.png){kind=icon}
返回
Class-discriminative domain generalization for semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2024.105393.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing domain generalization semantic segmentation methods aim to improve the generalization ability by learning domain-invariant information for generalizing well on unseen domains. However, these methods ignore the class discriminability of models, which may lead to a class confusion problem. In this paper, a class-discriminative domain generalization (CDDG) approach is proposed to simultaneously alleviate the distribution shift and class confusion for semantic segmentation. Specifically, a dual prototypical contrastive learning module is proposed. Since the high-frequency component is consistent across different domains, a class-text-guided high-frequency prototypical contrastive learning is proposed. It uses text embeddings as prior knowledge for guiding the learning of high-frequency prototypical representation from high-frequency components to mine domain-invariant information and further improve the generalization ability. However, the domain-specific information may also contain label-related information which refers to the discrimination of a specific class. Thus, only learning the domain-invariant information may limit the class discriminability of models. To address this issue, a low-frequency prototypical contrastive learning is proposed to learn the class- discriminative representation from low-frequency components since it is more domain-specific across different domains. Finally, the class-discriminative representation and high-frequency prototypical representation are fused to simultaneously improve the generalization ability and class discriminability of the model. Extensive experiments demonstrate that the proposed approach outperforms current methods on single- and multi-source domain generalization benchmarks.
Keyword:
Domain generalization
Text embeddings
Dual prototypical contrastive learning
Semantic segmentation
期刊
IF:
4.2
论文数:
4.1K
被引数:
6.7K
机构
引用论文
Mechanical and corrosion behavior of Cu, Cr, Ni and Zn electroplating on corten A588 steel for scope for betterment in ambient construction applications在corten A588钢上电镀Cu，Cr，Ni和Zn的机械和腐蚀行为，以改善环境中的应用
OAAI
OAAI分享收藏分享收藏Determinants of quality of life in patients with fibromyalgia: A structural equation modeling approach纤维肌痛患者生活质量的决定因素: 结构方程建模方法.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容