YYYinhui Yu

Yinhui Yu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yinhui Yu has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Adaptive Management With Learning-Based Page-Level FTL for Flash-Based SSDs

    by Haodong Lin, Shengzhe Wang, Zihang Lin, Suzhen Wu, Hong Jiang, Jie Zhang, Yinhui Yu, Bo Mao

  • Open Access

    Machine Learning Analysis of Coastal Water Pollution in China: Drivers and Complex Relationships

    by Dehong Sun, Senwei Zheng, Yinhui Yu

    This study investigates the nonlinear effects of socioeconomic, pollution control, and technological innovation factors on seawater pollution using a Generalised Additive Model (GAM) and panel data from 11 Chinese coastal provinces (2018-2023). Key findings indicate: (1) Chemical Oxygen Demand Emissions (CODE) from direct marine discharge sources showed a temporal pattern of “initial increase, subsequent decrease, and gradual stabilisation”, with significant spatial heterogeneity - Zhejiang recorded the highest emissions, Tianjin the lowest; (2) GAM revealed significant nonlinear relationships between most variables and CODE; (3) Factor impacts exhibited distinct range-dependent characteristics. These findings provide a scientific basis for identifying key pollution sources and formulating differentiated control strategies, leading to targeted policy recommendations.

  • Open Access

    Enhancing Quantum Approximate Optimization Algorithm Through Manifold Optimization

    by Qingqing Yu, Yinhui Yu, Rong Jin

    We propose the models of Riemannian manifold optimization techniques to enhance the performance of the quantum approximate optimization algorithm (QAOA) for combinatorial optimization problems on near‐term quantum devices. The approach leverages the intrinsic geometric structure of the problem domain, addressing the nonconvexity of the QAOA objective function and overcoming challenges posed by traditional gradient descent optimizers. We introduce three Riemannian optimization methods, including Riemannian steepest descent, Riemannian conjugate gradient, and Riemannian trust regions for QAOA, and demonstrate their superiority over other techniques, such as Bayesian optimization, particle swarms, Nelder–Mead, and Adam. Riemannian trust regions generally achieve a convergence speed that is three times faster than other methods such as Adan, TuRBO, and Adam.

  • Open Access

    Unified diffusion‐based object detection in multi‐modal and low‐light remote sensing images

    by Xu Sun, Yinhui Yu, Qing Cheng

    Remote sensing object detection remains a challenge under complex conditions such as low light, adverse weather, modality attacks or losses. Previous approaches typically alleviate this problem by enhancing visible images or leveraging multi‐modal fusion technologies. In view of this, the authors propose a unified framework based on YOLO‐World that combines the advantages of both schemes, achieving more adaptable and robust remote sensing object detection in complex real‐world scenarios. This framework introduces a unified modality modelling strategy, allowing the model to learn abundant object features from multiple remote sensing datasets. Additionally, a U‐fusion neck based on the diffusion method is designed to effectively remove modality‐specific noise and generate missing complementary features. Extensive experiments were conducted on four remote sensing image datasets: Multimodal VEDAI, DroneVehicle, unimodal VisDrone and UAVDT. This approach achieves average precision scores of 50.5, 55.3, 25.1, and 20.7, which outperforms advanced multimodal remote sensing object detection methods and low‐light image enhancement techniques.


  • Low-Rank Multimodal Remote Sensing Object Detection With Frequency Filtering Experts

