计算机科学
域适应
水准点(测量)
人工智能
混乱
公制(单位)
领域(数学分析)
机器学习
深度学习
任务(项目管理)
图层(电子)
适应(眼睛)
模式识别(心理学)
数学
分类器(UML)
数学分析
精神分析
物理
经济
光学
有机化学
化学
管理
地理
运营管理
心理学
大地测量学
作者
Eric Tzeng,Judy Hoffman,Ning Zhang,Kate Saenko,Trevor Darrell
出处
期刊:Cornell University - arXiv
日期:2014-01-01
被引量:2048
标识
DOI:10.48550/arxiv.1412.3474
摘要
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.
科研通智能强力驱动
Strongly Powered by AbleSci AI