.png){kind=icon}
返回
Cluster Alignment With Target Knowledge Mining for Unsupervised Domain Adaptation Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2022.3222634.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised domain adaptation (UDA) carries out knowledge transfer from the labeled source domain to the unlabeled target domain. Existing feature alignment methods in UDA semantic segmentation achieve this goal by aligning the feature distribution between domains. However, these feature alignment methods ignore the domain-specific knowledge of the target domain. In consequence, 1) the correlation among pixels of the target domain is not explored; and 2) the classifier is not explicitly designed for the target domain distribution. To conquer these obstacles, we propose a novel cluster alignment framework, which mines the domain-specific knowledge when performing the alignment. Specifically, we design a multi-prototype clustering strategy to make the pixel features within the same class tightly distributed for the target domain. Subsequently, a contrastive strategy is developed to align the distributions between domains, with the clustered structure maintained. After that, a novel affinity-based normalized cut loss is devised to learn task-specific decision boundaries. Our method enhances the model's adaptability in the target domain, and can be used as a pre-adaptation for self-training to boost its performance. Sufficient experiments prove the effectiveness of our method against existing state-of-the-art methods on representative UDA benchmarks.
Keyword:
Adaptation models
Correlation
Semantic segmentation
Clustering methods
Transforms
Benchmark testing
Task analysis
Unsupervised domain adaptation (UDA)
semantic segmentation
clustering
graph cut
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
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 ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Gross primary production of Mediterranean watersheds: Using isotope mass balance approach to improve estimationsEcohydrologyOAAI
EcohydrologyIF0
OAAI分享收藏Tinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients耳鸣再训练疗法 (TRT) 作为治疗耳鸣和高亢患者的方法
PREAI
分享收藏Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation通过不确定性估计纠正伪标签学习，用于领域自适应语义分割
PREAI
分享收藏IOT Based Smart Electric Pole2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)
2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)IF0
PREAI
分享收藏
查看更多内容