Renjie Huang
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
Renjie Huang has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Mao Ye
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Cheng Zhan
Southwest University
2 shared publications - Jianping Gou
Southwest University
2 shared publications - Lan Du
Monash University
2 shared publications - Qing Tian
University of Alabama at Birmingham
2 shared publications - Shaoning Zeng
Yangtze Delta Region Institute (Huzhou) University of Electronic Science and Technology of China Huzhou China
2 shared publications
Latest Publications
- 11 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Discriminative Relation-Aware Data-Free Adversarial Distillation
- 11 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Discriminative Relation-Aware Data-Free Adversarial Distillation
- 22 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
Online feature correlation knowledge distillation via adaptive ensemble teacher
- 22 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
Online feature correlation knowledge distillation via adaptive ensemble teacher
- Open Access
- 10 November 2025
- Published by Frontiers Media SA in Frontiers in Big Data
- Vol. 8, 1705587
PHTFNet-RPM: a probabilistic hybrid network with RPM for tobacco root disease forecasting
Introduction: Tobacco growers usually face particular challenges in predicting the risks of tobacco root diseases due to complex pathogenesis, concealed early symptoms, and heterogeneous farm conditions. Methods: To address this problem, we proposed a flexible Probabilistic Hybrid Temporal Fusion Network with Random Period Mask (PHTFNet-RPM). This model is designed to forecast future multi-day disease incidences and indices. It incorporates a hybrid input structure with RPM to handle configurable static management variables and time-series data of weather factors and disease metrics, using the RPM to simulate diverse absences of historical observations. The model's internal hierarchically aggregated modules learn cross-variable and cross-temporal feature representations to model the complex non-linear relationships. Furthermore, probabilistic theory-based uncertainty quantification is designed to enhance the model's credibility and reliability. Results: The proposed PHTFNet-RPM was validated using a large-scale time-series dataset of tobacco root diseases, organized from 20-year meteorological and disease survey records in Chuxiong Prefecture, Yunnan Province. Extensive comparative experiments demonstrated that our model achieves a 4.44%–16.43% lower mean absolute error (MAE) than existing models (including LR, SVR, CNN-LSTM, and LSTM-Attention). Discussion: The results confirm that the model can reliably forecast disease progression trends under different configurations, even when relying solely on historical weather observations. The integration of uncertainty quantification provides a robust tool for assessing prediction reliability, offering significant practical value for disease management.
- 10 November 2025
- Published by Frontiers Media SA in Frontiers in Big Data
- Vol. 8, 1705587
Open AccessPHTFNet-RPM: a probabilistic hybrid network with RPM for tobacco root disease forecasting
Introduction: Tobacco growers usually face particular challenges in predicting the risks of tobacco root diseases due to complex pathogenesis, concealed early symptoms, and heterogeneous farm conditions. Methods: To address this problem, we proposed a flexible Probabilistic Hybrid Temporal Fusion Network with Random Period Mask (PHTFNet-RPM). This model is designed to forecast future multi-day disease incidences and indices. It incorporates a hybrid input structure with RPM to handle configurable static management variables and time-series data of weather factors and disease metrics, using the RPM to simulate diverse absences of historical observations. The model's internal hierarchically aggregated modules learn cross-variable and cross-temporal feature representations to model the complex non-linear relationships. Furthermore, probabilistic theory-based uncertainty quantification is designed to enhance the model's credibility and reliability. Results: The proposed PHTFNet-RPM was validated using a large-scale time-series dataset of tobacco root diseases, organized from 20-year meteorological and disease survey records in Chuxiong Prefecture, Yunnan Province. Extensive comparative experiments demonstrated that our model achieves a 4.44%–16.43% lower mean absolute error (MAE) than existing models (including LR, SVR, CNN-LSTM, and LSTM-Attention). Discussion: The results confirm that the model can reliably forecast disease progression trends under different configurations, even when relying solely on historical weather observations. The integration of uncertainty quantification provides a robust tool for assessing prediction reliability, offering significant practical value for disease management.
- 22 July 2025
- Published by Springer Nature
- p. 213-225
WT-Based Feature Enhancement Network for Camouflaged Object Detection
- 22 July 2025
- Published by Springer Nature
- p. 213-225
WT-Based Feature Enhancement Network for Camouflaged Object Detection
- Open Access
- 7 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (4) , 1-21
Generative Adversarial Networks with Learnable Auxiliary Module for Image Synthesis
Training generative adversarial networks (GANs) for noise-to-image synthesis is a challenge task, primarily due to the instability of GANs’ training process. One of the key issues is the generator’s sensitivity to input data, which can cause sudden fluctuations in the generator’s loss value with certain inputs. This sensitivity suggests an inadequate ability to resist disturbances in the generator, causing the discriminator’s loss value to oscillate and negatively impacting the discriminator. Then, the negative feedback of discriminator is also not conducive to updating generator’s parameters, leading to suboptimal image generation quality. In response to this challenge, we present an innovative GANs model equipped with a learnable auxiliary module that processes auxiliary noise. The core objective of this module is to enhance the stability of both the generator and discriminator throughout the training process. To achieve this target, we incorporate a learnable auxiliary penalty and an augmented discriminator, designed to control the generator and reinforce the discriminator’s stability, respectively. We further apply our method to the Hinge and LSGANs loss functions, illustrating its efficacy in reducing the instability of both the generator and the discriminator. The tests we conducted on LSUN, CelebA, Market-1501, and Creative Senz3D datasets serve as proof of our method’s ability to improve the training stability and overall performance of the baseline methods.
