Yang Yang

Dr. Yang Yang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 July 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JDJuxing Di
Juxing Di
KXKaikai Xi
Kaikai Xi
YYYang Yang
Yang Yang
To address the challenges in floating waste detection on water surfaces, such as small object scale, irregular shapes, and strong background interference, this study proposes an enhanced detection model based on the YOLOv8s frame work, named ES-YOLOv8. The new model optimizes the feature fusion strategy in the neck, constructing a refined “160-80-40-20” multiscale detection frame work. Integrated with the Efficient Multiscale Attention (EMA) module, it significantly improves the model’s ability to extract features of small float ing objects. Additionally, an innovative Shape-IoU loss function is employed to optimize the bounding box regression accuracy of irregular targets through shape-sensitive constraints. This results in the development of an enhanced model that integrates feature enhancement, interference suppression, and localization optimization. Experimental results in a self-constructed floating waste dataset demonstrate that, compared to baseline YOLOv8s, the ES-YOLOv8 algorithm improves mAP@0.5 and mAP@0.5:0.95 by 5.4% and 6.1%, respectively. Compar ative experiments with state-of-the-art models further validate its superiority and effectiveness. Furthermore, experiments conducted on public datasets confirm the robustness and generalizability of ES-YOLOv8. This study aims to provide a high-precision, low-power-consumption technological solution for intelligent water governance, offering potential ecological and engineering applications.

14 May 2025 in IEEE Access
Verified
Journal Article
Open access
GLGuisuo Liu
Guisuo Liu
JDJuxing Di
Juxing Di
QWQing Wang
Qing Wang
YZYan Zhao
Yan Zhao
YYYang Yang
Yang Yang
Accurate pest identification is crucial for ensuring both high quality and high yield in rice production. This paper proposes RicePest-YOLO, a practical and generalizable model designed for agricultural pest detection, based on structural optimization and lightweight strategies applied to the YOLOv8 architecture. The model is specifically tailored to address the challenges of rice pest images, such as small insect size, complex backgrounds, and high inter-class similarity. In particular, it integrates ODConv and the BiFPN structure into the backbone and neck of YOLOv8n, enhancing the model’s ability to extract features from rice pest images. Subsequently, the Shape-IoU loss function is employed to enhance the model’s sensitivity and precision in target recognition. Furthermore, to facilitate the deployment of the new algorithm on embedded terminal devices, we applied Layer Adaptive Magnitude Pruning and Knowledge Distillation techniques for a lightweight model. The effectiveness of the proposed model was evaluated on common rice pest datasets. Experimental results demonstrate that the proposed model outperforms YOLOv8n, achieving an mAP@0.5 of 94.3%, and an mAP@0.5:0.95 of 67.3%, with 2.7% improvement in mAP@0.5 and 1.2% improvement in mAP@0.5:0.95. Comparison experiments with state-of-the-art models further demonstrated the proposed approach’s superiority. The model’s generalization and robustness were tested on the Pests dataset and the Paddy Rice Pest dataset. Results indicated a 2.6% and 3.0% improvement in mAP@0.5, and a 2.8% and 4.0% increase in mAP@0.5:0.95, respectively. Additionally, Experimental results show that the lightweight version of RicePest-YOLO reduced parameters by 48.1% and GFLOPs by 50%, with only a marginal decrease of 0.4% in mAP@0.5. The results validate that the proposed model is not only effective and efficient but also robust and lightweight, making it a promising solution for rice pest detection and offering valuable support for pest management in precision agriculture.

11 November 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
SWShouluan Wu
Shouluan Wu
JFJianglong Fu
Jianglong Fu
LLLiefa Liao
Liefa Liao
CSChao Song
Chao Song
YFYating Fang
Yating Fang
YYYang Yang
Yang Yang
The detection of defects on steel surfaces constitutes a vital area of research in computer vision, characterized by its complexity and variety, which pose significant difficulties for accurate identification. In this context, we introduce a deep learning framework that combines multi-channel random coding with modules for multi-scale feature fusion to tackle the challenges of low recognition accuracy and insufficient classification power prevalent in conventional models. Our model capitalizes on the self-attention mechanism associated with the Transformer architecture, alongside the strong feature extraction capabilities of Convolutional Neural Networks (CNNs), to facilitate a combined improvement in performance. To start, we enhance the model’s feature extraction functionality by incorporating ResNet18 along with global self-attention. Next, we bring forth a novel improvement to the backbone network by adding a multi-channel shuffled encoding module, which effectively encodes various features through the interactions of different convolutional groups, thus minimizing the number of parameters. Additionally, we introduce a multi-feature fusion module UPC-SimAM (upsample concatenated Simple Parameter-Free Attention Module), which is free from parameter redundancy to bolster the model’s capacity to merge multi-scale features. Our experiments on the NEU-DET and GC10-DE datasets demonstrate that our model outperforms existing state-of-the-art techniques regarding detection efficiency. Specifically, the model registers a classification accuracy of 91.72%, an mAP@0.5 of 83.03%, and an mAP@0.5:0.95 of 45.55% on the NEU-DET dataset. On the GC10-DE dataset, it achieves a classification precision of 76.73%, an mAP@0.5 of 65.03%, and an mAP@0.5:0.95 of 32.46%. Through detailed ablation studies and visualization experiments, we affirm the considerable potential and benefits of the proposed SH-DETR model in the field of detecting defects on steel surfaces.

