Mengyang Pu

Dr. Mengyang Pu

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
8 January 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZLZhihao Liu
Zhihao Liu
HYHui Yin
Hui Yin
YMYANG MI
YANG MI
MPMengyang Pu
Mengyang Pu
SWSong Wang
Song Wang
Shadow removal can significantly improve the image visual quality and has many applications in computer vision. Deep learning methods based on CNNs have become the most effective approach for shadow removal by training on either paired data, where both the shadow and underlying shadow-free versions of an image are known, or unpaired data, where shadow and shadow-free training images are totally different with no correspondence. In practice, CNN training on unpaired data is more preferred given the easiness of training data collection. In this paper, we present a new Lightness-Guided Shadow Removal Network (LG-ShadowNet) for shadow removal by training on unpaired data. In this method, we first train a CNN module to compensate for the lightness and then train a second CNN module with the guidance of lightness information from the first CNN module for final shadow removal. We also introduce a loss function to further utilise the colour prior of existing data. Extensive experiments on widely used ISTD, adjusted ISTD and USR datasets demonstrate that the proposed method outperforms the state-of-the-art methods with training on unpaired data.

15 December 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
RYRumeng Yi
Rumeng Yi
YHYaping Huang
Yaping Huang
QGQingji Guan
Qingji Guan
MPMengyang Pu
Mengyang Pu
RZRunsheng Zhang
Runsheng Zhang
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly aim at image-level tasks, which can not capture the relationship between neighboring labels in one image. Therefore, we propose a graph-based label noise detection and correction framework to deal with pixel-level noisy labels. In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from these noisy labels according to the cross-entropy loss. Then, we adopt a superpixel-based graph to represent the relations of spatial adjacency and semantic similarity between pixels in one image. Finally we correct the noisy labels using a Graph Attention Network (GAT) supervised by detected clean labels. We comprehensively conduct experiments on PASCAL VOC 2012, PASCAL-Context, MS-COCO and Cityscapes datasets. The experimental results show that our proposed semi-supervised method achieves the state-of-the-art performances and even outperforms the fully-supervised models on PASCAL VOC 2012 and MS-COCO datasets in some cases.

21 November 2024 in Electronics
Verified
Journal Article
Open access
PDF file
HWHua WU
Hua WU
HHHaotian Hong
Haotian Hong
Li SunLi Sun
Li Sun
XBXiaojing Bai
Xiaojing Bai
MPMengyang Pu
Mengyang Pu
This paper introduces Answer-Augmented Prompting (AAP), an innovative approach that leverages the Response Consistency of History of Dialogue (HoD) phenomenon in Large Language Models (LLMs). AAP not only achieves significantly superior performance enhancements compared to traditional augmentation methods but also exhibits a stronger potential for “jailbreaking”, allowing models to produce unsafe or misleading responses. By strategically modifying the HoD, AAP influences LLM performance in a dual manner: it promotes accuracy while amplifying risks associated with bypassing built-in safeguards. Our experiments demonstrate that AAP outperforms standard methods in both effectiveness and the ability to elicit harmful content. To address these risks, we propose comprehensive mitigation strategies for both LLM service providers and end-users. This research offers valuable insights into the implications of Response Consistency in LLMs, underscoring the promise and peril of this powerful capability.

1 June 2026 in Expert Systems with Applications
Verified
Journal Article
Closed access
HWHua WU
Hua WU
WZWanhao Zheng
Wanhao Zheng
MZMinghao Zhang
Minghao Zhang
XBXiaojing Bai
Xiaojing Bai
MPMengyang Pu
Mengyang Pu
YXYuhan Xu
Yuhan Xu

1 May 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HWHua WU
Hua WU
HHHaotian Hong
Haotian Hong
JMJiayu Mao
Jiayu Mao
ZYZhexun Yin
Zhexun Yin
YWYanxiong Wu
Yanxiong Wu
YLYIHUAN LI
YIHUAN LI
Large language models (LLMs) have been widely used in real-world applications due to their ability to decipher and make sense of perturbed information. However, the performance of LLMs that suffered from input perturbations has not been fully analyzed. In this paper, we propose a self-correction reflection method inspired by human cognition to improve robustness and mitigate the impact of perturbations on LLM performance. Firstly, we analyze the vulnerabilities of tokenization in LLMs through empirical demonstrations, comparative analysis with human cognition, and theoretical investigation of perturbation susceptibility. Secondly, we imitate the correction of input information in the human brain, which is enhanced by the consistency principle, aiming to enable the model to correct the perturbation and reduce the impact on the final response. Finally, we conduct experiments to validate the method’s efficacy, demonstrating improved performance across multiple models and datasets. We introduce a new evaluation metric, Model-Specific Cosine Similarity (MSCS), to quantify how well a specific model understands perturbation text, providing a more comprehensive evaluation of different LLM architectures. Particularly for different types of perturbations, after applying self-correction reflection, the average MSCS improvement across all models reaches 10.88%, while the average ACC improvement is 10.22%. The study also underscores the need for more innovative tokenization techniques and architectural design to achieve human-like cognitive robustness. This study could pave the way for more reliable, adaptable, and intelligent language models capable of thriving in practical applications.

25 December 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HWHua WU
Hua WU
ZHZhe Huang
Zhe Huang
WZWanhao Zheng
Wanhao Zheng
XBXiaojing Bai
Xiaojing Bai
Li SunLi Sun
Li Sun
MPMengyang Pu
Mengyang Pu
The semantic segmentation of drone LiDAR data is important in intelligent industrial operation and maintenance. However, current methods are not effective in directly processing airborne true-color point clouds that contain geometric and color noise. To overcome this challenge, we propose a novel hybrid learning framework, named SSGAM-Net, which combines supervised and semi-supervised modules for segmenting objects from airborne noisy point clouds. To the best of our knowledge, we are the first to build a true-color industrial point cloud dataset, which is obtained by drones and covers 90,000 m2. Secondly, we propose a plug-and-play module, named the Global Adjacency Matrix (GAM), which utilizes only few labeled data to generate the pseudo-labels and guide the network to learn spatial relationships between objects in semi-supervised settings. Finally, we build our point cloud semantic segmentation network, SSGAM-Net, which combines a semi-supervised GAM module and a supervised Encoder–Decoder module. To evaluate the performance of our proposed method, we conduct experiments to compare our SSGAM-Net with existing advanced methods on our expert-labeled dataset. The experimental results show that our SSGAM-Net outperforms the current advanced methods, reaching 85.3% in mIoU, which ranges from 4.2 to 58.0% higher than other methods, achieving a competitive level.