Rui Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rui Huang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Wei Huang
School of Communication and Information Engineering, Shanghai University, Shanghai, China
3 shared publications- Wei Huang
School of Communication & Information Engineering, Shanghai University, Shanghai, P. R. China
3 shared publications Guopeng Zhang
School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publicationsJunli Chen
School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publicationsDan Zeng
1 shared publicationFengcai Zheng
School of Communication and Information Engineering, Shanghai University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 2076-2087
Dual-View Dynamic Sample Partition for Classification of Multilabel Remote Sensing Images With Noisy Labels
In recent years, deep-learning-based multi-label remote sensing image classification has achieved significant progress. However, deep learning usually requires a large quantity of training samples with clean labels for effective model learning. In practical applications, it is difficult to obtain the accurately and extensively labeled samples due to the constraints on manpower and materials. The presence of noisy labels will impair deep learning models' performance. To address this issue, the paper proposes to distinguish the samples with noisy labels from the ones with clean labels through dual-view dynamic sample partition and apply distinct loss item for each type of samples in the objective function. In the method, a new discrepancy metric is first presented to measure the inconsistency between the predicted labels obtained from the dual perspectives and the existing noisy labels for each sample image. Then, a joint loss function that incorporates the binary cross-entropy (BCE) loss for the samples with clean labels and the multi-label generalized cross-entropy (MGCE) loss for the samples with noisy labels is designed for network training to enhance the robustness against noise. Extensive experimental results of multi-label remote sensing image classification with noisy labels show that the proposed method outperforms some state-of-the-art methods, especially when the label noise rate is higher.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 2076-2087
Open AccessDual-View Dynamic Sample Partition for Classification of Multilabel Remote Sensing Images With Noisy Labels
In recent years, deep-learning-based multi-label remote sensing image classification has achieved significant progress. However, deep learning usually requires a large quantity of training samples with clean labels for effective model learning. In practical applications, it is difficult to obtain the accurately and extensively labeled samples due to the constraints on manpower and materials. The presence of noisy labels will impair deep learning models' performance. To address this issue, the paper proposes to distinguish the samples with noisy labels from the ones with clean labels through dual-view dynamic sample partition and apply distinct loss item for each type of samples in the objective function. In the method, a new discrepancy metric is first presented to measure the inconsistency between the predicted labels obtained from the dual perspectives and the existing noisy labels for each sample image. Then, a joint loss function that incorporates the binary cross-entropy (BCE) loss for the samples with clean labels and the multi-label generalized cross-entropy (MGCE) loss for the samples with noisy labels is designed for network training to enhance the robustness against noise. Extensive experimental results of multi-label remote sensing image classification with noisy labels show that the proposed method outperforms some state-of-the-art methods, especially when the label noise rate is higher.
- 6 May 2025
- Published by Elsevier in Neurocomputing
- Vol. 641
Spatial-adaptive mixup for domain adaptation in nighttime semantic segmentation
- 6 May 2025
- Published by Elsevier in Neurocomputing
- Vol. 641
Spatial-adaptive mixup for domain adaptation in nighttime semantic segmentation
- 22 December 2024
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 16 (2) , 170-180
Label enhancement for multi-label classification of remote sensing images with missing labels
- 22 December 2024
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 16 (2) , 170-180
Label enhancement for multi-label classification of remote sensing images with missing labels
- Open Access
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 20344-20354
Domain Adaptation for Multilabel Remote Sensing Image Annotation With Contrastive Pseudo-Label Generation
Deep-learning-based multi-label remote sensing image annotation (MLRSIA) is receiving increasing attention in recent years. MLRSIA needs a large volume of labeled samples for effective training of the deep models. However, the scarcity of labeled samples is a common challenge in this field. Domain adaptation (DA), aiming to transfer knowledge from label-rich datasets (source domains) to label-scarce datasets (target domains), has become an effective means to address this problem of limited labeled samples. But most of the existing DA models are primarily designed for single-label annotation tasks, leaving the application of DA to multi-label annotation tasks as an open issue. In this paper, a DA method for multi-label remote sensing image annotation, named Contrastive Pseudo-Label Generation (CPLG), is proposed. CPLG mainly consists of two parts: generating and selecting pseudo labels for the samples in the target domain, and enhancing the cross-domain feature consistency through contrastive learning. Specifically, the soft predictions (or posterior probabilities) and the corresponding pseudo labels of the target samples are first generated using neighborhood aggregation. Then, a positive and negative pseudo-label selection strategy is designed to refine these pseudo labels. Finally, a contrastive loss is introduced to align the similar sample features between the source and target domains to avoid that the pseudo labels of the target samples are overly biased towards the source domain, further improving the precision of these pseudo labels. The MLRSIA experiments, conducted across four different DA scenarios on three benchmark datasets, demonstrate the advantages of the proposed CPLG compared to other state-of-the-art methods.
