Qing En
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
Qing En has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Fangfang Liang
School of Information Science and Technology, Hebei Agricultural University, Baoding 071001, China
5 shared publications - Yuhong Guo
Carleton University
4 shared publications - Lijuan Duan
College of Computer Science, Beijing University of Technology, Beijing, China
3 shared publications - Wei Ma
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
2 shared publications - Abdullah Alchihabi
School of Computer Science Carleton University Canada
1 shared publication Bian Ma
Beijing Univ Technol, Beijing Key Lab Trusted Comp, Beijing 100124, Peoples R China
1 shared publication
Latest Publications
- Open Access
- 20 July 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (14) , 1552
Semantic-Decoupled Dual Attention Network for Robust Apple Disease Detection
Apple leaf disease detection in orchards faces a unique challenge: lesion regions (foreground) are semantically important but visually less salient (weak texture, blurred boundaries), while background distractors (soil, weeds) are visually salient but semantically irrelevant. Traditional models, reliant on visual saliency, are usually misled by strong background textures. Unlike humans who first use leaf shape to locate possible lesions and then examine local textures, these models lack this semantic-guided strategy, leading to inaccurate detection. To address this problem, we propose a Semantic-Decoupled Dual Attention Network (SD-DAN). The core idea is to achieve target-distractor separation via semantic decoupling and then foreground enhancement and background suppression via dual attention. The network consists of two core modules. First, a frequency-enhanced preprocessing module adaptively fuses low- and high-frequency information to highlight lesion details and suppress redundant low-frequency information. Second, an attention-based foreground-background decoupling and enhancement module explicitly separates foreground and background with a learnable threshold, and applies a dual-attention mechanism: spatial-frequency enhancement to the foreground (active focusing) and spatial-frequency suppression to the background (active filtering), to improve discriminative features of apple disease. Experiments on the Apple Leaf Disease Dataset 9 (ALDD9) and the Apple Leaf Diseases Dataset demonstrate that SD-DAN achieves strong performance and consistently outperforms mainstream detectors across nine common apple disease detection tasks.
- 20 July 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (14) , 1552
Open AccessSemantic-Decoupled Dual Attention Network for Robust Apple Disease Detection
Apple leaf disease detection in orchards faces a unique challenge: lesion regions (foreground) are semantically important but visually less salient (weak texture, blurred boundaries), while background distractors (soil, weeds) are visually salient but semantically irrelevant. Traditional models, reliant on visual saliency, are usually misled by strong background textures. Unlike humans who first use leaf shape to locate possible lesions and then examine local textures, these models lack this semantic-guided strategy, leading to inaccurate detection. To address this problem, we propose a Semantic-Decoupled Dual Attention Network (SD-DAN). The core idea is to achieve target-distractor separation via semantic decoupling and then foreground enhancement and background suppression via dual attention. The network consists of two core modules. First, a frequency-enhanced preprocessing module adaptively fuses low- and high-frequency information to highlight lesion details and suppress redundant low-frequency information. Second, an attention-based foreground-background decoupling and enhancement module explicitly separates foreground and background with a learnable threshold, and applies a dual-attention mechanism: spatial-frequency enhancement to the foreground (active focusing) and spatial-frequency suppression to the background (active filtering), to improve discriminative features of apple disease. Experiments on the Apple Leaf Disease Dataset 9 (ALDD9) and the Apple Leaf Diseases Dataset demonstrate that SD-DAN achieves strong performance and consistently outperforms mainstream detectors across nine common apple disease detection tasks.
