Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning
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_ | 1866911792575283200 |
|---|---|
| author | Ahn, Woo-Jin Yang, Geun-Yeong Choi, Hyun-Duck Lim, Myo-Taeg |
| author_facet | Ahn, Woo-Jin Yang, Geun-Yeong Choi, Hyun-Duck Lim, Myo-Taeg |
| contents | Deep learning models for semantic segmentation often experience performance degradation when deployed to unseen target domains unidentified during the training phase. This is mainly due to variations in image texture (\ie style) from different data sources. To tackle this challenge, existing domain generalized semantic segmentation (DGSS) methods attempt to remove style variations from the feature. However, these approaches struggle with the entanglement of style and content, which may lead to the unintentional removal of crucial content information, causing performance degradation. This study addresses this limitation by proposing BlindNet, a novel DGSS approach that blinds the style without external modules or datasets. The main idea behind our proposed approach is to alleviate the effect of style in the encoder whilst facilitating robust segmentation in the decoder. To achieve this, BlindNet comprises two key components: covariance alignment and semantic consistency contrastive learning. Specifically, the covariance alignment trains the encoder to uniformly recognize various styles and preserve the content information of the feature, rather than removing the style-sensitive factor. Meanwhile, semantic consistency contrastive learning enables the decoder to construct discriminative class embedding space and disentangles features that are vulnerable to misclassification. Through extensive experiments, our approach outperforms existing DGSS methods, exhibiting robustness and superior performance for semantic segmentation on unseen target domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06122 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning Ahn, Woo-Jin Yang, Geun-Yeong Choi, Hyun-Duck Lim, Myo-Taeg Computer Vision and Pattern Recognition Deep learning models for semantic segmentation often experience performance degradation when deployed to unseen target domains unidentified during the training phase. This is mainly due to variations in image texture (\ie style) from different data sources. To tackle this challenge, existing domain generalized semantic segmentation (DGSS) methods attempt to remove style variations from the feature. However, these approaches struggle with the entanglement of style and content, which may lead to the unintentional removal of crucial content information, causing performance degradation. This study addresses this limitation by proposing BlindNet, a novel DGSS approach that blinds the style without external modules or datasets. The main idea behind our proposed approach is to alleviate the effect of style in the encoder whilst facilitating robust segmentation in the decoder. To achieve this, BlindNet comprises two key components: covariance alignment and semantic consistency contrastive learning. Specifically, the covariance alignment trains the encoder to uniformly recognize various styles and preserve the content information of the feature, rather than removing the style-sensitive factor. Meanwhile, semantic consistency contrastive learning enables the decoder to construct discriminative class embedding space and disentangles features that are vulnerable to misclassification. Through extensive experiments, our approach outperforms existing DGSS methods, exhibiting robustness and superior performance for semantic segmentation on unseen target domains. |
| title | Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.06122 |