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 20344-20354
Open AccessDomain Adaptation for Multilabel Remote Sensing Image Annotation With Contrastive Pseudo-Label Generation
Deep-learning-based multi-label remote sensing image annotation (MLRSIA) is receiving increasing attention in recent years. MLRSIA needs a large volume of labeled samples for effective training of the deep models. However, the scarcity of labeled samples is a common challenge in this field. Domain adaptation (DA), aiming to transfer knowledge from label-rich datasets (source domains) to label-scarce datasets (target domains), has become an effective means to address this problem of limited labeled samples. But most of the existing DA models are primarily designed for single-label annotation tasks, leaving the application of DA to multi-label annotation tasks as an open issue. In this paper, a DA method for multi-label remote sensing image annotation, named Contrastive Pseudo-Label Generation (CPLG), is proposed. CPLG mainly consists of two parts: generating and selecting pseudo labels for the samples in the target domain, and enhancing the cross-domain feature consistency through contrastive learning. Specifically, the soft predictions (or posterior probabilities) and the corresponding pseudo labels of the target samples are first generated using neighborhood aggregation. Then, a positive and negative pseudo-label selection strategy is designed to refine these pseudo labels. Finally, a contrastive loss is introduced to align the similar sample features between the source and target domains to avoid that the pseudo labels of the target samples are overly biased towards the source domain, further improving the precision of these pseudo labels. The MLRSIA experiments, conducted across four different DA scenarios on three benchmark datasets, demonstrate the advantages of the proposed CPLG compared to other state-of-the-art methods.
- 26 December 2023
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (6) , 2495-2511
Multi-label learning with incomplete labels via dual manifold mappings
- 26 December 2023
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (6) , 2495-2511
Multi-label learning with incomplete labels via dual manifold mappings
- Open Access
- 29 October 2023
- Published by MDPI AG in Electronics
- Vol. 12 (21) , 4445
Self-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion
Low-light image enhancement is a challenging task in non-uniform low-light conditions, often resulting in local overexposure, noise amplification, and color distortion. To obtain satisfactory enhancement results, most models must resort to carefully selected paired or multi-exposure data sets. In this paper, we propose a self-supervised framework for non-uniform low-light image enhancement to address these issues, only requiring low-light images on their own for training. We first design a robust Retinex model-based image exposure enhancement network (EENet) to obtain global brightness enhancement and noise removal of images by carefully designing the loss function of each decomposition map. Then, to correct overexposed areas in the enhanced image, we incorporate the inverse image of the low-light image for enhancement using EENet. Furthermore, a three-branch asymmetric exposure fusion network (TAFNet) is designed. The two enhanced images and the original image are used as the TAFNet inputs to obtain a globally well-exposed and detail-rich image. Experimental results demonstrate that our framework outperforms some state-of-the-art methods in visual and quantitative comparisons.
- 29 October 2023
- Published by MDPI AG in Electronics
- Vol. 12 (21) , 4445
Open AccessSelf-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion
Low-light image enhancement is a challenging task in non-uniform low-light conditions, often resulting in local overexposure, noise amplification, and color distortion. To obtain satisfactory enhancement results, most models must resort to carefully selected paired or multi-exposure data sets. In this paper, we propose a self-supervised framework for non-uniform low-light image enhancement to address these issues, only requiring low-light images on their own for training. We first design a robust Retinex model-based image exposure enhancement network (EENet) to obtain global brightness enhancement and noise removal of images by carefully designing the loss function of each decomposition map. Then, to correct overexposed areas in the enhanced image, we incorporate the inverse image of the low-light image for enhancement using EENet. Furthermore, a three-branch asymmetric exposure fusion network (TAFNet) is designed. The two enhanced images and the original image are used as the TAFNet inputs to obtain a globally well-exposed and detail-rich image. Experimental results demonstrate that our framework outperforms some state-of-the-art methods in visual and quantitative comparisons.
