Classification and Model Explanation of Traditional Dwellings Based on Improved Swin Transformer

被引:0
|
作者
Miao, Shangbo [1 ]
Zhang, Chenxi [2 ]
Piao, Yushun [1 ]
Miao, Yalin [3 ]
机构
[1] Shenyang Jianzhu Univ, Sch Architecture & Urban Planning, Shenyang 110168, Peoples R China
[2] Southwest Jiaotong Univ, Sch Mech Engn, Chengdu 610031, Peoples R China
[3] Xian Univ Technol, Sch Printing Packaging & Digital Media, Xian 710048, Peoples R China
基金
中国国家自然科学基金;
关键词
traditional dwellings; feature extraction and classification; CNN; Swin Transformer; explainability; Grad-CAM;
D O I
10.3390/buildings14061540
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The extraction of features and classification of traditional dwellings plays significant roles in preserving and ensuring the sustainable development of these structures. Currently, challenges persist in subjective classification and the accuracy of feature extraction. This study focuses on traditional dwellings in Gansu Province, China, employing a novel model named Improved Swin Transformer. This model, based on the Swin Transformer and parallel grouped Convolutional Neural Networks (CNN) branches, aims to enhance the accuracy of feature extraction and classification precision. Furthermore, to validate the accuracy of feature extraction during the prediction process and foster trust in AI systems, explainability research was conducted using Grad-CAM-generated heatmaps. Initially, the Gansu Province Traditional Dwelling Dataset (GTDD) is established. On the constructed GTDD dataset, the Improved Swin Transformer attains an accuracy of 90.03% and an F1 score of 87.44%. Comparative analysis with ResNet-50, ResNeXt-50, and Swin Transformer highlights the outstanding performance of the improved model. The confusion matrix of the Improved Swin Transformer model reveals the classification results across different regions, indicating that the primary influencing factors are attributed to terrain, climate, and cultural aspects. Finally, using Grad-CAM-generated heatmaps for explaining classifications, it is observed that the Improved Swin Transformer model exhibits more accurate localization and focuses on features compared to the other three models. The model demonstrates exceptional feature extraction ability with minimal influence from the surrounding environment. Simultaneously, through the heatmaps generated by the Improved Swin Transformer for traditional residential areas in five regions of Gansu, it is evident that the model accurately extracts architectural features such as roofs, facades, materials, windows, etc. This validates the consistency of features extracted by the Improved Swin Transformer with traditional methods and enhances trust in the model and decision-making. In summary, the Improved Swin Transformer demonstrates outstanding feature extraction ability and accurate classification, providing valuable insights for the protection and style control of traditional residential areas.
引用
收藏
页数:24
相关论文
共 50 条
  • [1] An improved Swin transformer for sandstone micro-image classification
    Huo, Fengcai
    Li, Hongjiang
    Dong, Hongli
    Ren, Weijian
    GEOENERGY SCIENCE AND ENGINEERING, 2025, 247
  • [2] Efficient Lung Cancer Image Classification and Segmentation Algorithm Based on an Improved Swin Transformer
    Sun, Ruina
    Pang, Yuexin
    Li, Wenfa
    ELECTRONICS, 2023, 12 (04)
  • [3] BiCFormer: Swin Transformer based model for classification of benign and malignant pulmonary nodules
    Zhao, Xiaoping
    Xu, Jingjing
    Lin, Zhichen
    Xue, Xingan
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (07)
  • [4] Optimization of automatic classification for women’s pants based on the swin transformer model
    Shaoqin Pan
    Ping Wang
    Chen Yang
    Fashion and Textiles, 11 (1)
  • [5] Classification of Solar Radio Spectrum Based on Swin Transformer
    Chen, Jian
    Yuan, Guowu
    Zhou, Hao
    Tan, Chengming
    Yang, Lei
    Li, Siqi
    UNIVERSE, 2023, 9 (01)
  • [6] Improved deep learning image classification algorithm based on Swin Transformer V2
    Wei, Jiangshu
    Chen, Jinrong
    Wang, Yuchao
    Luo, Hao
    Li, Wujie
    PEERJ COMPUTER SCIENCE, 2023, 9
  • [7] Improved deep learning image classification algorithm based on Swin Transformer V2
    Wei J.
    Chen J.
    Wang Y.
    Luo H.
    Li W.
    PeerJ Computer Science, 2023, 9
  • [8] Classification of maize growth stages using the Swin Transformer model
    Fu L.
    Huang H.
    Wang H.
    Huang S.
    Chen D.
    Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (14): : 191 - 200
  • [9] A Driving Area Detection Algorithm Based on Improved Swin Transformer
    Li, Ying
    Liu, Shuang
    Sheng, Huankun
    SSRN, 2023,
  • [10] A Driving Area Detection Algorithm Based on Improved Swin Transformer
    Liu, Shuang
    Li, Ying
    Sheng, Huankun
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (02) : 227 - 234