inspired by the strong connection between sparse coding and CNNs, we also explore training strategies to encourage neural networks to learn sparser features. Through numerical experiments, we demonstrate the effectiveness of these approaches, providing valuable insight for the design of efficient and interpretable deep learning models.
- 19 June 2026
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
In this work, we explore the intersection of sparse coding theory and deep learning to enhance our understanding of feature extraction capabilities in advanced neural network architectures. We begin by introducing a novel class of Deep Sparse Coding (DSC) models and establish a thorough theoretical analysis of their uniqueness and stability properties. By applying iterative algorithms to these DSC models, we derive convergence rates for convolutional neural networks (CNNs) in their ability to extract sparse features. This provides a strong theoretical foundation for the use of CNNs in sparse feature-learning tasks. We additionally extend this convergence analysis to more general neural network architectures, including those with diverse activation functions, as well as self-attention and transformer-based models. This broadens the applicability of our findings to a wide range of deep learning methods for the extraction of deep-sparse features. Inspired by the strong connection between sparse coding and CNNs, we also explore training strategies to encourage neural networks to learn sparser features. Through numerical experiments, we demonstrate the effectiveness of these approaches, providing valuable insight for the design of efficient and interpretable deep learning models.
- Top Cited Papers
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (9) , 11634-11648
Permutation Equivariant Graph Framelets for Heterophilous Graph Learning
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations beyond the one-hop neighborhood. In this article, we develop a new way to implement multiscale extraction via constructing Haar-type graph framelets with desired properties of permutation equivariance, efficiency, and sparsity, for deep learning tasks on graphs. We further design a graph framelet neural network model permutation equivariant graph framelet augmented network (PEGFAN) based on our constructed graph framelets. The experiments are conducted on a synthetic dataset and nine benchmark datasets to compare the performance with other state-of-the-art models. The result shows that our model can achieve the best performance on certain datasets of heterophilous graphs (including the majority of heterophilous datasets with relatively larger sizes and denser connections) and competitive performance on the remaining.
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (9) , 11634-11648
Top Cited PapersPermutation Equivariant Graph Framelets for Heterophilous Graph Learning
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations beyond the one-hop neighborhood. In this article, we develop a new way to implement multiscale extraction via constructing Haar-type graph framelets with desired properties of permutation equivariance, efficiency, and sparsity, for deep learning tasks on graphs. We further design a graph framelet neural network model permutation equivariant graph framelet augmented network (PEGFAN) based on our constructed graph framelets. The experiments are conducted on a synthetic dataset and nine benchmark datasets to compare the performance with other state-of-the-art models. The result shows that our model can achieve the best performance on certain datasets of heterophilous graphs (including the majority of heterophilous datasets with relatively larger sizes and denser connections) and competitive performance on the remaining.
- 22 February 2024
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 22 (03) , 635-654
Approximation analysis of CNNs from a feature extraction view
Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures and structures. In this paper, we establish some analysis for linear feature extraction by a deep multi-channel convolutional neural networks (CNNs), which demonstrates the power of deep learning over traditional linear transformations, like Fourier, wavelets, redundant dictionary coding methods. Moreover, we give an exact construction presenting how linear features extraction can be conducted efficiently with multi-channel CNNs. It can be applied to lower the essential dimension for approximating a high-dimensional function. Rates of function approximation by such deep networks implemented with channels and followed by fully connected layers are investigated as well. Harmonic analysis for factorizing linear features into multi-resolution convolutions plays an essential role in our work. Nevertheless, a dedicate vectorization of matrices is constructed, which bridges 1D CNN and 2D CNN and allows us to have corresponding 2D analysis.
- 22 February 2024
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 22 (03) , 635-654
Approximation analysis of CNNs from a feature extraction view
Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures and structures. In this paper, we establish some analysis for linear feature extraction by a deep multi-channel convolutional neural networks (CNNs), which demonstrates the power of deep learning over traditional linear transformations, like Fourier, wavelets, redundant dictionary coding methods. Moreover, we give an exact construction presenting how linear features extraction can be conducted efficiently with multi-channel CNNs. It can be applied to lower the essential dimension for approximating a high-dimensional function. Rates of function approximation by such deep networks implemented with channels and followed by fully connected layers are investigated as well. Harmonic analysis for factorizing linear features into multi-resolution convolutions plays an essential role in our work. Nevertheless, a dedicate vectorization of matrices is constructed, which bridges 1D CNN and 2D CNN and allows us to have corresponding 2D analysis.
