Kai Sheng

Prof. Kai Sheng

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
21 April 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ALAo Lei
Ao Lei
KFKyon Fenng
Kyon Fenng
KSKai Sheng
Kai Sheng
HZHongyu Zhao
Hongyu Zhao
XHXin He
Xin He
ZCZigang Chen
Zigang Chen
The application of deep learning in remote sensing image classification has been paid more and more attention by industry and academia. However, manually designed remote sensing image classification models based on convolutional neural networks usually require sophisticated expert knowledge. Moreover, it is notoriously difficult to design a model with both high classification accuracy and few parameters. Recently, neural architecture search (NAS) has emerged as an effective method that can greatly reduce the heavy burden of manually designing models. However, it remains a challenge to search for a classification model with high classification accuracy and few parameters in the huge search space. To tackle this challenge, we propose TPENAS, a two-phase evolutionary neural architecture search framework, which optimizes the model using computational intelligence techniques in two search phases. In the first search phase, TPENAS searches for the optimal depth of the model. In the second search phase, TPENAS searches for the structure of the model from the perspective of the whole model. Experiments on three open benchmark datasets demonstrate that our proposed TPENAS outperforms the state-of-the-art baselines in both classification accuracy and reducing parameters.

29 July 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YLYiting Liu
Yiting Liu
Jianzhao LiJianzhao Li
Jianzhao Li
Maoguo GongMaoguo Gong
Maoguo Gong
HLHuilin Liu
Huilin Liu
KSKai Sheng
Kai Sheng
YZYu Zhou
Yu Zhou
Self-supervised learning, which leverages unlabeled data to learn useful feature representations by constructing auxiliary tasks, has been widely explored in few-shot scene classification to improve the feature representation and generalization capabilities of deep models in scarce data. However, most of the current related work adopts specific self-supervised auxiliary tasks (SSATs) for combinatorial improvement, and does not explore the intrinsic connection between different pretext tasks. In practice, the linkage of SSATs is complex, and the optimization of task-sharing parameters by minimizing linear combinations of losses can be conflicting. In addition, although a single combination of SSAT can improve certain performance on the baseline, it is not the personalized optimal solution on various remote sensing datasets with diverse properties. In this paper, we propose a collaborative self-supervised evolution (so-called CSENet) framework for few-shot remote sensing scene classification to automatically search for appropriate weights in balancing the task conflicts. In contrast to most existing methods, which consider all SSATs to be equally efficacious or fixed-weighted for the few-shot main task, CSENet achieves autonomous co-evolutionary optimization by encoding arbitrary self-supervised weights. Specifically, the complex self-supervised combinations for different remote sensing data are transformed into an evolutionary optimization problem, where chromosomes with weighting variables obtain the optimal combination with genetic operators. Based on the transfer learning few-shot training paradigm, CSENet first efficiently searches for optimal self-supervised combinations with potential by the proposed automatic collaborative evolution strategy, and automatically adjusts the weights without manual settings. Importantly, CSENet provides both inductive and transductive inference, and supports the embedding of arbitrary SSATs. The effectiveness of the proposed framework is demonstrated by state-of-the-art (SOTA) results on three benchmark datasets.

23 January 2025 in Nonlinear Dynamics
Verified
Journal Article
Closed access
PDF file
WWWenkang Wan
Wenkang Wan
KSKai Sheng
Kai Sheng
QCQing Cai
Qing Cai
LALei Ao
Lei Ao
NONan Ouyang
Nan Ouyang
DSDejene M. Sime
Dejene M. Sime

19 December 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
NONan Ouyang
Nan Ouyang
LALei Ao
Lei Ao
QCQing Cai
Qing Cai
WWWenkang Wan
Wenkang Wan
XRXiaojiang Ren
Xiaojiang Ren
KSKai Sheng
Kai Sheng
Traffic prediction is an essential function of intelligent transportation system for traffic control and autonomous driving. Most existing methods encode traffic spatial and temporal data separately, and then design a feature fusion module to correlate spatial and temporal features. However, spatial information is often static, and repetitive static spatial encoding leads to waste of resources, especially in large-scale traffic network prediction. In this paper, we propose a dynamic edge interaction encoding method for spatio-temporal features based on inverse Transformer (iTransformer) and Graph Transformer, named iTPGT-former. The dynamic edge interaction process is designed to embed dynamic temporal features into static edges via a convolutional embedding module. To enhance the Graph Transformer, a relative position encoding strategy based on the self-attentive score of the positive definite kernel (PDK) on graphs and a method for graph substructure encoding (GSE) via enumeration of paths are introduced. In the experimental and discussion session, the iTPGT-former is considered for accuracy, parameters, inference speed, and rich ablation experiments are provided based on six publicly available traffic datasets. The results show that iTPGT-former outperforms the baseline model in both traffic flow and traffic speed prediction. The maximum improvement is achieved in the METR-LA 60-min speed prediction task, with 15.2% reduction in Mean Absolute Percentage Error (MAPE). In addition, the inference of iTPGT-former is significantly faster than the GCN-based method. Our implementation of the iTPGT-former is available at https://github.com/ouyangnann/iTPGTN-former.

31 January 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Jianzhao LiJianzhao Li
Jianzhao Li
SWShanfeng Wang
Shanfeng Wang
RYRui Yang
Rui Yang
Maoguo GongMaoguo Gong
Maoguo Gong
ZHZhuping Hu
Zhuping Hu
YZYu Zhou
Yu Zhou
Remote sensing scenarios usually involve sensitive geographic information on national security and regional development. In the commonly used centralized machine learning paradigm, data dispersed in various locations are concentrated and processed on a single server, which is prone to privacy leakage and data security concerns. Besides, it is difficult to solve the high heterogeneity of remote sensing images by simply applying federated learning algorithms to scene classification. In this paper, we formulate a federated remote sensing scene classification (FedSC) framework, and design a customized neural architecture search (CNAS) to achieve both global generality for multi-party collaborative distributed training and local specificity for personalized remote sensing scene customization. The proposed FedSC is generalizable to be implemented in any mannually designed networks, network pruning strategies, or NAS methods related to remote sensing scene classification. While the designed CNAS not only achieves collaborative distributed training in protecting participant data privacy to obtain a generalized global model, but also provides a customized local model for each participant that is more in line with the characteristics of private remote sensing scenarios. Overall, the proposed FedSCCNAS provides a novel federated collaborative training paradigm for remote sensing scene classification in terms of data privacy, data heterogeneity, and personalized customization. Extensive analytical and comparative experiments on three benchmark remote sensing scene classification datasets validate the versatility and effectiveness of our methods, the proposed FedSCCNAS exhibits superior competitiveness compared to state-of-the-art methods.

21 February 2025 in Nonlinear Dynamics
Verified
Journal Article
Closed access
PDF file
XLXiaofan Liu
Xiaofan Liu
KSKai Sheng
Kai Sheng
YYYoshiki Yamaguchi
Yoshiki Yamaguchi
YXYongfang Xie
Yongfang Xie
YYYunyi Yan
Yunyi Yan
YTYe Tao
Ye Tao