.png){kind=icon}
返回
Domain Adaptation Using the Replay Buffer: Adaptive Sampling Using Domain-Specific Classifier
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3507044.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Domain adaptation is a method used to reduce discrepancy between source and target domains and to enhance generalization performance by transforming the distribution of source images. This study proposes a method to improve domain adaptation, which is based on selecting feature-rich images from their respective domains. Training images are represented based on their proximity to the domain by applying a domain-specific classifier. The method then selects more representative images from the training set using adaptive sampling. Based on the confidence from the classifier, less confident images in the mini-batch are replaced by more confident images in the replay buffer. This approach enhances the quality of the training set, ensuring the model focuses on high-quality, domain-relevant data. Experimental results demonstrate the efficiency of the proposed method, achieving consistent improvements with an average FID reduction of 6.60% across various tasks. Additionally, Additionally, it is extensively shown that the proposed method can improve recent methods on various domain adaptation tasks, both quantitatively and qualitatively.
Keyword:
Domain adaptation
adaptive sampling
adaptive sampling
replay buffer
replay buffer
domain-specific classifier
domain-specific classifier
domain-specific classifier
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
分享收藏Surgical therapy and next-generation sequencing-based genetic alteration analysis of malignant solitary fibrous tumor of the pleura胸膜恶性孤立性纤维瘤的外科治疗和基于二代测序的遗传学改变分析
OAAI
OAAI分享收藏Red, green, and blue electrochromism in ambipolar poly(amine–amide–imide)s based on electroactive tetraphenyl‐p‐phenylenediamine units基于电活性四苯基 p-苯二胺单元的双极性聚 (胺-酰胺-酰亚胺) 中的红色，绿色和蓝色电致变色
PREAI
分享收藏分享收藏Is SA shared or distributed in team work? An exploratory study in an intelligence analysis task
PREAI
分享收藏
查看更多内容