16 December 2024 in IEEE Access
Verified
Journal Article
Open access
YYYang Yang
Yang Yang
FFFangtao Feng
Fangtao Feng
GLGuisuo Liu
Guisuo Liu
JDJuxing Di
Juxing Di
In recent years, deep learning has been extensively applied to small object detection, achieving significant advancements. Nevertheless, there remains substantial potential to improve both the effectiveness and efficiency of small object detection in Uncrewed aerial vehicle (UAV) images. In this article, we propose a novel YOLO model with multi-scale, effective, and lightweight methods for traffic small object detection, termed MEL-YOLO. Initially, the improved model reconstructed the multi-scale network structure, the high-resolution feature enhancement network increases size from 40x40 to 160x160. Secondly, the improved model incorporates a decoupled detection head, which separates the classification task from the localization task, thereby improving detection accuracy while increasing detection complexity. Furthermore, we explore the Soft-NMS algorithm to effectively mitigate small object occlusion and reduce missed detection. Finally, this study emphasizes the design of a lightweight model by introducing a model pruning strategy along with the Ghost module. We have selected four C3 modules, each with a substantial number of output channels, to integrate with the Ghost module. This method results in fewer parameters, lower GFLOPs, and higher FPS. Experiment on the VisDrone2019 public dataset, compared to the baseline YOLOv5s, our model demonstrates an improvement of 8.5% in mAP@0.5 and 6.2% increase in mAP@0.5:0.95. Furthermore, there is a 55.7% reduction in parameters, a decrease of 7.0% GFLOPs, and an increase of 11.3% in FPS. To demonstrates the versatility and robustness of MEL-YOLO model, we conducted validation experiments on the SODA10M and CCTSDB datasets, where the mAP@0.5 improved by 1.9% and 1.2%, the FPS increased by 18 frame/s and 6 frame/s, respectively. These results align with our expectations, indicating that our model is a more effective and lightweight algorithm for dense and small objects detection in aerial images.

2 September 2025 in IEEE Access
Verified
Journal Article
Open access
JDJuxing Di
Juxing Di
KXKaikai Xi
Kaikai Xi
HNHuichang Niu
Huichang Niu
XWXiawei Wu
Xiawei Wu
YYYang Yang
Yang Yang
The swift advancement of UAV technology is accelerating the intelligent transformation of object detection methods. UAV applications now span both civilian and military sectors, playing a crucial role in scenarios such as aerial surveying, disaster response, and security monitoring. However, UAV image detection faces numerous challenges: targets are affected by flight altitude and viewing angle, leading to significant scale variations; dynamic flight results in constantly changing spatial layouts and complex backgrounds—such as dense vegetation and building textures—often weaken or obscure object features, making detection more difficult. To tackle these issues, we present a novel YOLOv8-based model tailored for small object detection in UAV images. In response to the prevalence of small targets in UAV images, the model enhances the multi-scale network structure and introduces the Large Separable Kernel Attention-enhanced Spatial Pyramid Pooling Fast Layer (SPPF-LSKA), improving the model’s capability to extract features from and respond to small objects. Furthermore, the introduction of the Minimum Point Distance IoU (MPDIoU) and Soft Non-Maximum Suppression (Soft-NMS) enables effective detection of overlapping and occluded targets. Experimental results on the VisDrone2019 dataset show that, compared with YOLOv8, the improved model increases mAP@0.5 by 7.6%, reduces parameter count by 23%, and has a model size of just 5MB. Compared with other current algorithms, The enhanced model delivers the best detection performance, highlighting the effectiveness of the proposed approach.

21 March 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
JDJuxing Di
Juxing Di
QWQing Wang
Qing Wang
YYYang Yang
Yang Yang
Accurate detection of small objects in complex low-altitude scenes is crucial for the widespread deployment of unmanned aerial vehicles (UAVs). However, UAV imagery often suffers from small object scales, cluttered backgrounds, and challenging feature extraction. To address these issues, we propose CSMA-DETR, an efficient transformer-based UAV object detection network with convolutional self-attention and matchability-adaptive classification. First, we design a novel feature extractor, Cross-Spatial Emulating Self-Attention with Convolution (CESC), which jointly integrates convolutional self-attention with spatial-domain processing. By using shared large kernels and hierarchical dynamic kernels, CESC emulates long-range dependency modeling and instance-adaptive behaviors of self-attention, strengthening multi-scale representations while reducing computational cost. Second, we introduce the Linear Patch-Aware Attention Feature Interaction (LPAFI) module. A multi-branch patch-aware attention mechanism captures cross-scale local correspondences, and a multi-scale linear attention mechanism further fuses CNN-style local detail representation with global context modeling, enabling efficient integration of local and global features. Finally, we propose Matchability-Varifocal Loss (MVL) to better optimize low-quality matched samples. MVL combines IoU-aware and matchability-aware weighting to dynamically adjust loss contributions and strengthen supervision for low-quality samples, accelerating convergence and improving robustness. Experiments on VisDrone2019 show that CSMA-DETR significantly outperforms the baseline, improving mAP50 and mAP50:95 by 5% and 2%, respectively, while reducing parameters and computation by 7.0% and 4.6%. Additional evaluations on DIOR and HIT-UAV further verify its effectiveness in cluttered scenes with densely distributed small objects, providing an efficient solution for real-time UAV detection.