Learning Robust Shape-Based Features for Domain Generalization
Domain generalization is a challenging problem of learning models that can generalize to novel testing domains which are unavailable during training and follow different distributions from training domains. In this paper, we introduce a simple but effective method for domain generalization, which is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9050708/ |
| _version_ | 1819295708182740992 |
|---|---|
| author | Yexun Zhang Ya Zhang Qinwei Xu Ruipeng Zhang |
| author_facet | Yexun Zhang Ya Zhang Qinwei Xu Ruipeng Zhang |
| author_sort | Yexun Zhang |
| collection | DOAJ |
| description | Domain generalization is a challenging problem of learning models that can generalize to novel testing domains which are unavailable during training and follow different distributions from training domains. In this paper, we introduce a simple but effective method for domain generalization, which is based on the object shape hypothesis. The main idea is from some recent studies which demonstrate that leading the network to focus more on the object shape and recognizing objects through shape-based features are more significant and robust. To achieve this, we first stylize source domain images into randomly sampled styles through a style transfer network and then use both the stylized images and original source domain images to learn the classification model. With images of the same content but different styles (textures), we expect the network to classify according to the global object shape rather than local textures and further transfer the object shape knowledge to novel domains. By this way, the generalization ability of the classification model will be improved. We conduct extensive experiments on PACS, VLCS and OfficeHome benchmarks and both the quantitative and qualitative analysis demonstrate the effectiveness of the proposed method. |
| first_indexed | 2024-12-24T04:46:30Z |
| format | Article |
| id | doaj.art-09203d17f7f74b8ea5f17d89b7573b66 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-24T04:46:30Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-09203d17f7f74b8ea5f17d89b7573b662022-12-21T17:14:40ZengIEEEIEEE Access2169-35362020-01-018637486375610.1109/ACCESS.2020.29842799050708Learning Robust Shape-Based Features for Domain GeneralizationYexun Zhang0https://orcid.org/0000-0001-7306-1865Ya Zhang1Qinwei Xu2Ruipeng Zhang3Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, ChinaCooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, ChinaCooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, ChinaCooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, ChinaDomain generalization is a challenging problem of learning models that can generalize to novel testing domains which are unavailable during training and follow different distributions from training domains. In this paper, we introduce a simple but effective method for domain generalization, which is based on the object shape hypothesis. The main idea is from some recent studies which demonstrate that leading the network to focus more on the object shape and recognizing objects through shape-based features are more significant and robust. To achieve this, we first stylize source domain images into randomly sampled styles through a style transfer network and then use both the stylized images and original source domain images to learn the classification model. With images of the same content but different styles (textures), we expect the network to classify according to the global object shape rather than local textures and further transfer the object shape knowledge to novel domains. By this way, the generalization ability of the classification model will be improved. We conduct extensive experiments on PACS, VLCS and OfficeHome benchmarks and both the quantitative and qualitative analysis demonstrate the effectiveness of the proposed method.https://ieeexplore.ieee.org/document/9050708/Domain generalizationlearning shape-based features |
| spellingShingle | Yexun Zhang Ya Zhang Qinwei Xu Ruipeng Zhang Learning Robust Shape-Based Features for Domain Generalization IEEE Access Domain generalization learning shape-based features |
| title | Learning Robust Shape-Based Features for Domain Generalization |
| title_full | Learning Robust Shape-Based Features for Domain Generalization |
| title_fullStr | Learning Robust Shape-Based Features for Domain Generalization |
| title_full_unstemmed | Learning Robust Shape-Based Features for Domain Generalization |
| title_short | Learning Robust Shape-Based Features for Domain Generalization |
| title_sort | learning robust shape based features for domain generalization |
| topic | Domain generalization learning shape-based features |
| url | https://ieeexplore.ieee.org/document/9050708/ |
| work_keys_str_mv | AT yexunzhang learningrobustshapebasedfeaturesfordomaingeneralization AT yazhang learningrobustshapebasedfeaturesfordomaingeneralization AT qinweixu learningrobustshapebasedfeaturesfordomaingeneralization AT ruipengzhang learningrobustshapebasedfeaturesfordomaingeneralization |