Changan Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Changan Yuan has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Long Chen
Guangxi Academic of sciences, Nanning, China
2 shared publications - Ye He
Guangxi Association for Artificial Intelligence, Nanning, China
2 shared publications Chengcheng Huang
Nanning Normal University
1 shared publication- Dingjia Chen
Guangxi Key Lab of Human–Machine Interaction and Intelligent Decision, Guangxi Academy of Science, Nanning 530007, China
1 shared publication - Huixian Liao
Guangxi Key Lab of Human–Machine Interaction and Intelligent Decision, Guangxi Academy of Science, Nanning 530007, China
1 shared publication - Jianhui Jiang
Guangxi Academic of Sciences, Nanning 530007, China
1 shared publication
Latest Publications
- Open Access
- 10 January 2026
- Published by Springer Nature in Neural Processing Letters
- Vol. 58 (1)
EGDCF: Edge-Guided Diffusion Networks with Coarse-to-Fine Learning for Image Denoising
- 10 January 2026
- Published by Springer Nature in Neural Processing Letters
- Vol. 58 (1)
Open AccessEGDCF: Edge-Guided Diffusion Networks with Coarse-to-Fine Learning for Image Denoising
- Open Access
- 30 October 2025
- Published by MDPI AG in Electronics
- Vol. 14 (21) , 4243
Robust Denoising of Structure Noise Through Dual-Diffusion Brownian Bridge Modeling and Coupled Sampling
Recent denoising methods based on diffusion models typically formulate the task as a conditional generation process initialized from a standard Gaussian distribution. However, such stochastic initialization often leads to redundant sampling steps and unstable results due to the neglect of structured noise characteristics. To address these limitations, we propose a novel framework that directly bridges the probabilistic distributions of noisy and clean images while jointly modeling structured noise. We introduce Dual-diffusion Brownian Bridge Coupled Sampling (DBBCS) the first framework to incorporate Brownian bridge diffusion into image denoising. DBBCS synchronously models the distributions of clean images and structural noise via two coupled diffusion processes. Unlike conventional diffusion models, our method starts sampling directly from noisy observations and jointly optimizes image reconstruction and noise estimation through a coupled posterior sampling scheme. This allows for dynamic refinement of intermediate states by adaptively updating the sampling gradients using residual feedback from both image and noise paths. Specifically, DBBCS employs two parallel Brownian bridge models to learn the distributions of clean images and noise. During inference, their respective residual processes regulate each other to progressively enhance both denoising and noise estimation. A consistency constraint is enforced among the estimated noise, the reconstructed image, and the original noisy input to ensure stable and physically coherent results. Extensive experiments on standard benchmarks demonstrate that DBBCS achieves superior performance in both visual fidelity and quantitative metrics, offering a robust and efficient solution to image denoising.
- 30 October 2025
- Published by MDPI AG in Electronics
- Vol. 14 (21) , 4243
Open AccessRobust Denoising of Structure Noise Through Dual-Diffusion Brownian Bridge Modeling and Coupled Sampling
Recent denoising methods based on diffusion models typically formulate the task as a conditional generation process initialized from a standard Gaussian distribution. However, such stochastic initialization often leads to redundant sampling steps and unstable results due to the neglect of structured noise characteristics. To address these limitations, we propose a novel framework that directly bridges the probabilistic distributions of noisy and clean images while jointly modeling structured noise. We introduce Dual-diffusion Brownian Bridge Coupled Sampling (DBBCS) the first framework to incorporate Brownian bridge diffusion into image denoising. DBBCS synchronously models the distributions of clean images and structural noise via two coupled diffusion processes. Unlike conventional diffusion models, our method starts sampling directly from noisy observations and jointly optimizes image reconstruction and noise estimation through a coupled posterior sampling scheme. This allows for dynamic refinement of intermediate states by adaptively updating the sampling gradients using residual feedback from both image and noise paths. Specifically, DBBCS employs two parallel Brownian bridge models to learn the distributions of clean images and noise. During inference, their respective residual processes regulate each other to progressively enhance both denoising and noise estimation. A consistency constraint is enforced among the estimated noise, the reconstructed image, and the original noisy input to ensure stable and physically coherent results. Extensive experiments on standard benchmarks demonstrate that DBBCS achieves superior performance in both visual fidelity and quantitative metrics, offering a robust and efficient solution to image denoising.
