Yufeng Cui

Mr. Yufeng Cui


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 August 2023 in Journal of Systems Engineering and Electronics
Verified
Journal Article
Closed access
YCYufeng Cui
Yufeng Cui
YWYongliang Wang
Yongliang Wang
WLWeijian Liu
Weijian Liu
QDQinglei Du
Qinglei Du
XZXichuan Zhang
Xichuan Zhang
XLXuhui Li
Xuhui Li
Aiming at the problem of detecting a distributed target when signal mismatch occurs, this paper proposes a tunable detector parameterized by an adjustable parameter. By adjusting the parameter, the tunable detector can achieve robust or selective detection of mismatched signals. Moreover, the proposed tunable detector, with a proper tunable parameter, can provide higher detection probability compared with existing detectors in the case of no signal mismatch. In addition, the proposed tunable detector possesses the constant false alarm rate property with the unknown noise covariance matrix.

9 November 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
YCYufeng Cui
Yufeng Cui
YWYongliang Wang
Yongliang Wang
WLWeijian Liu
Weijian Liu
QDQinglei Du
Qinglei Du
JLJun Liu
Jun Liu
In this letter, we consider the problem of detecting a signal in a kind of nonhomogeneity environment caused by random unknown interference. We propose an effective detector according to the detector design criterion of the two-step Durbin test or the two-step Wald test. The simulation results show that the proposed detector can provide slightly superior performance than that of existing detectors while maintaining approximately the same computational load, both under hypothetical interference conditions and other interference conditions.

1 January 2017
Verified
Conference Paper
Open access
PDF file
JWJiarong Wei
Jiarong Wei
LWLiying Wei
Liying Wei
YCYufeng Cui
Yufeng Cui

11 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
YCYufeng Cui
Yufeng Cui
LZLichen Zhao
Lichen Zhao
峰梁峰 梁
峰 梁
YLYangguang Li
Yangguang Li
JSJing SHAO
Jing SHAO
Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is because researchers do not choose consistent training recipes and even use different data, hampering the fair comparison between different methods. In this work, we propose CLIP-benchmark, a first attempt to evaluate, analyze, and benchmark CLIP and its variants. We conduct a comprehensive analysis of three key factors: data, supervision, and model architecture. We find considerable intuitive or counter-intuitive insights: (1). Data quality has a significant impact on performance. (2). Certain supervision has different effects for Convolutional Networks (ConvNets) and Vision Transformers (ViT). Applying more proper supervision can effectively improve the performance of CLIP. (3). Curtailing the text encoder reduces the training cost but not much affect the final performance. Moreover, we further combine DeCLIP with FILIP, bringing us the strongest variant DeFILIP. The CLIP-benchmark would be released at: https://github.com/Sense-GVT/DeCLIP for future CLIP research.