AdaTransform: Adaptive Data Transformation

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)(2019)

引用 19|浏览154
暂无评分
摘要
Data augmentation is widely used to increase data variance in training deep neural networks. However, previous methods require either comprehensive domain knowledge or high computational cost. Can we learn data transformation automatically and efficiently with limited domain knowledge? Furthermore, can we leverage data transformation to improve not only network training but also network testing? In this work, we propose adaptive data transformation to achieve the two goals. The AdaTransform can increase data variance in training and decrease data variance in testing. Experiments on different tasks prove that it can improve generalization performance.
更多
查看译文
关键词
high computational cost,leverage data transformation,network training,network testing,adaptive data transformation,AdaTransform,decrease data variance,data augmentation,deep neural networks,domain knowledge
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