- 13 November 2022
- Published by Elsevier in Pattern Recognition
- Vol. 135
Face anti-spoofing using feature distilling and global attention learning
- 13 November 2022
- Published by Elsevier in Pattern Recognition
- Vol. 135
Face anti-spoofing using feature distilling and global attention learning
- Open Access
- 7 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 10087
Near-Infrared Image Colorization Using Asymmetric Codec and Pixel-Level Fusion
This paper mainly studies the colorization of near-infrared (NIR) images. Image colorization methods cannot be extended to NIR image colorization since the wavelength band of the NIR image exceeds the visible light spectral range and it is often linearly independent of the luminance of the RGB image. Furthermore, a symmetric codec, which cannot guarantee the ability of the encoder to extract features, is often used as the main frame of the network in both CNN-based colorization networks and CycleGAN-based colorization networks. In order to deal with the investigated problem, we propose a novel NIR colorization method using asymmetric codec (ACD) and pixel-level fusion. ACD is designed to improve the feature extraction ability of the encoder by allowing the information to enter deeper into the model and learning more non-redundant information. In addition, the global and local feature fusion networks (GLFFNet) are embedded between the encoder and the decoder to improve the prediction of the subtle color information of the image. The ACD and GLFFNet together constitute the colorization network (ColorNet) in this paper. Bilateral filtering and weighted least squares filtering (BFWLS) are used to fuse the pixel-level information of the input NIR image into the raw output image of the ColorNet. Finally, an intensive comparison analysis based on common datasets is conducted to verify superiority over existing methods in qualitative and quantitative visual assessments.
- 7 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 10087
Open AccessNear-Infrared Image Colorization Using Asymmetric Codec and Pixel-Level Fusion
This paper mainly studies the colorization of near-infrared (NIR) images. Image colorization methods cannot be extended to NIR image colorization since the wavelength band of the NIR image exceeds the visible light spectral range and it is often linearly independent of the luminance of the RGB image. Furthermore, a symmetric codec, which cannot guarantee the ability of the encoder to extract features, is often used as the main frame of the network in both CNN-based colorization networks and CycleGAN-based colorization networks. In order to deal with the investigated problem, we propose a novel NIR colorization method using asymmetric codec (ACD) and pixel-level fusion. ACD is designed to improve the feature extraction ability of the encoder by allowing the information to enter deeper into the model and learning more non-redundant information. In addition, the global and local feature fusion networks (GLFFNet) are embedded between the encoder and the decoder to improve the prediction of the subtle color information of the image. The ACD and GLFFNet together constitute the colorization network (ColorNet) in this paper. Bilateral filtering and weighted least squares filtering (BFWLS) are used to fuse the pixel-level information of the input NIR image into the raw output image of the ColorNet. Finally, an intensive comparison analysis based on common datasets is conducted to verify superiority over existing methods in qualitative and quantitative visual assessments.
- Open Access
- 22 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 6951-6961
Multilabel Remote Sensing Image Annotation With Multiscale Attention and Label Correlation
Deep-learning-based multilabel image annotation is receiving increasing attention in the field of remote sensing due to the great success of deep networks in single-label remote sensing image classification. Compared with those low-level features, the features extracted by the convolutional neural network (CNN) are more informative and can alleviate the problem of semantic gap. However, the CNN model tends to ignore the smaller objects when objects of different sizes exist in an image. In addition, how to efficiently leverage the correlation among multiple labels to enhance annotation performance remains an open issue. In this article, we propose an end-to-end deep learning framework for multilabel remote sensing image annotation. The framework is composed of a multiscale feature fusion module, a channel-spatial attention learning module, and a label correlation extraction module. The multiscale features from different layers of a CNN model are first fused and refined by using a channel-spatial attention mechanism. Then, the label correlation information is extracted from a label co-occurrence matrix and embedded into the multiscale attentive features to increase the discriminative ability of the resulting image features. The experiments on two benchmark datasets demonstrate the superiority of the proposed method in comparison with the state-of-the-art methods.
- 22 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 6951-6961
Open AccessMultilabel Remote Sensing Image Annotation With Multiscale Attention and Label Correlation
Deep-learning-based multilabel image annotation is receiving increasing attention in the field of remote sensing due to the great success of deep networks in single-label remote sensing image classification. Compared with those low-level features, the features extracted by the convolutional neural network (CNN) are more informative and can alleviate the problem of semantic gap. However, the CNN model tends to ignore the smaller objects when objects of different sizes exist in an image. In addition, how to efficiently leverage the correlation among multiple labels to enhance annotation performance remains an open issue. In this article, we propose an end-to-end deep learning framework for multilabel remote sensing image annotation. The framework is composed of a multiscale feature fusion module, a channel-spatial attention learning module, and a label correlation extraction module. The multiscale features from different layers of a CNN model are first fused and refined by using a channel-spatial attention mechanism. Then, the label correlation information is extracted from a label co-occurrence matrix and embedded into the multiscale attentive features to increase the discriminative ability of the resulting image features. The experiments on two benchmark datasets demonstrate the superiority of the proposed method in comparison with the state-of-the-art methods.
- 5 June 2021
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 12 (9) , 2659-2672
Local positive and negative label correlation analysis with label awareness for multi-label classification
- 5 June 2021
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 12 (9) , 2659-2672
Local positive and negative label correlation analysis with label awareness for multi-label classification