- 11 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 320
Attention-based unsupervised prompt learning for SAM in leaf disease segmentation
- 11 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 320
Attention-based unsupervised prompt learning for SAM in leaf disease segmentation
- 16 December 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (8) , 5405-5419
Dynamic text prompt joint multimodal features for accurate plant disease image captioning
- 16 December 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (8) , 5405-5419
Dynamic text prompt joint multimodal features for accurate plant disease image captioning
- 22 November 2024
- Published by Elsevier in Measurement
- Vol. 242
HDFA-Net: A high-dimensional decoupled frequency attention network for steel surface defect detection
- 22 November 2024
- Published by Elsevier in Measurement
- Vol. 242
HDFA-Net: A high-dimensional decoupled frequency attention network for steel surface defect detection
- 1 November 2024
- Published by Springer Nature
- p. 290-303
Multi-prototype Co-saliency Model for Plant Disease Detection
- 1 November 2024
- Published by Springer Nature
- p. 290-303
Multi-prototype Co-saliency Model for Plant Disease Detection
- 22 August 2024
- Published by Springer Nature
- p. 267-283
AKGNet: Attribute Knowledge Guided Unsupervised Lung-Infected Area Segmentation
- 22 August 2024
- Published by Springer Nature
- p. 267-283
AKGNet: Attribute Knowledge Guided Unsupervised Lung-Infected Area Segmentation
- 5 August 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 185, 152-159
Enhancing zero-shot object detection with external knowledge-guided robust contrast learning
- 5 August 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 185, 152-159
Enhancing zero-shot object detection with external knowledge-guided robust contrast learning
- Open Access
Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation
Medical image segmentation typically demands extensive dense annotations for model training, which is both time-consuming and skill-intensive. To mitigate this burden, exemplar-based medical image segmentation methods have been introduced to achieve effective training with only one annotated image. In this paper, we introduce a novel Cross-model Mutual learning framework for Exemplar-based Medical image Segmentation (CMEMS), which leverages two models to mutually excavate implicit information from unlabeled data at multiple granularities. CMEMS can eliminate confirmation bias and enable collaborative training to learn complementary information by enforcing consistency at different granularities across models. Concretely, cross-model image perturbation based mutual learning is devised by using weakly perturbed images to generate high-confidence pseudo-labels, supervising predictions of strongly perturbed images across models. This approach enables joint pursuit of prediction consistency at the image granularity. Moreover, cross-model multi-level feature perturbation based mutual learning is designed by letting pseudo-labels supervise predictions from perturbed multi-level features with different resolutions, which can broaden the perturbation space and enhance the robustness of our framework. CMEMS is jointly trained using exemplar data, synthetic data, and unlabeled data in an end-to-end manner. Experimental results on two medical image datasets indicate that the proposed CMEMS outperforms the state-of-the-art segmentation methods with extremely limited supervision.
Open AccessCross-model Mutual Learning for Exemplar-based Medical Image Segmentation
Medical image segmentation typically demands extensive dense annotations for model training, which is both time-consuming and skill-intensive. To mitigate this burden, exemplar-based medical image segmentation methods have been introduced to achieve effective training with only one annotated image. In this paper, we introduce a novel Cross-model Mutual learning framework for Exemplar-based Medical image Segmentation (CMEMS), which leverages two models to mutually excavate implicit information from unlabeled data at multiple granularities. CMEMS can eliminate confirmation bias and enable collaborative training to learn complementary information by enforcing consistency at different granularities across models. Concretely, cross-model image perturbation based mutual learning is devised by using weakly perturbed images to generate high-confidence pseudo-labels, supervising predictions of strongly perturbed images across models. This approach enables joint pursuit of prediction consistency at the image granularity. Moreover, cross-model multi-level feature perturbation based mutual learning is designed by letting pseudo-labels supervise predictions from perturbed multi-level features with different resolutions, which can broaden the perturbation space and enhance the robustness of our framework. CMEMS is jointly trained using exemplar data, synthetic data, and unlabeled data in an end-to-end manner. Experimental results on two medical image datasets indicate that the proposed CMEMS outperforms the state-of-the-art segmentation methods with extremely limited supervision.
