Search

Your search keyword '"Lu, Yijie"' showing total 270 results
Start Over Author "Lu, Yijie"
270 results on '"Lu, Yijie"'

4. WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather Removal

Author

Luo, Yulin, Zhao, Rui, Wei, Xiaobao, Chen, Jinwei, Lu, Yijie, Xie, Shenghao, Wang, Tianyu, Xiong, Ruiqin, Lu, Ming, and Zhang, Shanghang

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Adverse weather removal tasks like deraining, desnowing, and dehazing are usually treated as separate tasks. However, in practical autonomous driving scenarios, the type, intensity,and mixing degree of weather are unknown, so handling each task separately cannot deal with the complex practical scenarios. In this paper, we study the blind adverse weather removal problem. Mixture-of-Experts (MoE) is a popular model that adopts a learnable gate to route the input to different expert networks. The principle of MoE involves using adaptive networks to process different types of unknown inputs. Therefore, MoE has great potential for blind adverse weather removal. However, the original MoE module is inadequate for coupled multiple weather types and fails to utilize multi-scale features for better performance. To this end, we propose a method called Weather-aware Multi-scale MoE (WM-MoE) based on Transformer for blind weather removal. WM-MoE includes two key designs: WEather-Aware Router (WEAR) and Multi-Scale Experts (MSE). WEAR assigns experts for each image token based on decoupled content and weather features, which enhances the model's capability to process multiple adverse weathers. To obtain discriminative weather features from images, we propose Weather Guidance Fine-grained Contrastive Learning (WGF-CL), which utilizes weather cluster information to guide the assignment of positive and negative samples for each image token. Since processing different weather types requires different receptive fields, MSE leverages multi-scale features to enhance the spatial relationship modeling capability, facilitating the high-quality restoration of diverse weather types and intensities. Our method achieves state-of-the-art performance in blind adverse weather removal on two public datasets and our dataset. We also demonstrate the advantage of our method on downstream segmentation tasks.

Published
2023

11. Assembly Regulates Gamma Radiation Polymerization of Polytelluoxane.

Author

Zhang, Shenghan, Lu, Yijie, Song, Junjie, Guan, Jun, Dai, Yiheng, Cao, Wei, and Xu, Huaping

Abstract

Regulating chemical drug's responsiveness to gamma radiation is crucial for achieving better therapeutic effects in cancer treatment. Most research focused on thermodynamic chemical structure design, while little attention was paid to kinetic regulate strategy, which possesses greater universality and security. In this study, we achieved a kinetic‐based regulate strategy of gamma radiation reaction, through the construction of microphase environment during polymerization of polytelluoxane (PTeO). We designed hydrophobic segments forming large compound micelles (LCMs) assembly to create kinetically favorable higher concentration for radiation‐induced reaction. It exhibited a > ten times higher responsiveness and, as far as we know, merely required a minimum dosage of 5 Gy for polymerization to occur. What's more, by taking advantages of the assembly change with Te−O hydrophilic segments and gamma radiation, polymerization became milder with lower polydispersity than previous methods. Such kinetic‐based regulate strategy could offer a novel perspective on the design of radiation‐responsive chemoradiotherapy and other radiation‐induced chemical process. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

15. Quantitative Comparative Study on the Performance of a Valve-Controlled Actuator and Electro-Hydrostatic Actuator.

Author

Yang, Bo, Lu, Yijie, Jiang, Haoyi, Ling, Zhenfei, Li, Tong, Liu, Hao, and Ouyang, Xiaoping

Subjects
ELECTRICAL load, CONDITIONED response, QUANTITATIVE research, PERFORMANCE theory, COMPARATIVE studies, DYNAMIC testing, HYDROSTATIC extrusion, ACTUATORS
Abstract

The development of the electrification of aircraft has prompted aviation hydraulic systems to shift from traditional centralized valve actuators (CVAs) to electro-hydrostatic actuators (EHAs). In this paper, aiming at the demand for a quantitative comparison of performance between CVAs and EHAs, CVA and EHA prototypes with the same power level and test platform were developed. Then, based on the power flow and dynamic models of the CVA and EHA, simulation and experimental comparative tests were conducted using different load spectrum test conditions and step response test conditions. The comparative test results showed that the efficiency of the EHA was better than that of the CVA, and the dynamic response of the CVA was better than that of the EHA. Finally, a power loss quantification and parameter sensitivity analysis were performed to reveal the impact of different parameters on the different power losses and to provide suggestions for improving the performance of CVAs and EHAs. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

