Kuan Li

Dr. Kuan Li

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
26 December 2023
Verified
Book Chapter
Closed access
PDF file
HCHaoyuan Chen
Haoyuan Chen
YHYufei Han
Yufei Han
YLYanyi Li
Yanyi Li
PXPin Xu
Pin Xu
KLKuan Li
Kuan Li
JYJianping Yin
Jianping Yin

26 September 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
HCHaoyuan Chen
Haoyuan Chen
YHYufei Han
Yufei Han
LYLinwei Yao
Linwei Yao
XWXin Wu
Xin Wu
KLKuan Li
Kuan Li
JYJianping Yin
Jianping Yin
Traditional U-shape segmentation models can achieve excellent performance with an elegant structure. However, the single-layer decoder structure of U-Net or SwinUnet is too “thin” to exploit enough information, resulting in large semantic differences between the encoder and decoder parts. Things get worse in the field of medical image processing, where annotated data are more difficult to obtain than other tasks. Based on this observation, we propose a U-like model named MS-UNet with a plug-and-play adaptive denoising module and ELoss for the medical image segmentation task in this study. Instead of the single-layer U-Net decoder structure used in Swin-UNet and TransUNet, we specifically designed a multi-scale nested decoder based on the Swin Transformer for U-Net. The proposed multi-scale nested decoder structure allows for the feature mapping between the decoder and encoder to be semantically closer, thus enabling the network to learn more detailed features. In addition, ELoss could improve the attention of the model to the segmentation edges, and the plug-and-play adaptive denoising module could prevent the model from learning the wrong features without losing detailed information. The experimental results show that MS-UNet could effectively improve network performance with more efficient feature learning capability and exhibit more advanced performance, especially in the extreme case with a small amount of training data. Furthermore, the proposed ELoss and denoising module not only significantly enhance the segmentation performance of MS-UNet but can also be applied individually to other models.

18 November 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
QCQichao Chen
Qichao Chen
KLKuan Li
Kuan Li
ZCZhiyuan Chen
Zhiyuan Chen
TMTomas Maul
Tomas Maul
JYJianping Yin
Jianping Yin
Out-of-distribution (OOD) detection is a crucial problem in practice, especially, for the safe deployment of machine learning models in industrial settings. Previous work has used free energy as a score function and proposed a fine-tuning method that utilized OOD data in the training phase of the classification model, which achieves a higher performance on the OOD detection task compared with traditional methods. One key drawback, however, is that the loss function parameters are highly dependent on involved datasets, which means it cannot be dynamically adapted and implemented in others settings; in other words, the general ability of the energy score is considerably limited. In this work, our point of departure is to enlarge distinguishability between in-distribution features and OOD data. Consequently, we present a simple yet effective sparsity-regularized (SR) tuning framework for this purpose. Our framework has two types of workflows depending on if external OOD data is available, the complexity of the original training loss is sharply reduced by adopting this modification, meanwhile, the adapted ability and detection performance are enhanced. Also, we contribute a mini dataset as a light and efficient alternative of the previous large-scale one. In the experiments, we verify the effectiveness of our framework in a wide range of typical datasets along with common network architectures.

12 March 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
FZFuyong Zhang
Fuyong Zhang
KLKuan Li
Kuan Li
ZRZiliang Ren
Ziliang Ren
Learning-based classifiers are found to be vulnerable to attacks by adversarial samples. Some works suggested that ensemble classifiers tend to be more robust than single classifiers against evasion attacks. However, recent studies have shown that this is not necessarily the case under more realistic settings of black-box attacks. In this paper, we propose a novel ensemble approach to improve the robustness of classifiers against evasion attacks by using diversified feature selection and a stochastic aggregation strategy. Our proposed scheme includes three stages. Firstly, the adversarial feature selection algorithm is used to select a feature each time that can trade-offbetween classification accuracy and robustness, and add it to the feature vector bank. Secondly, each feature vector in the bank is used to train a base classifier and is added to the base classifier bank. Finally, m classifiers from the classifier bank are randomly selected for decision-making. In this way, it can cause each classifier in the base classifier bank to have good performance in terms of classification accuracy and robustness, and it also makes it difficult to estimate the gradients of the ensemble accurately. Thus, the robustness of classifiers can be improved without reducing the classification accuracy. Experiments performed using both Linear and Kernel SVMs on genuine datasets for spam filtering, malware detection, and handwritten digit recognition demonstrate that our proposed approach significantly improves the classifiers’ robustness against evasion attacks.

21 October 2022
Verified
Conference Paper
Open access
PXPin Xu
Pin Xu
XWXin Wu
Xin Wu
YLYanyi Li
Yanyi Li
EHEjaz Ul Haq
Ejaz Ul Haq
JYJianping Yin
Jianping Yin
KLKuan Li
Kuan Li
In order to increase the segmentation impact of the Diabetic Foot Ulcer Challenge 2022 dataset, we train a selection of popular deep learning segmentation algorithms and improve training methods, such as adding Dice term to loss function, employing transfer learning and poly learning rate update strategy, etc., in this paper. Experiments show that our method is effective, we get a Dice score of 0.7045, which is better than the official baseline result of 0.6277. Moreover, we integrate the above segmentation models using four ensemble methods to evaluate segmentation performance, such as Averaging, Weighting, Voting, and Stacking. We observed that our proposed one-layer CNN stacking network exhibits superior segmentation performance (Dice score: 0.7142) compared to single CNN model and other three ensemble methods. Our performance surpasses the baseline result, placing us in the top 10 in the Diabetic Foot Ulcer Challenge 2022.

30 September 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
HCHaoyuan Chen
Haoyuan Chen
SZSihang Zhou
Sihang Zhou
KLKuan Li
Kuan Li
JYJianping Yin
Jianping Yin
JHJian Huang
Jian Huang
In the realm of human–robot interaction, the integration of visual and verbal cues has become increasingly significant. This paper focuses on the challenges and advancements in referring image segmentation (RIS), a task that involves segmenting images based on textual descriptions. Traditional approaches to RIS have primarily focused on pixel-level classification. These methods, although effective, often overlook the interconnectedness of pixels, which can be crucial for interpreting complex visual scenes. Furthermore, while the PolyFormer model has shown impressive performance in RIS, its large number of parameters and high training data requirements pose significant challenges. These factors restrict its adaptability and optimization on standard consumer hardware, hindering further enhancements in subsequent research. Addressing these issues, our study introduces a novel two-branch decoder framework with SAM (segment anything model) for RIS. This framework incorporates an MLP decoder and a KAN decoder with a multi-scale feature fusion module, enhancing the model’s capacity to discern fine details within images. The framework’s robustness is further bolstered by an ensemble learning strategy that consolidates the insights from both the MLP and KAN decoder branches. More importantly, we collect the segmentation target edge coordinates and bounding box coordinates as input cues for the SAM model. This strategy leverages SAM’s zero-sample learning capabilities to refine and optimize the segmentation outcomes. Our experimental findings, based on the widely recognized RefCOCO, RefCOCO+, and RefCOCOg datasets, confirm the effectiveness of this method. The results not only achieve state-of-the-art (SOTA) performance in segmentation but are also supported by ablation studies that highlight the contributions of each component to the overall improvement in performance.