- 7 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (4) , 1-21
Open AccessGenerative Adversarial Networks with Learnable Auxiliary Module for Image Synthesis
Training generative adversarial networks (GANs) for noise-to-image synthesis is a challenge task, primarily due to the instability of GANs’ training process. One of the key issues is the generator’s sensitivity to input data, which can cause sudden fluctuations in the generator’s loss value with certain inputs. This sensitivity suggests an inadequate ability to resist disturbances in the generator, causing the discriminator’s loss value to oscillate and negatively impacting the discriminator. Then, the negative feedback of discriminator is also not conducive to updating generator’s parameters, leading to suboptimal image generation quality. In response to this challenge, we present an innovative GANs model equipped with a learnable auxiliary module that processes auxiliary noise. The core objective of this module is to enhance the stability of both the generator and discriminator throughout the training process. To achieve this target, we incorporate a learnable auxiliary penalty and an augmented discriminator, designed to control the generator and reinforce the discriminator’s stability, respectively. We further apply our method to the Hinge and LSGANs loss functions, illustrating its efficacy in reducing the instability of both the generator and the discriminator. The tests we conducted on LSUN, CelebA, Market-1501, and Creative Senz3D datasets serve as proof of our method’s ability to improve the training stability and overall performance of the baseline methods.
- Open Access
Yield Evaluation of Citrus Fruits based on the YoloV5 compressed by Knowledge Distillation
In the field of planting fruit trees, pre-harvest estimation of fruit yield is important for fruit storage and price evaluation. However, considering the cost, the yield of each tree cannot be assessed by directly picking the immature fruit. Therefore, the problem is a very difficult task. In this paper, a fruit counting and yield assessment method based on computer vision is proposed for citrus fruit trees as an example. Firstly, images of single fruit trees from different angles are acquired and the number of fruits is detected using a deep Convolutional Neural Network model YOLOv5, and the model is compressed using a knowledge distillation method. Then, a linear regression method is used to model yield-related features and evaluate yield. Experiments show that the proposed method can accurately count fruits and approximate the yield.
Open AccessYield Evaluation of Citrus Fruits based on the YoloV5 compressed by Knowledge Distillation
In the field of planting fruit trees, pre-harvest estimation of fruit yield is important for fruit storage and price evaluation. However, considering the cost, the yield of each tree cannot be assessed by directly picking the immature fruit. Therefore, the problem is a very difficult task. In this paper, a fruit counting and yield assessment method based on computer vision is proposed for citrus fruit trees as an example. Firstly, images of single fruit trees from different angles are acquired and the number of fruits is detected using a deep Convolutional Neural Network model YOLOv5, and the model is compressed using a knowledge distillation method. Then, a linear regression method is used to model yield-related features and evaluate yield. Experiments show that the proposed method can accurately count fruits and approximate the yield.
- Open Access
- 19 May 2021
- Published by MDPI AG in Agriculture
- Vol. 11 (5) , 460
A Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies
Citrus flies are important quarantine pests in citrus plantations. Electronic traps (e-traps) based on computer vision are the most popular types of equipment for monitoring them. However, most current e-traps are inefficient and unreliable due to requiring manual operations and lack of reliable detection and identification algorithms of citrus fly images. To address these problems, this paper presents a monitoring scheme based on automatic e-traps and novel recognition algorithms. In this scheme, the prototype of an automatic motor-driven e-trap is firstly designed based on a yellow sticky trap. A motor autocontrol algorithm based on Local Binary Pattern (LBP) image analysis is proposed to automatically replace attractants in the e-trap for long-acting work. Furthermore, for efficient and reliable statistics of captured citrus flies, based on the differences between two successive sampling images of the e-trap, a simple and effective detection algorithm is presented to continuously detect the newly captured citrus flies from the collected images of the e-trap. Moreover, a Multi-Attention and Multi-Part convolutional neural Network (MAMPNet) is proposed to exploit discriminative local features of citrus fly images to recognize the citrus flies in the images. Finally, extensive simulation experiments validate the feasibility and efficiency of the designed e-trap prototype and its autocontrol algorithm, as well as the reliability and effectiveness of the proposed detection and recognition algorithms for citrus flies.
