Yuxuan Cheng

Dr. Yuxuan Cheng

orcid

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
3 November 2024
Verified
Book Chapter
Closed access
PDF file
MCMing Chen
Ming Chen
YCYuxuan Cheng
Yuxuan Cheng
XHXinwei He
Xinwei He
XWXinyue Wang
Xinyue Wang
YAYan Aze
Yan Aze
JXJinhai Xiang
Jinhai Xiang

23 July 2024 in Foods
Verified
Journal Article
Open access
PDF file
YCYuxuan Cheng
Yuxuan Cheng
一黄一丹 黄
一丹 黄
JZJingjing Zhang
Jingjing Zhang
XZXuehong Zhang
Xuehong Zhang
Qiaohua WangQiaohua Wang
Qiaohua Wang
Wei FanWei Fan
Wei Fan
The presence of cracks reduces egg quality and safety, and can easily cause food safety hazards to consumers. Machine vision-based methods for cracked egg detection have achieved significant success on in-domain egg data. However, the performance of deep learning models usually decreases under practical industrial scenarios, such as the different egg varieties, origins, and environmental changes. Existing researches that rely on improving network structures or increasing training data volumes cannot effectively solve the problem of model performance decline on unknown egg testing data in practical egg production. To address these challenges, a novel and robust detection method is proposed to extract max domain-invariant features to enhance the model performance on unknown test egg data. Firstly, multi-domain egg data are built on different egg origins and acquisition devices. Then, a multi-domain trained strategy is established by using Maximum Mean Discrepancy with Normalized Squared Feature Estimation (NSFE-MMD) to obtain the optimal matching egg training domain. With the NSFE-MMD method, the original deep learning model can be applied without network structure improvements, which reduces the extremely complex tuning process and hyperparameter adjustments. Finally, robust cracked egg detection experiments are carried out on several unknown testing egg domains. The YOLOV5 (You Only Look Once v5) model trained by the proposed multi-domain training method with NSFE-MMD has a detection mAP of 86.6% on the unknown test Domain 4, and the YOLOV8 (You Only Look Once v8) model has a detection mAP of 88.8% on Domain 4, which is an increase of 8% and 4.4% compared to the best performance of models trained on a single domain, and an increase of 4.7% and 3.7% compared to models trained on all domains. In addition, the YOLOV5 model trained by the proposed multi-domain training method has a detection mAP of 87.9% on egg data of the unknown testing Domain 5. The experimental results demonstrate the robustness and effectiveness of the proposed multi-domain training method, which can be more suitable for the large quantity and variety of egg detection production.

13 July 2025
Verified
Conference Paper
Open access
XHXinwei He
Xinwei He
LMLiang Ma
Liang Ma
YCYuxuan Cheng
Yuxuan Cheng
ZWZhichuan Wang
Zhichuan Wang
YWYulong Wang
Yulong Wang
XBXiang Bai
Xiang Bai

15 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
HZHaoyu Zhang
Haoyu Zhang
YCYuxuan Cheng
Yuxuan Cheng
WFWenqi Fan
Wenqi Fan
YCYulong Chen
Yulong Chen
YZYifan Zhang
Yifan Zhang
Graph neural networks (GNNs) have achieved remarkable success in various domains, yet they often struggle with domain adaptation due to significant structural distribution shifts and insufficient exploration of transferable patterns. One of the main reasons behind this is that traditional approaches do not treat global and local patterns discriminatingly so that some local details in the graph may be violated after multi-layer GNN. Our key insight is that domain shifts can be better understood through spectral analysis, where low-frequency components often encode domain-invariant global patterns, and high-frequency components capture domain-specific local details. As such, we propose FracNet (\underline{\textbf{Fr}}equency \underline{\textbf{A}}ware \underline{\textbf{C}}ontrastive Graph \underline{\textbf{Net}}work) with two synergic modules to decompose the original graph into high-frequency and low-frequency components and perform frequency-aware domain adaption. Moreover, the blurring boundary problem of domain adaptation is improved by integrating with a contrastive learning framework. Besides the practical implication, we also provide rigorous theoretical proof to demonstrate the superiority of FracNet. Extensive experiments further demonstrate significant improvements over state-of-the-art approaches.

3 October 2025
Verified
Book Chapter
Closed access
PDF file
HZHaoyu Zhang
Haoyu Zhang
YCYuxuan Cheng
Yuxuan Cheng
WFWenqi Fan
Wenqi Fan
YCYulong Chen
Yulong Chen
YZYifan Zhang
Yifan Zhang

27 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
TZTong Zhang
Tong Zhang
HLHaoyang Liu
Haoyang Liu
PZPeiyan Zhang
Peiyan Zhang
YCYuxuan Cheng
Yuxuan Cheng
HWHaohan Wang
Haohan Wang
In the field of computer graphics, the use of vector graphics, particularly Scalable Vector Graphics (SVG), represents a notable development from traditional pixel-based imagery. SVGs, with their XML-based format, are distinct in their ability to directly and explicitly represent visual elements such as shape, color, and path. This direct representation facilitates a more accurate and logical depiction of graphical elements, enhancing reasoning and interpretability. Recognizing the potential of SVGs, the machine learning community has introduced multiple methods for image vectorization. However, transforming images into SVG format while retaining the relational properties and context of the original scene remains a key challenge. Most vectorization methods often yield SVGs that are overly complex and not easily interpretable. In response to this challenge, we introduce our method, Simple-SVG-Generation (S\textsuperscript{2}VG\textsuperscript{2}). Our method focuses on producing SVGs that are both accurate and simple, aligning with human readability and understanding. With simple images, we evaluate our method with reasoning tasks together with advanced language models, the results show a clear improvement over previous SVG generation methods. We also conducted surveys for human evaluation on the readability of our generated SVGs, the results also favor our methods.