- Open Access
Efficient Low-Rank GNN Defense Against Structural Attacks
Graph Neural Networks (GNNs) have been shown to possess strong representation abilities over graph data. However, GNNs are vulnerable to adversarial attacks, and even minor perturbations to the graph structure can significantly degrade their performance. Existing methods either are ineffective against sophisticated attacks or require the optimization of dense adjacency matrices, which is time-consuming and prone to local minima. To remedy this problem, we propose an Efficient Low-Rank Graph Neural Network (ELR-GNN) defense method, which aims to learn low-rank and sparse graph structures for defending against adversarial attacks, ensuring effective defense with greater efficiency. Specifically, ELR-GNN consists of two modules: a Coarse Low-Rank Estimation Module and a Fine-Grained Estimation Module. The first module adopts the truncated Singular Value Decomposition (SVD) to initialize the low-rank adjacency matrix estimation, which serves as a starting point for optimizing the low-rank matrix. In the second module, the initial estimate is refined by jointly learning a low-rank sparse graph structure with the GNN model. Sparsity is incorporated into the learned low-rank adjacency matrix by pruning weak connections, which can reduce redundant data while maintaining valuable information. As a result, instead of using the dense adjacency matrix directly, ELR-GNN can learn a low-rank and sparse estimate of it in a simple, efficient and easy to optimize manner. The experimental results demonstrate that ELR-GNN outperforms the state-of-the-art GNN defense methods in the literature, in addition to being very efficient and easy to train.
Open AccessEfficient Low-Rank GNN Defense Against Structural Attacks
Graph Neural Networks (GNNs) have been shown to possess strong representation abilities over graph data. However, GNNs are vulnerable to adversarial attacks, and even minor perturbations to the graph structure can significantly degrade their performance. Existing methods either are ineffective against sophisticated attacks or require the optimization of dense adjacency matrices, which is time-consuming and prone to local minima. To remedy this problem, we propose an Efficient Low-Rank Graph Neural Network (ELR-GNN) defense method, which aims to learn low-rank and sparse graph structures for defending against adversarial attacks, ensuring effective defense with greater efficiency. Specifically, ELR-GNN consists of two modules: a Coarse Low-Rank Estimation Module and a Fine-Grained Estimation Module. The first module adopts the truncated Singular Value Decomposition (SVD) to initialize the low-rank adjacency matrix estimation, which serves as a starting point for optimizing the low-rank matrix. In the second module, the initial estimate is refined by jointly learning a low-rank sparse graph structure with the GNN model. Sparsity is incorporated into the learned low-rank adjacency matrix by pruning weak connections, which can reduce redundant data while maintaining valuable information. As a result, instead of using the dense adjacency matrix directly, ELR-GNN can learn a low-rank and sparse estimate of it in a simple, efficient and easy to optimize manner. The experimental results demonstrate that ELR-GNN outperforms the state-of-the-art GNN defense methods in the literature, in addition to being very efficient and easy to train.
- Open Access
Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation
Medical image segmentation methods typically rely on numerous dense annotated images for model training, which are notoriously expensive and time-consuming to collect. To alleviate this burden, weakly supervised techniques have been exploited to train segmentation models with less expensive annotations. In this paper, we propose a novel point-supervised contrastive variance method (PSCV) for medical image semantic segmentation, which only requires one pixel-point from each organ category to be annotated. The proposed method trains the base segmentation network by using a novel contrastive variance (CV) loss to exploit the unlabeled pixels and a partial cross-entropy loss on the labeled pixels. The CV loss function is designed to exploit the statistical spatial distribution properties of organs in medical images and their variance distribution map representations to enforce discriminative predictions over the unlabeled pixels. Experimental results on two standard medical image datasets demonstrate that the proposed method outperforms the state-of-the-art weakly supervised methods on point-supervised medical image semantic segmentation tasks.
Open AccessAnnotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation
Medical image segmentation methods typically rely on numerous dense annotated images for model training, which are notoriously expensive and time-consuming to collect. To alleviate this burden, weakly supervised techniques have been exploited to train segmentation models with less expensive annotations. In this paper, we propose a novel point-supervised contrastive variance method (PSCV) for medical image semantic segmentation, which only requires one pixel-point from each organ category to be annotated. The proposed method trains the base segmentation network by using a novel contrastive variance (CV) loss to exploit the unlabeled pixels and a partial cross-entropy loss on the labeled pixels. The CV loss function is designed to exploit the statistical spatial distribution properties of organs in medical images and their variance distribution map representations to enforce discriminative predictions over the unlabeled pixels. Experimental results on two standard medical image datasets demonstrate that the proposed method outperforms the state-of-the-art weakly supervised methods on point-supervised medical image semantic segmentation tasks.