Contrastive learning for one-shot building shape recognition using vector polygon transformers
Accurate building shape recognition is essential for cartographic generalization, urban planning, and geographic analysis, but existing methods struggle with numerous categories and limited samples. This paper presents a novel contrastive learning-based method for building shape recognition that imp...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2025.2471087 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327123022479360 |
|---|---|
| author | Longfei Cui Haizhong Qian Junkui Xu Chao Li Xinyu Niu |
| author_facet | Longfei Cui Haizhong Qian Junkui Xu Chao Li Xinyu Niu |
| author_sort | Longfei Cui |
| collection | DOAJ |
| description | Accurate building shape recognition is essential for cartographic generalization, urban planning, and geographic analysis, but existing methods struggle with numerous categories and limited samples. This paper presents a novel contrastive learning-based method for building shape recognition that improves accuracy and broadens recognizable types in one-shot scenarios. It employs a vector polygon transformer deep neural network (VPT-DNN) for automatic feature extraction, avoiding manual calculation. By employing contrastive learning, the model effectively distinguishes between various building shapes in an unsupervised manner, requiring only a single labeled sample per shape category. Experiments demonstrate 85.1% average accuracy on a 10-category dataset, surpassing existing few-shot methods. The model generalizes effectively, achieving 87.9% accuracy on an unseen European dataset without retraining. The adoption of this methodology reduces costs associated with manual operations and enhances the overall process of building recognition and classification. |
| format | Article |
| id | doaj-art-b0083aed01994d12a605c4c960e8b93f |
| institution | Kabale University |
| issn | 1010-6049 1752-0762 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj-art-b0083aed01994d12a605c4c960e8b93f2025-08-20T03:47:58ZengTaylor & Francis GroupGeocarto International1010-60491752-07622025-12-0140110.1080/10106049.2025.2471087Contrastive learning for one-shot building shape recognition using vector polygon transformersLongfei Cui0Haizhong Qian1Junkui Xu2Chao Li3Xinyu Niu4Institute of Geospatial Information, Information Engineering University, Zhengzhou, ChinaInstitute of Geospatial Information, Information Engineering University, Zhengzhou, ChinaCollege of Geography and Environmental Science, Henan University, Kaifeng, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, Luoyang, ChinaInstitute of Geospatial Information, Information Engineering University, Zhengzhou, ChinaAccurate building shape recognition is essential for cartographic generalization, urban planning, and geographic analysis, but existing methods struggle with numerous categories and limited samples. This paper presents a novel contrastive learning-based method for building shape recognition that improves accuracy and broadens recognizable types in one-shot scenarios. It employs a vector polygon transformer deep neural network (VPT-DNN) for automatic feature extraction, avoiding manual calculation. By employing contrastive learning, the model effectively distinguishes between various building shapes in an unsupervised manner, requiring only a single labeled sample per shape category. Experiments demonstrate 85.1% average accuracy on a 10-category dataset, surpassing existing few-shot methods. The model generalizes effectively, achieving 87.9% accuracy on an unseen European dataset without retraining. The adoption of this methodology reduces costs associated with manual operations and enhances the overall process of building recognition and classification.https://www.tandfonline.com/doi/10.1080/10106049.2025.2471087Contrastive learningVPT-DNNone-shot learningbuilding shape recognition |
| spellingShingle | Longfei Cui Haizhong Qian Junkui Xu Chao Li Xinyu Niu Contrastive learning for one-shot building shape recognition using vector polygon transformers Geocarto International Contrastive learning VPT-DNN one-shot learning building shape recognition |
| title | Contrastive learning for one-shot building shape recognition using vector polygon transformers |
| title_full | Contrastive learning for one-shot building shape recognition using vector polygon transformers |
| title_fullStr | Contrastive learning for one-shot building shape recognition using vector polygon transformers |
| title_full_unstemmed | Contrastive learning for one-shot building shape recognition using vector polygon transformers |
| title_short | Contrastive learning for one-shot building shape recognition using vector polygon transformers |
| title_sort | contrastive learning for one shot building shape recognition using vector polygon transformers |
| topic | Contrastive learning VPT-DNN one-shot learning building shape recognition |
| url | https://www.tandfonline.com/doi/10.1080/10106049.2025.2471087 |
| work_keys_str_mv | AT longfeicui contrastivelearningforoneshotbuildingshaperecognitionusingvectorpolygontransformers AT haizhongqian contrastivelearningforoneshotbuildingshaperecognitionusingvectorpolygontransformers AT junkuixu contrastivelearningforoneshotbuildingshaperecognitionusingvectorpolygontransformers AT chaoli contrastivelearningforoneshotbuildingshaperecognitionusingvectorpolygontransformers AT xinyuniu contrastivelearningforoneshotbuildingshaperecognitionusingvectorpolygontransformers |