.png){kind=icon}
返回
Independent-interactive Knowledge Learning for Multi-source Domain Adaptive Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2025.103642.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• 提出了一种新颖的多源域自适应目标检测方法。
• 采用双注意力特征对齐来缓解负迁移。
• 类关系匹配增强了特征的可区分性。
• 在四个任务上的实验验证了所提出方法的优越性。
Keyword:
multi-source domain adaptation
object detection
dual attention feature alignment
class relationship matching
negative transfer mitigation
期刊
IF:
15.5
论文数:
4.2K
被引数:
2.7W
机构
暂无机构信息
引用论文
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks更快的r-cnn: 基于区域建议网络的实时目标检测
OAAI
OAAI分享收藏Training multi-source domain adaptation network by mutual information estimation and minimization.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Improving RGB-infrared object detection with cascade alignment-guided transformer利用级联对准制导变压器改进RGB红外目标检测INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI基于深度语义和边缘信息融合的多模态MRI脑肿瘤分割INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏Reducing bi-level feature redundancy for unsupervised domain adaptationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容