    by Xu Sun, Yinhui Yu, Qing Cheng

    Visible-infrared object detection for remote sensing images plays an important role in the unmanned aerial vehicle (UAV) around-the-clock application. Most of the existing work focuses on designing complex network architectures to fuse complementary features, while few methods consider computational complexity and susceptibility against modality attacks, limiting the deployment of state-of-the-art frameworks. In this paper, we present a low-rank multimodal object detection approach with frequency filtering experts, called LF-MDet, which is based on the advanced DINO (detection transformer with improved denoising anchor boxes) framework. This approach achieves more accurate detection with fewer computational resources. In particular, when the specific modality is attacked or missing, our method still maintains higher robustness towards such pervasive perturbations. Specifically, we propose a low-rank enhancement technology and a dynamic illumination-aware mask module to enable a single backbone network in the form of batch formulation to unbiasedly and compatibly extract multimodal features. Furthermore, we design a lightweight frequency expert encoder from the frequency domain perspective to efficiently fuse complementary features by filtering out amplitude noise components and mixing feature tokens. Extensive experiments are conducted on the multimodal remote sensing object detection datasets, VEDAI and DroneVehicle. The results demonstrate the superiority of the proposed approach over advanced multimodal remote sensing object detectors. Compared to the baseline method, our LF-MDet effectively reduces the floating point of operations (FLOPs) by approximately 65% while improving detection accuracy. The code is available at https://github.com/cq100/LF-MDet.


  • Open Access

    Robust and Discriminative Feature Learning via Mutual Information Maximization for Object Detection in Aerial Images

    by Xu Sun, Yinhui Yu, Qing Cheng

    Object detection in unmanned aerial vehicle (UAV) aerial images has become increasingly important in military and civil applications. General object detection models are not robust enough against interclass similarity and intraclass variability of small objects, and UAV-specific nuisances such as uncontrolled weather conditions. Unlike previous approaches focusing on high-level semantic information, we report the importance of underlying features to improve detection accuracy and robustness from the information-theoretic perspective. Specifically, we propose a robust and discriminative feature learning approach through mutual information maximization (RD-MIM), which can be integrated into numerous object detection methods for aerial images. Firstly, we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain. Then, we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories. Finally, we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields. We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking (UAVDT) datasets to prove the effectiveness of the proposed method. The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods, achieving relative growth rates of 51.0% and 39.4% in corruption robustness, respectively. Our code is available at (accessed on 2 August 2024).


  • Open Access

    Expert teacher based on foundation image segmentation model for object detection in aerial images

    by Yinhui Yu, Xu Sun, Qing Cheng

    Despite the remarkable progress of general object detection, the lack of labeled aerial images limits the robustness and generalization of the detector. Teacher–student learning is a feasible solution on natural image domain, but few works focus on unlabeled aerial images. Inspired by foundation models with the powerful generalization in computer vision field, we propose an expert teacher framework based on foundation image segmentation model called ET-FSM. Our approach provides the performance gains for the student detector by generating high-quality pseudo-labels for unlabeled aerial images. In the ET-FSM, we design the binary detector with expert guidance mechanism to sufficiently leverage the extra knowledge obtained from the foundation image segmentation model, which accurately detects object positions in the complex backgrounds. Also, we present the momentum contrast classification module to distinguish confused object categories in aerial images. To demonstrate the effectiveness of the proposed method, we construct an unlabeled aerial image dataset covering various scenes. The experiments are conducted on diverse types of student detectors. The results show that the proposed approach achieves superior performance compared to existing methods, and allows the student detector to achieve fully supervised performance with much less labeled aerial images. Our dataset and code are available athttps://github.com/cq100/ET-FSM.


  • LED recognition method based on deep learning in UAV optical camera communication

    by Xu Sun, YinHui Yu, Qing Cheng

    Optical camera communication (OCC) is a potential technology in unmanned aerial vehicle (UAV) communication scenes, which can be used as a complementary scheme for radio frequency (RF) technology to effectively mitigate electromagnetic interference. The UAV OCC system still has the problems of low reliability, poor robustness, and long latency. In this paper, we propose the n -ary image that contains binary image information with different thresholds for the LED area. In addition, the multi-spectrum fast recognition (MFR) algorithm based on deep learning is designed. The MFR algorithm combines the frequency channel attention (FCA) and the involution convolution operator, which take the n -ary image as input to accurately identify the LED state. The experiment results show that the proposed method can reduce the bit error rate (BER) and latency of the UAV OCC system.