22. MoWE: Mixture of Weather Experts for Multiple Adverse Weather Removal

Author

Luo, Yulin, Zhao, Rui, Wei, Xiaobao, Chen, Jinwei, Lu, Yijie, Xie, Shenghao, Wang, Tianyu, Xiong, Ruiqin, Lu, Ming, and Zhang, Shanghang

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Currently, most adverse weather removal tasks are handled independently, such as deraining, desnowing, and dehazing. However, in autonomous driving scenarios, the type, intensity, and mixing degree of the weather are unknown, so the separated task setting cannot deal with these complex conditions well. Besides, the vision applications in autonomous driving often aim at high-level tasks, but existing weather removal methods neglect the connection between performance on perceptual tasks and signal fidelity. To this end, in upstream task, we propose a novel \textbf{Mixture of Weather Experts(MoWE)} Transformer framework to handle complex weather removal in a perception-aware fashion. We design a \textbf{Weather-aware Router} to make the experts targeted more relevant to weather types while without the need for weather type labels during inference. To handle diverse weather conditions, we propose \textbf{Multi-scale Experts} to fuse information among neighbor tokens. In downstream task, we propose a \textbf{Label-free Perception-aware Metric} to measure whether the outputs of image processing models are suitable for high level perception tasks without the demand for semantic labels. We collect a syntactic dataset \textbf{MAW-Sim} towards autonomous driving scenarios to benchmark the multiple weather removal performance of existing methods. Our MoWE achieves SOTA performance in upstream task on the proposed dataset and two public datasets, i.e. All-Weather and Rain/Fog-Cityscapes, and also have better perceptual results in downstream segmentation task compared to other methods. Our codes and datasets will be released after acceptance.

Published
2023

40. Noninherited Factors in Fetal Congenital Heart Diseases Based on Bayesian Network: A Large Multicenter Study

Author

Ruan, Yanping, primary, Liu, Xiangyu, additional, Zhu, Haogang, additional, Lu, Yijie, additional, Liu, Xiaowei, additional, Han, Jiancheng, additional, Sun, Lin, additional, Zhang, Ye, additional, Gu, Xiaoyan, additional, Zhao, Ying, additional, Li, Lei, additional, Ran, Suzhen, additional, Chen, Jingli, additional, Yu, Qiong, additional, Xu, Yan, additional, Xia, Hongmei, additional, and He, Yihua, additional

Published
2021
Full Text
View/download PDF

42. Monitoring the reaction kinetics of waterborne 2‐pack polyurethane coatings in the dispersion and during film formation.

Author

Zhou, Hang, Liu, Yang, Lu, Yijie, Tran, Kenneth, Schackmann, Joshua, Zhang, Margaret, Soleimani, Mohsen, Lucas, Frédéric, and Winnik, Mitchell A.

Subjects
CHEMICAL kinetics, HEXAMETHYLENE diisocyanate, POLYURETHANES, DISPERSION (Chemistry), CHEMICAL reactions, ACRYLIC coatings
Abstract

We examine the nature of the chemical reactions taking place in a waterborne two‐component polyurethane formulation consisting of an acrylic polyol latex and a hydrophilically modified polyisocyanate (hmPIC) based on the trimer of hexamethylene diisocyanate. The hmPIC was diluted with 30 wt.% of an organic solvent to reduce its viscosity and formed small (~20 nm) droplets when dispersed in water. In mixtures of the polyol and hmPIC, we monitored the rate of NCO group disappearance in the dispersed state by FTIR and showed that it varied with the choice of organic solvent. We developed a method based upon 19F NMR to distinguish the reaction of the NCO groups with OH groups from the polyol from its reaction with water. FTIR measurements on films formed from these dispersions showed how the disappearance of NCO groups depended on relative humidity. In a more semi‐quantitative way, these measurements indicated the relative extent of urethane versus urea formation in these model coatings. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

44. Efficient Strategies for Microglia Replacement in the Central Nervous System

Author

Xu, Zhen, primary, Rao, Yanxia, additional, Huang, Yubin, additional, Zhou, Tian, additional, Feng, Rui, additional, Xiong, Shanshan, additional, Yuan, Ti-Fei, additional, Qin, Shan, additional, Lu, Yijie, additional, Zhou, Xin, additional, Li, Xiaoyu, additional, Qin, Bo, additional, Mao, Ying, additional, and Peng, Bo, additional

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results