Tailoring Mixup to Data using Kernel Warping functions.
CoRR(2023)
摘要
Data augmentation is an essential building block for learning efficient deep
learning models. Among all augmentation techniques proposed so far, linear
interpolation of training data points, also called mixup, has found to be
effective for a large panel of applications. While the majority of works have
focused on selecting the right points to mix, or applying complex non-linear
interpolation, we are interested in mixing similar points more frequently and
strongly than less similar ones. To this end, we propose to dynamically change
the underlying distribution of interpolation coefficients through warping
functions, depending on the similarity between data points to combine. We
define an efficient and flexible framework to do so without losing in
diversity. We provide extensive experiments for classification and regression
tasks, showing that our proposed method improves both performance and
calibration of models. Code available in
https://github.com/ENSTA-U2IS/torch-uncertainty
更多查看译文
关键词
kernel warping functions,data
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