Improving the Generalization Ability of Deep Neural Networks for Cross-Domain Visual Recognition
IEEE Transactions on Cognitive and Developmental Systems(2021)
摘要
Feature learning with deep neural networks (DNNs) has made remarkable progress in recent years. However, its data-driven nature makes the collection of labeled training data expensive or impossible when the testing domain changes. Here, we propose a method of transferable feature learning and instance-level adaptation to improve the generalization ability of DNNs so as to mitigate the domain shift...
更多查看译文
关键词
Feature extraction,Visualization,Object detection,Neural networks,Training,Training data,Task analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要