- Open Access
- 27 February 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (5) , 1164
MFANet: A Collar Classification Network Based on Multi-Scale Features and an Attention Mechanism
The collar is an important part of a garment that reflects its style. The collar classification task is to recognize the collar type in the apparel image. In this paper, we design a novel convolutional module called MFA (multi-scale features attention) to address the problems of high noise, small recognition target and unsatisfactory classification effect in collar feature recognition, which first extracts multi-scale features from the input feature map and then encodes them into an attention weight vector to enhance the representation of important parts, thus improving the ability of the convolutional block to combat noise and extract small target object features. It also reduces the computational overhead of the MFA module by using the depth-separable convolution method. Experiments on the collar dataset Collar6 and the apparel dataset DeepFashion6 (a subset of the DeepFashion database) show that MFANet is able to perform at a relatively small number of collars. MFANet can achieve better classification performance than most current mainstream convolutional neural networks for complex collar images with less computational overhead. Experiments on the standard dataset CIFAR-10 show that MFANet also outperforms current mainstream image classification algorithms.
- 27 February 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (5) , 1164
Open AccessMFANet: A Collar Classification Network Based on Multi-Scale Features and an Attention Mechanism
The collar is an important part of a garment that reflects its style. The collar classification task is to recognize the collar type in the apparel image. In this paper, we design a novel convolutional module called MFA (multi-scale features attention) to address the problems of high noise, small recognition target and unsatisfactory classification effect in collar feature recognition, which first extracts multi-scale features from the input feature map and then encodes them into an attention weight vector to enhance the representation of important parts, thus improving the ability of the convolutional block to combat noise and extract small target object features. It also reduces the computational overhead of the MFA module by using the depth-separable convolution method. Experiments on the collar dataset Collar6 and the apparel dataset DeepFashion6 (a subset of the DeepFashion database) show that MFANet is able to perform at a relatively small number of collars. MFANet can achieve better classification performance than most current mainstream convolutional neural networks for complex collar images with less computational overhead. Experiments on the standard dataset CIFAR-10 show that MFANet also outperforms current mainstream image classification algorithms.
- 4 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (5) , 2629-2638
Predicting MiRNA-Disease Associations by Graph Representation Learning Based on Jumping Knowledge Networks
Growing studies have shown that miRNAs are inextricably linked with many human diseases, and a great deal of effort has been spent on identifying their potential associations. Compared with traditional experimental methods, computational approaches have achieved promising results. In this article, we propose a graph representation learning method to predict miRNA-disease associations. Specifically, we first integrate the verified miRNA-disease associations with the similarity information of miRNA and disease to construct a miRNA-disease heterogeneous graph. Then, we apply a graph attention network to aggregate the neighbor information of nodes in each layer, and then feed the representation of the hidden layer into the structure-aware jumping knowledge network to obtain the global features of nodes. The output features of miRNAs and diseases are then concatenated and fed into a fully connected layer to score the potential associations. Through five-fold cross-validation, the average AUC, accuracy and precision values of our model are 93.30%, 85.18% and 88.90%, respectively. In addition, for three case studies of the esophageal tumor, lymphoma and prostate tumor, 46, 45 and 45 of the top 50 miRNAs predicted by our model were confirmed by relevant databases. Overall, our method could provide a reliable alternative for miRNA-disease association prediction.
- 4 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (5) , 2629-2638
Predicting MiRNA-Disease Associations by Graph Representation Learning Based on Jumping Knowledge Networks
Growing studies have shown that miRNAs are inextricably linked with many human diseases, and a great deal of effort has been spent on identifying their potential associations. Compared with traditional experimental methods, computational approaches have achieved promising results. In this article, we propose a graph representation learning method to predict miRNA-disease associations. Specifically, we first integrate the verified miRNA-disease associations with the similarity information of miRNA and disease to construct a miRNA-disease heterogeneous graph. Then, we apply a graph attention network to aggregate the neighbor information of nodes in each layer, and then feed the representation of the hidden layer into the structure-aware jumping knowledge network to obtain the global features of nodes. The output features of miRNAs and diseases are then concatenated and fed into a fully connected layer to score the potential associations. Through five-fold cross-validation, the average AUC, accuracy and precision values of our model are 93.30%, 85.18% and 88.90%, respectively. In addition, for three case studies of the esophageal tumor, lymphoma and prostate tumor, 46, 45 and 45 of the top 50 miRNAs predicted by our model were confirmed by relevant databases. Overall, our method could provide a reliable alternative for miRNA-disease association prediction.
- 5 October 2020
- Published by Springer Nature
- p. 355-366
A Classification Algorithm for Real Collar Images
- 5 October 2020
- Published by Springer Nature
- p. 355-366
A Classification Algorithm for Real Collar Images