- 19 May 2021
- Published by MDPI AG in Agriculture
- Vol. 11 (5) , 460
Open AccessA Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies
Citrus flies are important quarantine pests in citrus plantations. Electronic traps (e-traps) based on computer vision are the most popular types of equipment for monitoring them. However, most current e-traps are inefficient and unreliable due to requiring manual operations and lack of reliable detection and identification algorithms of citrus fly images. To address these problems, this paper presents a monitoring scheme based on automatic e-traps and novel recognition algorithms. In this scheme, the prototype of an automatic motor-driven e-trap is firstly designed based on a yellow sticky trap. A motor autocontrol algorithm based on Local Binary Pattern (LBP) image analysis is proposed to automatically replace attractants in the e-trap for long-acting work. Furthermore, for efficient and reliable statistics of captured citrus flies, based on the differences between two successive sampling images of the e-trap, a simple and effective detection algorithm is presented to continuously detect the newly captured citrus flies from the collected images of the e-trap. Moreover, a Multi-Attention and Multi-Part convolutional neural Network (MAMPNet) is proposed to exploit discriminative local features of citrus fly images to recognize the citrus flies in the images. Finally, extensive simulation experiments validate the feasibility and efficiency of the designed e-trap prototype and its autocontrol algorithm, as well as the reliability and effectiveness of the proposed detection and recognition algorithms for citrus flies.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Energy Minimization for Data Collection in Wireless Sensor Networks with UAV
Unmanned aerial vehicle (UAV) enabled communication has emerged as an appealing technology in wireless sensor networks (WSNs) for efficient data collection. This paper studies the energy issues for data collection in UAV enabled WSNs. It is revealed that a fundamental tradeoff exists between the energy consumption of UAV and that of all sensor nodes (SNs). To characterize such a tradeoff, an optimization problem is formulated to minimize the weighted sum of the energy consumption of UAV and SNs, via jointly optimizing the UAV trajectory, mission completion time, as well as the wake-up scheduling for all SNs. As the formulated problem is a non-convex problem with infinite variables over time, it is difficult to be optimally solved. To tackle this issue, the original problem is transformed into a discretized equivalent with path discretization method, and then a locally optimal solution is obtained by applying the successive convex approximation and block coordinate descent techniques. Simulations are conducted to corroborate our study and show the flexible tradeoff achieved by the proposed design for energy balance between UAV and SNs.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Energy Minimization for Data Collection in Wireless Sensor Networks with UAV
Unmanned aerial vehicle (UAV) enabled communication has emerged as an appealing technology in wireless sensor networks (WSNs) for efficient data collection. This paper studies the energy issues for data collection in UAV enabled WSNs. It is revealed that a fundamental tradeoff exists between the energy consumption of UAV and that of all sensor nodes (SNs). To characterize such a tradeoff, an optimization problem is formulated to minimize the weighted sum of the energy consumption of UAV and SNs, via jointly optimizing the UAV trajectory, mission completion time, as well as the wake-up scheduling for all SNs. As the formulated problem is a non-convex problem with infinite variables over time, it is difficult to be optimally solved. To tackle this issue, the original problem is transformed into a discretized equivalent with path discretization method, and then a locally optimal solution is obtained by applying the successive convex approximation and block coordinate descent techniques. Simulations are conducted to corroborate our study and show the flexible tradeoff achieved by the proposed design for energy balance between UAV and SNs.
- 27 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 25 (4) , 541-545
Off-Feature Information Incorporated Metric Learning for Face Recognition
Distance metric learning suppresses the intraclass variation while preserving the inter-class variation between two feature vectors. However, these two types of information are mixed in the feature vectors that need to be separated based on learning from the training data. The limited training data may not be able to well separate these two types of information and hence limits the effectiveness of metric learning. This letter proposes to exploit off-feature information to help suppress the intraclass variation of the feature vectors. For face recognition, some identity-independent information such as pose, expression, and occlusion is extracted from source images and utilized as the off-feature information to enhance the performance of distance metric learning. In training, the algorithm learns how to incorporate the off-feature information to suppress the intraclass variation of features. In recognition, the similarity score of a face image pair is determined by its distance in feature space and that of off-feature space. Extensive experiments demonstrate that the proposed off-feature information incorporated metric learning is helpful to suppress the intraclass variation of feature vectors, which visibly enhances the existing metric learning algorithms.
- 27 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 25 (4) , 541-545
Off-Feature Information Incorporated Metric Learning for Face Recognition
Distance metric learning suppresses the intraclass variation while preserving the inter-class variation between two feature vectors. However, these two types of information are mixed in the feature vectors that need to be separated based on learning from the training data. The limited training data may not be able to well separate these two types of information and hence limits the effectiveness of metric learning. This letter proposes to exploit off-feature information to help suppress the intraclass variation of the feature vectors. For face recognition, some identity-independent information such as pose, expression, and occlusion is extracted from source images and utilized as the off-feature information to enhance the performance of distance metric learning. In training, the algorithm learns how to incorporate the off-feature information to suppress the intraclass variation of features. In recognition, the similarity score of a face image pair is determined by its distance in feature space and that of off-feature space. Extensive experiments demonstrate that the proposed off-feature information incorporated metric learning is helpful to suppress the intraclass variation of feature vectors, which visibly enhances the existing metric learning algorithms.
- 23 November 2014
- Published by Springer Nature in The Visual Computer
- Vol. 31 (12) , 1683-1695
Learning to pool high-level features for face representation
- 23 November 2014
- Published by Springer Nature in The Visual Computer
- Vol. 31 (12) , 1683-1695
Learning to pool high-level features for face representation