- 24 July 2023
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Imaging Sciences
- Vol. 16 (3) , 1177-1194
Spherical Image Inpainting with Frame Transformation and Data-Driven Prior Deep Networks
Spherical image processing has been widely applied in many important fields, such as omnidirectional vision for autonomous cars, global climate modeling, and medical imaging. It is nontrivial to extend an algorithm developed for flat images to the spherical ones. In this work, we focus on the challenging task of spherical image inpainting with a deep learning-based regularizer. Instead of a naive application of existing models for planar images, we employ a fast directional spherical Haar framelet transform and develop a novel optimization framework based on a sparsity assumption of the framelet transform. Furthermore, by employing progressive encoder-decoder architecture, a new and better-performed deep CNN denoiser is carefully designed and works as an implicit regularizer. Finally, we use a plug-and-play method to handle the proposed optimization model, which can be implemented efficiently by training the CNN denoiser prior. Numerical experiments are conducted and show that the proposed algorithms can greatly recover damaged spherical images and achieve the best performance over purely using a deep learning denoiser and a plug-and-play model.
- 24 July 2023
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Imaging Sciences
- Vol. 16 (3) , 1177-1194
Spherical Image Inpainting with Frame Transformation and Data-Driven Prior Deep Networks
Spherical image processing has been widely applied in many important fields, such as omnidirectional vision for autonomous cars, global climate modeling, and medical imaging. It is nontrivial to extend an algorithm developed for flat images to the spherical ones. In this work, we focus on the challenging task of spherical image inpainting with a deep learning-based regularizer. Instead of a naive application of existing models for planar images, we employ a fast directional spherical Haar framelet transform and develop a novel optimization framework based on a sparsity assumption of the framelet transform. Furthermore, by employing progressive encoder-decoder architecture, a new and better-performed deep CNN denoiser is carefully designed and works as an implicit regularizer. Finally, we use a plug-and-play method to handle the proposed optimization model, which can be implemented efficiently by training the CNN denoiser prior. Numerical experiments are conducted and show that the proposed algorithms can greatly recover damaged spherical images and achieve the best performance over purely using a deep learning denoiser and a plug-and-play model.
- 29 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (4) , 4400-4410
Convolutional Neural Networks for Spherical Signal Processing via Area-Regular Spherical Haar Tight Framelets
In this article, we develop a general theoretical framework for constructing Haar-type tight framelets on any compact set with a hierarchical partition. In particular, we construct a novel area-regular hierarchical partition on the two spheres and establish its corresponding spherical Haar tight framelets with directionality. We conclude by evaluating and illustrate the effectiveness of our area-regular spherical Haar tight framelets in several denoising experiments. Furthermore, we propose a convolutional neural network (CNN) model for spherical signal denoising, which employs fast framelet decomposition and reconstruction algorithms. Experiment results show that our proposed CNN model outperforms threshold methods and processes strong generalization and robustness.
- 29 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (4) , 4400-4410
Convolutional Neural Networks for Spherical Signal Processing via Area-Regular Spherical Haar Tight Framelets
In this article, we develop a general theoretical framework for constructing Haar-type tight framelets on any compact set with a hierarchical partition. In particular, we construct a novel area-regular hierarchical partition on the two spheres and establish its corresponding spherical Haar tight framelets with directionality. We conclude by evaluating and illustrate the effectiveness of our area-regular spherical Haar tight framelets in several denoising experiments. Furthermore, we propose a convolutional neural network (CNN) model for spherical signal denoising, which employs fast framelet decomposition and reconstruction algorithms. Experiment results show that our proposed CNN model outperforms threshold methods and processes strong generalization and robustness.
- 1 June 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 557-560
A Digital Video Watermarking Algorithm Based on DCT Domain
In order to solve the conflict with robustness and invisibility of video watermark, the algorithms proposed in this paper select certain blocks according to the texture. By using the binary image to deal with logistic chaotic map and error-correction coding as watermarked data can improve the robustness and security. The low frequency signals of the selected blocks are modified such that their Discrete Cosine Transform (DCT) fulfills a constraint imposed by the watermark code. Experiment results show that this algorithm provides a larger embedding capacity and has a certain robustness and invisibility.
- 1 June 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 557-560
A Digital Video Watermarking Algorithm Based on DCT Domain
In order to solve the conflict with robustness and invisibility of video watermark, the algorithms proposed in this paper select certain blocks according to the texture. By using the binary image to deal with logistic chaotic map and error-correction coding as watermarked data can improve the robustness and security. The low frequency signals of the selected blocks are modified such that their Discrete Cosine Transform (DCT) fulfills a constraint imposed by the watermark code. Experiment results show that this algorithm provides a larger embedding capacity and has a certain robustness and invisibility.