DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911848206434304 |
|---|---|
| author | Yang, Juncheng Li, Zuchao Xie, Shuai Yu, Wei Li, Shijun |
| author_facet | Yang, Juncheng Li, Zuchao Xie, Shuai Yu, Wei Li, Shijun |
| contents | Domain generalization faces challenges due to the distribution shift between training and testing sets, and the presence of unseen target domains. Common solutions include domain alignment, meta-learning, data augmentation, or ensemble learning, all of which rely on domain labels or domain adversarial techniques. In this paper, we propose a Dual-Stream Separation and Reconstruction Network, dubbed DSDRNet. It is a disentanglement-reconstruction approach that integrates features of both inter-instance and intra-instance through dual-stream fusion. The method introduces novel supervised signals by combining inter-instance semantic distance and intra-instance similarity. Incorporating Adaptive Instance Normalization (AdaIN) into a two-stage cyclic reconstruction process enhances self-disentangled reconstruction signals to facilitate model convergence. Extensive experiments on four benchmark datasets demonstrate that DSDRNet outperforms other popular methods in terms of domain generalization capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13848 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization Yang, Juncheng Li, Zuchao Xie, Shuai Yu, Wei Li, Shijun Computer Vision and Pattern Recognition Domain generalization faces challenges due to the distribution shift between training and testing sets, and the presence of unseen target domains. Common solutions include domain alignment, meta-learning, data augmentation, or ensemble learning, all of which rely on domain labels or domain adversarial techniques. In this paper, we propose a Dual-Stream Separation and Reconstruction Network, dubbed DSDRNet. It is a disentanglement-reconstruction approach that integrates features of both inter-instance and intra-instance through dual-stream fusion. The method introduces novel supervised signals by combining inter-instance semantic distance and intra-instance similarity. Incorporating Adaptive Instance Normalization (AdaIN) into a two-stage cyclic reconstruction process enhances self-disentangled reconstruction signals to facilitate model convergence. Extensive experiments on four benchmark datasets demonstrate that DSDRNet outperforms other popular methods in terms of domain generalization capabilities. |
| title | DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.13848 |