Yiyang Shen

Yiyang Shen

Auto-generated profile, based on publicly available information

Yiyang Shen

Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China

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
2 October 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YSYiyang Shen
Yiyang Shen
RYRongwei Yu
Rongwei Yu
PWPeng Wu
Peng Wu
Haoran XieHaoran Xie
Haoran Xie
LGLina Gong
Lina Gong
Mingqiang WeiMingqiang Wei
Mingqiang Wei
LiDAR and camera, as two different sensors, supply geometric (point clouds) and semantic (RGB images) information of 3D scenes. However, it is still challenging for existing methods to fuse data from the two cross sensors, making them complementary for quality 3D object detection (3OD). We propose ImLiDAR, a new 3OD paradigm to narrow the cross-sensor discrepancies by progressively fusing the multi-scale features of camera Images and LiDAR point clouds. ImLiDAR enables to provide the detection head with cross-sensor yet robustly fused features. To achieve this, two core designs exist in ImLiDAR. First, we propose a cross-sensor dynamic message propagation module to combine the best of the multi-scale image and point features. Second, we raise a direct set prediction problem that allows designing an effective set-based detector to tackle the inconsistency of the classification and localization confidences, and the sensitivity of hand-tuned hyperparameters. Besides, the novel set-based detector can be detachable and easily integrated into various detection networks. Comparisons on the KITTI, nuScenes, and SUN-RGBD datasets all show clear visual and numerical improvements of our ImLiDAR over forty-five state-of-the-art 3OD methods.

1 January 2023 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
YSYiyang Shen
Yiyang Shen
RYRongwei Yu
Rongwei Yu
NSNi Shu
Ni Shu
Jing QinJing Qin
Jing Qin
Mingqiang WeiMingqiang Wei
Mingqiang Wei
Object detection remains challenging in hazy weather conditions due to the poor visibility of captured images. There are currently two types of detectors capable of adapting to varying weather conditions: (i) low‐level adaptation methods that combine one detector with an additional dehazing network and (ii) high‐level adaptation methods that explore various kinds of domain adaptation knowledge. However, neither of these approaches can achieve desirable performance due to their inherent limitations. We raise an intriguing question—if combining both low‐level adaptation and high‐level adaptation, can improve the generalization ability of a detector in hazy weather conditions? To answer it, we propose a Joint High‐Low Adaptation Object Detection paradigm (HLA‐HOD) in hazy weather conditions. By combining both low‐level adaptation and high‐level adaptation, HLA‐HOD achieves superior performance on hazy images without requiring ground‐truth bounding boxes or clean images. Extensive experiments demonstrate that our method outperforms state‐of‐the‐art low‐level and high‐level adaptation methods by a large margin both quantitatively and qualitatively.

1 January 2024 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
RYRongwei Yu
Rongwei Yu
JXJingyi Xiang
Jingyi Xiang
NSNi Shu
Ni Shu
PZPeihao Zhang
Peihao Zhang
YLYizhan Li
Yizhan Li
LWLina Wang
Lina Wang
We propose a novel model‐free unsupervised learning paradigm to tackle the unfavorable prevailing problem of real‐world image deraining, dubbed MUL‐Derain. Beyond existing unsupervised deraining efforts, MUL‐Derain leverages a model‐free Multiscale Attentive Filtering (MSAF) to handle multiscale rain streaks. Therefore, formulation of any rain imaging is not necessary, and it requires neither iterative optimization nor progressive refinement operations. Meanwhile, MUL‐Derain can efficiently compute spatial coherence and global interactions by modeling long‐range dependencies, allowing MSAF to learn useful knowledge from a larger or even global rain region. Furthermore, we formulate a novel multiloss function to constrain MUL‐Derain to preserve both color and structure information from the rainy images. Extensive experiments on both synthetic and real‐world datasets demonstrate that our MUL‐Derain obtains state‐of‐the‐art performance over un/semisupervised methods and exhibits competitive advantages over the fully‐supervised ones.

27 October 2023
Verified
Conference Paper
Closed access
TXTang Xiaoyu
Tang Xiaoyu
WZWan Zihan
Wan Zihan
SYShen Yiyang
Shen Yiyang
The simulation data is complete, but the measured data is unbalanced or missing, which makes it difficult to apply the data-driven model. In addition, there are many adjustable hyperparameters and artificially adjusted random factors in the data-driven model, which leads to the final result of the model. Insufficient precision. Therefore, this paper proposes a rolling bearing fault image recognition method based on hyperparameter optimization and transfer learning.First, build a simulation model to generate some samples, and then screen the network through noise resistance, select a network with strong robustness, and then input the network with strong noise resistance with simulation data. In this paper, AlexNet depth volume is selected. A neural network is integrated and the model is tuned through hyperparameter optimization techniques. Finally, this paper constructs a model by migrating the evaluation model from the simulation domain to the measured data domain through feature projection to make up for the scarcity of samples. It is verified by experiments that the actual measurement data of rolling bearing faults from Case Western Reserve University is used, and the overall accuracy of the model is improved by means of the hyperparameter optimization method. In addition, this paper also uses transfer learning and feature projection methods to solve the problem of scarcity of measured fault samples, and has a good transfer effect and high accuracy after transfer. The above results have verified the improvement effect and good noise immunity of the above method.

19 July 2026
Verified
Conference Paper
Open access
YSYiyang Shen
Yiyang Shen
YYYin Yang
Yin Yang
KZKun Zhou
Kun Zhou
TSTianjia Shao
Tianjia Shao